CN117522117A - Ecological risk assessment method and early warning system based on ecological protection red line demarcation - Google Patents
Ecological risk assessment method and early warning system based on ecological protection red line demarcation Download PDFInfo
- Publication number
- CN117522117A CN117522117A CN202311471889.7A CN202311471889A CN117522117A CN 117522117 A CN117522117 A CN 117522117A CN 202311471889 A CN202311471889 A CN 202311471889A CN 117522117 A CN117522117 A CN 117522117A
- Authority
- CN
- China
- Prior art keywords
- data
- ecological
- index
- module
- early warning
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012502 risk assessment Methods 0.000 title claims abstract description 44
- 238000007781 pre-processing Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 15
- 208000025174 PANDAS Diseases 0.000 claims abstract description 7
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 claims abstract description 7
- 235000016496 Panda oleosa Nutrition 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims abstract description 4
- 230000035945 sensitivity Effects 0.000 claims description 42
- 238000004162 soil erosion Methods 0.000 claims description 39
- 239000002689 soil Substances 0.000 claims description 37
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 28
- 210000002569 neuron Anatomy 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 240000004718 Panda Species 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 6
- 238000013079 data visualisation Methods 0.000 claims description 6
- 238000004451 qualitative analysis Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 230000006872 improvement Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000001704 evaporation Methods 0.000 claims description 3
- 230000008020 evaporation Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 238000013450 outlier detection Methods 0.000 claims description 3
- 238000012567 pattern recognition method Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 241000894007 species Species 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 240000000220 Panda oleosa Species 0.000 abstract 1
- 230000007613 environmental effect Effects 0.000 description 2
- 230000036449 good health Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation 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
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Geometry (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
Abstract
The invention relates to the technical field of ecological risk assessment, and discloses an ecological risk assessment method and an early warning system based on ecological protection red line demarcation, wherein the method comprises a data preprocessing module for calling NumPy and Pandas and reading and processing large-scale remote sensing image data preprocessing by combining an API of a GEE platform based on a Matlab tool and based on JavaScript and Python interfaces in a Google Earth Engine platform; an index calculation module for carrying out ecological risk assessment index grading information on the data processed by the data preprocessing module; the dynamic monitoring module is used for acquiring the data of the data preprocessing module and the index calculation module in real time or periodically, and updating and dynamically monitoring the data; and the early warning and decision support module is used for receiving the monitoring information transmitted by the dynamic monitoring module, triggering early warning and providing decision support through the change trend of the index and the threshold setting. The invention can more accurately know the state of the ecological system in real time, form monitoring index data and provide relevant reference basis for ecological protection and management work.
Description
Technical Field
The invention relates to the technical field of ecological risk assessment, in particular to an ecological risk assessment method and an early warning system based on ecological protection red line demarcation.
Background
With the growth of population and the development of economy, the protection and management of the ecological environment has become a global focus of attention. The ecological protection red line is widely applied to ecological environment protection and ecological resource management as an important management means and policy tool. However, the conventional ecological protection red line demarcation method has some limitations, and the risk condition of the ecological system cannot be comprehensively estimated, but the demarcation by the ecological protection red line is not enough to comprehensively estimate and monitor the risk condition of the ecological system, so that an advanced technical means and a scientific estimation method are needed, but the current risk estimation of the ecological system mainly estimates the condition and the characteristics of the ecological system by constructing models such as experience, process and the like, which are all steady-state models in nature, are mainly used for some post forecast, and cannot comprehensively estimate and simulate the future pattern evolution trend. However, the BP neural network can extract regularity characteristics through learning and organizing past experiences and store the regularity characteristics in a network structure, and can simulate and predict current and future ecological conditions. In addition, the demand for real-time monitoring and early warning systems is also growing so as to be able to respond to ecological risks in time and to formulate corresponding protection and management measures. In this context, for the above-mentioned problems, there is a need for an ecological risk assessment method and an early warning system based on ecological protection red line demarcation.
Disclosure of Invention
The invention aims to provide an ecological risk assessment method and an early warning system based on ecological protection red line demarcation. The invention provides an ecological risk assessment method and an early warning system based on ecological protection red line demarcation, wherein the method accurately demarcates the ecological protection red line, combines a BP neural network technical means and a scientific assessment method to accurately assess and monitor the risk condition of an ecological system in real time, can more accurately know the state of the ecological system in real time, and provides relevant reference basis for ecological protection and management work.
