CN114970302B - Regional groundwater condition prediction method based on groundwater monitoring system - Google Patents
Regional groundwater condition prediction method based on groundwater monitoring system Download PDFInfo
- Publication number
- CN114970302B CN114970302B CN202210500900.7A CN202210500900A CN114970302B CN 114970302 B CN114970302 B CN 114970302B CN 202210500900 A CN202210500900 A CN 202210500900A CN 114970302 B CN114970302 B CN 114970302B
- Authority
- CN
- China
- Prior art keywords
- groundwater
- prediction
- observation
- water
- prediction result
- 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.)
- Active
Links
- 239000003673 groundwater Substances 0.000 title claims abstract description 154
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 18
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 134
- 238000005086 pumping Methods 0.000 claims abstract description 42
- 238000009826 distribution Methods 0.000 claims description 49
- 238000003809 water extraction Methods 0.000 claims description 26
- 239000002245 particle Substances 0.000 claims description 18
- 238000009499 grossing Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 10
- 238000012417 linear regression Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 239000002349 well water Substances 0.000 claims description 5
- 235000020681 well water Nutrition 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000001556 precipitation Methods 0.000 claims description 4
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 238000011002 quantification Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 34
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 238000013398 bayesian method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- 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
- 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
- G06Q50/06—Energy or water supply
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a regional groundwater condition prediction method based on a groundwater monitoring system, which comprises the following steps: by combining observation data in a groundwater observation system with real-time monitoring data, based on SVR, a water pumping quantity prediction function and a water pumping quantity-groundwater water level prediction function of each observation well are established, and the groundwater level is predicted in real time, so that the problems that the conventional groundwater condition estimation modeling is long in time consumption and needs a large amount of hydrogeological parameters, and the conventional groundwater condition estimation modeling is limited by complicated geological conditions, uncertainty of water condition prediction parameters, mathematical modeling burden and other factors are solved, a relatively accurate regional groundwater condition quantification prediction tool is not formed, accurate prediction of each part of the regional groundwater condition cannot be refined, and urban, town regional groundwater management cannot be well serviced.
Description
Technical Field
The invention belongs to the technical field of computer machine learning, and particularly relates to a regional groundwater condition prediction method based on a groundwater monitoring system.
Background
The more serious the application of water resources is under the influence of climate change and uneven water resource distribution in most areas of China, the less the related groundwater hydrologic data is because of complex hydrogeological conditions. Because the groundwater has the characteristics of stable water quantity, good water quality and the like, the groundwater is one of important water sources for agricultural irrigation, enterprise production and urban resident life, and particularly in arid and semiarid regions where the surface is deficient in water, the groundwater is often used as a local main water source. In the regional water supply problem, the underground water resource plays a vital role, and if the underground water resource is not properly managed, the overuse of the underground water resource easily causes problems such as stratum subsidence and collapse, causes the water resource attenuation in local areas, even causes the underground water pollution problem, and brings serious environmental problems. In 2020, the whole North China plain has a tendency of lowering of underground water level due to the fact that rainfall is generally low in recent years. Therefore, reasonable use of groundwater resources is necessary to be enhanced, scientific and effective supervision is implemented, the safety of groundwater is protected, and sustainable development and utilization of groundwater resources are promoted.
The traditional underground water condition estimation is to calculate the available water quantity of the underground water system by various hydraulic tests and numerical modes, modeling is long in time consumption and needs a large amount of hydrogeologic parameters, the modeling is limited by complicated geological conditions, uncertainty of water condition prediction parameters, mathematical modeling burden and other factors, a precise regional underground water condition quantitative prediction tool is not formed, precise prediction of the underground water condition of each part of the region cannot be refined, regional water supply management cannot be well served, and particularly, water supply is stopped, water supply is limited, water supply quantity is limited and water supply time is deployed according to a single early warning parameter model, so that inconvenience is caused to life of residents, and enterprise production or engineering scheduling is even influenced.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to provide the regional groundwater condition prediction method based on the groundwater monitoring system, which can solve the problems that the traditional estimation modeling of the groundwater condition consumes a long time and needs a large amount of hydrogeologic parameters, is limited by complex geological conditions, uncertainty of the water condition prediction parameters, mathematical modeling burden and other factors, does not form a precise regional groundwater condition quantification prediction tool, cannot refine the precise prediction of each part of the regional groundwater condition, and cannot well serve the management of the regional groundwater in cities, towns and villages.
In order to solve the problems, the invention provides a regional groundwater condition prediction method based on a groundwater monitoring system, which comprises the following steps:
s1: establishing a water extraction quantity prediction function and a water extraction quantity-groundwater level prediction function of each observation well based on SVR by combining observation data in a groundwater observation system with real-time monitoring data and based on support vector regression;
s2: calculating the pumping-water level drainage relation between a pumping well and a corresponding observation well by using a Markov-Monte Carlo method, simultaneously calculating a plurality of groundwater water condition parameters by using observation data monitored in real time by using the observation network, obtaining particles to approximate posterior probability distribution by iterative screening on samples based on probability distribution established by Bayesian theory, and simultaneously calculating a water level prediction result of each observation well and a water pumping prediction result of each observation well so as to avoid coupling among each prediction parameter;
s3: according to the coordinates and distribution conditions of the observation wells, defining a prediction area covering all the observation wells, covering the whole monitoring network area by the prediction area, and performing grid division on the whole prediction area to generate n multiplied by n grid points;
s4: constructing Thiessen polygons of a monitoring network area, and combining Euclidean distance transformation to correspond to a coordinate set U e Is incorporated into the observation well coordinate set U m Wherein, two-dimensional array U is formed m+e Reconsolidating Thiessen polygon vertex coordinate set U V Coordinate point set U for forming two-dimensional array representation set observation well coordinates, euclidean distance transformation coordinates and Thiessen polygon vertex coordinates m+e+V ；
Simulating a prediction area covering the whole monitoring network according to a Thiessen polygon constructed by an observation area by utilizing the observation well water level prediction result, assigning values to the generated n multiplied by n grid points, and setting a Thiessen polygon V of an observation well i in the Thiessen polygon i Assigning the regional grid points to obtain the ground water level prediction result of the observation well i, and assigning the water pumping prediction result of the observation well to V at the same time i Regional networkGrid points are used for generating a preliminary prediction result of the water pumping quantity of the area and generating a preliminary prediction result of the groundwater level of the area;
s5: constructing a convex polygon point set U containing all scattered points by observing well coordinates, euclidean distance transformation coordinates and Thiessen polygon vertex coordinates m+e+V Dividing the convex polygon into mutually disjoint triangles, adjusting adjacent triangles to obtain weighted triangulation, calculating through triangle interpolation values, correcting according to the preliminary prediction results corresponding to each point in the coordinate point set, and correcting the generated preliminary prediction results of groundwater level-water pumping area distribution in real time;
s6: smoothing the corrected groundwater level-water pumping distribution area water regime prediction result by using a Gaussian smoothing function to obtain a final prediction result, further correcting the prediction result by using a gradient double-threshold detection, carrying out statistical analysis on the groundwater regime prediction result by using a support vector regression algorithm and the groundwater regime prediction result by using a Markov-Monte Carlo algorithm, creating an array of preservation results according to the accuracy of comparing the analysis prediction results with the residual error statistical distribution, and determining a preservation optimization prediction model as a stable groundwater level prediction system model.
