CN116630122A - Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation - Google Patents
Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation Download PDFInfo
- Publication number
- CN116630122A CN116630122A CN202310907730.9A CN202310907730A CN116630122A CN 116630122 A CN116630122 A CN 116630122A CN 202310907730 A CN202310907730 A CN 202310907730A CN 116630122 A CN116630122 A CN 116630122A
- Authority
- CN
- China
- Prior art keywords
- data
- ecological
- hydrologic
- lake
- regulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000004044 response Effects 0.000 title claims abstract description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 150
- 238000003062 neural network model Methods 0.000 claims abstract description 46
- 238000004088 simulation Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000011160 research Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 19
- 230000001105 regulatory effect Effects 0.000 claims description 46
- 230000008859 change Effects 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 9
- 239000013074 reference sample Substances 0.000 claims description 9
- 239000000523 sample Substances 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 239000004973 liquid crystal related substance Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 4
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000001276 controlling effect Effects 0.000 claims 7
- 238000004891 communication Methods 0.000 description 24
- 241000195493 Cryptophyta Species 0.000 description 12
- 230000000694 effects Effects 0.000 description 7
- 239000000126 substance Substances 0.000 description 5
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 239000002028 Biomass Substances 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005094 computer simulation Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012851 eutrophication Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 229910052698 phosphorus Inorganic materials 0.000 description 2
- 239000011574 phosphorus Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000192700 Cyanobacteria Species 0.000 description 1
- 238000006424 Flood reaction Methods 0.000 description 1
- 229910019142 PO4 Inorganic materials 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000004071 biological effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000001970 hydrokinetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- NBIIXXVUZAFLBC-UHFFFAOYSA-K phosphate Chemical compound [O-]P([O-])([O-])=O NBIIXXVUZAFLBC-UHFFFAOYSA-K 0.000 description 1
- 239000010452 phosphate Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Fluid Mechanics (AREA)
- Mathematical Optimization (AREA)
- Primary Health Care (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
Abstract
The invention provides a lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation, comprising the following steps: determining a research area, and constructing a training set and a testing set; constructing a time sequence prediction neural network model based on a graph structure, respectively training and testing by adopting a training set and a testing set, and predicting hydrological data and ecological data of each acquisition point in a preset future time by adopting the tested time sequence prediction neural network model; constructing a river and lake hydrological hydrodynamic simulation model, and obtaining hydrological data and ecological data of at least M acquisition points by taking hydrological data and ecological data of at least N acquisition points as input; and screening scheduling schemes meeting the requirements by adopting a decision method, and constructing a lake ecological regulation scheme set. The invention can accurately and rapidly provide the ecological hydraulics regulation and control method and strategy of the water-receiving lake under different water conditions.
Description
Technical Field
The invention relates to a hydraulic regulation technology, in particular to a lake ecological hydraulic regulation method based on hydrologic-ecological response relation.
Background
The water system communication takes rivers, lakes, reservoirs and the like as water system units, adopts engineering and non-engineering measures such as reasonable dredging, communication, drainage, scheduling and the like, establishes or improves hydraulic connection between water bodies of the rivers, the lakes and the reservoirs, and is an important measure for solving the water safety problems such as frequent floods, water resource shortage, water environment deterioration and the like.
The shallow lakes are generally in an eutrophication state and even have blue algae bloom disasters due to the influence of strong human activities, climate change and other factors. The water system communication can regulate the water level of the shallow lake, shorten the water changing period and change the flow field of the water receiving lake while establishing the water communication of the river and the lake, and the influence on the substance migration and the biological population and the functions of the water receiving shallow lake cannot be ignored. Because of the existence of various risk factors such as pollutant transfer, exogenous species input, hydrokinetic disturbance and the like, the influence of water system communication on the water ecological system is controversial, and the comprehensive benefit of water system communication engineering application is severely restricted. Shallow lakes are more sensitive to changes in hydrologic factors such as water level, water changing period, lake flow structure and the like than deep lakes due to the characteristic of shallow water. Scientific evaluation of the water environmental effect of the river and lake water of the water system communication engineering, clarification of the driving mechanism of the engineering influencing the ecological environment of the river and lake water, and the provision of a targeted regulation and control method and strategy are key to solving the problem.
Further research and innovation is needed.
Disclosure of Invention
The application aims to: provides a lake ecological hydraulic regulation and control method based on hydrologic-ecological response relationship to solve the problems existing in the prior art. It is another object of the present application to provide a system for implementing the above method.
The technical scheme is as follows: according to one aspect of the application, a lake ecological hydraulic regulation and control method based on hydrologic-ecological response relation is provided, which is characterized by comprising the following steps:
s1, determining a research area, constructing a river and lake water network topology containing acquisition point information, acquiring hydrological data and ecological data of each acquisition point, constructing time sequence data, and constructing a training set and a testing set based on the time sequence data;
s2, constructing a time sequence prediction neural network model based on a graph structure, respectively training and testing by adopting a training set and a testing set, and predicting hydrological data and ecological data of each acquisition point in a preset future time by adopting the tested time sequence prediction neural network model;
s3, constructing a river and lake hydrologic hydrodynamic simulation model, taking hydrologic data and ecological data of at least N acquisition points as input, obtaining hydrologic data and ecological data of at least M acquisition points, and comparing the hydrologic data and ecological data with a prediction result of a time sequence prediction neural network model; if the error is within the threshold value, the time sequence prediction neural network model is used as a hydrologic ecological corresponding relation prediction model; n, M is a natural number greater than 1;
S4, constructing a regulation scheme set, simulating by adopting a river and lake hydrologic hydrodynamic model to obtain hydrologic data, and predicting ecological data of each acquisition point by using the hydrologic data as input through a time sequence prediction neural network model; evaluating whether the ecological data meets the requirements; and screening scheduling schemes meeting the requirements by adopting a decision method, and constructing a lake ecological regulation scheme set.
According to one aspect of the present application, the step S1 is further:
s11, determining a research area and acquiring research data, and extracting river and lake water systems from the research data by adopting ArcGIS or QGIS to generate a river network file; allocating unique identification ID for each river and lake; acquiring position information of an acquisition point, and performing space matching on the acquisition point and a river network file to generate a river and lake water network topology file containing the acquisition point information;
step S12, acquiring or calling hydrological data and ecological data of each acquisition point, and carrying out statistics and summary alignment according to a standard format to form a hydrological data table and an ecological data table of each acquisition point;
step S13, merging the hydrological data table and the ecological data table of each acquisition point according to a time sequence to form a time sequence data table of each acquisition point, and selecting data from the time sequence table as an input variable and an output variable;
And S14, dividing the training set and the testing set according to a predetermined proportion according to a time sequence data table, and respectively converting the training set and the testing set into an array or tensor suitable for an input/output format of the model according to the requirements of the model.
According to one aspect of the present application, the step S2 is further:
s21, reading and analyzing the river and lake water network topology, obtaining characteristic data of the river and lake water network topology, constructing a time sequence prediction neural network model based on a graph structure according to the characteristic data, configuring super parameters including learning rate, batch size and optimizers, and screening loss functions and evaluation indexes;
s22, carrying out complement processing on time sequence data in the training set and the test set by adopting a sliding window method and a sequence filling method, and identifying whether abnormal values exist in the training set and the test set through an abnormal detection algorithm; obtaining a preprocessed training set and a preprocessed testing set;
and S23, predicting hydrological data and ecological data of each acquisition point in a preset time in the future by adopting the tested time sequence prediction neural network model.
