Meteorological drought prediction method based on space-time analysis

Abstract

The invention relates to the technical field of meteorological prediction, in particular to a meteorological drought prediction method based on space-time analysis, which constructs a meteorological drought space-time prediction model by combining multi-source feature aggregation, a self-attention mechanism and an optimized time convolutional network, and can predict the meteorological drought by taking meteorological elements of multivariate space-time features as a basis. The meteorological drought level in the preset future time period is accurately predicted, and more powerful support is provided for formulating a drought management plan to maintain natural resources and reduce loss caused by drought.

Description

Technical Field

[0001] The invention relates to the technical field of meteorological forecasting, in particular to a meteorological drought forecasting method based on time-space analysis. Background Art

[0002] Drought in the meteorological sense develops slowly, lasts for a long time, has relatively vague start and end marks, and is highly destructive. The impact of drought is not limited to the agricultural field, but also involves multiple aspects such as food supply, ecological environment and social stability. Therefore, combining future changes in meteorological elements to predict the time, scope and intensity of future droughts is crucial for formulating drought management plans to maintain natural resources, and is an effective way to reduce losses caused by drought.

[0003] Drought prediction models can be roughly divided into three categories: models based on physical mechanisms, models based on data-driven, and hybrid models.

[0004] Deep learning, with its advantages in data-driven, complex relationship modeling, personalized prediction, model improvement, data integration, decision support and resource conservation, provides a more comprehensive, accurate and efficient solution for drought prediction. The existing technology uses deep learning technology to predict drought, and by establishing nonlinear functions to explore the complex relationship between input variables and target variables, it has lower computing costs and better prediction performance. Among them, the temporal convolutional network has better time series modeling capabilities, parallel processing capabilities and multi-scale information capture capabilities in the field of meteorological drought prediction. It can capture details and overall features in the data at different levels, which helps to more comprehensively understand the spatial and temporal information in meteorological data.

[0005] When exploring meteorological drought prediction, due to the spatiotemporal correlation between monitoring stations, the drought situation in one area is spatially linked to the drought situation in other areas. Therefore, it is considered to conduct spatiotemporal correlation analysis on the data of multiple monitoring stations. By identifying stations with similar climatic conditions and consistent drought levels, the regional distribution, development trends and potential impacts of drought can be more effectively assessed. However, there is no similar solution in the existing technology.

[0006] Therefore, it is necessary to design a meteorological drought prediction method based on spatiotemporal analysis. By constructing a spatiotemporal prediction model for meteorological drought, it is possible to accurately predict the meteorological drought level in a preset future time period based on meteorological elements with multivariate spatiotemporal characteristics. Summary of the invention

[0007] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a meteorological drought prediction method based on spatiotemporal analysis. By constructing a meteorological drought spatiotemporal prediction model, it is possible to accurately predict the meteorological drought level in a preset future time period based on meteorological elements with multivariate spatiotemporal characteristics.

[0008] In order to achieve the above object, the present invention provides a meteorological drought prediction method based on spatiotemporal analysis:

[0009] The following steps are involved:

[0010] S1, obtain meteorological element data and drought index, and perform data preprocessing:

[0011] S1-1, download the continuous data of various meteorological elements in recent years, including precipitation, temperature, sunshine duration, relative humidity, evaporation and air pressure, and pre-process the data, where abnormal values ​​are replaced by the average value of nearby data, and missing values ​​are filled by time interpolation method;

[0012] S1-2, calculate the meteorological drought assessment index through some meteorological element data in the data, and use the standardized precipitation evapotranspiration index SPEI combined with the meteorological element data obtained in S1 to comprehensively assess the degree and impact of drought;

[0013] By calculating the standardized precipitation evapotranspiration index SPEI, the drought index at the time scale of 1, 3, 6, and 12 months is obtained. The calculation formula is:

[0014]

[0015] Among them, C0=2.515517, C1=0.802853, C2=0.010328; d1=1.432788, d2=0.189269, d3=0.001308; Where F(X) is the cumulative function of the log-logistic probability distribution;

[0016] S1-3, after merging the meteorological element data and the SPEI value, normalize them and divide the processed data into a training set accounting for 80% and a test set accounting for 20%;