Optionally, S1 specifically includes the following steps:
s11: establishing a training sample set according to time sequence corresponding to different observation well coordinatesHistorical observation data representing the pumping capacity, and establishing a training sample set according to time series corresponding to different observation well coordinates>Historical observation data representing groundwater level;
s12: training a model function in sample space under the following constraintsy i Epsilon { -1, +1}, relaxation variable ζ i 0 or more, relaxation variable, eta i Gtoreq 0, i=0, 1,2 … t, i representing the i-th time point; t represents the total number of observation time points; the loss function is:
wherein C is>A constant of 0; epsilon gives the position of the decision surface; μ represents a normal vector of the decision plane; zeta type toy i And eta i Is a relaxation variable; meets the optimization target to obtain the precipitation prediction model function f 1 (x a ，t i ) Wherein t is i Time x is represented a Representing the water extraction;
under the following constraint conditionsObtaining a groundwater level prediction model function f 2 (x a ，x b ) Wherein x is a Representing the water extraction; x is x b Representing groundwater level; the water pumping quantity and the groundwater level at the future moment are predicted in real time;
s13: data on water extraction observationsAnd historical observations of groundwater level +.>And (3) performing linear regression, constructing various water pumping quantity-groundwater level linear regression models, calculating to obtain residual errors, performing comparative analysis, comparing the prediction result of the linear regression model function with the groundwater level result of support vector regression prediction, and analyzing the prediction precision to obtain an optimized model.
Optionally, in step S2, a pumping-water level drainage relationship between the pumping well and the observation well corresponding to the pumping well is calculated based on a markov-monte carlo method, so as to avoid coupling between each predicted parameter, and specifically includes the following steps:
s21: establishing a probability model for continuously calculating water regime parameters based on a Bayesian theory, wherein the water regime observation historical data can calculate probability distribution of a plurality of water regime parameters including water pumping quantity and groundwater level at the same time;
setting t 0 Time t 0 Each observation well and the collected water condition observation data before the moment are X t Posterior probability P (x a ,x b ,t|X t ) Can be expressed as:
wherein x is a Representing the water extraction; x is x b Representing groundwater level; t is t 0 Predicting a starting time; t is t
Is the predicted time;
s22: sample taking simplified model phi t (x a ，x b ，t|X t ) Q (·) is a priori distributed P (phi) in conformity with the q distribution t |φ t-1 ) I represents the ith particle conforming to the q distribution, denoted ast represents the moment, iterated by i=1, …, N loops;
the posterior probability distribution can be approximated as:
wherein the first weight coefficient v of the ith particle at time t t i The total number may be normalized to 1,n is the total number of particles, and delta represents the equal proportion probability;
based on updated observed data X t In the calculation of the water regime parameters, all particle weights are re-normalized to:
wherein L (X) t |φ t )＝L(X t |x a ，x b T) as a second weight coefficient, calculating the water pumping-water level drainage relation of the water pumping well and the observation well corresponding to the water pumping well through a plurality of particles with weights, and constructing a regional groundwater condition prediction model.
Optionally, S3 specifically includes the following steps:
s31: defining a prediction area covering all observation wells according to the coordinates and distribution conditions of the observation wells, wherein the prediction area covers the whole monitoring network area, and carrying out grid division on the prediction area and establishment of an observation well coordinate array based on real-time monitoring data provided by the monitoring network;
s32: based on the grid divided by the prediction area, a two-dimensional array of the grid point area center is created with the abscissa (x n ，y n ) An n×n region U as the center n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Initializing all points in the array as an identity matrix function, wherein l and h are the distances between adjacent grid points in the x direction and the y direction respectively, and x n ＝l×n，y n ＝h×n；
S33: constructing a two-dimensional array U corresponding to the position coordinates of the observation well m ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x m-1 ,y m-1 ),(x m ,y m )}，(x m ，y m ) Is U (U) m The water regime prediction result corresponding to the m observation well.
