CN117633539A - Underground water drought identification method and device for uneven site distribution - Google Patents
Underground water drought identification method and device for uneven site distribution Download PDFInfo
- Publication number
- CN117633539A CN117633539A CN202410102915.7A CN202410102915A CN117633539A CN 117633539 A CN117633539 A CN 117633539A CN 202410102915 A CN202410102915 A CN 202410102915A CN 117633539 A CN117633539 A CN 117633539A
- Authority
- CN
- China
- Prior art keywords
- drought
- groundwater
- data
- sequence
- water level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000009826 distribution Methods 0.000 title claims abstract description 33
- 239000003673 groundwater Substances 0.000 claims abstract description 282
- 238000011160 research Methods 0.000 claims abstract description 76
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 37
- 238000001556 precipitation Methods 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 30
- 238000004891 communication Methods 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 7
- 230000009897 systematic effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000009933 burial Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- CUKSFECWKQBVED-INIZCTEOSA-N Decursin Chemical compound C1=CC(=O)OC2=C1C=C1C[C@H](OC(=O)C=C(C)C)C(C)(C)OC1=C2 CUKSFECWKQBVED-INIZCTEOSA-N 0.000 description 1
- CUKSFECWKQBVED-UHFFFAOYSA-N Grandivittin Natural products C1=CC(=O)OC2=C1C=C1CC(OC(=O)C=C(C)C)C(C)(C)OC1=C2 CUKSFECWKQBVED-UHFFFAOYSA-N 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- JXZWWIMXTVJNSF-UHFFFAOYSA-N decursin Natural products CC(=CC(=O)OC1Oc2cc3OC(=O)C=Cc3cc2CC1(C)C)C JXZWWIMXTVJNSF-UHFFFAOYSA-N 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The application provides a method and a device for identifying drought of groundwater for uneven site distribution, which relate to the technical field of drought management and response and comprise the following steps: acquiring historical monitoring information and position information of a ground water monitoring station point of a target research area, and gridding the target research area; reconstructing the groundwater level sequence of each grid point of the target research area based on a machine learning algorithm and an inverse distance interpolation method; determining a standardized underground water level index sequence of each grid point of a target research area based on a preset standardized precipitation index algorithm and combining a moving average method; based on the run theory, the groundwater drought event is identified, and the groundwater drought event characteristics are determined. The method solves the problems that systematic errors exist in the current regional groundwater level interpolation based on the non-uniform groundwater monitoring site data, and the accuracy of groundwater drought identification is poor.
Description
Technical Field
The application relates to the technical field of drought management and handling, in particular to a method and a device for identifying groundwater drought oriented to uneven site distribution.
Background
The underground water has the characteristics of wide distribution, stable water temperature, better water quality and easy exploitation, and is an important water supply source for various cities due to the lack of surface water resources in China. With the aggravation of climate change and human activity, extreme weather hydrologic events occur frequently, and groundwater drought also occurs at times. Once a long-duration groundwater drought event occurs, the water use guarantee of an ecological system and economy and society is greatly influenced, so that the method for accurately and effectively identifying the groundwater drought has practical significance.
The underground water monitoring station is used as an important component of the hydrologic station network, and provides important basic data support in the aspects of dynamically mastering the change of underground water level and water quantity, promoting the optimal allocation of underground water resources, scientifically managing and the like. However, the density of the underground water monitoring stations in China is still small, the space distribution is still uneven, the monitoring result of the underground water in the area is inaccurate, and the condition and the change trend of the underground water system cannot be comprehensively known.
A large number of facts show that the shallow groundwater level is closely related to the ground elevation, and is influenced by the distribution of precipitation in years and the water used for human activities such as irrigation and life, and the shallow groundwater level change has certain regularity and periodicity. Aiming at the non-uniform ground water monitoring site space distribution, how to fully utilize site basic information and actual measurement information and establish a ground water drought space-time identification method is an important precondition for accurately and effectively carrying out ground water drought characteristic analysis and reasonably optimizing and configuring ground water resources.
Disclosure of Invention
The embodiment of the application aims to provide a groundwater drought identification method and device oriented to uneven site distribution, which are used for solving the problems that systematic errors exist in the current area groundwater level interpolation based on uneven groundwater monitoring site data, and the accuracy of groundwater drought identification is poor.
In a first aspect, a method for identifying drought of groundwater for uneven site distribution is provided, which may include:
acquiring groundwater data of a target research area in a historical time period; the underground water data are obtained by converting original monitoring underground water data of a historical time period in the target research area based on an elevation system of a preset historical time point; the underground water data comprise a collecting position, collecting time, underground water elevation and an underground water level value;
after gridding the target research area, reconstructing the groundwater level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method to obtain an area groundwater level sequence of the target research area;
based on a preset standardized precipitation index construction algorithm, standardizing the regional groundwater level sequence to obtain a standardized groundwater level index sequence;
And processing the standardized groundwater level index sequence based on a run theory, determining a groundwater drought event in a target research area, and determining the characteristics of the groundwater drought event.
In one possible implementation, before acquiring groundwater data for the target study area over the historical period of time, the method further includes:
acquiring original monitoring groundwater data of a historical time period in the target research area;
and performing outlier processing on the original monitored groundwater data by adopting a 3sigma processing algorithm to obtain the groundwater data.