[0017] S1-4, feature selection is performed before inputting the data into the model. The Pearson correlation coefficient is used to measure the linear relationship between the meteorological characteristics of the data set and the drought index of different time spans. The Pearson correlation coefficient ranges from -1 to +1. The closer to +1, the higher the correlation. The calculation formula of the Pearson correlation coefficient is:

[0018]

[0019] Where r is the Pearson correlation coefficient, x i and i are the observed values ​​of two variables; and are the means of the two variables respectively; since not all positively correlated meteorological features have a significant impact on drought index prediction, different correlation thresholds are used to test the prediction performance, and the meteorological features that have a relatively large impact on the output are extracted as input features;

[0020] S2, site spatial correlation analysis:

[0021] Calculate the probability of consistency of drought levels between the target site and other sites in the same period, and select and determine sites that are spatially correlated;

[0022] The probability threshold selection was tested experimentally, and the results under different thresholds were compared to select the optimal threshold that can effectively identify the associated sites while avoiding too many false positives;

[0023] S2-1, the climate conditions are similar within the similar distance range, and the upper limit of the distance between the relevant stations is set to 50-70 kilometers. The Haversine formula is used to calculate the distance between the two stations, that is, the calculation formula is:

[0024]

[0025]

[0026] d = R·c;

[0027] in, is the latitude of two points in radians, ω is the longitude of two points in radians, and R is the radius of the Earth;

[0028] S2-2, select stations with similar climate conditions and significant consistency in drought levels as spatially related stations, and classify meteorological drought levels into five levels: no drought, mild drought, moderate drought, severe drought, and extreme drought according to the meteorological drought level standard;

[0029] S2-3, integrate the spatiotemporal information of monitoring stations that meet the spatial correlation, where the input feature is the four-dimensional vector X(B,T,N,C) of spatiotemporal data of different stations, where B represents the number of samples, T represents the time step, N represents the number of stations, and C represents the number of features; given the input feature X = [X1, X2, X3, ..., X n ] is a vector of N feature matrices containing spatiotemporal data of different sites, which integrates the input information of X in the dimensions of multiple sites and uses multiple 1×1 convolution kernels to expand the dimension of this multi-channel information;

[0030] S2-4, using a 1×1 convolution kernel to reduce the dimension to 1, aggregate the data features, and increase the dimension to improve the feature extraction capability of multiple monitoring station information, aggregating the input data into a two-dimensional feature vector;

[0031] 1×1 convolution is a dimension increasing or decreasing module, which is used to effectively increase the model capacity, that is, to increase nonlinearity and eliminate computational bottlenecks;

[0032] S3, prediction model training:

[0033] Construct a spatiotemporal prediction model for meteorological drought based on a temporal convolutional network through multi-feature aggregation, train the model using the integrated multi-site information results, and use the trained model as a drought prediction model to achieve drought prediction;

[0034] S3-1, using the data of the training set to input the prediction model, input the vector containing the spatiotemporal feature information into the model, and train the model using the forward propagation method. Through layer-by-layer processing, the abstract representation of the input features is effectively learned and extracted, and then the model parameters are updated using back propagation. After continuous iterative optimization, the optimal prediction model is generated;

[0035] S3-2, the prediction model consists of a convolutional layer, a linear encoding layer, a self-attention layer, a temporal convolutional network TCN, and a decoding layer;

[0036] The convolution layer input is processed by the convolution layer and batch normalization layer to extract preliminary features. The convolution features are then encoded using the linear layer encoding layer and Dropout is applied. The self-attention layer mechanism is then applied to the encoded features to capture global dependencies. TCN is used to further extract temporal features. Finally, the decoder outputs the prediction results.

[0037] S3-2-1, the query vector Q, key vector K and value vector V corresponding to the self-attention layer mechanism are calculated by using the similarity between Q and K, and then the weights of V with different inputs are adjusted by weighted summation using the attention score, that is, the formula is:

[0038]

[0039] d k is the dimension of each attention head;

[0040] The prediction model simultaneously focuses on and integrates different aspects of the input data sequence to improve the model's ability to handle long-term dependencies and complex relationships in meteorological data;

[0041] S3-2-2, the temporal convolutional network consists of multiple residual unit stacks. The residual module includes two convolution units and a nonlinear mapping unit. Each convolution unit includes a one-dimensional dilated causal convolution, weight normalization, Relu activation function and Dropout operation;

[0042] Causal convolution means that the current time t is only related to the input at time t and before time t;