The invention is realized in the following way:
the invention provides an ecological risk early warning system based on ecological protection red line demarcation, which comprises a data preprocessing module based on a Matlab tool, based on JavaScript and Python programming interfaces in a Google Earth Engine platform, calling NumPy, pandas, scikit-learn and an OpenCV library, and reading and processing large-scale remote sensing image data preprocessing by combining with an API of a GEE platform;
an index calculation module for carrying out ecological risk assessment index grading information on the data processed by the data preprocessing module;
the dynamic monitoring module is used for acquiring the data of the data preprocessing module and the index calculation module in real time or periodically, and updating and dynamically monitoring the data;
the early warning and decision support module is used for receiving the monitoring information transmitted by the dynamic monitoring module, triggering early warning and providing decision support through the change trend of the index and the threshold setting;
the visualization and reporting module is used for receiving the evaluation result and the early warning information in the early warning and decision support module and displaying the ecological risk distribution, the risk level, the spatial distribution of key influence factors, the evaluation result and the early warning information to a decision maker in an intuitive manner;
the data updating and continuous improvement module is used for visualizing and reporting the monitoring result information in the module and is responsible for periodically updating the data.
Further, the invention provides an ecological risk assessment method based on ecological protection red line demarcation, which is specifically implemented according to the following steps of;
S 1 the data preprocessing module calls NumPy, pandas, scikit-learn and OpenCV libraries based on Matlab tool and based on JavaScript and Python programming interface in Google Earth Engine platform, and reads and processes large-scale remote sensing image data by combining with API of GEE platform; the remote sensing image data and other data sources comprise sentinel No. 2 data with the spatial resolution of 10m, DEM topographic data with the spatial resolution of 12.5m, land utilization data with the spatial resolution of 10m, 1:1000000 soil data with the spatial resolution of 1km, and investigation data of rainfall, air temperature and evaporative meteorological data of each site in a research area;
the remote sensing image data preprocessing comprises cloud processing, radiometric calibration, atmospheric correction, format conversion and cutting, and the meteorological data processing mainly comprises missing value elimination, interpolation, projection and cutting.
S 2 Specifically obtaining water and soil conservation data, water conservation data and biodiversity protection data in a monitored area through an index calculation module, and respectively adopting a Quantile function and combining qualitative analysis according to the total soil erosion amount, the water conservation capacity and the biodiversity index BI;
S 3 dividing three results of the total soil erosion amount, the water conservation capacity and the biological diversity index BI into 3 grades of a high-grade protection grade, a medium-grade warning grade and a low-grade restoration grade through an index calculation module, respectively extracting low-grade areas of water and soil conservation, water conservation and biological diversity protection, carrying out superposition analysis on the three evaluation results to obtain an overlapped area, and setting the overlapped area into a service function red line area of a biological system; the ecological environment sensitivity is evaluated and graded by constructing two indexes of soil desertification sensitivity and soil erosion sensitivity;
S 4 according to the soil desertification sensitivity index and the soil erosion sensitivity index, a method combining a natural breakpoint method and qualitative analysis is adoptedThe method comprises the steps of dividing the two results into 3 levels, namely general sensitivity, sensitivity and extremely sensitivity, extracting a soil desertification extremely sensitive area and a soil erosion extremely sensitive area, and performing superposition analysis calculation on the two types of sensitive red line areas to obtain an ecological environment sensitive red line area;
S 5 and performing superposition analysis on the ecosystem service function red line area and the ecosystem sensitive red line area to obtain a final ecological red line protection demarcation area.
Further, in step S 1 Wherein, the calculation of the soil and water conservation data is to evaluate the soil and water conservation based on the RUSLE soil erosion model, and calculate the soil erosion amount by combining the land utilization, gradient and rainfall data;
the water conservation is calculated based on a water balance equation, and the related input variables comprise the amount of precipitation, surface runoff, evaporation and the number of types of ecosystems;
the biodiversity protection is to construct a biodiversity monitoring and evaluating index system from the landscape structure LDI, the species diversity SDI and the ecological system quality EQU.
Further, in step S 2 In the method, the desertification sensitivity of the area is evaluated by adopting a wettability index, soil texture, days of wind generation and vegetation coverage;
soil erosion sensitivity is evaluated by comprehensively considering rainfall, landform, vegetation and soil texture factors on the basis of a general soil erosion equation USLE.
Further, in step S 3 In the method, ecological risk evaluation is carried out based on a BP neural network model, and the method specifically comprises the following steps of:
S 3.1 firstly, training a BP neural network model, wherein the training process of the model uses paired input samples and output samples for training, and neurons of the model are expressed in a layer form and comprise three parts, namely an input layer, an implicit layer and an output layer;
wherein the formula of the input layer is as formula (1);
wherein Ci is the ith index of the neurons of the input layer, namely the total soil erosion amount, the water conservation amount, the soil desertification sensitivity index and the soil erosion sensitivity index according to the biodiversity index, and m is the number of the indexes of the neurons of the input layer, and the value is 5;
hidden layer calculation is shown as formula (2);
wherein N is the number of neurons of an hidden layer, the value is 7, N is the number of neurons of an output layer, and a is a constant between 0 and 10;
the calculation formula of the output layer is shown as formula (3);
dj is an ecological system risk assessment index obtained by j variables transmitted to an output layer by an implicit layer, the number of neurons of the output layer is set to be 1, and the value range of n is 0-1;
S 3.2 training a model, namely training by using paired input samples and paired output samples, selecting 500 samples in a ecological red line protection demarcation area, wherein 350 samples are used for training a neural network, and 150 samples are used as test data;
S 3.3 the ecological risk evaluation is carried out on the data obtained by the data preprocessing module through the model obtained through training.