In one possible implementation, the processing the groundwater level data of each grid point in the historical period to obtain a regional groundwater level sequence of the target research region includes:
inputting the ground water level data of each grid point in the historical time period into a trained XGBoost algorithm model to obtain a regional ground water level inter-moon sequence output by the XGBoost algorithm model, wherein the regional ground water level inter-moon sequence comprises ground water level data of each month in the historical time period;
calculating groundwater data corresponding to n groundwater level monitoring stations closest to the target research area by adopting an inverse distance interpolation method to obtain daily groundwater data corresponding to each grid point;
Calculating a month moving average water level value based on the daily ground water data corresponding to each grid point, and subtracting the month moving average water level value from the daily ground water level value corresponding to each grid point to obtain a regional ground water level intra-month sequence of the target research region, wherein the regional ground water level intra-month sequence comprises ground water level intra-month fluctuation data of a month scale removal trend in the historical time period;
and adding the regional groundwater level inter-moon sequence with the data of the corresponding position in the regional groundwater level inter-moon sequence to obtain the regional groundwater level sequence of the target research region, wherein the regional groundwater level sequence comprises daily groundwater level data of each grid point in the historical time period.
In one possible implementation, the processing the regional groundwater level sequence based on a preset standardized precipitation index construction algorithm to obtain a standardized groundwater level index sequence includes:
calculating a years moving average water level value based on water level data corresponding to each grid point in the regional water level sequence, and subtracting the years moving average water level value from the water level value corresponding to each grid point to obtain a water level sequence of the last year trend of the target research region, wherein the water level sequence of the last year trend comprises water level fluctuation data of the last year trend;
And after the detrending underground water level sequence is standardized, referring to a construction flow of a standardized rainfall index, and processing the standardized detrending underground water level sequence to obtain a standardized underground water level index sequence.
In one possible implementation, processing the normalized groundwater level index sequence based on a run-length theory, determining a groundwater drought event within a target study area includes:
based on the run theory, if the standardized groundwater level index value of each time point in the standardized groundwater level index sequence is smaller than or equal to a preset drought threshold value, determining grid points corresponding to the corresponding standardized groundwater level index values as drought grid points;
traversing a target research area, and carrying out space combination on target drought grid points in the determined drought grid points to obtain drought patches, wherein the target drought grid points are adjacent drought grid points;
and overlapping drought patches of adjacent time nodes in space, determining the overlapping area of an overlapping area, determining the drought patches with the overlapping area larger than a preset area as the same groundwater drought event, and giving the same drought event number.
In one possible implementation, the method further comprises:
for two groundwater drought events with the interval time of 1 month, if a spatial intersection exists between the ending time point of the previous field groundwater drought event and the starting time point of the next field groundwater drought event, and the drought index value of the spatial union of the interval months is smaller than a first drought index threshold value R0, merging the two groundwater drought events into the same field groundwater drought event;
and (3) rejecting the underground water drought event with the drought duration of only 1 month when a plurality of drought index values are larger than a second drought index threshold value R2.
In one possible implementation, determining groundwater drought event characteristics includes:
extracting features of the groundwater drought event to obtain the features of the groundwater drought event;
the groundwater drought event features include drought start time, drought end time, drought duration, drought average area, drought maximum area, drought shroud area, drought average intensity, drought maximum intensity, and drought intensity.
In a second aspect, a device for identifying drought in groundwater for uneven site distribution is provided, the device may include:
The acquisition unit is used for acquiring groundwater data of the target research area in a historical time period; the underground water data are obtained by converting original monitoring underground water data of a historical time period in the target research area based on an elevation system of a preset historical time point; the underground water data comprise a collecting position, collecting time, underground water elevation and an underground water level value;
the processing unit is used for reconstructing the ground water level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method after gridding the target research area to obtain an area ground water level sequence of the target research area;
and standardizing the regional groundwater level sequence based on a preset standardized precipitation index construction algorithm to obtain a standardized groundwater level index sequence;
and the determining unit is used for processing the standardized groundwater level index sequence based on a run-length theory, determining groundwater drought events in a target research area and determining groundwater drought event characteristics.
In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory are in communication with each other via the communication bus;
A memory for storing a computer program;
a processor for implementing the method steps of any one of the above first aspects when executing a program stored on a memory.
In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the method steps of any of the first aspects.
According to the underground water drought identification method for uneven site distribution, underground water data of a target research area in a historical time period need to be acquired; the underground water data are obtained by converting original monitoring underground water data of a historical time period in a target research area based on an elevation system of a preset historical time point; the groundwater data comprises a collecting position, collecting time, groundwater elevation and groundwater level value; after gridding the target research area, reconstructing the groundwater level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method to obtain an area groundwater level sequence of the target research area; based on a preset standardized precipitation index construction algorithm, standardizing the regional groundwater level sequence to obtain a standardized groundwater level index sequence; based on a run theory, the standardized groundwater level index sequence is processed, groundwater drought events in a target research area are determined, and groundwater drought event characteristics are determined. The method solves the problems that systematic errors exist in the current regional groundwater level interpolation based on the non-uniform groundwater monitoring site data, and the accuracy of groundwater drought identification is poor.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for identifying drought of groundwater for uneven site distribution provided in an embodiment of the present application;
fig. 2 is a schematic flow chart of another method for identifying drought of groundwater for uneven site distribution according to an embodiment of the present application;
FIG. 3 is a schematic diagram of comparing predicted data and test data of an optimal model based on XGBoost algorithm according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a relationship between a groundwater level and a ground elevation according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an underground water drought identification device facing to uneven site distribution according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it being understood that the preferred embodiments described herein are for illustration and explanation only, and are not intended to limit the present application, and embodiments and features of embodiments of the present application may be combined with each other without conflict.