According to one aspect of the present application, the step S3 is further:
s31, constructing a river and lake hydrologic and hydrodynamic force simulation model, and acquiring hydrologic data and ecological data of each acquisition point, river and lake topography, boundary conditions and hydraulic construction information; and calibrating model parameters;
S32, constructing a hydrologic hydrodynamic simulation scene, obtaining simulation scenes of at least two areas and at least two time periods, and aiming at each simulation scene, obtaining hydrologic data and ecological data of at least M acquisition points by taking hydrologic data and ecological data of at least N acquisition points as input;
s33, comparing the output result with a predicted result of the time sequence predicted neural network model; and if the error is within the threshold value, using the time sequence prediction neural network model as a hydrologic ecological corresponding relation prediction model.
According to an aspect of the present application, in the step S31, the process of calibrating the model parameters specifically includes:
s31a, collecting hydrological data and hydrodynamic data of a river and a lake, and dividing parameters of a river and a lake hydrological hydrodynamic simulation model into basic parameters, key parameters and secondary parameters;
step S31b, according to the spatial correlation of rivers and lakes, hydrologic data and hydrodynamic data of upstream and downstream or adjacent sections are selected as input items, basic parameters of target sections are selected as output items, a parameter calibration neural network model is constructed, and the BP optimization algorithm is used for training the parameter calibration neural network model to obtain estimated values of the basic parameters;
Step S31c, according to the time correlation of the river, the hydrologic data and the hydrodynamic data of the historical field are selected as a reference sample set, and the hydrologic data and the hydrodynamic data of the current field are selected as a target sample set; calculating the distance between the target sample and the reference sample by using a K nearest neighbor algorithm, and selecting K reference samples with the minimum distance; obtaining a rating value of the key parameter by using a linear regression method according to the key parameter of the reference sample and the hydrological data and hydrodynamic data of the target sample;
and S31d, selecting at least two evaluation indexes as an optimization objective function, searching an optimal solution set in a given parameter range by utilizing a multi-objective optimization algorithm, and selecting an optimal solution according to the pareto front edge to obtain an optimized value of a secondary parameter.
According to one aspect of the present application, the step S4 is further:
s41, reading the water network topology of the rivers and lakes and the hydraulic construction data of each river and lake in a research area, taking each hydraulic construction as a regulating node, dividing the regulating strategy of the regulating node into a basic regulating strategy and a maneuvering regulating strategy according to constraint conditions, regulating targets and regulating strategy characteristics, constructing a regulating scheme comprising at least two regulating nodes, and generating a regulating scheme set aiming at different regulating scenes;
Step S42, sequentially adjusting the regulation and control scheme aiming at each regulation and control scene, and simulating by using a river and lake hydrologic hydrodynamic model to obtain hydrologic data;
s43, predicting ecological data of each acquisition point through a time sequence prediction neural network model by taking hydrologic data as input; evaluating whether the ecological data meets the requirements; and screening scheduling schemes meeting the requirements by adopting an analytic hierarchy process, and constructing a lake ecological regulation scheme set.
According to one aspect of the present application, the step S41 of classifying the regulation policies of the regulation nodes into a basic regulation policy and a maneuvering regulation policy includes:
step S41a, reading the regulation strategy of each regulation node one by one, judging whether the regulation strategy causes the change of the topology of the river and lake water network, and if so, marking the regulation node as a dynamic regulation node; constructing a dynamic regulation node set;
step S41b, changing the regulation and control strategy of the dynamic regulation and control nodes one by one to form a dynamic river and lake water network topology set;
step S41c, aiming at a dynamic river and lake topology water network, calculating the change amount of the regulation strategy of each regulation node on hydrologic data and ecological data one by one, and arranging in a descending order;
and step S41d, selecting the regulation strategies of the P previous regulation nodes as basic regulation strategies, and taking the rest regulation strategies as maneuvering regulation strategies.
According to one aspect of the present application, in the step S43, the process of screening the scheduling schemes meeting the requirements by using the analytic hierarchy process and constructing the lake ecological regulation scheme set is further as follows:
step S43a, constructing a hierarchical structure model of a scheduling scheme, wherein the hierarchical structure model comprises a target layer, a criterion layer and a scheme layer;
step S43b, constructing a judgment matrix, and comparing elements of the alignment rule layer and the scheme layer in pairs to give a score of relative importance;
step S43c, carrying out hierarchical single sequencing and consistency check, namely calculating weight vectors and maximum characteristic roots of all elements according to the judgment matrix, and checking whether the consistency index of the judgment matrix is smaller than a threshold value;
and step S44d, performing hierarchical total sequencing and consistency check, sequencing and screening the scheduling schemes according to the comprehensive weight, and selecting an optimal scheme meeting the requirements.
According to an aspect of the present application, the step S12a is further:
step S12a, constructing at least two water regime periods according to basic data of a research area, and collecting or calling hydrological data and ecological data of each collecting point for each water regime period, wherein the water regime periods comprise Feng Ping withered periods;
and step S12b, counting, pooling and aligning according to a standard format to form a hydrological data table and an ecological data table of each acquisition point.
According to another aspect of the application, a lake ecological hydraulic regulation system based on hydrologic-ecological response relation comprises:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the processor for execution by the processor to implement the hydrologic-ecological response relationship-based lake ecological hydraulic regulation method of any one of the above technical schemes.
The beneficial effects are that: by using the method of the application, the hydrologic-ecological response mechanism of the shallow water lake affected by the water system communication is disclosed; meanwhile, a water system communication multidimensional target collaborative hydraulic regulation and control technology system based on hydrologic-ecological response is established, and a regulation and control method and strategy of ecological hydraulics of the water-receiving lake under different water conditions are provided. The related art advantages and effects will be described in detail later.
Drawings
Fig. 1 is a flow chart of the present application.
Fig. 2 is a flowchart of step S1 of the present application.
Fig. 3 is a flow chart of step S2 of the present application.
Fig. 4 is a flowchart of step S3 of the present application.
Detailed Description
At present, the research on the quantifiable relationship between different hydrological parameters of a water lake and biological population response under the influence of water system communication is less, so that the existing water system communication hydraulic regulation and control method lacks a reliable ecological basis, and the expected ecological dispatching effect is difficult to obtain.
As shown in fig. 1, according to an aspect of the present application, there is provided a lake ecological hydraulic regulation method based on hydrologic-ecological response relationship, which is characterized by comprising the steps of:
s1, determining a research area, constructing a river and lake water network topology containing acquisition point information, acquiring hydrological data and ecological data of each acquisition point, constructing time sequence data, and constructing a training set and a testing set based on the time sequence data;
s2, constructing a time sequence prediction neural network model based on a graph structure, respectively training and testing by adopting a training set and a testing set, and predicting hydrological data and ecological data of each acquisition point in a preset future time by adopting the tested time sequence prediction neural network model; the model can more accurately predict the hydrological data and the ecological data of each acquisition point in a period of time in the future, and improves the prediction precision.