[0043] The extended convolution operation for the index of the input data sequence is described as:

[0044]

[0045] Where s is the index of the sequence used to represent the current time step or position, d is the dilation factor, k is the filter size, i is a non-negative integer, and sd·i is the localization of some information in the history;

[0046] S3-2-3, the temporal convolutional network is a multi-layer fully convolutional network, which sequentially connects the input layer, the first hidden layer, the second hidden layer, the third hidden layer and the output layer;

[0047] The convolution operation extracts useful features by moving the sliding window, i.e., the convolution kernel, on the feature matrix and calculating the weighted sum of the elements in the window and the convolution kernel;

[0048] Each of the first hidden layer, the second hidden layer, and the third hidden layer gradually abstracts and extracts key information from the input data sequence through causal convolution. As the number of layers increases, the network captures more complex and higher-level features, thereby achieving efficient learning and feature extraction at different levels of the network;

[0049] During the training and testing of the temporal convolutional network, different network depths and filter sizes are adjusted and set to improve the model accuracy, so as to flexibly adapt to the requirements of temporal feature extraction at different scales;

[0050] S3-2-4, when constructing the prediction model, it is necessary to predefine the hyperparameters, loss function and optimization algorithm of the meteorological drought spatiotemporal prediction model; the hyperparameters include the number of network layers, convolution kernel size, number of convolution kernels, learning rate, dropout rate, batch size, sequence length and output dimension; among which, a grid search is performed when the number of network layers and kernel size of the meteorological drought spatiotemporal prediction model are specified;

[0051] The mean square error (MSE) was selected as the loss function of the training process, and the Adam optimizer was used to perform gradient descent optimization on the random objective function of the model. In the subsequent experiments, the performance and generalization ability of the prediction model were optimized by adjusting parameters according to the experimental results.

[0052] S3-3, the criteria for determining the spatiotemporal prediction model for meteorological drought are:

[0053] Evaluation index determination coefficient R 2 and root mean square error RMSE;

[0054] Index determination coefficient R 2It indicates the linear correlation between the predicted data and the observed data. It is an indicator to measure the model fit. The closer its value is to 1, the better the model fits the data. Its calculation formula is:

[0055]

[0056] Among them, y i is the observed value, is the predicted value, N is the number of data points;

[0057] in, is the average of the actual values;

[0058] The root mean square error (RMSE) is used to measure the average model prediction error and to indicate the closeness between the predicted value and the observed value. The lower the index value, the higher the prediction accuracy. The calculation formula is:

[0059]

[0060] S4, determine the drought degree of the area to be predicted according to the predicted drought index:

[0061] The output results of the meteorological drought prediction model are analyzed, and the predicted SPEI values ​​are divided into drought levels according to the drought grade classification standards to determine the degree of drought in the predicted area within the next preset time period.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] Compared with the method of only considering a single site or simply merging data from multiple sites, the present invention can accurately identify sites with similar climatic conditions and significant consistency in drought levels as spatially associated sites by calculating the probability of consistency between the target site and other sites in the same period, and combining the experimentally optimized probability threshold and geographic distance limit (50 to 70 kilometers). At the same time, by efficiently integrating multi-dimensional spatiotemporal data, comprehensive aggregation of multi-source features is achieved, spatial and temporal information in the data is better mined, and details and overall features in the data are captured.

[0064] The present invention also combines multi-source feature aggregation, self-attention mechanism and optimized temporal convolutional network to form a new and efficient drought prediction solution. It also significantly improves the performance of the model by improving technical details, optimizing algorithms, adjusting network structures, and improving feature extraction methods, thereby achieving more accurate drought prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a data preprocessing flow chart of the present invention.

[0066] Figure 2This is a diagram of the meteorological drought spatiotemporal prediction model based on spatiotemporal analysis provided by the present invention.