Optionally, S4 specifically includes the following steps:
s41: construction of Thiessen polygons for monitoring network areas: constructing Thiessen polygons for the predicted area according to the N observation well coordinates, and generating Thiessen polygons by taking the neighboring observation wells as perpendicular bisectors, namely V N A figure;
v constructed according to the observation area by using the observation well water level prediction result N The map pair covers the whole monitoringSimulating a prediction area of the net, assigning values to the generated n multiplied by n grid points, and setting a Thiessen polygon V of an observation well i in the Thiessen polygons i Assigning the regional grid points to obtain the ground water level prediction result of the observation well i, and assigning the water pumping prediction result of the observation well to V at the same time i Regional grid points;
s42: in D f (x i ，y i ) Representing coordinates (x) i ，y i ) Is calculated as the Euclidean distance transform of f (x j ，y j ) Representing coordinates (x) j ，y j ) The consumption function of (x) i ,y i )∈U n ，(x j ,y j )∈U n ，D f (x i ,y i )＝min(((x i ,y i )-(x j ,y j )) 2 +f(x j ,y j ) Traversing n x n region U) n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Calculating to obtain a coordinate set U corresponding to Euclidean distance transformation e Is incorporated into the observation well coordinate set U m Wherein, two-dimensional array U is formed m+e Combining Thiessen polygon vertex coordinate set U V Forming a coordinate set U corresponding to the two-dimensional array representation set observation well coordinates and Euclidean distance transformation e Coordinate point set U of coordinates and Thiessen polygon vertex coordinates m+e+V 。
Optionally, S5 specifically includes the following steps:
s51: the generated two-dimensional array corresponds to the position coordinates of the observation well and the Euclidean distance is transformed to a corresponding coordinate set U e Two-dimensional array U of coordinates and Thiessen polygon vertex coordinates m+e+V Each coordinate point corresponds to U m+e+V Corresponding water condition prediction result of observation well, U m+e+V Each coordinate point corresponds to a time sequence groundwater condition prediction result, which is formed by U m+e+V The points in (a) are used as end points to form a closed line segment of the triangulation network;
S52：U m+e+V the points in the mesh are used as end points to form a triangular mesh convex polygonPoint U n The point set of the medium envelope is U k ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x k-1 ,y k-1 ),(x k ,y k ) Any two points of which weight is omega ij Dividing the convex polygon into a plurality of mutually disjoint triangles to generate a triangle net with weight;
s53: the structure comprises U m+e+V Triangle subdivision of all coordinate point areas is obtained by recursion, triangle subdivision of a triangular net is obtained, triangle interpolation calculation is carried out on the triangular net, and each coordinate point set U in the triangular net is obtained k And further correcting the corresponding time sequence water extraction prediction result and the groundwater level prediction result, and optimizing and updating the generated preliminary prediction result.
Optionally, S6 specifically includes the following steps:
S61：U n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Each center of grid points in the } region (x i ,y i ) The gaussian kernel is constructed as follows:
wherein sigma is the standard deviation of Gaussian distribution in a Gaussian kernel generator, and represents the discrete degree of prediction result data;
s62: carrying out Gaussian smoothing on the corrected water extraction prediction result and the groundwater level prediction result, calculating transverse gradients and longitudinal gradients of the prediction result by adopting a sobel function, carrying out edge detection by adopting a canny function to set double thresholds, carrying out double threshold detection by utilizing a weak gradient value, and further correcting the prediction result of the whole area to obtain a final prediction result;
s63: smoothing the generated prediction result by adopting a Gaussian smoothing function based on the actually measured data, further correcting to obtain a final prediction result, and simulating regional distribution of the groundwater condition prediction result by adopting a regression algorithm of SVR and the groundwater condition prediction result calculated based on a Markov-Monte Carlo method;
s64: based on the comparison of the predicted results of different algorithms, the precision and the calculation efficiency of prediction are statistically analyzed, the temperature and rainfall or/and snowfall and surface subsidence information during monitoring are added, the influence of different conditions on the final predicted result is analyzed, and a regional groundwater water regime prediction model with robustness is stored according to the precision and the calculation efficiency analysis.
Advantageous effects
The regional groundwater condition prediction method based on the groundwater monitoring system provided by the embodiment of the invention can realize the prediction of the whole groundwater condition in the whole monitoring region, is not influenced by the positions of observation wells and the distribution conditions of the observation wells, can predict whether the observation data are sufficient or not, only can obtain the observation data in a plurality of limited observation wells and pumping wells (groups) which are discretely distributed in the periphery of the monitoring region, and can simultaneously perform the comparison analysis of precision and calculation efficiency aiming at a plurality of different prediction methods through the existing observation data, refine the groundwater level distribution of each partial region of the prediction region and reflect the groundwater condition of each partial region of the prediction region in real time. In addition, the invention can realize the prediction of groundwater conditions by constructing a water extraction prediction function and establishing a water extraction-groundwater level drainage relation function, can also reduce the coupling between the water extraction and the groundwater level, and simultaneously establishes the water extraction-groundwater level drainage relation prediction function based on a Markov-Monte Carlo method. And according to the accuracy analysis of the actual case prediction result, storing a regional groundwater condition prediction model with robustness. The problems that the traditional underground water regime estimation modeling is long in time consumption and needs a large amount of hydrogeologic parameters, is limited by complex geological conditions, uncertainty of water regime prediction parameters, mathematical modeling burden and other factors, a relatively accurate regional underground water regime quantitative prediction tool is not formed yet, accurate prediction of each part of underground water regime of a region cannot be refined, regional water supply management cannot be well served, and particularly, water supply stopping, water supply limiting and water supply time deployment are carried out on the whole region according to a single early warning parameter model, inconvenience is caused for life of residents, and enterprise production or engineering scheduling can be influenced.
Drawings
FIG. 1 is a flow chart of regional groundwater condition prediction based on a groundwater monitoring system according to an embodiment of the invention;
FIG. 2 is a schematic diagram of simulated distribution of groundwater level observation data in an embodiment of the invention;
Detailed Description
According to an embodiment of the present invention, referring to fig. 1, a regional groundwater condition prediction method based on a groundwater monitoring system includes the following steps:
s1: collecting groundwater level observation information through observation well (group) water level observation equipment according to time sequence, collecting water extraction amount observation information near the observation wells, collecting air temperature and rainfall (snowfall) information, and collecting and arranging extracted observation data according to coordinates of the observation wells.
And constructing a water extraction prediction function and a water extraction-groundwater level prediction function through a support vector regression (Support Vector Regression, SVR) model by using the existing observation data, so as to predict the groundwater level in the future.