S3, constructing a river and lake hydrologic hydrodynamic simulation model, taking hydrologic data and ecological data of at least N acquisition points as input, obtaining hydrologic data and ecological data of at least M acquisition points, and comparing the hydrologic data and ecological data with a prediction result of a time sequence prediction neural network model; if the error is within the threshold value, the time sequence prediction neural network model is used as a hydrologic ecological corresponding relation prediction model; n, M is a natural number greater than 1. This step is used to improve the reliability and accuracy of the model.
S4, constructing a regulation scheme set, simulating by adopting a river and lake hydrologic hydrodynamic model to obtain hydrologic data, and predicting ecological data of each acquisition point by using the hydrologic data as input through a time sequence prediction neural network model; evaluating whether the ecological data meets the requirements; and screening scheduling schemes meeting the requirements by adopting a decision method, and constructing a lake ecological regulation scheme set.
In this embodiment, by combining the water network topology of the river and the lake with the acquisition points, the hydrologic data and the ecological data of the time and space of the lake and the river are obtained, the data are further analyzed, the time-space evolution process and the response relationship of the hydrologic data and the ecological data are obtained, the spatial correlation information of the time sequence data is extracted by a time sequence prediction neural network model based on a graph structure, and is coupled with and contrasted with a model of hydrologic hydrodynamic force, so that the data processing speed and the prediction accuracy are improved, a basis is provided for the simulation of a subsequent regulation scheme, after the corresponding data are obtained, the regulation scheme is simulated and predicted by the hydrologic hydrodynamic model, and the regulation scheme is screened according to the evaluation output result. In a word, the embodiment utilizes the multiple factors such as the periodicity of the hydrological weather, the biological activity data set, the sensitive biological screening, the index weight setting and the like to construct a more accurate and comprehensive biological habitat quality assessment model. This helps to provide powerful support for ecological protection, hydraulic engineering planning and environmental improvement.
According to one aspect of the present application, the step S1 is further:
s11, determining a research area and acquiring research data, and extracting river and lake water systems from the research data by adopting ArcGIS or QGIS to generate a river network file; allocating unique identification ID for each river and lake; and acquiring position information of the acquisition points, and performing space matching on the acquisition points and the river network file to generate a river and lake water network topology file containing the acquisition point information. River and lake water system information with different data sources are fused to the same river and lake water network topology file, so that the data integrity is improved, the data processing efficiency can be improved, and the errors of manual operation can be reduced.
Step S12, acquiring or calling hydrological data and ecological data of each acquisition point, and carrying out statistics and summary alignment according to a standard format to form a hydrological data table and an ecological data table of each acquisition point; the method can better reflect the relation between time series data, so that the hydrological data and the ecological data of each acquisition point in a future period of time can be predicted more accurately.
Step S13, merging the hydrological data table and the ecological data table of each acquisition point according to a time sequence to form a time sequence data table of each acquisition point, and selecting data from the time sequence table as an input variable and an output variable;
And S14, dividing the training set and the testing set according to a predetermined proportion according to a time sequence data table, and respectively converting the training set and the testing set into an array or tensor suitable for an input/output format of the model according to the requirements of the model. The performance test of the model on independent and unknown data is ensured, and the reliability of practical application is enhanced. The method can also ensure the accuracy and reliability of the data, thereby improving the model prediction accuracy.
According to the method, the system and the device, the factors such as river and lake water network topology, hydraulic construction, hydrologic data and ecological data can be comprehensively considered, a time sequence prediction neural network model and a river and lake hydrologic hydrodynamic simulation model are constructed, evaluation and screening of a lake ecological regulation scheme are achieved, and scientific basis and technical support are provided for lake ecological protection and restoration. Meanwhile, a regulation scheme set aiming at different regulation targets and constraint conditions can be generated according to different regulation scenes, and an optimal or optimized scheme meeting the requirements is screened by adopting a decision method such as a analytic hierarchy process and the like, so that a guidance opinion with strong operability is provided for lake ecological regulation.
For the data acquisition process, taking a certain water receiving lake as an example, a field fixed point tracking observation means is adopted, monitoring points are arranged on two lakes and a lake-entering river, indexes such as the water level, the flow rate and the water body of a water receiving lake area in a flood period and a non-flood period, nitrogen and phosphorus concentrations in different forms, population abundance of floating algae, exogenous input water quantity of engineering, source substance flux of nitrogen and phosphorus, exogenous algae biomass and the like are observed once every 5 days, the flood period and the non-flood period are continuously observed for 2 months respectively, and synchronous change rules between the physical and chemical habitats of the water receiving lakes and the fluctuation of the floating algae community are analyzed. After the related data are collected, the quantitative relationship between the elements such as the water level, the water changing period, the water conveying time period and the like of the water receiving lake and the planktonic algae community can be established by applying data analysis methods such as multi-component correlation (MVC), linear regression (GLM), structural Equation Model (SEM) and the like to mainly analyze the synchronous response of the hydrological parameter change of the water receiving lake and the planktonic algae community and the physical and chemical habitat parameter.
According to another aspect of the application, the relevant data may also be obtained by laboratory simulation means, such as: constructing a microcosm simulation system of an ecological system of a water receiving lake based on a continuous flow culture device, and respectively setting 4 repeated systems; lake water is used as a circulating water source to strip the influence of water system communication exogenous material input; the hydrologic parameters such as different water levels of the water receiving lake, water changing period and the like are set, and the laboratory simulates the change of physical and chemical habitat and planktonic algae biomass in the microcosm system. The experimental period is consistent with the field, 60 days, and the physicochemical parameters of the water body and the planktonic algae community of the micro-universe system of the receiving lake are measured every 5 days.
According to one aspect of the present application, the step S2 is further:
and S21, reading and analyzing the river and lake water network topology, obtaining characteristic data of the river and lake water network topology, constructing a time sequence prediction neural network model based on a graph structure according to the characteristic data, configuring super parameters including learning rate, batch size and optimizers, and screening loss functions and evaluation indexes. By reading and analyzing the water network topology of the river and the lake, the space structure information of the water network can be effectively extracted, the relevance and the influence degree among all the acquisition points in the water network are reflected, and a foundation is provided for the construction of a time sequence prediction neural network model; by constructing a time sequence prediction neural network model based on a graph structure, the water network topology information and the time sequence information can be fully utilized, high-precision prediction of hydrologic data and ecological data is realized, and meanwhile, the method has strong generalization capability and robustness; by configuring the super parameters, the learning efficiency and the convergence rate of the model can be adjusted according to different water network characteristics and data characteristics, and the performance and the effect of the model are optimized; by screening the loss function and the evaluation index, a proper model evaluation method can be selected according to different prediction targets and requirements, and the prediction error and accuracy of the model can be quantized.