Fig. 1 is a schematic flow chart of a method for identifying drought of groundwater for uneven site distribution provided in an embodiment of the application. As shown in fig. 1, the method may include:
step S110, obtaining groundwater data of a target research area in a historical time period.
In specific implementation, position information such as longitude, latitude, elevation and the like of a ground water monitoring station in a historical time period in a target research area is collected, and raw ground water data such as a collection position, collection time, ground water elevation, ground water level value, burial depth and the like monitored by the corresponding ground water monitoring station are collected, so that raw ground water data in the historical time period in the target research area is obtained.
Then, the collected original monitoring groundwater data is cleaned, in particular:
first, raw groundwater data is checked for rationality, including year, month, day, latitude and longitude ranges, elevation ranges, etc. And judging and processing abnormal values of the groundwater level or burial depth monitoring data, and removing or changing obviously wrong outlier data points.
In a specific embodiment, a 3sigma processing algorithm is adopted to perform outlier processing on the original groundwater data to obtain groundwater data. That is, when X > μ+3σ or X < μ -3σ, where μ is the station data average value and σ is the station data standard deviation, the data is preliminarily judged to be an outlier.
And secondly, converting the original monitored groundwater data in the historical time period in the target research area based on an elevation system of a preset historical time point, namely uniformly converting the ground elevation data and the groundwater monitoring data into ground elevation data and groundwater level data of the same elevation system, and obtaining groundwater data which can be processed.
And step S120, after gridding the target research area, reconstructing the ground water level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method to obtain an area ground water level sequence of the target research area.
In a specific implementation, the following steps are performed:
step 1, after gridding a target research area, comprehensively considering factors such as computer performance, time cost and the like, and selecting a proper supervised learning algorithm. Model parameters are trained and screened by taking years, months, longitudes, latitudes and ground elevations as input features and shallow groundwater levels as tag data. The basic information of years, months, longitudes, latitudes, ground elevations and the like in the research period of the research area is meshed, input into a trained model, and ground water level month scale data reconstructed by all grid points are obtained through calculation. Among other supervised learning algorithms, the choice includes multiple linear regression, decision trees, support vector machines, neural networks, etc.
The application adopts a distributed gradient enhancement library XGBoost. XGBoost is one of the gradient lifting tree models, the models are generated serially, and the sum of all the models is taken as output. Meanwhile, the loss function is subjected to second-order Taylor expansion, the loss function is optimized by utilizing second-order derivative information of the loss function, and whether nodes are split or not is selected according to whether the loss function is reduced or not. When a model is specifically constructed, adopting a grid search and 5-fold cross validation method to conduct parameter optimization on the maximum depth of the tree and the total number of the tree, and according to a decision coefficient R 2 Selecting optimal parameters, R 2 The calculation formula of (2) is as follows:
wherein y is i Is the actual value in the verification set, y pred Is a model predictive value.
Specifically, the ground water level data of each grid point in the historical time period is input into a trained XGBoost algorithm model to obtain a regional ground water level inter-moon sequence output by the XGBoost algorithm model, wherein the regional ground water level inter-moon sequence can comprise ground water level data of each month in the historical time period.
Step 2, calculating groundwater data corresponding to n groundwater level monitoring stations closest to the target research area by adopting an inverse distance interpolation method, and obtaining daily groundwater data corresponding to each grid point; and calculating a month moving average water level value based on the daily underground water data corresponding to each grid point, and subtracting the month moving average water level value from the daily underground water level value corresponding to each grid point to obtain an intra-month sequence of the regional underground water level of the target research region.
Specifically, a moving average method may be adopted to calculate a moving average water level value corresponding to each grid point, for example, a 30-day moving average water level value of each grid point, and then subtracting the moving average value from the ground water level value of each grid point to finally obtain the intra-month fluctuation value of the ground water level with the going-month scale trend.
The calculation formula of the moving average method is as follows:
in the formula, MA t Is a moving average at time point t, X t Is the sequence value at time point t, n is the size of the moving average window, representing the number of data points considered in calculating the average. In this step, t is taken to 30 (about 1 month).
And step 3, adding the data of the corresponding positions in the regional groundwater level inter-moon sequence and the regional groundwater level intra-moon sequence to obtain the regional groundwater level sequence of the target research region.
Wherein the regional groundwater level sequence may include daily groundwater level data for each grid point over a historical period of time.
And step 130, normalizing the regional groundwater level sequence based on a preset normalized precipitation index construction algorithm to obtain a normalized groundwater level index sequence.
The underground water level may continuously drop under the influence of human factors such as long-time underground water exploitation, and difficulty is caused to the drought identification of the underground water. Calculating the moving average water level value of each grid point for many years by adopting a moving average method, and specifically: taking t in the moving average formula to 1100 (about 3 years), the moving average water level value of each grid point for many years can be obtained.
And then, acquiring a water level sequence of the last year trend of the target research area based on the water level value of the years moving average corresponding to each grid point and the water level data of each grid point in the water level sequence of the area, specifically subtracting the water level value of the years moving average from the water level data (the water level data of each grid point) in the water level sequence of the area, and finally obtaining a water level fluctuation value of which the years trend is removed, so as to remove the influence of long-term human activity factors, namely the water level sequence of the last year trend can comprise water level fluctuation data of which the years trend is removed.
And after normalizing the trended underground water level sequence, referring to a construction flow of the normalized precipitation index, and processing the normalized trended underground water level sequence to obtain a normalized underground water level index sequence.
Specifically, the construction flow of the standardized groundwater level index is as follows: and taking each grid point as a basic space unit, and selecting Gamma and Pearson III types as basic distribution types.