[0067] Figure 3 A flow chart of a meteorological drought prediction method based on spatiotemporal analysis provided by the present invention. DETAILED DESCRIPTION

[0068] See also Figures 1 to 3 , the present invention is further described in conjunction with the accompanying drawings:

[0069] The following steps are involved:

[0070] S1, obtain meteorological element data and drought index, and perform data preprocessing:

[0071] S1-1, download the continuous data of various meteorological elements in recent years, including precipitation, temperature, sunshine duration, relative humidity, evaporation and air pressure, and pre-process the data, where abnormal values ​​are replaced by the average value of nearby data, and missing values ​​are filled by time interpolation method;

[0072] S1-2, calculate the meteorological drought assessment index through some meteorological element data in the data, and use the standardized precipitation evapotranspiration index SPEI combined with the meteorological element data obtained in S1 to comprehensively assess the degree and impact of drought;

[0073] By calculating the standardized precipitation evapotranspiration index SPEI, the drought index at the time scale of 1, 3, 6, and 12 months is obtained. The calculation formula is:

[0074]

[0075] Among them, C0=2.515517, C1=0.802853, C2=0.010328; d1=1.432788, d2=0.189269, d3=0.001308; Where F(X) is the cumulative function of the log-logistic probability distribution;

[0076] S1-3, after merging the meteorological element data and the SPEI value, normalize them and divide the processed data into a training set accounting for 80% and a test set accounting for 20%;

[0077] S1-4, feature selection is performed before inputting the data into the model. The Pearson correlation coefficient is used to measure the linear relationship between the meteorological characteristics of the data set and the drought index of different time spans. The Pearson correlation coefficient ranges from -1 to +1. The closer to +1, the higher the correlation. The calculation formula of the Pearson correlation coefficient is:

[0078]

[0079] Where r is the Pearson correlation coefficient, x i and i are the observed values ​​of two variables; and are the means of the two variables respectively; since not all positively correlated meteorological features have a significant impact on drought index prediction, different correlation thresholds are used to test the prediction performance, and the meteorological features that have a relatively large impact on the output are extracted as input features;

[0080] S2, site spatial correlation analysis:

[0081] Calculate the probability of consistency of drought levels between the target site and other sites in the same period, and select and determine sites that are spatially correlated;

[0082] The probability threshold selection was tested experimentally, and the results under different thresholds were compared to select the optimal threshold that can effectively identify the associated sites while avoiding too many false positives;

[0083] S2-1, the climate conditions are similar within the similar distance range, and the upper limit of the distance between the relevant stations is set to 50-70 kilometers. The Haversine formula is used to calculate the distance between the two stations, that is, the calculation formula is:

[0084]

[0085] d = R·c;

[0086] in, is the latitude of two points in radians, ω is the longitude of two points in radians, and R is the radius of the Earth;

[0087] S2-2, select stations with similar climatic conditions and significant consistency in drought levels. As stations with spatial correlation, the meteorological drought levels can be divided into five levels according to the meteorological drought level standards: no drought, light drought, moderate drought, severe drought, and extreme drought, as shown in the following table:

[0088] grade type SPEI 1 No drought -0.5<SPEI 2 Mild drought -1.0<SPEI≤-0.5 3 Moderate Drought -1.5<SPEI≤-1.0 4 Severe drought -2.0<SPEI≤-1.5 5 Extreme drought SPEI≤-2.0

[0089] S2-3, integrate the spatiotemporal information of monitoring stations that meet the spatial correlation, where the input feature is the four-dimensional vector X(B,T,N,C) of spatiotemporal data of different stations, where B represents the number of samples, T represents the time step, N represents the number of stations, and C represents the number of features; given the input feature X = [X1, X2, X3, ..., X n ] is a vector of N feature matrices containing spatiotemporal data of different sites, which integrates the input information of X in the dimensions of multiple sites and uses multiple 1×1 convolution kernels to expand the dimension of this multi-channel information;

[0090] S2-4, using a 1×1 convolution kernel to reduce the dimension to 1, aggregate the data features, and increase the dimension to improve the feature extraction capability of multiple monitoring station information, aggregating the input data into a two-dimensional feature vector;

[0091] 1×1 convolution is a dimension increasing or decreasing module, which is used to effectively increase the model capacity, that is, to increase nonlinearity and eliminate computational bottlenecks;

[0092] S3, prediction model training:

[0093] Construct a spatiotemporal prediction model for meteorological drought based on a temporal convolutional network through multi-feature aggregation, train the model using the integrated multi-site information results, and use the trained model as a drought prediction model to achieve drought prediction;

[0094] S3-1, using the data of the training set to input the prediction model, input the vector containing the spatiotemporal feature information into the model, and train the model using the forward propagation method. Through layer-by-layer processing, the abstract representation of the input features is effectively learned and extracted, and then the model parameters are updated using back propagation. After continuous iterative optimization, the optimal prediction model is generated;

[0095] S3-2, the prediction model consists of a convolutional layer, a linear encoding layer, a self-attention layer, a temporal convolutional network TCN, and a decoding layer;

[0096] The convolution layer input is processed by the convolution layer and batch normalization layer to extract preliminary features. The convolution features are then encoded using the linear layer encoding layer and Dropout is applied. The self-attention layer mechanism is then applied to the encoded features to capture global dependencies. TCN is used to further extract temporal features. Finally, the decoder outputs the prediction results.