S22, carrying out complement processing on time sequence data in the training set and the test set by adopting a sliding window method and a sequence filling method, and identifying whether abnormal values exist in the training set and the test set through an abnormal detection algorithm; and obtaining a preprocessed training set and a preprocessed testing set. The method has the advantages that the problem of data missing or incomplete can be solved by adopting a sliding window method and a sequence filling method to carry out completion processing on time sequence data, the integrity and consistency of model input data are ensured, and the stability and reliability of a model are improved; whether abnormal values exist in the training set and the testing set is identified through an abnormal detection algorithm, so that noise or interference factors in data can be eliminated, prediction deviation and variance of a model are reduced, and accuracy and robustness of the model are improved.
And S23, predicting hydrological data and ecological data of each acquisition point in a preset time in the future by adopting the tested time sequence prediction neural network model. The method realizes real-time monitoring and forecasting of the dynamic change condition of the river and lake water network.
In a word, the embodiment provides a basis for the prediction of the hydrological data and the ecological data of the river and lake water network with high precision, high efficiency and high reliability, and improves the generalization capability and the robustness of the model.
According to one aspect of the present application, the step S3 is further:
s31, constructing a river and lake hydrologic and hydrodynamic force simulation model, and acquiring hydrologic data and ecological data of each acquisition point, river and lake topography, boundary conditions and hydraulic construction information; and calibrating model parameters; the step can provide reference data for verification of the time sequence prediction neural network model, and the model is more detailed and accurate.
S32, constructing a hydrologic hydrodynamic simulation scene, obtaining simulation scenes of at least two areas and at least two time periods, and aiming at each simulation scene, obtaining hydrologic data and ecological data of at least M acquisition points by taking hydrologic data and ecological data of at least N acquisition points as input; the simulation scenes of at least two areas and at least two time periods ensure the diversity of scene coverage, are beneficial to capturing various possible hydrologic ecological change conditions, and further improve the generalization capability of the model. The spatial and temporal scalability of the model is also enhanced.
S33, comparing the output result with a predicted result of the time sequence predicted neural network model; and if the error is within the threshold value, using the time sequence prediction neural network model as a hydrologic ecological corresponding relation prediction model. The method is used for improving the accuracy and reliability of model prediction. The model can better capture the dynamic characteristic and the nonlinear characteristic of the hydrologic ecological relationship, and improves the accuracy and the credibility of prediction.
The embodiment can better reflect the variation trend of the lake ecosystem under different conditions, thereby more comprehensively evaluating the prediction capability of the time sequence prediction neural network model.
In other words, through different simulation scenes, data of other acquisition points can be obtained through partial acquisition point simulation, namely, simulation and prediction are performed in space by focusing on the acquisition point data of the previous period, and the acquisition point data of the subsequent period can be simulated, so that the prediction in time is realized. Providing a basis for the preference of subsequent regulatory schemes.
According to an aspect of the present application, in the step S31, the process of calibrating the model parameters specifically includes:
s31a, collecting hydrological data and hydrodynamic data of a river and a lake, and dividing parameters of a river and a lake hydrological hydrodynamic simulation model into basic parameters, key parameters and secondary parameters;
step S31b, according to the spatial correlation of rivers and lakes, hydrologic data and hydrodynamic data of upstream and downstream or adjacent sections are selected as input items, basic parameters of target sections are selected as output items, a parameter calibration neural network model is constructed, and the BP optimization algorithm is used for training the parameter calibration neural network model to obtain estimated values of the basic parameters;
Step S31c, according to the time correlation of the river, the hydrologic data and the hydrodynamic data of the historical field are selected as a reference sample set, and the hydrologic data and the hydrodynamic data of the current field are selected as a target sample set; calculating the distance between the target sample and the reference sample by using a K nearest neighbor algorithm, and selecting K reference samples with the minimum distance; obtaining a rating value of the key parameter by using a linear regression method according to the key parameter of the reference sample and the hydrological data and hydrodynamic data of the target sample;
and S31d, selecting at least two evaluation indexes as an optimization objective function, searching an optimal solution set in a given parameter range by utilizing a multi-objective optimization algorithm, and selecting an optimal solution according to the pareto front edge to obtain an optimized value of a secondary parameter.
In the embodiment, the parameter calibration neural network model is constructed and trained by utilizing the BP optimization algorithm, and the estimation of model parameters is combined with a modern machine learning method, so that the accuracy and the efficiency of parameter estimation are improved. And the model parameters are rated by combining the time correlation and the space correlation of the river, so that the adaptability and the accuracy of the model parameters are effectively improved. According to the embodiment, a multi-objective optimization algorithm is utilized to realize comprehensive balance among a plurality of evaluation indexes, so that the comprehensiveness and adaptability of model parameter optimization are improved.
In a word, the prediction accuracy and reliability of the model are improved by calibrating parameters of the river and lake hydrodynamics simulation model. According to different parameter types and characteristics, different methods are adopted for calibration, the spatial correlation and the time correlation of the river and lake water network are fully utilized, the nonlinear relation and the linear relation among parameters are utilized, and the calibration effect and efficiency are improved; multiple evaluation indexes can be comprehensively considered, an optimal solution set is sought, and an optimal solution is selected according to the pareto front edge, so that comprehensive evaluation and optimization adjustment of the model prediction effect are realized. Meanwhile, the method can better reflect the influence of natural environment and human activities on the lake ecological system, thereby better guiding the lake ecological hydraulic regulation and control work.
According to one aspect of the application, the calibration of model parameters may also be achieved by: and constructing a three-dimensional hydrodynamic force-water quality-planktonic algae model of the lake, and calibrating and verifying the model by applying continuous observation data of hydrologic, physicochemical and ecological factors of the water-bearing lake in different water conditions. The horizontal direction of the model adopts a Cartesian rectangular coordinate system, and the vertical direction adopts sigma coordinates and is divided into 10 layers. The boundary conditions of the model are input by the atmosphere, wind speed and direction, communication in and out of the lake flow, water quality and sediment. Atmospheric conditions, wind farms, rainfall data are collected from the monitoring stations. Assuming an initial water level of horizontal, an initial flow rate of 0 m/s, a model calculation time of 365 d, and a time step of 10 s. The calibration of the model adopts the field observation data, and several continuous field observation results are selected for calibration and verification. The state variables mainly simulated by the model are water temperature, dissolved oxygen, ammonia nitrogen concentration, phosphate concentration, blue algae abundance and the like of the water body.
According to one aspect of the present application, the step S4 is further:
s41, reading the water network topology of the rivers and lakes and the hydraulic construction data of each river and lake in a research area, taking each hydraulic construction as a regulating node, dividing the regulating strategy of the regulating node into a basic regulating strategy and a maneuvering regulating strategy according to constraint conditions, regulating targets and regulating strategy characteristics, constructing a regulating scheme comprising at least two regulating nodes, and generating a regulating scheme set aiming at different regulating scenes; by reading the river and lake water network topology and hydraulic construction data in the research area, the whole situation of the water resource system can be effectively mastered, and the accuracy and the reliability of the scheme are improved.
Step S42, sequentially adjusting the regulation and control scheme aiming at each regulation and control scene, and simulating by using a river and lake hydrologic hydrodynamic model to obtain hydrologic data; and constructing a regulation and control scheme set according to different regulation and control scenes, and screening a scheduling scheme meeting the requirements by evaluating ecological data, so that the scientization and the precision of lake ecological regulation and control are realized.