S1 specifically comprises the following steps:
s11: establishing a training sample set according to time sequence corresponding to different observation well coordinatesHistorical observation data representing the pumping capacity, and establishing a training sample set according to time series corresponding to different observation well coordinates>Historical observation data representing groundwater level.
S12: training a model function in a sample space, determining a width epsilon, giving a position of a decision surface, wherein mu is a normal vector of the decision surface, determining the direction of the decision surface, and introducing a relaxation variable xi i And eta i In the followingConstraint conditionsy i E { -1, +1} relaxation variable ζ i Not less than 0, relaxation variable eta i I=0, 1,2 … t, i denotes the i-th time point, t denotes the total number of observation time points, and the loss function is as follows:
wherein C is>A constant of 0, ε gives the position of the decision plane, μ represents the normal vector of the decision plane, ζ i And eta i To relax the variable and meet the optimization target, obtain the precipitation prediction model function f 1 (x a ，t i ) Wherein t is i Time x is represented a Representing the water extraction, again subject to the following constraintsObtaining a groundwater level prediction model function f 2 (x a ，x b )，x a Represents the water pumping quantity x b And the groundwater level is represented, so that the water pumping quantity and the groundwater level at the future moment can be predicted in real time.
S13: data on water extraction observationsHistorical observation data of groundwater level +.>And (3) performing linear regression, constructing various water pumping quantity-groundwater level linear regression models (such as least square, polynomial regression and logarithmic linear regression), and calculating residual errors for comparative analysis. And comparing the prediction result of the linear regression model function with the groundwater level result predicted by the SVR in S12, and analyzing the prediction accuracy.
S2: and estimating the water pumping-water level drainage relation between the water pumping well (group) and the observation well corresponding to the water pumping well (group) based on a Markov-Monte Carlo method, and constructing a regional groundwater condition prediction model.
S2 specifically comprises the following steps:
s21: a probability model for continuously calculating water regime parameters is established based on Bayesian theory (Bayesian method), and the water regime observation historical data can simultaneously estimate probability distribution of a plurality of water regime parameters including water pumping quantity and groundwater level. Let t 0 Time of day t0 The water condition observation data collected by each observation well and nearby before the moment is X t Posterior probability P (x a ，x b ，t|X t ) Can be expressed as follows:
wherein x is a Represents the water pumping quantity x b Represents the groundwater level, t 0 And predicting the starting time, wherein t is the predicted time.
S22: with a large number of weighted particles to approximate the posterior distribution, the estimation results can be calculated through iteration:
sample taking simplified model phi t (x a ，x b ，t|X t ) Q (·) is generally defined simply as a priori distribution P (phi) t |φ t-1 ) I represents the ith particle conforming to the q distribution, denoted ast denotes the moment, starting the loop iteration with i=1, …, N. The posterior probability distribution can be approximated as follows:
wherein the weight coefficient v of the ith particle at the moment t t i The total number of which may be normalized to 1,n is the total number of particles, and delta represents the equal proportion probability.
Observation data X updated with each step t Participating in the estimation of water regime parameters, all particle weights are re-normalized to
Wherein L (X) t |φ t )＝L(X t |x a ，x b And t) taking the water pumping well (group) and the water pumping-water level drainage relation of the corresponding observation well as new weight coefficients, and constructing a regional groundwater condition prediction model through a large number of particles with weights.
S3: defining a prediction area covering all observation wells (groups) according to coordinates and distribution conditions of the observation wells, covering the whole monitoring network area by the prediction area, carrying out grid division on the area, providing initial conditions for preliminary prediction of subsequent Thiessen polygons combined with Euclidean distance transformation, interpolation calculation and simulation smoothing of the area, dividing the initial conditions into n multiplied by n grids, setting transverse and longitudinal distances l and h of the grids, and uniformly initializing the initial conditions by a unit matrix function.
S3 specifically comprises the following steps:
s31: defining a prediction area covering all observation wells (groups) according to the coordinates and distribution conditions of the observation wells, wherein the prediction area covers the whole monitoring network area, and performing grid division on the prediction area and establishment of an observation well coordinate array by using real-time monitoring data provided by the monitoring network as completely as possible;
s32: based on the grid divided by the prediction area, a two-dimensional array of the grid point area center is created with the abscissa (x n ，y n ) An n×n region U as the center n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Initializing all points in the array as an identity matrix function, wherein l and h are the distances between adjacent grid points in the x direction and the y direction respectively, and x n ＝l×n，y n ＝h×n；
S33: constructing a two-dimensional array U corresponding to the position coordinates of the observation well m ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x m-1 ,y m-1 ),(x m ,y m )}，(x m ，y m ) Is U (U) m A water regime prediction result corresponding to the m observation well;
through the steps, the division of the grid of the prediction area and the establishment of an array of the prediction situation of the water condition of the observation well are completed, conditions are provided for subsequent preliminary prediction, correction calculation and smooth calculation, and the precipitation and groundwater level at any position in the prediction area can be still predicted under the condition that the monitoring network is sparsely distributed and lacks sufficient observation data.
S4: simulating a preliminary prediction result for the prediction area: constructing Voronoi polygons with perpendicular bisectors of adjacent observation wells, N observation wells, i.e. V N The image is divided into N Thiessen polygons by taking the coordinates of the observation well as the center, one observation well is added, and n+1 Thiessen polygons are generated, namely V N+1 Drawing, combining Euclidean distance transformation corresponding coordinate set U e Is incorporated into the observation well coordinate set U m In the middle, a new two-dimensional array U is formed m+e Reconsolidating Thiessen polygon vertex coordinate set U V Coordinate point set U for forming two-dimensional array to represent set observation well coordinates, euclidean distance transformed coordinates and Thiessen polygon vertex coordinates m+e+V Thus, the whole prediction area is simulated, and a preliminary prediction result of the whole area is obtained;
and simulating the whole prediction area to obtain a preliminary prediction result of groundwater condition distribution of the whole area.
S4 specifically comprises the following steps:
s41: construction of Thiessen polygons for monitoring network areas: constructing Thiessen polygons for the predicted area according to the N observation well coordinates, and generating Thiessen polygons by taking the neighboring observation wells as perpendicular bisectors, namely V N A drawing. If an observation well is newly added, a new V is generated N A figure;
v constructed according to the observation area by using the observation well water level prediction result N The graph simulates a prediction area covering the whole monitoring network, assigns values to n multiplied by n grid points generated in S3, and lets TaiThiessen polygon V of observation well i among the sen polygons i The regional grid points are assigned to be the ground water level prediction result of the observation well i, and meanwhile, the water extraction prediction result near the observation well is assigned to V i The area grid points,
s42: in D f (x i ，y i ) Representing coordinates (x) i ，y i ) Is calculated as the Euclidean distance transform of f (x j ，y j ) Representing coordinates (x) j ，y j ) The consumption function of (x) i ,y i )∈U n ，(x j ,y j )∈U n ，D f (x i ,y i )＝min(((x i ,y i )-(x j ,y j )) 2 +f(x j ,y j ) Traversing n x n region U) n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) The Euclidean distance transformation corresponding coordinate set U is calculated e Is incorporated into the observation well coordinate set U m In the middle, a new two-dimensional array U is formed m+e Combining Thiessen polygon vertex coordinate set U V Coordinate point set U for forming two-dimensional array to represent set observation well coordinates, euclidean distance transformed coordinates and Thiessen polygon vertex coordinates m+e+V 。
Step S1 and step S2, according to the prediction result of groundwater water conditions, performing assignment according to different Thiessen polygons in Thiessen polygons constructed by an observation area, using observation well coordinates as central Thiessen polygons to assign an observation water level or a prediction water level of the observation well, and combining Euclidean distance transformation to correspond to a coordinate set U e Forming a new two-dimensional array U m+e Reconsolidating Thiessen polygon vertex coordinate set U V Coordinate point set U for forming two-dimensional array to express coordinate of set observation well, coordinate corresponding to Euclidean distance transformation and coordinate of Thiessen polygon vertex m+e+V Thus, the whole prediction area is simulated, and a preliminary prediction result of the whole area is obtained;
s5: corresponding coordinates and Thiessen polygon vertex coordinate structures are transformed through observation of well coordinates and Euclidean distancesBuild and contain all coordinate points U m+e+V Adjusting adjacent triangles, correcting the preliminary prediction result in real time through the weighted triangle section of the maximum convex hull point set, forming two triangles with common edges by observation wells to form a polygon, surrounding all coordinate points, correcting the corresponding water condition prediction result of the maximum convex polygon point set point by point according to the prediction result of each observation well, and correcting the preliminary prediction result generated in the step S4 in real time;
s5 specifically comprises the following steps:
s51: and (3) correspondingly converting the two-dimensional array generated in the step (S4) into a two-dimensional array U corresponding to the position coordinates of the observation well, the Euclidean distance conversion corresponding coordinates and the Thiessen polygon vertex coordinates m+e+V Each coordinate point corresponds to U m+e+V In one of the steps S1 and S2, the corresponding water condition prediction result of the observation well, U m+e+V Each coordinate point corresponds to a time sequence groundwater condition prediction result, which is formed by U m+e+V The points in (a) are used as end points to form a closed line segment of the triangulation network;
S52：U m+e+V the points in (a) are used as end points to form a triangulation network convex polygon, and the points in (U) are used as grid points n The point set of the medium envelope is U k ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x k-1 ,y k-1 ),(x k ,y k ) Any two of the dot shapes have a weight of omega ij The convex polygon is divided into a plurality of mutually disjoint triangles to generate a triangle net with weight.
S53: the structure comprises U m+e+V Triangle subdivision of all coordinate point areas is performed, weight function values corresponding to a triangular net are obtained recursively, triangle interpolation calculation is performed on the triangular net, and each coordinate point set U in the triangular net is calculated k And (3) further correcting the corresponding time sequence water extraction prediction result and the groundwater level prediction result, and optimizing and updating the preliminary prediction result generated in the step (S4).
S6: smoothing the prediction result in the step S5 by adopting a Gaussian smoothing function to obtain a final prediction result; and (3) carrying out statistical analysis on the groundwater condition prediction results obtained in the step S1 and the groundwater condition prediction results obtained in the step S2 and calculated based on the Markov-Monte Carlo method, and analyzing the accuracy of the prediction results.
S61：U n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Each center of grid points in the } region (x i ,y i ) Constructing a Gaussian kernel functionSigma is the standard deviation of Gaussian distribution in a Gaussian kernel generator, and represents the discrete degree of prediction result data;
s62: and (3) carrying out Gaussian smoothing on the corrected water extraction prediction result and the groundwater level prediction result in the step (S5), calculating the transverse gradient and the longitudinal gradient of the prediction result by adopting a sobel function, carrying out edge detection by adopting a canny function to set double thresholds, carrying out double threshold detection by utilizing a weak gradient value, and further correcting the prediction result of the whole area to obtain a final prediction result.
S63: smoothing the prediction result generated in the step S5 by adopting a Gaussian smoothing function according to the actually measured data by adopting the regional groundwater level distribution simulation result generated in the step S4-S6, further correcting to obtain a final prediction result, and simulating regional distribution by adopting the step S4-S6 for the groundwater condition prediction result of the step S1 by adopting various regression algorithms such as support vector regression and the groundwater condition prediction result based on Markov-Monte Carlo algorithm in the step S2.
S64: different groundwater condition prediction algorithms can be loaded in the step S1 and the step S2, the predicted results of the different algorithms are compared, the predicted precision, calculation efficiency and the like are statistically analyzed, information such as air temperature, rainfall and/or snowfall, ground subsidence and the like during monitoring is added, the influence of the detail conditions on the final predicted result is analyzed, and a regional groundwater condition prediction model with robustness is stored according to the analysis of the precision and the calculation efficiency.
As shown in fig. 2, the water level distribution of the underground water in the area is obtained by using the data of the observation of the water level in a certain city construction area and a certain day through steps S4 to S6 in a numerical simulation process, the water level distribution of the underground water in the area is obtained within the range of 150m×40m, the dots represent the positions of the observation wells, the colors represent the water level height of the observation wells from light to deep (-5 to 25 m), the water level distribution of the underground water after interpolation of the triangular net is obtained through steps S4 and S5, and finally the water level distribution of the underground water in the area after smoothing in step S6 is obtained.
The invention is different from the traditional groundwater condition numerical prediction model or machine learning method, adopts a single observation well with discrete distribution to predict, estimates the groundwater condition of the whole area according to an empirical formula, and under the condition that observation data is lacking in certain areas, the estimation has great error on the water condition distribution condition of the whole area, so that the groundwater condition prediction is inaccurate, and particularly, the whole area is subjected to water cut-off, water supply quantity limitation and water supply time deployment according to a single early warning parameter model, thereby causing inconvenience to life of residents and even affecting the production or engineering schedule of enterprises. The invention can realize the prediction of the whole groundwater condition in the whole monitoring area, is not influenced by the positions of the observation wells and the distribution conditions of the observation wells, can predict whether the observation data are sufficient or not, only can obtain the observation data in a plurality of limited observation wells and pumping wells (groups) which are discretely distributed in the periphery of the monitoring area, but also can simultaneously carry out the comparison analysis of precision and calculation efficiency by the existing observation data aiming at a plurality of different prediction methods, refine the groundwater level distribution of each partial area of the prediction area and reflect the groundwater condition of each partial area of the prediction area in real time. In addition, the invention can realize the prediction of groundwater conditions by constructing a water extraction prediction function and establishing a water extraction-groundwater level drainage relation function, can also reduce the coupling between the water extraction and the groundwater level, and simultaneously establishes the water extraction-groundwater level drainage relation prediction function based on a Markov-Monte Carlo method. And according to the accuracy analysis of the actual case prediction result, storing a regional groundwater condition prediction model with robustness.
It will be readily appreciated by those skilled in the art that the above advantageous ways can be freely combined and superimposed without conflict.
Claims (7)
1. The regional groundwater condition prediction method based on the groundwater monitoring system is characterized by comprising the following steps:
s1: establishing a water extraction prediction function and a water extraction-groundwater level prediction function of each observation well based on support vector regression by combining observation data in a groundwater observation system with real-time monitoring data, and predicting the groundwater level in real time;
s2: calculating the pumping-water level drainage relation between a pumping well and a corresponding observation well by using a Markov-Monte Carlo method, simultaneously calculating a plurality of groundwater water condition parameters by using observation data monitored in real time by using the observation network, obtaining particles to approximate posterior probability distribution by iterative screening on samples based on probability distribution established by Bayesian theory, and simultaneously calculating a water level prediction result of each observation well and a water pumping prediction result of each observation well so as to avoid coupling among each prediction parameter;
s3: according to the coordinates and distribution conditions of the observation wells, defining a prediction area covering all the observation wells, covering the whole monitoring network area by the prediction area, and performing grid division on the whole prediction area to generate n multiplied by n grid points;
s4: constructing Thiessen polygons of a monitoring network area, and combining Euclidean distance transformation to correspond to a coordinate set U e Is incorporated into the observation well coordinate set U m Wherein, two-dimensional array U is formed m+e Reconsolidating Thiessen polygon vertex coordinate set U V Coordinate point set U for forming two-dimensional array representation set observation well coordinates, euclidean distance transformation coordinates and Thiessen polygon vertex coordinates m+e+V ；
Simulating a prediction area covering the whole monitoring network according to a Thiessen polygon constructed by an observation area by utilizing the observation well water level prediction result, assigning values to the generated n multiplied by n grid points, and setting a Thiessen polygon V of an observation well i in the Thiessen polygon i Assigning values to regional grid points to obtain the ground water level prediction result of the observation well i, and simultaneouslyAssigning the prediction result of the water pumping quantity of the observation well to V i Generating a preliminary prediction result of the water pumping quantity of the area and a preliminary prediction result of the groundwater level of the area at the grid points of the area;
s5: constructing a convex polygon point set U containing all scattered points by observing well coordinates, euclidean distance transformation intersection point coordinates and Thiessen polygon vertex coordinates m+e+V Dividing the convex polygon into mutually disjoint triangles, adjusting adjacent triangles to obtain weighted triangulation, calculating through triangle interpolation values, correcting according to the preliminary prediction results corresponding to each point in the coordinate point set, and correcting the generated preliminary prediction results of groundwater level-water pumping area distribution in real time;
s6: smoothing the corrected groundwater level-water pumping distribution area water regime prediction result by using a Gaussian smoothing function to obtain a final prediction result, further correcting the prediction result by using a gradient double-threshold detection, carrying out statistical analysis on the groundwater regime prediction result by using a support vector regression algorithm and the groundwater regime prediction result by using a Markov-Monte Carlo algorithm, creating an array of storage results according to the accuracy of comparing the analysis prediction results with the residual error statistical distribution, and storing the optimized prediction model as a stable groundwater level prediction system model.
2. The regional groundwater condition prediction method based on a groundwater monitoring system according to claim 1, wherein S1 specifically comprises the following steps:
s11: establishing a training sample set according to time sequence corresponding to different observation well coordinatesHistorical observation data representing the pumping capacity, and establishing a training sample set according to time series corresponding to different observation well coordinates>Historical observation data representing groundwater level;
s12: training a model function in sample space under the following constraintsy i Epsilon { -1, +1}, relaxation variable ζ i Not less than 0, relaxation variable eta i Gtoreq 0, i=0, 1,2 … t, i representing the i-th time point; t represents the total number of observation time points; the loss function is:
wherein C is>A constant of 0; epsilon gives the position of the decision surface; μ represents a normal vector of the decision plane; zeta type toy i And eta i Is a relaxation variable; meets the optimization target to obtain the precipitation prediction model function f 1 (x a ，t i ) Wherein t is i Time x is represented a Representing the water extraction;
under the following constraint conditionsObtaining a groundwater level prediction model function f 2 (x a ，x b ) Wherein x is a Representing the water extraction; x is x b Representing groundwater level; the water pumping quantity and the groundwater level at the future moment are predicted in real time;
s13: data on water extraction observationsAnd historical observations of groundwater level +.>Performing linear regression, constructing various water pumping quantity-groundwater level linear regression models, calculating to obtain residual errors, performing comparative analysis, comparing the prediction result of the linear regression model function with the groundwater level result of support vector regression prediction, analyzing the prediction precision, and optimizing the prediction model.
3. The regional groundwater condition prediction method based on a groundwater monitoring system according to claim 1, wherein in step S2, a pumping-water level drainage relationship between a pumping well and its corresponding observation well is calculated based on a markov-monte carlo method, so as to avoid coupling between each prediction parameter, and specifically comprising the following steps:
s21: establishing a probability model for continuously calculating water regime parameters based on a Bayesian theory, wherein the water regime observation historical data can calculate probability distribution of a plurality of water regime parameters including water pumping quantity and groundwater level at the same time;
setting t 0 Time t 0 Each observation well and the collected water condition observation data before the moment are X t Posterior probability P (x a ,x b ,t|X t ) Can be expressed as:
wherein x is a Representing the water extraction; x is x b Representing groundwater level; t is t 0 Predicting a starting time; t is the predicted time;
s22: sample taking simplified model phi t (x a ，x b ，t|X t ) Q (·) is a priori distributed P (phi) in conformity with the q distribution t |φ t-1 ) I represents the ith particle conforming to the q distribution, denoted ast represents the moment, iterated by i=1, …, N loops;
the posterior probability distribution can be approximated as:
wherein the first weight coefficient of the ith particle at time tThe total number can be normalized to 1,/or->N is the total number of particles; delta represents an equal proportion probability;
based on updated observed data X t In the calculation of the water regime parameters, all particle weights are re-normalized to:
wherein L (X) t |φ t )＝L(X t |x a ，x b T) as a second weight coefficient, calculating the water pumping-water level drainage relation of the water pumping well and the observation well corresponding to the water pumping well through a plurality of particles with weights, and constructing a regional groundwater condition prediction model.
4. The regional groundwater condition prediction method based on a groundwater monitoring system according to claim 1, wherein S3 specifically comprises the following steps:
s31: defining a prediction area covering all observation wells according to the coordinates and distribution conditions of the observation wells, wherein the prediction area covers the whole monitoring network area, and carrying out grid division on the prediction area and establishment of an observation well coordinate array based on real-time monitoring data provided by the monitoring network;
s32: based on the grid divided by the prediction area, a two-dimensional array of the grid point area center is created with the abscissa (x n ，y n ) An n×n region U as the center n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Initializing all points in the array as an identity matrix function, wherein l and h are the distances between adjacent grid points in the x direction and the y direction respectively, and x n ＝l×n，y n ＝h×n；
S33: constructing a two-dimensional array U corresponding to the position coordinates of the observation well m ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x m-1 ,y m-1 ),(x m ,y m )}，(x m ，y m ) Is U (U) m The water regime prediction result corresponding to the m observation well.
5. The regional groundwater condition prediction method based on a groundwater monitoring system according to claim 1, wherein S4 specifically includes the following steps:
s41: construction of Thiessen polygons for monitoring network areas: constructing Thiessen polygons for the predicted area according to the N observation well coordinates, and generating Thiessen polygons by taking the neighboring observation wells as perpendicular bisectors, namely V N A figure;
v constructed according to the observation area by using the observation well water level prediction result N The graph simulates a prediction area covering the whole monitoring network, assigns values to the generated n multiplied by n grid points, and sets a Thiessen polygon V of an observation well i in the Thiessen polygons i Assigning the regional grid points to obtain the ground water level prediction result of the observation well i, and assigning the water pumping prediction result of the observation well to V at the same time i Regional grid points;
s42: in D f (x i ，y i ) Representing coordinates (x) i ，y i ) Is calculated as the Euclidean distance transform of f (x j ，y j ) Representing coordinates (x) j ，y j ) The consumption function of (x) i ,y i )∈U n ，(x j ,y j )∈U n ，D f (x i ,y i )＝min(((x i ,y i )-(x j ,y j )) 2 +f(x j ,y j ) Traversing n x n region U) n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Calculating to obtain a coordinate set U corresponding to Euclidean distance transformation e Is incorporated into the observation well coordinate set U m Wherein, two-dimensional array U is formed m+e Combining Thiessen polygon vertex coordinate set U V Coordinate point set U for forming two-dimensional array representation set observation well coordinates, euclidean distance transformation coordinates and Thiessen polygon vertex coordinates m+e+V 。
6. The regional groundwater condition prediction method based on a groundwater monitoring system according to claim 1, wherein S5 specifically includes the following steps:
s51: the generated two-dimensional array U corresponds to the two-dimensional array U of the position coordinates of the observation well, the Euclidean distance transformation coordinates and the Thiessen polygon vertex coordinates m+e+V Each coordinate point corresponds to U m+e+V Corresponding water condition prediction result of observation well, U m+e+V Each coordinate point corresponds to a time sequence groundwater condition prediction result, which is formed by U m+e+V The points in (a) are used as end points to form a closed line segment of the triangulation network;
S52：U m+e+V the points in (a) are used as end points to form a triangulation network convex polygon, and the points in (U) are used as grid points n The point set of the medium envelope is U k ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x k-1 ,y k-1 ),(x k ,y k ) Any two points of which weight is omega ij Dividing the convex polygon into a plurality of mutually disjoint triangles to generate a triangle net with weight;
s53: the structure comprises U m+e+V Triangle subdivision of all coordinate point areas is obtained by recursion, triangle subdivision of a triangular net is obtained, triangle interpolation calculation is carried out on the triangular net, and each coordinate point set U in the triangular net is obtained k And further correcting the corresponding time sequence water extraction prediction result and the groundwater level prediction result, and optimizing and updating the generated preliminary prediction result.
7. The regional groundwater condition prediction method based on a groundwater monitoring system according to claim 1, wherein S6 specifically includes the following steps:
S61：U n ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n-1 ,y n-1 ),(x n ,y n ) Each center of grid points in the } region (x i ,y i ) The gaussian kernel is constructed as follows:
wherein sigma is the standard deviation of Gaussian distribution in a Gaussian kernel generator, and represents the discrete degree of prediction result data;
s62: carrying out Gaussian smoothing on the corrected water extraction prediction result and the groundwater level prediction result, calculating transverse gradients and longitudinal gradients of the prediction result by adopting a sobel function, carrying out edge detection by adopting a canny function to set double thresholds, carrying out double threshold detection by utilizing a weak gradient value, and further correcting the prediction result of the whole area to obtain a final prediction result;
s63: smoothing the generated prediction result by adopting a Gaussian smoothing function based on the actually measured data, further correcting to obtain a final prediction result, and simulating regional distribution of the groundwater condition prediction result by adopting a regression algorithm of SVR and the groundwater condition prediction result calculated based on a Markov-Monte Carlo method;
s64: based on the comparison of the predicted results of different algorithms, the precision and the calculation efficiency of prediction are statistically analyzed, the temperature and rainfall or/and snowfall and surface subsidence information during monitoring are added, the influence of different conditions on the final predicted result is analyzed, and a regional groundwater water regime prediction model with robustness is stored according to the precision and the calculation efficiency analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210500900.7A CN114970302B (en) | 2022-05-10 | 2022-05-10 | Regional groundwater condition prediction method based on groundwater monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210500900.7A CN114970302B (en) | 2022-05-10 | 2022-05-10 | Regional groundwater condition prediction method based on groundwater monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114970302A CN114970302A (en) | 2022-08-30 |
| CN114970302B true CN114970302B (en) | 2024-03-15 |
Family
ID=82981874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210500900.7A Active CN114970302B (en) | 2022-05-10 | 2022-05-10 | Regional groundwater condition prediction method based on groundwater monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114970302B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115687883B (en) * | 2022-11-18 | 2024-04-30 | 水利部信息中心 | Shallow groundwater storage variable calculation method based on kilometer grid |
| CN117390471B (en) * | 2023-12-12 | 2024-03-26 | 山东省地质矿产勘查开发局第八地质大队(山东省第八地质矿产勘查院) | Hydrogeological data management method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019076078A1 (en) * | 2017-10-16 | 2019-04-25 | 中国环境科学研究院 | Multi-objective optimization method for groundwater pollution monitoring network |
| CN110580328A (en) * | 2019-09-11 | 2019-12-17 | 江苏省地质工程勘察院 | Method for repairing underground water level monitoring value loss |
| CN114254561A (en) * | 2021-12-17 | 2022-03-29 | 奥格科技股份有限公司 | Waterlogging prediction method, waterlogging prediction system and storage medium |
-
2022
- 2022-05-10 CN CN202210500900.7A patent/CN114970302B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019076078A1 (en) * | 2017-10-16 | 2019-04-25 | 中国环境科学研究院 | Multi-objective optimization method for groundwater pollution monitoring network |
| CN110580328A (en) * | 2019-09-11 | 2019-12-17 | 江苏省地质工程勘察院 | Method for repairing underground water level monitoring value loss |
| CN114254561A (en) * | 2021-12-17 | 2022-03-29 | 奥格科技股份有限公司 | Waterlogging prediction method, waterlogging prediction system and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘长生 ; .基于支持向量机理论的地下水水源地动态预测模型.勘察科学技术.2010,(第01期),第22-25 页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114970302A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114970302B (en) | Regional groundwater condition prediction method based on groundwater monitoring system | |
| Hancock et al. | Spatial interpolation of large climate data sets using bivariate thin plate smoothing splines | |
| CN110263111B (en) | Priori knowledge-based space-time monitoring method for land utilization/coverage information | |
| CN114254561A (en) | Waterlogging prediction method, waterlogging prediction system and storage medium | |
| Jalalkamali | Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters | |
| CN112446559B (en) | Large-range ground subsidence space-time prediction method and system based on deep learning | |
| CN113610301B (en) | Prediction algorithm for representing ground settlement time sequence evolution | |
| CN107133398B (en) | River runoff prediction method based on complex network | |
| CN113051638B (en) | Building height optimal configuration method and device | |
| CN115182398B (en) | Groundwater level and earth surface subsidence prediction method for earthquake early warning area | |
| CN113128055B (en) | Distributed hydrological model space calibration method based on runoff yield coefficient | |
| JP7153330B2 (en) | Sediment disaster prediction device, computer program, sediment disaster prediction method and map information | |
| CN114723149A (en) | Soil moisture content prediction method and device, electronic equipment and storage medium | |
| CN112381334B (en) | High-steep slope deformation trend prediction method based on multi-factor fuzzy time sequence | |
| CN117291444B (en) | Digital rural business management method and system | |
| CN116738669A (en) | Urban surface runoff simulation method, device, equipment and storage medium | |
| CN109063388A (en) | The micro climate architecture design addressing design method of wind environment simulation | |
| CN113987969A (en) | Land-water dynamic simulation model of multi-elevation scale water flow network | |
| CN116663395A (en) | Rainfall equivalent surface generation method based on regression of support vector machine of parameter optimization | |
| WO2019128018A1 (en) | Method for determining wind resource, and apparatus | |
| Mikołajewski et al. | Development of cluster analysis methodology for identification of model rainfall hyetographs and its application at an urban precipitation field scale | |
| CN115438590A (en) | Rainfall forecast correction method and system based on BP neural network | |
| Govindarajan et al. | A scalable algorithm for dispersing population | |
| Ali et al. | Statistical downscaling of precipitation and temperature using gene expression programming | |
| CN117332544B (en) | Urban rainfall flood model modeling method by combining vector and grid hydrologic calculation unit |
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 |