[0097] S3-2-1, the query vector Q, key vector K and value vector V corresponding to the self-attention layer mechanism are calculated by using the similarity between Q and K, and then the weights of V with different inputs are adjusted by weighted summation using the attention score, that is, the formula is:

[0098]

[0099] d k is the dimension of each attention head;

[0100] The prediction model simultaneously focuses on and integrates different aspects of the input data sequence to improve the model's ability to handle long-term dependencies and complex relationships in meteorological data;

[0101] S3-2-2, the temporal convolutional network consists of multiple residual unit stacks. The residual module includes two convolution units and a nonlinear mapping unit. Each convolution unit includes a one-dimensional dilated causal convolution, weight normalization, Relu activation function and Dropout operation;

[0102] Causal convolution means that the current time t is only related to the input at time t and before time t;

[0103] The extended convolution operation for the index of the input data sequence is described as:

[0104]

[0105] Where s is the index of the sequence used to represent the current time step or position, d is the dilation factor, k is the filter size, i is a non-negative integer, and sd·i is the localization of some information in the history;

[0106] S3-2-3, the temporal convolutional network is a multi-layer fully convolutional network, which sequentially connects the input layer, the first hidden layer, the second hidden layer, the third hidden layer and the output layer;

[0107] The convolution operation extracts useful features by moving the sliding window, i.e., the convolution kernel, on the feature matrix and calculating the weighted sum of the elements in the window and the convolution kernel;

[0108] Each of the first hidden layer, the second hidden layer, and the third hidden layer gradually abstracts and extracts key information from the input data sequence through causal convolution. As the number of layers increases, the network captures more complex and higher-level features, thereby achieving efficient learning and feature extraction at different levels of the network;

[0109] During the training and testing of the temporal convolutional network, different network depths and filter sizes are adjusted and set to improve the model accuracy, so as to flexibly adapt to the requirements of temporal feature extraction at different scales;

[0110] S3-2-4, when constructing the prediction model, it is necessary to predefine the hyperparameters, loss function and optimization algorithm of the meteorological drought spatiotemporal prediction model; the hyperparameters include the number of network layers, convolution kernel size, number of convolution kernels, learning rate, dropout rate, batch size, sequence length and output dimension; among which, a grid search is performed when the number of network layers and kernel size of the meteorological drought spatiotemporal prediction model are specified;

[0111] The mean square error (MSE) was selected as the loss function of the training process, and the Adam optimizer was used to perform gradient descent optimization on the random objective function of the model. In the subsequent experiments, the performance and generalization ability of the prediction model were optimized by adjusting parameters according to the experimental results.

[0112] S3-3, the criteria for determining the spatiotemporal prediction model for meteorological drought are:

[0113] Evaluation index determination coefficient R 2 and root mean square error RMSE;

[0114] Index determination coefficient R 2 It indicates the linear correlation between the predicted data and the observed data. It is an indicator to measure the model fit. The closer its value is to 1, the better the model fits the data. Its calculation formula is:

[0115]

[0116] Among them, y i is the observed value, is the predicted value, N is the number of data points;

[0117] in, is the average of the actual values;

[0118] The root mean square error (RMSE) is used to measure the average model prediction error and to indicate the closeness between the predicted value and the observed value. The lower the index value, the higher the prediction accuracy. The calculation formula is:

[0119]

[0120] Where SSE is the sum of squared errors; N is the number of samples used, and the calculation formula for SSE is:

[0121]

[0122] S4, determine the drought degree of the area to be predicted according to the predicted drought index:

[0123] The output results of the meteorological drought prediction model are analyzed, and the predicted SPEI values ​​are divided into drought levels according to the drought grade classification standards to determine the degree of drought in the predicted area within the next preset time period.