S43, predicting ecological data of each acquisition point through a time sequence prediction neural network model by taking hydrologic data as input; evaluating whether the ecological data meets the requirements; and screening scheduling schemes meeting the requirements by adopting an analytic hierarchy process, and constructing a lake ecological regulation scheme set.
In this embodiment, according to different constraint conditions, regulation targets and regulation policy characteristics, a regulation scheme including at least two regulation nodes is constructed, and a regulation scheme set is generated for different regulation scenes, so as to improve diversity and adaptability of the regulation scheme. And the dynamic prediction and evaluation of the ecological condition of the river and the lake can be realized.
According to one aspect of the present application, the step S41 of classifying the regulation policies of the regulation nodes into a basic regulation policy and a maneuvering regulation policy includes:
step S41a, reading the regulation strategy of each regulation node one by one, judging whether the regulation strategy causes the change of the topology of the river and lake water network, and if so, marking the regulation node as a dynamic regulation node; constructing a dynamic regulation node set; the flexibility and pertinence of the regulation and control scheme can be improved;
step S41b, changing the regulation and control strategy of the dynamic regulation and control nodes one by one to form a dynamic river and lake water network topology set;
step S41c, aiming at a dynamic river and lake topology water network, calculating the change amount of the regulation strategy of each regulation node on hydrologic data and ecological data one by one, and arranging in a descending order; the method can reflect the spatial structure change of the river and lake water network under different regulation strategies, and provides a basis for dynamic simulation of the river and lake water network.
And step S41d, selecting the regulation strategies of the P previous regulation nodes as basic regulation strategies, and taking the rest regulation strategies as maneuvering regulation strategies. P is a natural number greater than 1. Can realize the basic guarantee and flexible adjustment of the ecological condition of the river and the lake.
In the embodiment, the flexibility and pertinence of the regulation scheme can be improved by distinguishing the basic regulation strategy and the maneuvering regulation strategy, and different hydrological conditions and ecological requirements can be effectively dealt with. The dynamic regulation nodes are found out by reading and judging the regulation strategies of the regulation nodes one by one, so that the network topology change of the river and the lake can be better understood and captured, and a more proper regulation strategy is formulated. By forming a dynamic river and lake water network topology set, the spatial structure change of the river and lake water network under different regulation strategies can be reflected, and a foundation is provided for dynamic simulation of the river and lake water network. And aiming at the dynamic river and lake topology water network, the change amount of the regulation strategy of each regulation node on the hydrologic data and the ecological data is calculated, so that the most critical regulation strategy for the system is found out, and the basis is provided for the establishment of the follow-up regulation strategy. Finally, the basic guarantee of the ecological conditions of the rivers and lakes is realized by selecting the regulation strategies of the P regulation nodes as basic regulation strategies, meanwhile, the maneuvering regulation strategies are adopted to flexibly cope with different conditions, and the ecological requirements and the water resource management are comprehensively balanced.
According to one aspect of the present application, in the step S43, the process of screening the scheduling schemes meeting the requirements by using the analytic hierarchy process and constructing the lake ecological regulation scheme set is further as follows:
step S43a, constructing a hierarchical structure model of a scheduling scheme, wherein the hierarchical structure model comprises a target layer, a criterion layer and a scheme layer;
step S43b, constructing a judgment matrix, and comparing elements of the alignment rule layer and the scheme layer in pairs to give a score of relative importance;
step S43c, carrying out hierarchical single sequencing and consistency check, namely calculating weight vectors and maximum characteristic roots of all elements according to the judgment matrix, and checking whether the consistency index of the judgment matrix is smaller than a threshold value;
and step S44d, performing hierarchical total sequencing and consistency check, sequencing and screening the scheduling schemes according to the comprehensive weight, and selecting an optimal scheme meeting the requirements.
According to one aspect of the application, this can also be achieved by the following method. Based on the synergic criteria and methods of different water conditions and multidimensional targets, an intelligent optimization scheduling method based on a modern optimization theory is developed by using methods such as an extensible primitive theory and a non-dominant ranking genetic algorithm (NSGA-II); and the ecological hydraulics model and the optimal scheduling method module are coupled to form the water system communication multidimensional target collaborative hydraulic regulation and control technical model. Selecting typical hydrologic years of a research area, collecting parameter data such as hydrologic and water quality, and adopting an ecological hydraulics model of the water-bearing lake to simulate hydrologic, physicochemical and algae index change of the water-bearing lake under the influence of water system communication engineering aiming at the hydrologic conditions of different hydrologic years; the hydraulic regulation and control scene of flood control, water supply and ecological safety of water is comprehensively planned, multi-objective collaborative optimization is carried out according to the calculation result, the water system communication hydraulic regulation and control scheme which is preferably suitable for different hydrologic year water conditions is constructed, the hydraulic regulation and control method and strategy of typical regional water system communication project flood control-water supply-ecological multi-dimensional objective collaborative, and technical support is provided for river and lake ecological risk management and control of the water system communication project.
According to an aspect of the present application, the step S12a is further:
step S12a, constructing at least two water regime periods according to basic data of a research area, and collecting or calling hydrological data and ecological data of each collecting point for each water regime period, wherein the water regime periods comprise Feng Ping withered periods;
and step S12b, counting, pooling and aligning according to a standard format to form a hydrological data table and an ecological data table of each acquisition point.
In this embodiment, seasonal changes and dynamic evolution of the lake ecosystem can be better reflected by constructing at least two water conditions periods. This allows for a more accurate assessment of the status and trends of the lake ecosystem. In other words, by constructing at least two water conditions periods (such as a full period, a flat period, a dead period, a flood period and a non-flood period), the assessment result is ensured to fully cover various water conditions of the research area, so that the accuracy and the reliability of the assessment are improved. By forming the hydrological and ecological data tables for each acquisition point, subsequent data analysis and adjustment can be made easier, thereby better assessing the quality of the biological habitat. By combining hydrological and ecological data for multiple water regime periods, reliable data support can be provided for trade-off analysis and decision making in the relevant field.
According to another aspect of the application, a lake ecological hydraulic regulation system based on hydrologic-ecological response relation comprises:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the processor for execution by the processor to implement the hydrologic-ecological response relationship-based lake ecological hydraulic regulation method of any one of the above technical schemes.
In the present embodiment, the time-series prediction neural network model may employ a neural network module such as DCRNN (a model employed in the present embodiment), GAT (Graph Attention Network), encoder and decoder based, for example Transformer, convS S. The river and lake hydrodynamics simulation model can adopt a shallow lake physical-ecological process simulation platform LAMP, hydroMPM (a two-dimensional coupling hydrodynamics model) and Delft3D (a three-dimensional hydrodynamics-eutrophication model).