Firstly, fitting the ground water average water level of each ten days, comparing the mean square error to optimize distribution and estimating parameters by adopting a maximum likelihood method;
and converting the cumulative distribution of the average water level of the underground water into standard normal distribution, and obtaining a standardized underground water level index through inverse standardization. Wherein, the probability density function of Gamma distribution is as follows:
where x is the value of a random variable, alpha is a shape parameter, beta is a scale parameter,is a Gamma function, which is a generalization of the factorization of the shape parameter α.
The probability density function for the pearson type iii distribution is shown below:
where x is the value of a random variable, a is a shape parameter, b is a scale parameter, and c is a skew parameter.
The mean square error is used for measuring the square sum of the difference between the model predicted value and the actual observed value, and the calculation formula is as follows:
Wherein Y is i Is the actual value of the i-th observed data point,is the model predictive value of the ith observation data point and n is the number of observation data points.
And step 140, processing the standardized groundwater level index sequence based on a run theory, determining a groundwater drought event in a target research area, and determining the characteristics of the groundwater drought event.
In a specific implementation, a preset drought threshold R1 is set with reference to a drought class classification standard of a standardized precipitation index.
Depending on the travel Cheng Lilun, the groundwater drought grid points at each time point are screened out, and the research area is traversed by utilizing an n multiplied by n grid: if the standardized groundwater level index value of each time point in the standardized groundwater level index sequence is larger than a preset drought threshold R1, determining the current grid point corresponding to the corresponding standardized groundwater level index value as a non-drought grid point.
If the standardized groundwater level index value of each time point in the standardized groundwater level index sequence is smaller than or equal to a preset drought threshold value, determining the current grid point corresponding to the corresponding standardized groundwater level index value as a drought grid point.
Traversing the target research area, if the corresponding elements of the adjacent grid points are still drought grid points, merging to form drought patches, and reserving the drought patches of which the time points are larger than the preset minimum patch area;
Overlapping drought patches of adjacent time points in space to determine the overlapping area of the overlapping area;
if the overlapping area is larger than the preset minimum overlapping area, determining that drought patches at adjacent time points belong to a field of groundwater drought events, and giving the same drought event numbers.
The preset minimum overlapping area may be determined according to the following formula:
wherein 1 and 0 respectively represent the spatial overlap of the existence and non-existence of the present field groundwater drought event and the previous field groundwater drought event; a is that t And A t-1 Plaque areas of a local field groundwater drought event and a last field groundwater drought event are respectively represented; a is that ST Representing the area of the investigation region; minA (MinA) t,t-1 Representing the minimum overlapping area of the plaque areas of the drought event of the field and the drought event of the ground water of the previous field; α represents the minimum percentage of overlap based on the area of the investigation region; beta represents the minimum percentage of overlap based on the area of the drought event.
In some embodiments, the method may further comprise:
for two groundwater drought events with the interval time of 1 month, if a spatial intersection exists between the ending time point of the previous field groundwater drought event and the starting time point of the next field groundwater drought event, and the drought index value of the spatial union of the interval months is smaller than a first drought index threshold value R0, merging the two groundwater drought events into the same field groundwater drought event;
And (3) rejecting the underground water drought event with the drought duration of only 1 month when a plurality of drought index values are larger than a second drought index threshold value R2.
In some embodiments, after determining the groundwater drought event in the target research area, feature extraction may also be performed on the groundwater drought event to obtain a groundwater drought event feature;
groundwater drought event characteristics may include drought start time, drought end time, drought duration, drought average area, drought maximum area, drought shroud area, drought average intensity, drought maximum intensity, and drought intensity.
Wherein, the drought duration is the total time that a ground water drought event has elapsed from the beginning to the end; the drought average area is the average value of the occupied area of each time point within the duration of a ground water drought event; the drought maximum area is the maximum value of the occupied area of each time point within the duration of a ground water drought event; the drought cage area is the union area of the grid points occupied by each time point within the duration of a ground water drought event; drought intensity is the accumulated value of drought indexes of grid points at each time point within the duration of a ground water drought event; the drought average intensity is the ratio of the drought intensity to the drought duration of a field of groundwater drought events; the drought maximum intensity is the minimum value of the drought index at each grid point at each time point within the duration of a drought event.
In one example, another method for identifying drought in groundwater with uneven site distribution, as shown in FIG. 2, may include:
(1) The Huaibei plain is selected as a research area, and 2005-2020 annual book of groundwater level monitoring in China is collected, and shallow groundwater data in Henan, shandong, anhui and Jiangsu 4 provinces are screened. Because all the underground water monitoring stations have more detailed address, elevation, groundwater level or burial depth information, but only partial underground water monitoring stations have longitude and latitude information, the address information of the underground water monitoring stations is converted into WGS84 longitude and latitude coordinate information by adopting a geocoding service provided by a Google map and other platforms.
(2) And carrying out rationality check on the basic information of the underground water monitoring station and the original data of the monitoring information, wherein the rationality check comprises years, months, days, longitude and latitude ranges, elevation ranges and the like. And screening abnormal values of the groundwater level or the buried depth monitoring data by adopting a 3sigma method, judging one by one, and removing or changing obviously wrong outlier data points. And uniformly converting the ground elevation data and the ground water monitoring data into ground elevation and ground water level data of a yellow sea elevation system in 1985.
(3) Based on XGBoost algorithm, reconstructing a regional groundwater level inter-lunar sequence, taking year, month, longitude, latitude and ground elevation as input characteristics, taking shallow groundwater level as tag data, and adopting grid search and 5-fold cross validation methods to perform parameter optimization on the maximum depth of the tree and the total number of the tree, wherein the maximum depth selection range of the tree is 1-10, the total number selection range of the tree is 100-1000, and the parameter optimization process is shown in table 1. As can be seen from comparing the test results of 100 sets of parameters, when 7 is taken as the maximum depth and 300 is taken as the total number of trees, the model effect is best, and the predicted data and the test data of the optimal model are compared as shown in FIG. 3. The basic information of years, months, longitudes, latitudes, ground elevations and the like in the research period of the research area is gridded (the spatial resolution is 0.25 degrees multiplied by 0.25 degrees), and the basic information is input into a trained model, so that ground water level month scale data reconstructed at each grid point are obtained through calculation.
TABLE 1XGBoost Algorithm parameter preference
(4) Aiming at each grid point in the research area, searching 8 shallow groundwater level monitoring stations closest to the research area, and calculating the groundwater level of each grid point by adopting an inverse distance interpolation method. On the basis, a moving average method is adopted to calculate 30-day moving average water level values of all grid points, and then the moving average value is subtracted from the ground water level values of all grid points to finally obtain the ground water level intra-month fluctuation value of the decursin scale trend.
(5) And adding the regional groundwater level inter-month sequence reconstructed based on the machine learning algorithm and the regional groundwater level intra-month sequence reconstructed based on the inverse distance interpolation method, and calculating to obtain the reconstructed regional groundwater level sequence.
(6) And calculating a moving average water level value of each grid point for 1100 days (about 3 years) by adopting a moving average method, and subtracting the moving average value from the ground water level value of each grid point to obtain the ground water level fluctuation value with the trend removed for a plurality of years. And (5) normalizing the trended groundwater level time sequence by using a Min-Max normalization method. And (3) selecting Gamma and Pearson III types as basic distribution types, fitting the average value of the standardized groundwater level in each ten days of each grid point, optimizing distribution according to the fitted mean square error, estimating parameters by adopting a maximum likelihood method, converting the cumulative frequency distribution of the average water level in the groundwater into standard normal distribution, and obtaining the standardized groundwater level index through inverse standardization.
(7) Setting a threshold R1 to be-0.5 according to a non-drought and light drought dividing limit of a standardized precipitation index of meteorological drought grade (GB/T20481-2017), depending on a bay Cheng Lilun, screening out groundwater drought grid points at each time point, traversing a research area by utilizing a 3X 3 grid, merging to form drought patches if elements corresponding to adjacent grid points are still drought grid points, and referring to regional drought process monitoring and evaluating method (QX/T597-2021), wherein only the drought patches (about 5% of the area of the research area) of each time point of the research area are reserved. And (3) spatially superposing drought patches at adjacent time points, referring to regional drought process monitoring and evaluating methods (QX/T597-2021) and related documents, setting alpha as 1%, setting beta as 20%, and if the overlapped area is larger than the minimum overlapped area, considering that the two drought patches belong to the same drought event, and giving the same drought event number.
(8) The threshold R2 is set to-1.0 and R0 is set to 0 by referring to the light and medium drought demarcation limit of the standardized precipitation index of Meteorological drought class (GB/T20481-2017).
For 2 drought events with the interval time of 1 month, if a spatial intersection exists between the last drought time point of the previous drought event and the first drought time point of the next drought event, and the spatial union drought index value of the interval month is smaller than 0, merging the 2 drought events into 1 drought event. For drought events with a duration of only 1 month, if the index value is greater than-1.0, the drought event is rejected.
(9) By relying on the run theory, the characteristics of the groundwater drought event are extracted, including the starting time, the ending time, the duration, the average area, the maximum area, the cage area, the average intensity, the maximum intensity, the intensity and the like.
Because the shallow Water level has good correlation with the ground elevation, as shown in fig. 4, the advantage of the identification method of the application is illustrated by reproducing the relationship between the shallow Water level table (vertical axis) and the ground elevation DEM (horizontal axis), wherein the actually measured shallow Water level data is obs, the data calculated by the inverse distance interpolation method is idw, the data calculated by the XGBoost algorithm is XGBoost, and the data calculated by the algorithm is xgboost_ idw. According to the actual measurement data relationship, most shallow groundwater levels are lower than the ground elevation (below the 1:1 line), but the groundwater level fluctuation range calculated by the inverse distance interpolation method is large, and a large amount of groundwater levels are higher than the ground elevation, which is unreasonable. The result of XGBoost algorithm is basically within the coverage range of the measured data, reflects objective rules but has insufficient time fluctuation. The method simultaneously absorbs the advantages of the XGBoost algorithm and the inverse distance interpolation method, can accurately analyze the relationship between the shallow water level and the ground elevation, longitude and latitude, year and month, embody the medium-long term change of the shallow water level along with time, and can better reflect the short-time fluctuation of the shallow water level along with time. From fig. 4, most of the calculation results of the method are in the coverage range of the measured data, and compared with the XGBoost algorithm, the calculation results of the method have wider coverage range and stronger volatility on the measured data, and embody the advantages of the method.
And on the basis of reconstructing the shallow groundwater level sequence of the Huaibei plain, carrying out the time-space recognition of the drought of the groundwater of the Huaibei plain, wherein the result of the time-space recognition of the drought of the groundwater of the Huaibei plain in 2005-2020 is shown in Table 2.
TABLE 2
| Drought of groundwater | Number of field times | Duration (ten days) | Cage area (grid number) | Intensity of intensity |
| Drought duration>=0 ten days | 72 | 588 | 2741 | 15328 |
| Drought duration>=3 ten days | 37 | 536 | 2174 | 14795 |
| Drought duration>=6 ten days | 24 | 487 | 1846 | 14300 |
| Drought duration>=9 ten days | 21 | 468 | 1755 | 14139 |
| Drought duration>18 ten days = | 12 | 363 | 1283 | 12391 |
| Drought duration>=36 ten days | 4 | 185 | 613 | 7678 |
Through drought space-time identification analysis, 37 fields of groundwater drought events with duration exceeding 3 ten days are obtained, and 26 fields of actual drought events (mostly pointing to weather with lower precipitation, soil moisture loss, crop yield reduction and the like and agricultural drought) related to regions such as 'Huabei', 'Huang Huai' winter wheat region ',' Henan ',' shandong ',' Anhui 'are obtained according to literature data such as' Chinese weather disaster annual survey 'of' Chinese 'of' in the national plain; with the actual drought event as a comparison standard, the groundwater drought event identified by space time can completely cover the occurrence period (with the ratio of 65.4%) of 17 actual drought events, partially cover the occurrence period (with the ratio of 19.2%) of 5 actual drought events, and the occurrence period of 4 actual drought events cannot cover (with the ratio of 15.4%), so that the identified groundwater drought event has good appearance on the occurrence of the actual drought event.
Corresponding to the method, the embodiment of the application also provides a device for identifying drought of groundwater facing to uneven site distribution, as shown in fig. 5, the device comprises:
an obtaining unit 510, configured to obtain groundwater data of a target study area in a historical period; the underground water data are obtained by converting original monitoring underground water data of a historical time period in the target research area based on an elevation system of a preset historical time point; the underground water data comprise a collecting position, collecting time, underground water elevation and an underground water level value;
the processing unit 520 is configured to reconstruct, after gridding the target research area, ground water level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method, to obtain an area ground water level sequence of the target research area;
and standardizing the regional groundwater level sequence based on a preset standardized precipitation index construction algorithm to obtain a standardized groundwater level index sequence;
and the determining unit 530 is configured to process the normalized groundwater level index sequence based on a run-length theory, determine a groundwater drought event in the target research area, and determine a groundwater drought event feature.
The functions of each functional unit of the groundwater drought identification device facing to uneven site distribution provided in the foregoing embodiments of the present application may be implemented through the foregoing method steps, so specific working processes and beneficial effects of each unit in the groundwater drought identification device facing to uneven site distribution provided in the embodiments of the present application are not repeated herein.
The embodiment of the present application further provides an electronic device, as shown in fig. 6, including a processor 610, a communication interface 620, a memory 630, and a communication bus 640, where the processor 610, the communication interface 620, and the memory 630 complete communication with each other through the communication bus 640.
A memory 630 for storing a computer program;
the processor 610, when executing the program stored in the memory 630, performs the following steps:
acquiring groundwater data of a target research area in a historical time period; the underground water data are obtained by converting original monitoring underground water data of a historical time period in the target research area based on an elevation system of a preset historical time point; the underground water data comprise a collecting position, collecting time, underground water elevation and an underground water level value;
After gridding the target research area, reconstructing the groundwater level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method to obtain an area groundwater level sequence of the target research area;
based on a preset standardized precipitation index construction algorithm, standardizing the regional groundwater level sequence to obtain a standardized groundwater level index sequence;
and processing the standardized groundwater level index sequence based on a run theory, determining a groundwater drought event in a target research area, and determining the characteristics of the groundwater drought event.
The communication bus mentioned above may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
Since the implementation manner and the beneficial effects of the solution to the problem of each device of the electronic apparatus in the foregoing embodiment may be implemented by referring to each step in the embodiment shown in fig. 1, the specific working process and the beneficial effects of the electronic apparatus provided in the embodiment of the present application are not repeated herein.
In yet another embodiment provided herein, a computer readable storage medium is provided, in which instructions are stored, which when run on a computer, cause the computer to perform the method for identifying groundwater drought oriented towards uneven site distribution described in any of the above embodiments.
In yet another embodiment provided herein, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform the non-uniform site-oriented drought identification method of any of the above embodiments.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following description be interpreted as including the preferred embodiments and all alterations and modifications as fall within the scope of the embodiments herein.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, given that such modifications and variations of the embodiments of the present application are within the scope of the embodiments of the present application and their equivalents, such modifications and variations are also intended to be included in the embodiments of the present application.
Claims (10)
1. An underground water drought identification method oriented to uneven site distribution, which is characterized by comprising the following steps:
acquiring groundwater data of a target research area in a historical time period; the underground water data are obtained by converting original monitoring underground water data of a historical time period in the target research area based on an elevation system of a preset historical time point; the underground water data comprise a collecting position, collecting time, underground water elevation and an underground water level value;
after gridding the target research area, reconstructing the groundwater level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method to obtain an area groundwater level sequence of the target research area;
Based on a preset standardized precipitation index construction algorithm, standardizing the regional groundwater level sequence to obtain a standardized groundwater level index sequence;
and processing the standardized groundwater level index sequence based on a run theory, determining a groundwater drought event in a target research area, and determining the characteristics of the groundwater drought event.
2. The method of claim 1, wherein prior to acquiring groundwater data for the target study area over the historical period of time, the method further comprises:
acquiring original monitoring groundwater data of a historical time period in the target research area;
and performing outlier processing on the original monitored groundwater data by adopting a 3sigma processing algorithm to obtain the groundwater data.
3. The method of claim 1, wherein reconstructing the ground water level data for each grid point over the historical time period based on a machine learning algorithm and an inverse distance interpolation to obtain a regional ground water level sequence for the target study region comprises:
inputting the ground water level data of each grid point in the historical time period into a trained XGBoost algorithm model to obtain a regional ground water level inter-moon sequence output by the XGBoost algorithm model, wherein the regional ground water level inter-moon sequence comprises ground water level data of each month in the historical time period;
Calculating groundwater data corresponding to n groundwater level monitoring stations closest to the target research area by adopting an inverse distance interpolation method to obtain daily groundwater data corresponding to each grid point;
calculating a month moving average water level value based on the daily ground water data corresponding to each grid point, and subtracting the month moving average water level value from the daily ground water level value corresponding to each grid point to obtain a regional ground water level intra-month sequence of the target research region, wherein the regional ground water level intra-month sequence comprises ground water level intra-month fluctuation data of a month scale removal trend in the historical time period;
and adding the regional groundwater level inter-moon sequence with the data of the corresponding position in the regional groundwater level inter-moon sequence to obtain the regional groundwater level sequence of the target research region, wherein the regional groundwater level sequence comprises daily groundwater level data of each grid point in the historical time period.
4. The method of claim 1, wherein normalizing the regional groundwater level sequence based on a preset normalized precipitation index construction algorithm to obtain a normalized groundwater level index sequence comprises:
calculating a years moving average water level value based on water level data corresponding to each grid point in the regional water level sequence, and subtracting the years moving average water level value from the water level value corresponding to each grid point to obtain a water level sequence of the last year trend of the target research region, wherein the water level sequence of the last year trend comprises water level fluctuation data of the last year trend;
And after the groundwater level sequence with the past year trend is standardized, referring to a construction flow of a standardized precipitation index, processing the standardized groundwater level sequence with the past year trend to obtain a standardized groundwater level index sequence.
5. The method of claim 1, wherein processing the normalized groundwater level index sequence based on a run length theory to determine groundwater drought events within a target study area comprises:
based on the run theory, if the standardized groundwater level index value of each time point in the standardized groundwater level index sequence is smaller than or equal to a preset drought threshold value, determining grid points corresponding to the corresponding standardized groundwater level index values as drought grid points;
traversing a target research area, and carrying out space combination on target drought grid points in the determined drought grid points to obtain drought patches, wherein the target drought grid points are adjacent drought grid points;
and overlapping drought patches of adjacent time nodes in space, determining the overlapping area of an overlapping area, determining the drought patches with the overlapping area larger than a preset area as the same groundwater drought event, and giving the same drought event number.
6. The method of claim 1, wherein the method further comprises:
for two groundwater drought events with the interval time of 1 month, if a spatial intersection exists between the ending time point of the previous field groundwater drought event and the starting time point of the next field groundwater drought event, and the drought index value of the spatial union of the interval months is smaller than a first drought index threshold value, merging the two groundwater drought events into the same field groundwater drought event;
and (3) rejecting the ground water drought event with the drought duration of only 1 month when a plurality of drought index values are larger than a second drought index threshold value.
7. The method of claim 1, wherein determining groundwater drought event characteristics comprises:
extracting features of the groundwater drought event to obtain the features of the groundwater drought event;
the groundwater drought event features include drought start time, drought end time, drought duration, drought average area, drought maximum area, drought shroud area, drought average intensity, drought maximum intensity, and drought intensity.
8. An apparatus for identifying drought in groundwater for uneven site distribution, the apparatus comprising:
The acquisition unit is used for acquiring groundwater data of the target research area in a historical time period; the underground water data are obtained by converting original monitoring underground water data of a historical time period in the target research area based on an elevation system of a preset historical time point; the underground water data comprise a collecting position, collecting time, underground water elevation and an underground water level value;
the processing unit is used for reconstructing the ground water level data of each grid point in the historical time period based on a machine learning algorithm and an inverse distance interpolation method after gridding the target research area to obtain an area ground water level sequence of the target research area;
and standardizing the regional groundwater level sequence based on a preset standardized precipitation index construction algorithm to obtain a standardized groundwater level index sequence;
and the determining unit is used for processing the standardized groundwater level index sequence based on a run-length theory, determining groundwater drought events in a target research area and determining groundwater drought event characteristics.
9. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus;
A memory for storing a computer program;
a processor for implementing the method of any of claims 1-7 when executing a program stored on a memory.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410102915.7A CN117633539B (en) | 2024-01-25 | 2024-01-25 | Underground water drought identification method and device for uneven site distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410102915.7A CN117633539B (en) | 2024-01-25 | 2024-01-25 | Underground water drought identification method and device for uneven site distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117633539A true CN117633539A (en) | 2024-03-01 |
| CN117633539B CN117633539B (en) | 2024-04-12 |
Family
ID=90035795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410102915.7A Active CN117633539B (en) | 2024-01-25 | 2024-01-25 | Underground water drought identification method and device for uneven site distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117633539B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180165616A1 (en) * | 2016-12-13 | 2018-06-14 | John Sun | System and Method for Producing and Distributing Information Relevant to Water Events |
| KR102073768B1 (en) * | 2019-10-16 | 2020-02-05 | 한국수자원공사 | Drought information supply system based on portal |
| CN111504425A (en) * | 2020-04-24 | 2020-08-07 | 中国水利水电科学研究院 | Method and device for estimating ecological underground water level in arid plain area |
| CN112765808A (en) * | 2021-01-15 | 2021-05-07 | 黄河勘测规划设计研究院有限公司 | Ecological drought monitoring and evaluating method |
| CN112837169A (en) * | 2021-01-11 | 2021-05-25 | 黄河勘测规划设计研究院有限公司 | Gridding drought comprehensive monitoring, early warning and evaluating method in drought process |
| EP3986128A1 (en) * | 2019-06-24 | 2022-04-27 | BASF Agro Trademarks GmbH | Decision system for crop efficiency product application using remote sensing based soil parameters |
| CN115081952A (en) * | 2022-07-28 | 2022-09-20 | 中国农业大学 | Regional agricultural drought identification method and system |
| CA3154014A1 (en) * | 2021-03-30 | 2022-09-30 | Climate Check, Inc. | Climate-based risk rating |
| CN116805439A (en) * | 2023-06-27 | 2023-09-26 | 武汉大学 | Drought prediction method and system based on artificial intelligence and atmospheric circulation mechanism |
| CN116842435A (en) * | 2023-06-07 | 2023-10-03 | 广西大学 | SWAP-based field drought three-dimensional measurement and time-space evolution visualization method |
-
2024
- 2024-01-25 CN CN202410102915.7A patent/CN117633539B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180165616A1 (en) * | 2016-12-13 | 2018-06-14 | John Sun | System and Method for Producing and Distributing Information Relevant to Water Events |
| EP3986128A1 (en) * | 2019-06-24 | 2022-04-27 | BASF Agro Trademarks GmbH | Decision system for crop efficiency product application using remote sensing based soil parameters |
| KR102073768B1 (en) * | 2019-10-16 | 2020-02-05 | 한국수자원공사 | Drought information supply system based on portal |
| CN111504425A (en) * | 2020-04-24 | 2020-08-07 | 中国水利水电科学研究院 | Method and device for estimating ecological underground water level in arid plain area |
| CN112837169A (en) * | 2021-01-11 | 2021-05-25 | 黄河勘测规划设计研究院有限公司 | Gridding drought comprehensive monitoring, early warning and evaluating method in drought process |
| CN112765808A (en) * | 2021-01-15 | 2021-05-07 | 黄河勘测规划设计研究院有限公司 | Ecological drought monitoring and evaluating method |
| CA3154014A1 (en) * | 2021-03-30 | 2022-09-30 | Climate Check, Inc. | Climate-based risk rating |
| CN115081952A (en) * | 2022-07-28 | 2022-09-20 | 中国农业大学 | Regional agricultural drought identification method and system |
| CN116842435A (en) * | 2023-06-07 | 2023-10-03 | 广西大学 | SWAP-based field drought three-dimensional measurement and time-space evolution visualization method |
| CN116805439A (en) * | 2023-06-27 | 2023-09-26 | 武汉大学 | Drought prediction method and system based on artificial intelligence and atmospheric circulation mechanism |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117633539B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | Landslide susceptibility mapping using random forest and boosted tree models in Pyeong-Chang, Korea | |
| Khadr | Forecasting of meteorological drought using Hidden Markov Model (case study: The upper Blue Nile river basin, Ethiopia) | |
| Lin et al. | Predictive ability of logistic regression, auto-logistic regression and neural network models in empirical land-use change modeling–a case study | |
| CN112200358B (en) | Landslide level prediction method, landslide level prediction device, landslide level prediction equipment and storage medium | |
| CN115688404B (en) | Rainfall landslide early warning method based on SVM-RF model | |
| CN112200354A (en) | Landslide prediction method, device, equipment and storage medium | |
| CN114611941A (en) | Landslide disaster evaluation method and system considering space dangerousness | |
| CN117370939B (en) | Basin rainfall runoff response relation evolution analysis method and system considering soil moisture content | |
| CN115937692B (en) | Coastal wetland carbon sink effect evaluation method and system | |
| Li | Exploring the potential of utilizing unsupervised machine learning for urban drainage sensor placement under future rainfall uncertainty | |
| Bastin et al. | Remotely-sensed analysis of ground-cover change in Queensland’s rangelands, 1988–2005 | |
| Balti et al. | Big data based architecture for drought forecasting using LSTM, ARIMA, and Prophet: Case study of the Jiangsu Province, China | |
| Sahu et al. | Density-based spatial clustering of application with noise approach for regionalisation and its effect on hierarchical clustering | |
| CN113486295B (en) | Fourier series-based ozone total amount change prediction method | |
| Tang et al. | The use of serially complete station data to improve the temporal continuity of gridded precipitation and temperature estimates | |
| Ali et al. | Raingauge network optimization in a tropical urban area by coupling cross-validation with the geostatistical technique | |
| CN112016744B (en) | Forest fire prediction method and device based on soil moisture and storage medium | |
| CN117633539B (en) | Underground water drought identification method and device for uneven site distribution | |
| CN117197646A (en) | Remote sensing automatic identification method and device for submerged plants, computer equipment and medium | |
| Wang et al. | Early warning of debris flow using optimized self-organizing feature mapping network | |
| CN116151437A (en) | Shallow collapse disaster early warning model establishment method, device, equipment and medium | |
| CN116089832A (en) | Method and device for reducing ground water reserves of gravity satellites and computer equipment | |
| CN115270598A (en) | Non-landslide sample selection method for easy-to-model and computer equipment | |
| Katti et al. | A Pluvial Flood Detection Model Using Machine Learning Techniques and Simulate The Flow of Water | |
| CN114662921B (en) | Sponge city construction method and system based on drainage basin management |
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 |