[0124] The above are only preferred embodiments of the present invention, which are only used to help understand the method and core ideas of the present application. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

[0125] The above embodiments can be implemented in whole or in part by software or hardware. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0126] The present invention solves the problem that the drought situation in one area is spatially linked to the drought situation in other areas, which is a result of insufficient research in the prior art on the regional distribution, development trend and potential impact of drought assessment. By combining multi-source feature aggregation, self-attention mechanism and optimized temporal convolutional network, a spatiotemporal prediction model for meteorological drought is constructed. The model can accurately predict the meteorological drought level in a preset future time period based on meteorological elements with multivariate spatiotemporal characteristics, thus providing stronger support for the formulation of drought management plans to maintain natural resources and reduce losses caused by drought.

Claims

1. A meteorological drought prediction method based on spatiotemporal analysis, It is characterized in that The following steps are involved: S1, obtain meteorological element data and drought index, and perform data preprocessing: S1-1, download various meteorological element data of recent years, including precipitation, temperature, sunshine duration, relative humidity, evaporation and air pressure, and pre-process the data, where abnormal values ​​are replaced by the average value of nearby data, and missing values ​​are filled by time interpolation method; S1-2, calculating the meteorological drought assessment index through some meteorological element data in the data, and combining the standardized precipitation evapotranspiration index SPEI with the meteorological element data obtained in S1 to comprehensively assess the degree and impact of drought; By calculating the standardized precipitation evapotranspiration index SPEI, the drought index at the time scale of 1, 3, 6, and 12 months is obtained. The calculation formula is: Among them, C 0 =2.515517, C 1 =0.802853, C 2 =0.010328; d 1 =1.432788, d 2 =0.189269, d 3 =0.001308; Where F(X) is the cumulative function of the log-logistic probability distribution; S1-3, after merging the meteorological element data and the SPEI value, normalize them and divide the processed data into a training set accounting for 80% and a test set accounting for 20%; S1-4, feature selection is performed before inputting the data into the model, and the Pearson correlation coefficient is used to measure the linear relationship between the meteorological characteristics of the data set and the drought index of different time spans. The Pearson correlation coefficient ranges from -1 to +1, and the closer to +1, the higher the correlation. The calculation formula of the Pearson correlation coefficient is: Where r is the Pearson correlation coefficient, x i and i are the observed values ​​of two variables; and are the means of the two variables respectively; since not all positively correlated meteorological features have a significant impact on drought index prediction, different correlation thresholds are used to test the prediction performance, and the meteorological features that have a relatively large impact on the output are extracted as input features; S2, site spatial correlation analysis: Calculate the probability of consistency of drought levels between the target site and other sites in the same period, and select and determine sites that are spatially correlated; The probability threshold is selected through experimental testing, and the results under different thresholds are compared to select the optimal threshold that can effectively identify the associated sites and avoid too many misjudgments; S2-1, the climate conditions are similar within the similar distance range, and the upper limit of the distance between the relevant stations is set to 50-70 kilometers. The Haversine formula is used to calculate the distance between the two stations, that is, the calculation formula is: d = R·c; in, is the latitude of two points in radians, ω is the longitude of two points in radians, and R is the radius of the Earth; S2-2, select stations with similar climate conditions and significant consistency in drought levels as spatially related stations, and classify meteorological drought levels into five levels: no drought, mild drought, moderate drought, severe drought, and extreme drought according to the meteorological drought level standard; S2-3, integrate the spatiotemporal information of monitoring stations that meet the spatial correlation, where the input feature is the four-dimensional vector X(B, T, N, C) of spatiotemporal data of different stations, where B represents the number of samples, T represents the time step, N represents the number of stations, and C represents the number of features; given the input feature X = [X 1 , X 2 , X 3 , …, X n ] is a vector of N feature matrices containing spatiotemporal data of different sites, which integrates the input information of X in the dimensions of multiple sites and uses multiple 1×1 convolution kernels to expand the dimension of this multi-channel information; S2-4, using a 1×1 convolution kernel to reduce the dimension to 1, aggregate the data features, and improve the feature extraction capability of multiple monitoring station information by increasing the dimension, and aggregate the input data into a two-dimensional feature vector; the 1×1 convolution is a dimension increase or decrease module, which is used to effectively increase the model capacity, that is, increase nonlinearity to eliminate calculation bottlenecks; S3, prediction model training: Construct a spatiotemporal prediction model for