In a word, through the research of the application, the time-space synchronous change rule of the hydrologic and ecological parameters of the water-bearing lakes under the influence of the water system communication in different water conditions is discovered, the quantitative relation between the sensitive hydrologic parameters of the lakes and the index of the planktonic algae community under the influence of the water system communication is established, and the hydrologic-ecological response mechanism of the water-bearing shallow water lakes under the influence of the water system communication is revealed; establishing a hydrologic-ecological response relation-based ecological hydraulic numerical simulation method of the water-bearing lake, simulating and providing a hydrologic parameter threshold value for avoiding the cyanobacteria bloom risk under the influence of water system communication, and providing theory and method basis for the hydraulic regulation and control of the water-bearing lake under the influence of water system communication; a water system communication multidimensional target collaborative hydraulic regulation and control technology system based on hydrologic-ecological response is established, and a regulation and control method and strategy of ecological hydraulics of the water-receiving lake under different water conditions are provided.
The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to the specific details of the above embodiments, and various equivalent changes can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the equivalent changes belong to the protection scope of the present invention.
Claims (10)
1. The lake ecological hydraulic regulation and control method based on hydrologic-ecological response relation is characterized by comprising the following steps:
s1, determining a research area, constructing a river and lake water network topology containing acquisition point information, acquiring hydrological data and ecological data of each acquisition point, constructing time sequence data, and constructing a training set and a testing set based on the time sequence data;
s2, constructing a time sequence prediction neural network model based on a graph structure, respectively training and testing by adopting a training set and a testing set, and predicting hydrological data and ecological data of each acquisition point in a preset future time by adopting the tested time sequence prediction neural network model;
s3, constructing a river and lake hydrologic hydrodynamic simulation model, taking hydrologic data and ecological data of at least N acquisition points as input, obtaining hydrologic data and ecological data of at least M acquisition points, and comparing the hydrologic data and ecological data with a prediction result of a time sequence prediction neural network model; if the error is within the threshold value, the time sequence prediction neural network model is used as a hydrologic ecological corresponding relation prediction model; n, M is a natural number greater than 1;
S4, constructing a regulation scheme set, simulating by adopting a river and lake hydrologic hydrodynamic model to obtain hydrologic data, and predicting ecological data of each acquisition point by using the hydrologic data as input through a time sequence prediction neural network model; evaluating whether the ecological data meets the requirements; and screening scheduling schemes meeting the requirements by adopting a decision method, and constructing a lake ecological regulation scheme set.
2. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation as set forth in claim 1, wherein the step S1 is further:
s11, determining a research area and acquiring research data, and extracting river and lake water systems from the research data by adopting ArcGIS or QGIS to generate a river network file; allocating unique identification ID for each river and lake; acquiring position information of an acquisition point, and performing space matching on the acquisition point and a river network file to generate a river and lake water network topology file containing the acquisition point information;
step S12, acquiring or calling hydrological data and ecological data of each acquisition point, and carrying out statistics and summary alignment according to a standard format to form a hydrological data table and an ecological data table of each acquisition point;
step S13, merging the hydrological data table and the ecological data table of each acquisition point according to a time sequence to form a time sequence data table of each acquisition point, and selecting data from the time sequence table as an input variable and an output variable;
And S14, dividing the training set and the testing set according to a predetermined proportion according to a time sequence data table, and respectively converting the training set and the testing set into an array or tensor suitable for an input/output format of the model according to the requirements of the model.
3. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation as set forth in claim 2, wherein the step S2 is further:
s21, reading and analyzing the river and lake water network topology, obtaining characteristic data of the river and lake water network topology, constructing a time sequence prediction neural network model based on a graph structure according to the characteristic data, configuring super parameters including learning rate, batch size and optimizers, and screening loss functions and evaluation indexes;
s22, carrying out complement processing on time sequence data in the training set and the test set by adopting a sliding window method and a sequence filling method, and identifying whether abnormal values exist in the training set and the test set through an abnormal detection algorithm; obtaining a preprocessed training set and a preprocessed testing set;
and S23, predicting hydrological data and ecological data of each acquisition point in a preset time in the future by adopting the tested time sequence prediction neural network model.
4. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation as set forth in claim 1, wherein the step S3 is further:
S31, constructing a river and lake hydrologic and hydrodynamic force simulation model, and acquiring hydrologic data and ecological data of each acquisition point, river and lake topography, boundary conditions and hydraulic construction information; and calibrating model parameters;
s32, constructing a hydrologic hydrodynamic simulation scene, obtaining simulation scenes of at least two areas and at least two time periods, and aiming at each simulation scene, obtaining hydrologic data and ecological data of at least M acquisition points by taking hydrologic data and ecological data of at least N acquisition points as input;
s33, comparing the output result with a predicted result of the time sequence predicted neural network model; and if the error is within the threshold value, using the time sequence prediction neural network model as a hydrologic ecological corresponding relation prediction model.
5. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation according to claim 1, wherein in the step S31, the process of calibrating model parameters specifically comprises:
s31a, collecting hydrological data and hydrodynamic data of a river and a lake, and dividing parameters of a river and a lake hydrological hydrodynamic simulation model into basic parameters, key parameters and secondary parameters;
step S31b, according to the spatial correlation of rivers and lakes, hydrologic data and hydrodynamic data of upstream and downstream or adjacent sections are selected as input items, basic parameters of target sections are selected as output items, a parameter calibration neural network model is constructed, and the BP optimization algorithm is used for training the parameter calibration neural network model to obtain estimated values of the basic parameters;
Step S31c, according to the time correlation of the river, the hydrologic data and the hydrodynamic data of the historical field are selected as a reference sample set, and the hydrologic data and the hydrodynamic data of the current field are selected as a target sample set; calculating the distance between the target sample and the reference sample by using a K nearest neighbor algorithm, and selecting K reference samples with the minimum distance; obtaining a rating value of the key parameter by using a linear regression method according to the key parameter of the reference sample and the hydrological data and hydrodynamic data of the target sample;
and S31d, selecting at least two evaluation indexes as an optimization objective function, searching an optimal solution set in a given parameter range by utilizing a multi-objective optimization algorithm, and selecting an optimal solution according to the pareto front edge to obtain an optimized value of a secondary parameter.
6. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation according to claim 5, wherein the step S4 is further as follows:
s41, reading the water network topology of the rivers and lakes and the hydraulic construction data of each river and lake in a research area, taking each hydraulic construction as a regulating node, dividing the regulating strategy of the regulating node into a basic regulating strategy and a maneuvering regulating strategy according to constraint conditions, regulating targets and regulating strategy characteristics, constructing a regulating scheme comprising at least two regulating nodes, and generating a regulating scheme set aiming at different regulating scenes;
Step S42, sequentially adjusting the regulation and control scheme aiming at each regulation and control scene, and simulating by using a river and lake hydrologic hydrodynamic model to obtain hydrologic data;
s43, predicting ecological data of each acquisition point through a time sequence prediction neural network model by taking hydrologic data as input; evaluating whether the ecological data meets the requirements; and screening scheduling schemes meeting the requirements by adopting an analytic hierarchy process, and constructing a lake ecological regulation scheme set.