Further, in step S 3.2 The selection of the samples comprises samples of different geographical areas, including mountain areas, coastal areas, grasslands, forests, wetlands and farmlands; the method comprises the following steps:
S 6.1 by identifying and eliminating outliers, filtering and smoothing noise data by outlier detection and data smoothingSliding treatment;
S 6.2 firstly, carrying out data analysis by adopting a statistical analysis technology and a pattern recognition method, and particularly exploring and describing sample data through a statistical chart and data visualization, wherein the exploring and describing comprises drawing a histogram, a scatter diagram and a box diagram to obtain the distribution, variability and abnormal conditions of the sample data;
S 6.3 evaluating the correlation between different variables in sample data by calculating Pearson correlation coefficients and drawing a correlation matrix heat map;
S 6.4 converting high-dimensional data into low-dimensional principal components through principal component analysis PCA dimension reduction technology to obtain the structure and variability of the data, the data mode and the relevance;
S 6.5 dividing sample data into different groups or categories through a k-means clustering algorithm to obtain a natural grouping structure in display data, and obtaining a potential risk type or risk level of an ecosystem;
S 6.6 normalization of all variables using the mapmamax function of the Matlab tool, converting the range of values entered into [ -1,1 []The input variables consist of the total soil erosion amount, the water conservation amount, the soil desertification sensitivity index and the soil erosion sensitivity index according to the biodiversity index, and the target output of the network is an ecological system risk assessment index;
S 6.7 testing different integer values between 4 and 40 by the Kolmogorov theorem and finding the number of hidden layer neurons with the smallest error by loop iteration;
S 6.8 selecting a tan sig function as a transfer function of an implicit layer, and taking a purel in function as a transfer function of an output layer to improve the adaptability of the model to the problem;
S 6.9 through back propagation and optimization algorithm, continuously adjusting network weight and bias to reduce error and improve performance of model, and evaluating ecological risk.
Further, in step S 4 In the method, the ecological risk assessment index is divided into 5 grades according to the range of 0-1, namely 1 grade, 2 grade, 3 grade and 4 gradeAnd 5 grades, wherein the ecological risk assessment indexes corresponding to the 1 grade and the 2 grade are lowest and lower, which means that the ecological system has good health state and stability, complete ecological function and higher ecological service quality; the level 3 corresponding ecological risk assessment index is centered, which indicates that the ecological system is exposed to potential threat and pressure, and part of ecological functions can be influenced; the level 4 and the level 5 respectively correspond to the higher and highest ecological risk assessment indexes, which indicate that the ecological system is in a dangerous state, the ecological functions are seriously degraded, and serious ecological disasters and environmental problems possibly accompany the ecological system, so that urgent and comprehensive ecological restoration and protection are needed. The method comprises the steps of carrying out green early warning display on an ecological risk grade of 1, carrying out blue early warning display on a grade of 2, carrying out yellow early warning display on a grade of 3, carrying out orange early warning prompt on a grade of 4, carrying out red early warning prompt on a grade of 5, and simultaneously carrying out early warning or focusing attention prompt on the grades of 4 and 5.
Further, the present invention provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a main controller implements a method according to any one of the above methods, and performs data visualization display through a front-end processing device and a visualization platform for data integration and image preprocessing.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the ecological protection red line is accurately defined, the ecological risk assessment model based on the BP neural network model is constructed in the range of the ecological protection red line, the ecological risk is quantitatively assessed, the BP neural network model can effectively process input data with different dimensions, and a representative and diverse sample data set is selected by considering key and influencing factors of the ecological system risk assessment, so that the model can accurately reflect real conditions and has universality, and the model is gradually optimized through learning and training to obtain accurate output results. Meanwhile, the real-time monitoring and early warning functions are realized, the progress of the ecological system assessment is tracked and assessed through dynamic monitoring historical data and real-time data, and the assessment result and early warning information are presented in an intuitive mode through the data visualization and reporting functions, so that a complete closed loop of monitoring-early warning-processing is formed. The ecological risk assessment method and the early warning system are scientific, accurate and practical, and have important theoretical and practical significance for ecological protection and management work.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings are also obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a system block diagram of the present invention;
fig. 3 is a schematic diagram of BP neural network construction of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Referring to fig. 1-3, an ecological risk early warning system based on ecological protection red line demarcation,
the ecological risk early warning system based on ecological protection red line demarcation is provided, and comprises a data preprocessing module based on a Matlab tool, based on JavaScript and Python programming interfaces in a Google Earth Engine platform, calling NumPy, pandas, scikit-learn and an OpenCV library, and reading and processing large-scale remote sensing image data preprocessing by combining with an API of a GEE platform;
an index calculation module for carrying out ecological risk assessment index grading information on the data processed by the data preprocessing module;
the dynamic monitoring module is used for acquiring the data of the data preprocessing module and the index calculation module in real time or periodically, and updating and dynamically monitoring the data;
the early warning and decision support module is used for receiving the monitoring information transmitted by the dynamic monitoring module, triggering early warning and providing decision support through the change trend of the index and the threshold setting;
the visualization and reporting module is used for receiving the evaluation result and the early warning information in the early warning and decision support module and displaying the ecological risk distribution, the risk level, the spatial distribution of key influence factors, the evaluation result and the early warning information to a decision maker in an intuitive manner;
the data updating and continuous improvement module is used for visualizing and reporting the monitoring result information in the module and is responsible for periodically updating the data.