meteorological drought based on a temporal convolutional network through multi-feature aggregation, train the model using the integrated multi-site information results, and use the trained model as a drought prediction model to achieve drought prediction; S3-1, using the data of the training set to input the prediction model, input the vector containing the spatiotemporal feature information into the model, and train the model using the forward propagation method. Through layer-by-layer processing, the abstract representation of the input features is effectively learned and extracted, and then the model parameters are updated using back propagation. After continuous iterative optimization, the optimal prediction model is generated; S3-2, the prediction model consists of a convolutional layer, a linear coding layer, a self-attention layer, a temporal convolutional network TCN and a decoding layer; The convolution layer input is processed by the convolution layer and batch normalization layer to extract preliminary features; then the convolution features are encoded using the linear layer encoding layer and Dropout is applied; then the self-attention layer mechanism is applied to the encoded features to capture global dependencies; TCN is used to further extract temporal features; and finally the prediction results are output through the decoder; S3-2-1, the query vector Q, key vector K and value vector V corresponding to the self-attention layer mechanism are calculated by using the similarity between Q and K to calculate the attention weight, and then the weight of V of different inputs is adjusted by weighted summation using the attention score, that is, the formula is: d k is the dimension of each attention head; The prediction model simultaneously focuses on and integrates different aspects of information in the input data sequence to improve the model's ability to handle long-term dependencies and complex relationships in meteorological data; S3-2-2, the temporal convolutional network is composed of a plurality of residual unit stacks, the residual module includes two convolution units and a nonlinear mapping unit, each convolution unit includes a one-dimensional dilated causal convolution, weight normalization, a Relu activation function and a Dropout operation; The causal convolution is expressed as the current time t is only related to the input at time t and before time t; The extended convolution operation for the index of the input data sequence is described as: Where s is the index of the sequence used to represent the current time step or position, d is the dilation factor, k is the filter size, i is a non-negative integer, and sd·i is the localization of some information in the history; S3-2-3, the temporal convolutional network is a multi-layer fully convolutional network, with an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer connected in sequence; The convolution operation extracts useful features by moving the sliding window, i.e., the convolution kernel, on the feature matrix and calculating the weighted sum of the elements in the window and the convolution kernel. Each of the first hidden layer, the second hidden layer, and the third hidden layer gradually abstracts and extracts key information from the input data sequence through causal convolution. As the number of layers increases, the network captures more complex and higher-level features, thereby achieving efficient learning and feature extraction at different levels of the network; During the training and testing of the temporal convolutional network, different network depths and filter sizes are adjusted and set to improve the model accuracy, so as to flexibly adapt to the requirements of temporal feature extraction at different scales; S3-2-4, when constructing the prediction model, it is necessary to predefine the hyperparameters, loss function and optimization algorithm of the meteorological drought spatiotemporal prediction model; the hyperparameters include the number of network layers, convolution kernel size, number of convolution kernels, learning rate, dropout rate, batch size, sequence length and output dimension; wherein, a grid search is performed when the number of network layers and kernel size of the meteorological drought spatiotemporal prediction model are specified; The mean square error (MSE) was selected as the loss function of the training process, and the Adam optimizer was used to perform gradient descent optimization on the random objective function of the model. In the subsequent experiments, the performance and generalization ability of the prediction model were optimized by adjusting parameters according to the experimental results. S3-3, the criteria for determining the meteorological drought spatiotemporal prediction model are: Evaluation index determination coefficient R 2 and root mean square error RMSE; The index determination coefficient R 2 It indicates the linear correlation between the predicted data and the observed data. It is an indicator to measure the model fit. The closer its value is to 1, the better the model fits the data. Its calculation formula is: Among them, y i is the observed value, is the predicted value, N is the number of data points; in, is the average of the actual values; The root mean square error RMSE is used to measure the average model prediction error, which is used to indicate the closeness between the predicted value and the observed value. The lower the index value, the higher the prediction accuracy. The calculation formula is: S4, determine the drought degree of the area to be predicted according to the predicted drought index: The output results of the meteorological drought prediction model are analyzed, and the predicted SPEI values ​​are classified into drought levels according to the drought level classification standard to determine the drought level of the area to be predicted in the next preset time period.

Images