7. The method for regulating the ecological and hydraulic power of lakes based on the hydrologic-ecological response relation according to claim 6, wherein the step S41 of dividing the regulating strategies of the regulating nodes into basic regulating strategies and maneuvering regulating strategies comprises the following steps:
step S41a, reading the regulation strategy of each regulation node one by one, judging whether the regulation strategy causes the change of the topology of the river and lake water network, and if so, marking the regulation node as a dynamic regulation node; constructing a dynamic regulation node set;
step S41b, changing the regulation and control strategy of the dynamic regulation and control nodes one by one to form a dynamic river and lake water network topology set;
step S41c, aiming at a dynamic river and lake topology water network, calculating the change amount of the regulation strategy of each regulation node on hydrologic data and ecological data one by one, and arranging in a descending order;
And step S41d, selecting the regulation strategies of the P previous regulation nodes as basic regulation strategies, and taking the rest regulation strategies as maneuvering regulation strategies.
8. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation according to claim 7, wherein in the step S43, a hierarchical analysis method is adopted to screen the scheduling schemes meeting the requirements, and the process of constructing the lake ecological regulation scheme set is further as follows:
step S43a, constructing a hierarchical structure model of a scheduling scheme, wherein the hierarchical structure model comprises a target layer, a criterion layer and a scheme layer;
step S43b, constructing a judgment matrix, and comparing elements of the alignment rule layer and the scheme layer in pairs to give a score of relative importance;
step S43c, carrying out hierarchical single sequencing and consistency check, namely calculating weight vectors and maximum characteristic roots of all elements according to the judgment matrix, and checking whether the consistency index of the judgment matrix is smaller than a threshold value;
and step S44d, performing hierarchical total sequencing and consistency check, sequencing and screening the scheduling schemes according to the comprehensive weight, and selecting an optimal scheme meeting the requirements.
9. The method for regulating and controlling ecological water power of lakes based on hydrologic-ecological response relation according to any one of claims 2 to 8, wherein the step S12 is further:
Step S12a, constructing at least two water regime periods according to basic data of a research area, and collecting or calling hydrological data and ecological data of each collecting point for each water regime period, wherein the water regime periods comprise Feng Ping withered periods;
and step S12b, counting, pooling and aligning according to a standard format to form a hydrological data table and an ecological data table of each acquisition point.
10. Lake ecological hydraulic regulation and control system based on hydrologic-ecological response relation, which is characterized by comprising:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the processor for execution by the processor to implement the hydrologic-ecoecological response relationship based lake ecological hydraulic regulation method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310907730.9A CN116630122B (en) | 2023-07-24 | 2023-07-24 | Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310907730.9A CN116630122B (en) | 2023-07-24 | 2023-07-24 | Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116630122A true CN116630122A (en) | 2023-08-22 |
| CN116630122B CN116630122B (en) | 2023-09-19 |
Family
ID=87610273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310907730.9A Active CN116630122B (en) | 2023-07-24 | 2023-07-24 | Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116630122B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116976529A (en) * | 2023-09-22 | 2023-10-31 | 南京大学 | Cross-river-basin water diversion method and system based on supply-demand prediction dynamic correction |
| CN117078114A (en) * | 2023-10-16 | 2023-11-17 | 水利部交通运输部国家能源局南京水利科学研究院 | Water quality evaluation method and system for water-bearing lakes under influence of diversion engineering |
| CN117116382A (en) * | 2023-10-18 | 2023-11-24 | 水利部交通运输部国家能源局南京水利科学研究院 | Water quality space-time prediction method and system for water-bearing lake under influence of diversion engineering |
| CN117150975A (en) * | 2023-10-31 | 2023-12-01 | 长江三峡集团实业发展(北京)有限公司 | Hydrodynamic model parameter optimization and hydrodynamic process simulation method and device |
| CN117236199A (en) * | 2023-11-14 | 2023-12-15 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for improving water quality and guaranteeing water safety of river and lake in urban water network area |
| CN117273313A (en) * | 2023-09-08 | 2023-12-22 | 中关村科学城城市大脑股份有限公司 | Water network regulation method, device, electronic equipment and computer readable medium |
| CN117875193A (en) * | 2024-03-12 | 2024-04-12 | 北京师范大学 | Lake thermodynamic process simulation method and simulation system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190354873A1 (en) * | 2018-02-16 | 2019-11-21 | Lucas Pescarmona | Analysis system and hydrology management for basin rivers |
| US20200149888A1 (en) * | 2018-11-08 | 2020-05-14 | Tsinghua University | Method and device for monitoring water volume change, computer device and storage medium |
| CN112183123A (en) * | 2020-09-15 | 2021-01-05 | 湖北省水利水电规划勘测设计院 | Method for analyzing water demand of ecological environment in river channel for water bloom prevention and control |
| CN112506990A (en) * | 2020-12-03 | 2021-03-16 | 河海大学 | Hydrological data anomaly detection method based on spatiotemporal information |
| AU2021103039A4 (en) * | 2021-06-02 | 2021-07-22 | Institute of Hydroecology, MWR&CAS | an ecological dispatch method and apparatus for complex ecosystem of lakes and rivers |
| CN114117848A (en) * | 2021-11-10 | 2022-03-01 | 北京师范大学 | Basin water environment simulation prediction method and device based on multi-model coupling |
| CN114240196A (en) * | 2021-12-21 | 2022-03-25 | 中国科学院东北地理与农业生态研究所 | Lake multi-water-source regulation and control method based on hydrodynamic force-water quality-ecological model |
| WO2022099852A1 (en) * | 2020-11-10 | 2022-05-19 | 广东粤海水务股份有限公司 | Health evaluation and diagnosis method for urban landscape lake water ecosystem |
| CN114548711A (en) * | 2022-02-09 | 2022-05-27 | 四川大学 | Cascade reservoir hydrological and ecological scheduling effect evaluation method based on fuzzy comprehensive evaluation method |
| CN115130736A (en) * | 2022-06-10 | 2022-09-30 | 武汉大学 | Method and system for determining hydrological ecological response relation and ecological flow based on Bayesian hierarchical model |
| CN115496148A (en) * | 2022-09-22 | 2022-12-20 | 中国长江三峡集团有限公司 | Method and device for evaluating large-scale hydrological situation change of river |
| CN115907436A (en) * | 2023-01-10 | 2023-04-04 | 河海大学 | Water resource water environment regulation and control method and system based on quality coupling forecast |
| CN116070971A (en) * | 2023-03-27 | 2023-05-05 | 水利部交通运输部国家能源局南京水利科学研究院 | Orderly flow regulation and control method and system for river and lake water system |
-
2023
- 2023-07-24 CN CN202310907730.9A patent/CN116630122B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190354873A1 (en) * | 2018-02-16 | 2019-11-21 | Lucas Pescarmona | Analysis system and hydrology management for basin rivers |