In the embodiment, the invention provides an ecological risk assessment method based on ecological protection red line demarcation, which is specifically implemented according to the following steps of;
S 1 the data preprocessing module calls NumPy, pandas, scikit-learn and OpenCV libraries based on Matlab tool and based on JavaScript and Python programming interface in Google Earth Engine platform, and reads and processes large-scale remote sensing image data by combining with API of GEE platform; the remote sensing image data and other data sources comprise sentinel No. 2 data with the spatial resolution of 10m, DEM topographic data with the spatial resolution of 12.5m and spatial resolutionThe soil utilization data of 10m and the soil data of 1:1000000 with the spatial resolution of 1km are the survey data of rainfall, air temperature and evaporative meteorological data of each site in a research area;
the remote sensing image data preprocessing comprises cloud processing, radiometric calibration, atmospheric correction, format conversion and cutting, and the meteorological data processing mainly comprises missing value elimination, interpolation, projection and cutting.
S 2 Specifically obtaining water and soil conservation data, water conservation data and biodiversity protection data in a monitored area through an index calculation module, and respectively adopting a Quantile function and combining qualitative analysis according to the total soil erosion amount, the water conservation capacity and the biodiversity index BI;
S 3 dividing three results of the total soil erosion amount, the water conservation capacity and the biological diversity index BI into 3 grades of a high-grade protection grade, a medium-grade warning grade and a low-grade restoration grade through an index calculation module, respectively extracting low-grade areas of water and soil conservation, water conservation and biological diversity protection, carrying out superposition analysis on the three evaluation results to obtain an overlapped area, and setting the overlapped area into a service function red line area of a biological system; the ecological environment sensitivity is evaluated and graded by constructing two indexes of soil desertification sensitivity and soil erosion sensitivity;
S 4 according to the soil desertification sensitivity index and the soil erosion sensitivity index, respectively, dividing the two results into 3 grades, namely general sensitivity, sensitivity and extremely sensitivity, extracting a soil desertification extremely sensitive area and a soil erosion extremely sensitive area, and performing superposition analysis calculation on the two types of sensitive red line areas to obtain an ecological environment sensitive red line area by adopting a method combining a natural breakpoint method and qualitative analysis;
S 5 and performing superposition analysis on the ecosystem service function red line area and the ecosystem sensitive red line area to obtain a final ecological red line protection demarcation area.
In the present embodiment, in step S 1 Wherein the calculation of the soil and water conservation data is based on the RUSLE soil erosion modelMaintaining to evaluate, and calculating the soil erosion amount by combining the land utilization, gradient and rainfall data;
the water conservation is calculated based on a water balance equation, and the related input variables comprise the amount of precipitation, surface runoff, evaporation and the number of types of ecosystems;
the biodiversity protection is to construct a biodiversity monitoring and evaluating index system from the landscape structure LDI, the species diversity SDI and the ecological system quality EQU.
In the present embodiment, in step S 2 In the method, the desertification sensitivity of the area is evaluated by adopting a wettability index, soil texture, days of wind generation and vegetation coverage;
soil erosion sensitivity is evaluated by comprehensively considering rainfall, landform, vegetation and soil texture factors on the basis of a general soil erosion equation USLE.
In the present embodiment, in step S 3 In the method, ecological risk evaluation is carried out based on a BP neural network model, and the method specifically comprises the following steps of:
S 3.1 firstly, training a BP neural network model, wherein the training process of the model uses paired input samples and output samples for training, and neurons of the model are expressed in a layer form and comprise three parts, namely an input layer, an implicit layer and an output layer;
wherein the formula of the input layer is as formula (1);
wherein Ci is the ith index of the neurons of the input layer, namely the total soil erosion amount, the water conservation amount, the soil desertification sensitivity index and the soil erosion sensitivity index according to the biodiversity index, and m is the number of the indexes of the neurons of the input layer, and the value is 5;
hidden layer calculation is shown as formula (2);
wherein N is the number of neurons of an hidden layer, the value is 7, N is the number of neurons of an output layer, and a is a constant between 0 and 10;
the calculation formula of the output layer is shown as formula (3);
dj is an ecological system risk assessment index obtained by j variables transmitted to an output layer by an implicit layer, the number of neurons of the output layer is set to be 1, and the value range of n is 0-1;
S 3.2 training a model, namely training by using paired input samples and paired output samples, selecting 500 samples in a ecological red line protection demarcation area, wherein 350 samples are used for training a neural network, and 150 samples are used as test data;
S 3.3 the ecological risk evaluation is carried out on the data obtained by the data preprocessing module through the model obtained through training.
In the present embodiment, in step S 3.2 The selection of the samples comprises samples of different geographical areas, including mountain areas, coastal areas, grasslands, forests, wetlands and farmlands; the method comprises the following steps:
S 6.1 adopting outlier detection and data smoothing technology, identifying and removing abnormal values, and filtering and smoothing noise data;
S 6.2 firstly, carrying out data analysis by adopting a statistical analysis technology and a pattern recognition method, and particularly exploring and describing sample data through a statistical chart and data visualization, wherein the exploring and describing comprises drawing a histogram, a scatter diagram and a box diagram to obtain the distribution, variability and abnormal conditions of the sample data;
S 6.3 evaluating the correlation between different variables in sample data by calculating Pearson correlation coefficients and drawing a correlation matrix heat map;
S 6.4 through the main partThe PCA dimension reduction technology converts high-dimensional data into low-dimensional main components to obtain the structure and variability of the data, and the data mode and relevance;
S 6.5 dividing sample data into different groups or categories through a k-means clustering algorithm to obtain a natural grouping structure in display data, and obtaining a potential risk type or risk level of an ecosystem;
S 6.6 normalization of all variables using the mapmamax function of the Matlab tool, converting the range of values entered into [ -1,1 []The input variables consist of the total soil erosion amount, the water conservation amount, the soil desertification sensitivity index and the soil erosion sensitivity index according to the biodiversity index, and the target output of the network is an ecological system risk assessment index;
S 6.7 testing different integer values between 4 and 40 by the Kolmogorov theorem and finding the number of hidden layer neurons with the smallest error by loop iteration;
S 6.8 selecting a tan sig function as a transfer function of an implicit layer, and taking a purelin function as a transfer function of an output layer to improve the adaptability of the model to the problem;
S 6.9 through back propagation and optimization algorithm, continuously adjusting network weight and bias to reduce error and improve performance of model, and evaluating ecological risk.
The optimization algorithm adopts a self-adaptive learning rate method, dynamically adjusts the learning rate according to the gradient magnitude and the history updating condition of each weight, uses a larger learning rate in the initial stage of training to accelerate the convergence rate, and uses a smaller learning rate in the later stage of training to improve the stability and convergence accuracy of the model, and is specifically shown as a formula (4) -a formula (8);
r＝ρr+(1-ρ)g 2 (4)
θ t+1 ＝ρθ t +(1-ρ)v t (5)
Wherein ρ is an attenuation coefficient, g is a gradient, θ t+1 A shift step value, θ, representing the parameter at the t+1st iteration t Representing parameters at the t-th iterationMove step value, v t Is the update amount at the t-th iteration.
Wherein r is t+1 Represents the cumulative gradient squared, g, at the t+1st iteration t+1 Representing the gradient value at the t+1st iteration, epsilon being a constant set to avoid the occurrence of denominators of 0;
the problem of overfitting is avoided, an L2 regularization technology is introduced, regularization items are added to an error function, the complexity of a model is restrained, the oversized weight is prevented, the generalization capability of the model is improved, and the L2 regularization model is as follows:
wherein L is a loss function, y (i) Andrespectively the predicted value and the true value of the ith sample, W is a weight, b is a bias value, m is the number of samples, n x For the network layer number, lambda is the super parameter;
introducing batch normalization operation into each hidden layer of the network, wherein the batch normalization can accelerate the training process of the network, reduce the problems of gradient disappearance and gradient explosion, and improve the adaptability of the network to input data;
by adopting the Dropout technology, the overfitting of the neural network is reduced, and in the training process, the output of part of neurons is set to zero with a certain probability, so that the network is forced to learn redundancy characteristics, the generalization capability of the network is improved, and the model is as follows:
y= (Xe M) Ω (8)
Wherein X is an input variable, e is a product of pixel by pixel, Ω is a weight matrix, Y is an output result, M is a mask obeying Bernoulli distribution, each element of the mask generates 1 with probability p, generates 0 with probability 1-p, and in a training stage, the Dropout method randomly makes the mask 0 with a certain probability;
through the use of different initial weights or parameter settings, integrated learning is carried out, each BP neural network model can develop unique feature extraction capacity and generalization capacity in the training process, each model can model and predict ecological risks from different angles, different data modes and correlations are captured, and prediction results of the models are integrated; the integration method adopts a weighted average technology, and comprehensively considers the prediction results of each model according to the performance and the confidence coefficient of each model to obtain a final ecological risk assessment index. To accommodate the needs of different data sets and problems.
In the present embodiment, in step S 4 The ecological risk assessment indexes are divided into 5 levels, namely 1 level, 2 level, 3 level, 4 level and 5 level according to the range of 0-1, wherein the ecological risk assessment indexes corresponding to the 1 level and the 2 level are lowest and lower, which means that the ecological system has good health state and stability, complete ecological function and higher ecological service quality; the level 3 corresponding ecological risk assessment index is centered, which indicates that the ecological system is exposed to potential threat and pressure, and part of ecological functions can be influenced; the level 4 and the level 5 respectively correspond to the higher and highest ecological risk assessment indexes, which indicate that the ecological system is in a dangerous state, the ecological functions are seriously degraded, and serious ecological disasters and environmental problems possibly accompany the ecological system, so that urgent and comprehensive ecological restoration and protection are needed. The method comprises the steps of carrying out green early warning display on an ecological risk grade of 1, carrying out blue early warning display on a grade of 2, carrying out yellow early warning display on a grade of 3, carrying out orange early warning prompt on a grade of 4, carrying out red early warning prompt on a grade of 5, and simultaneously carrying out early warning or focusing attention prompt on the grades of 4 and 5.
In this embodiment, the present invention provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a main controller implements a method according to any one of the foregoing methods, and performs data visualization display through a front-end processing device and a visualization platform for data integration and image preprocessing.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. Ecological risk early warning system based on ecological protection red line is delimited, its characterized in that: the system comprises a data preprocessing module, a data preprocessing module and a remote sensing image processing module, wherein the data preprocessing module is based on a Matlab tool, based on JavaScript and Python programming interfaces in a Google Earth Engine platform, calls NumPy, pandas, scikit-learn and an OpenCV library, and reads and processes large-scale remote sensing image data preprocessing by combining an API of a GEE platform;
an index calculation module for carrying out ecological risk assessment index grading information on the data processed by the data preprocessing module;
the dynamic monitoring module is used for acquiring the data of the data preprocessing module and the index calculation module in real time or periodically, and updating and dynamically monitoring the data;
the early warning and decision support module is used for receiving the monitoring information transmitted by the dynamic monitoring module, triggering early warning and providing decision support through the change trend of the index and the threshold setting;
the visualization and reporting module is used for receiving the evaluation result and the early warning information in the early warning and decision support module and displaying the ecological risk distribution, the risk level, the spatial distribution of key influence factors, the evaluation result and the early warning information to a decision maker in an intuitive manner;
the data updating and continuous improvement module is used for visualizing and reporting the monitoring result information in the module and is responsible for periodically updating the data.
2. The ecological risk assessment method based on ecological protection red line demarcation is characterized by comprising the following steps of: the method is specifically carried out according to the following steps of;
S 1 data preprocessing module based on Matlab tool, programming interface based on JavaScript and Python in Google Earth Engine platform, calling NumPy, pandas, scikit-learn, openCV library, and reading and processing large-scale remote sensing image data by combining with API of GEE platform;
S 2 specifically obtaining water and soil conservation data, water conservation data and biodiversity protection data in a monitored area through an index calculation module, and respectively adopting a Quantile function and combining qualitative analysis according to the total soil erosion amount, the water conservation capacity and the biodiversity index BI;
S 3 dividing three results of the total soil erosion amount, the water conservation capacity and the biological diversity index BI into 3 grades of a high-grade protection grade, a medium-grade warning grade and a low-grade restoration grade through an index calculation module, respectively extracting low-grade areas of water and soil conservation, water conservation and biological diversity protection, carrying out superposition analysis on the three evaluation results to obtain an overlapped area, and setting the overlapped area into a service function red line area of a biological system; the ecological environment sensitivity is evaluated and graded by constructing two indexes of soil desertification sensitivity and soil erosion sensitivity;
S 4 according to the soil desertification sensitivity index and the soil erosion sensitivity index, respectively, dividing the two results into 3 grades, namely general sensitivity, sensitivity and extremely sensitivity, extracting a soil desertification extremely sensitive area and a soil erosion extremely sensitive area, and performing superposition analysis calculation on the two types of sensitive red line areas to obtain an ecological environment sensitive red line area by adopting a method combining a natural breakpoint method and qualitative analysis;
S 5 and performing superposition analysis on the ecosystem service function red line area and the ecosystem sensitive red line area to obtain a final ecological red line protection demarcation area.
3. The ecological risk assessment method based on ecological protection red line demarcation according to claim 2, characterized in that: in step S 1 Wherein the calculation of the soil and water conservation data is based on the RUSLE soil erosion model to evaluate the soil and water conservation, and the soil utilization and slope are combinedCalculating soil erosion amount according to the rainfall data;
the water conservation is calculated based on a water balance equation, and the related input variables comprise the amount of precipitation, surface runoff, evaporation and the number of types of ecosystems;
the biodiversity protection is to construct a biodiversity monitoring and evaluating index system from the landscape structure LDI, the species diversity SDI and the ecological system quality EQU.
4. The ecological risk assessment method based on ecological protection red line demarcation according to claim 2, characterized in that in step S 2 In the method, the desertification sensitivity of the area is evaluated by adopting a wettability index, soil texture, days of wind generation and vegetation coverage;
soil erosion sensitivity is evaluated by comprehensively considering rainfall, landform, vegetation and soil texture factors on the basis of a general soil erosion equation USLE.
5. The ecological risk assessment method based on ecological protection red line demarcation according to claim 2, characterized in that in step S 3 In the method, ecological risk evaluation is carried out based on a BP neural network model, and the method specifically comprises the following steps of:
S 3.1 firstly, training a BP neural network model, wherein the training process of the model uses paired input samples and output samples for training, and neurons of the model are expressed in a layer form and comprise three parts, namely an input layer, an implicit layer and an output layer;
wherein the formula of the input layer is as formula (1);
input layer
Wherein Ci is the ith index of the neurons of the input layer, namely the total soil erosion amount, the water conservation amount, the soil desertification sensitivity index and the soil erosion sensitivity index according to the biodiversity index, and m is the number of the indexes of the neurons of the input layer, and the value is 5;
hidden layer calculation is shown as formula (2);
wherein N is the number of neurons of an hidden layer, the value is 7, N is the number of neurons of an output layer, and a is a constant between 0 and 10;
the calculation formula of the output layer is shown as formula (3);
dj is an ecological system risk assessment index obtained by j variables transmitted to an output layer by an implicit layer, the number of neurons of the output layer is set to be 1, and the value range of n is 0-1;
S 3.2 training a model, namely training by using paired input samples and paired output samples, selecting 500 samples in a ecological red line protection demarcation area, wherein 350 samples are used for training a neural network, and 150 samples are used as test data;
S 3.3 the ecological risk evaluation is carried out on the data obtained by the data preprocessing module through the model obtained through training.
6. The ecological risk assessment method based on ecological protection red line demarcation as described in claim 5, wherein in step S 3.2 The selection of the samples comprises samples of different geographical areas, including mountain areas, coastal areas, grasslands, forests, wetlands and farmlands; the method comprises the following steps:
S 6.1 adopting outlier detection and data smoothing technology, identifying and removing abnormal values, and filtering and smoothing noise data;
S 6.2 firstly, data analysis is carried out by adopting a statistical analysis technology and a pattern recognition method, and particularly, a statistical chart and data visualization are adoptedThe method comprises the steps of exploring and describing sample data, including drawing a histogram, a scatter diagram and a box diagram, and obtaining distribution, variability and abnormal conditions of the sample data;
S 6.3 evaluating the correlation between different variables in sample data by calculating Pearson correlation coefficients and drawing a correlation matrix heat map;
S 6.4 converting high-dimensional data into low-dimensional principal components through principal component analysis PCA dimension reduction technology to obtain the structure and variability of the data, the data mode and the relevance;
S 6.5 dividing sample data into different groups or categories through a k-means clustering algorithm to obtain a natural grouping structure in display data, and obtaining a potential risk type or risk level of an ecosystem;
S 6.6 normalization of all variables using the mapmamax function of the Matlab tool, converting the range of values entered into [ -1,1 []The input variables consist of the total soil erosion amount, the water conservation amount, the soil desertification sensitivity index and the soil erosion sensitivity index according to the biodiversity index, and the target output of the network is an ecological system risk assessment index;
S 6.7 testing different integer values between 4 and 40 by the Kolmogorov theorem and finding the number of hidden layer neurons with the smallest error by loop iteration;
S 6.8 selecting a tan sig function as a transfer function of an implicit layer, and taking a purelin function as a transfer function of an output layer to improve the adaptability of the model to the problem;
S 6.9 through back propagation and optimization algorithm, continuously adjusting network weight and bias to reduce error and improve performance of model, and evaluating ecological risk.
7. The ecological risk assessment method based on ecological protection red line demarcation according to claim 2, characterized in that in step S 4 In the method, the ecological risk assessment index is divided into 5 levels in the range of 0-1, namely 1 level, 2 level, 3 level, 4 level and 5 level, wherein the 1 level and 2 level correspond to the ecological riskThe assessment index is lowest and lower, and the ecological risk assessment index corresponding to level 3 is centered; the ecological risk assessment indexes corresponding to the class 4 and class 5 respectively are higher and highest.
8. The ecological risk assessment method based on ecological protection red line demarcation according to claim 7, wherein the early warning and decision support module is used for carrying out green early warning display on the ecological risk level 1, blue early warning display on the level 2, yellow early warning display on the level 3, orange early warning prompt on the level 4, red early warning prompt on the level 5, and early warning or focusing attention prompt on the levels 4 and 5.
9. The ecological risk assessment method based on ecological protection red line demarcation according to claim 2, wherein the remote sensing image data and other data sources comprise sentinel No. 2 data with a spatial resolution of 10m, DEM terrain data with a spatial resolution of 12.5m, land utilization data with a spatial resolution of 10m, 1:1000000 soil data with a spatial resolution of 1km, and survey data of rainfall, air temperature and evaporative emission meteorological data of each site in a research area;
the remote sensing image data preprocessing comprises cloud processing, radiometric calibration, atmospheric correction, format conversion and cutting, and the meteorological data processing mainly comprises missing value elimination, interpolation, projection and cutting.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a main controller implements the method according to any one of claims 1-9, and the data is visualized by a front-end processing device and a visualization platform for data integration and image preprocessing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311471889.7A CN117522117A (en) | 2023-11-07 | 2023-11-07 | Ecological risk assessment method and early warning system based on ecological protection red line demarcation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311471889.7A CN117522117A (en) | 2023-11-07 | 2023-11-07 | Ecological risk assessment method and early warning system based on ecological protection red line demarcation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117522117A true CN117522117A (en) | 2024-02-06 |
Family
ID=89754329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311471889.7A Pending CN117522117A (en) | 2023-11-07 | 2023-11-07 | Ecological risk assessment method and early warning system based on ecological protection red line demarcation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117522117A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853938A (en) * | 2024-03-08 | 2024-04-09 | 鲸服科技有限公司 | Ecological monitoring system and method based on image recognition |
-
2023
- 2023-11-07 CN CN202311471889.7A patent/CN117522117A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853938A (en) * | 2024-03-08 | 2024-04-09 | 鲸服科技有限公司 | Ecological monitoring system and method based on image recognition |
| CN117853938B (en) * | 2024-03-08 | 2024-05-10 | 鲸服科技有限公司 | Ecological monitoring system and method based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fijani et al. | Optimization of DRASTIC method by supervised committee machine artificial intelligence to assess groundwater vulnerability for Maragheh–Bonab plain aquifer, Iran | |
| CN108918815B (en) | Method for predicting heavy metal risk of soil | |
| CN108536908B (en) | Method for evaluating watershed water environment safety based on non-point source nitrogen and phosphorus loss risk | |
| Whittaker et al. | Detection of overparameterization and overfitting in an automatic calibration of SWAT | |
| CN112734694A (en) | Water quality monitoring method based on big data | |
| CN113408917B (en) | Natural disaster risk assessment method, device, computer equipment and storage medium | |
| CN117522117A (en) | Ecological risk assessment method and early warning system based on ecological protection red line demarcation | |
| CN112903606B (en) | Mangrove forest ecological restoration force assessment method based on unmanned aerial vehicle hyperspectrum | |
| CN117009887B (en) | Method and system for finely estimating and analyzing water environment quality of river basin | |
| Sadeghfam et al. | Next stages in aquifer vulnerability studies by integrating risk indexing with understanding uncertainties by using generalised likelihood uncertainty estimation | |
| CN116628519B (en) | Ecological fragile area identification method and system | |
| Noor et al. | Prediction map of rainfall classification using random forest and inverse distance weighted (IDW) | |
| CN116110210B (en) | Data-driven landslide hazard auxiliary decision-making method in complex environment | |
| Jager et al. | Cokriging to assess regional stream quality in the southern blue ridge province | |
| CN112907113A (en) | Vegetation change cause identification method considering spatial correlation | |
| Moradpanah et al. | Evaluation of Ecological Vulnerability of Coasts of the Caspian Sea Based on Multi-Criteria Decision Methods (Iran) | |
| CN116091103A (en) | Method, device, electronic equipment and medium for measuring and calculating periodic environment remediation | |
| CN113340898B (en) | Leaf area index space-time change characteristic research method | |
| Hu et al. | A Bayesian-based two-stage inexact optimization method for supporting stream water quality management in the Three Gorges Reservoir region | |
| Saranya et al. | A comparative evaluation of streamflow prediction using the SWAT and NNAR models in the Meenachil River Basin of Central Kerala, India | |
| Diaz-Ramirez et al. | Impacts of land use characterization in modeling hydrology and sediments for the Luxapallila Creek Watershed, Alabama and Mississippi | |
| Fortin | Spatial structure in population data | |
| Sulistyo et al. | Refining The Suitability Modeling of Sea Cucumber (Holothuria scabra) Using Fully Raster-Based Data | |
| CN113822495B (en) | Growth state prediction method, device, equipment and medium based on machine learning model | |
| CN117541078B (en) | Ecological protection strategy customizing method based on artificial canal development |
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 |