| US20200149888A1 (en) * | 2018-11-08 | 2020-05-14 | Tsinghua University | Method and device for monitoring water volume change, computer device and storage medium |
| CN112183123A (en) * | 2020-09-15 | 2021-01-05 | 湖北省水利水电规划勘测设计院 | Method for analyzing water demand of ecological environment in river channel for water bloom prevention and control |
| WO2022099852A1 (en) * | 2020-11-10 | 2022-05-19 | 广东粤海水务股份有限公司 | Health evaluation and diagnosis method for urban landscape lake water ecosystem |
| CN112506990A (en) * | 2020-12-03 | 2021-03-16 | 河海大学 | Hydrological data anomaly detection method based on spatiotemporal information |
| AU2021103039A4 (en) * | 2021-06-02 | 2021-07-22 | Institute of Hydroecology, MWR&CAS | an ecological dispatch method and apparatus for complex ecosystem of lakes and rivers |
| CN114117848A (en) * | 2021-11-10 | 2022-03-01 | 北京师范大学 | Basin water environment simulation prediction method and device based on multi-model coupling |
| CN114240196A (en) * | 2021-12-21 | 2022-03-25 | 中国科学院东北地理与农业生态研究所 | Lake multi-water-source regulation and control method based on hydrodynamic force-water quality-ecological model |
| CN114548711A (en) * | 2022-02-09 | 2022-05-27 | 四川大学 | Cascade reservoir hydrological and ecological scheduling effect evaluation method based on fuzzy comprehensive evaluation method |
| CN115130736A (en) * | 2022-06-10 | 2022-09-30 | 武汉大学 | Method and system for determining hydrological ecological response relation and ecological flow based on Bayesian hierarchical model |
| CN115496148A (en) * | 2022-09-22 | 2022-12-20 | 中国长江三峡集团有限公司 | Method and device for evaluating large-scale hydrological situation change of river |
| CN115907436A (en) * | 2023-01-10 | 2023-04-04 | 河海大学 | Water resource water environment regulation and control method and system based on quality coupling forecast |
| CN116070971A (en) * | 2023-03-27 | 2023-05-05 | 水利部交通运输部国家能源局南京水利科学研究院 | Orderly flow regulation and control method and system for river and lake water system |
Non-Patent Citations (4)
| Title |
|---|
| ZHANG HONG-BO 等: "Variation trends analysis of eco-hydrological factors in lower reaches of the Yellow River during the past 50 years", 《2010 INTERNATIONAL CONFERENCE ON MECHANIC AUTOMATION AND CONTROL ENGINEERING》, pages 4676 - 4679 * |
| 刘雪梅: "基于水动力-水质-水生态综合模型的查干湖多水源调控", 《中国博士学位论文全文数据库工程科技Ⅰ辑》, no. 02, pages 027 - 69 * |
| 吴时强 等: "引水工程湖泊水生态效应评估研究进展", 《南昌工程学院学报》, vol. 37, no. 06, pages 14 - 26 * |
| 王教元: "滇西北湖泊水文调控与生态环境响应的时空特征", 《中国博士学位论文全文数据库工程科技Ⅰ辑》, no. 01, pages 027 - 4 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273313A (en) * | 2023-09-08 | 2023-12-22 | 中关村科学城城市大脑股份有限公司 | Water network regulation method, device, electronic equipment and computer readable medium |
| CN116976529A (en) * | 2023-09-22 | 2023-10-31 | 南京大学 | Cross-river-basin water diversion method and system based on supply-demand prediction dynamic correction |
| CN116976529B (en) * | 2023-09-22 | 2023-12-26 | 南京大学 | Cross-river-basin water diversion method and system based on supply-demand prediction dynamic correction |
| CN117078114A (en) * | 2023-10-16 | 2023-11-17 | 水利部交通运输部国家能源局南京水利科学研究院 | Water quality evaluation method and system for water-bearing lakes under influence of diversion engineering |
| CN117078114B (en) * | 2023-10-16 | 2023-12-22 | 水利部交通运输部国家能源局南京水利科学研究院 | Water quality evaluation method and system for water-bearing lakes under influence of diversion engineering |
| CN117116382A (en) * | 2023-10-18 | 2023-11-24 | 水利部交通运输部国家能源局南京水利科学研究院 | Water quality space-time prediction method and system for water-bearing lake under influence of diversion engineering |
| CN117116382B (en) * | 2023-10-18 | 2023-12-26 | 水利部交通运输部国家能源局南京水利科学研究院 | Water quality space-time prediction method and system for water-bearing lake under influence of diversion engineering |
| CN117150975A (en) * | 2023-10-31 | 2023-12-01 | 长江三峡集团实业发展(北京)有限公司 | Hydrodynamic model parameter optimization and hydrodynamic process simulation method and device |
| CN117150975B (en) * | 2023-10-31 | 2024-01-26 | 长江三峡集团实业发展(北京)有限公司 | Hydrodynamic model parameter optimization and hydrodynamic process simulation method and device |
| CN117236199A (en) * | 2023-11-14 | 2023-12-15 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for improving water quality and guaranteeing water safety of river and lake in urban water network area |
| CN117236199B (en) * | 2023-11-14 | 2024-02-09 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for improving water quality and guaranteeing water safety of river and lake in urban water network area |
| CN117875193A (en) * | 2024-03-12 | 2024-04-12 | 北京师范大学 | Lake thermodynamic process simulation method and simulation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116630122B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116630122B (en) | Lake ecological hydraulic regulation and control method and system based on hydrologic-ecological response relation | |
| CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
| Mehrazar et al. | Adaptation of water resources system to water scarcity and climate change in the suburb area of megacities | |
| Zhang et al. | Assessment of hydropower sustainability: Review and modeling | |
| CN116090839B (en) | Multiple risk analysis and evaluation method and system for water resource coupling system | |
| CN114036838B (en) | Vertical water temperature simulation method based on multilayer LSTM neural network | |
| CN115374376B (en) | Small hydropower station ecological influence monitoring and evaluating method and system | |
| CN116485584B (en) | Method and system for cooperative regulation and control of WEE of river with large bottom slope in alpine region | |
| CN110334876A (en) | A kind of environment flow process adjustment method based on hydrological regimes, water quality and the more elements of biology | |
| Xia et al. | Bioindicator assessment framework of river ecosystem health and the detection of factors influencing the health of the Huai River Basin, China | |
| CN117236674A (en) | Urban river network hydrodynamic force accurate regulation and control and water environment lifting method and system | |
| Aldrees et al. | Evolutionary and ensemble machine learning predictive models for evaluation of water quality | |
| Setiawan et al. | Spatial modeling on land use change in regional scale of Java Island based-on biophysical characteristics | |
| CN117078114B (en) | Water quality evaluation method and system for water-bearing lakes under influence of diversion engineering | |
| Liu et al. | Evaluation of cultivated land quality using attention mechanism-back propagation neural network | |
| Xiong et al. | Assessing and decoupling ecosystem services evolution in karst areas: A multi-model approach to support land management decision-making | |
| CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
| CN112287299A (en) | River health change quantitative attribution method, device and system | |
| Wang et al. | Review of evaluation on ecological carrying capacity: The progress and trend of methodology | |
| CN111126827A (en) | Input-output accounting model construction method based on BP artificial neural network | |
| Shrestha et al. | Encapsulation of parametric uncertainty statistics by various predictive machine learning models: MLUE method | |
| CN110322124A (en) | A kind of collaboration Measurement Method of basin water systematic collaboration Bearing Capacity Evaluation element | |
| CN113269384B (en) | Method for early warning health state of river system | |
| CN115358587A (en) | Regional multi-department collaborative infrastructure planning method and system | |
| Alredaisy | Recommending the IHACRES model for water resources assessment and resolving water conflicts in Africa |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |