Multi-source satellite precipitation product fusion method and device in combination with sliding quadruple arrangement and random forest spatial interpolation

Abstract

The invention discloses a multi-source satellite precipitation product fusion method and device combining sliding quadruple arrangement and random forest spatial interpolation. The method comprises the following steps: acquiring a multi-source satellite precipitation product, multi-source environment covariant data and actual measurement site daily precipitation data, and unifying temporal-spatial resolution; the method comprises the following steps: acquiring a multi-source precipitation product sequence of each grid point on a drainage basin surface, combining any four sequences to construct a sample combination set, estimating a sequence error variance and an error covariance in each sliding window period based on sliding quadruple arrangement, constructing an error matrix according to the error variance and the error covariance, calculating the weight of each product, and obtaining satellite precipitation data after weighted averaging; constructing a sample set, dividing training and verification samples, and training the random forest spatial interpolation model; and predicting rainfall of the grid points according to the trained model, and integrating the predicted rainfall sequences of the grid points to form a set of rainfall product data. According to the method, the sliding quadruple arrangement analysis technology and the random forest spatial interpolation model are combined, and the fusion precision of satellite precipitation products is improved.

Description

Technical Field

[0001] The invention relates to a multi-source satellite precipitation product fusion method, and belongs to the field of hydrological and meteorological multi-source data fusion and precipitation estimation. Background Art

[0002] Precipitation is the fundamental driving factor of the global water cycle. Obtaining accurate precipitation information in a watershed is crucial for water resources management and hydrological modeling. Ground monitoring data provides the most reliable precipitation data for different applications, and such precipitation data has the highest accuracy. However, the sparse and uneven spatial distribution of rain gauges limits their ability to accurately grasp the spatial heterogeneity of precipitation, which is particularly prominent in remote mountainous areas and underdeveloped areas. In recent decades, satellite precipitation products and reanalysis products (based on physical and dynamic numerical models) with quasi-global scope have emerged one after another. Their higher temporal and spatial resolution and global coverage characteristics have gradually made them a new way to replace traditional precipitation observations and have been widely used in hydrology.

[0003] Satellite precipitation products inevitably contain random and systematic errors, which are mainly caused by measurement conditions, retrieval algorithms and satellite sensors. The performance of precipitation products is affected by background conditions, seasons, latitudes, and meteorological conditions. Direct application of raw products may bring greater uncertainty to precipitation analysis and corresponding hydrological applications. Fusion of multi-source precipitation products and combination with site observation data have become a popular method to improve the quality of satellite products. However, the commonly used precipitation fusion methods based on triple and quadruple permutation techniques do not take into account the time-varying characteristics of the errors of precipitation product set members on the one hand; on the other hand, such methods make a priori estimates of the true value when the measured data is unknown, so they cannot effectively utilize the measured data information. Machine learning algorithms usually establish a nonlinear relationship between the original precipitation product and the measured precipitation based on the inclusion of characteristic covariates, and then predict the true precipitation through the original precipitation product. Such methods cannot screen precipitation products in advance and perform preliminary processing on precipitation products; in addition, the accuracy and quality of the original precipitation products will affect the machine learning fusion effect. For example, precipitation products with very poor quality may cause overfitting problems in machine learning. Summary of the invention

[0004] Purpose of the invention: In view of the shortcomings of the prior art, the present invention proposes a multi-source satellite precipitation product fusion method and device combining sliding quartet permutation and random forest spatial interpolation, which can make full use of the quartet permutation analysis technology to estimate the error time-varying characteristics of the original precipitation product and perform a preliminary weighted average estimate, and then introduce measured information through the random forest spatial interpolation model to further improve the precipitation estimation accuracy.

[0005] Technical solution: A multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation, including the following steps:

[0006] (1) Obtain multi-source satellite precipitation products, multi-source environmental covariate data, and daily precipitation data at measured sites, and resample the multi-source precipitation products and environmental covariate data to the same temporal and spatial resolution;

[0007] (2) Based on a unified spatiotemporal resolution, the time series of multi-source satellite precipitation products at each grid point on the basin surface are obtained, and any four precipitation product sequences are combined to construct a sample combination set. The error variance and error covariance of the four precipitation sequences in each sample combination within each sliding window period are estimated based on the sliding quartet permutation analysis method. The error variance and error covariance of the same precipitation products in different sample combinations are arithmetic averaged to obtain the error variance of the multi-source precipitation products and the error covariance between products. An error matrix is ​​constructed based on the product error variance and the error covariance between products, and the weight coefficient of each product is calculated to obtain the satellite precipitation sequence after weighted average.

[0008] (3) On the grid with measured stations, the measured station precipitation is used as the dependent variable, and the weighted average satellite precipitation series, multi-source environmental covariate series, and the surrounding measured station precipitation series and station distance are used as independent variables. A sample set is constructed, divided into training samples and validation samples, and the random forest spatial interpolation model is trained;

[0009] (4) Based on the trained random forest spatial interpolation model, on the grid without measured stations, the weighted average satellite precipitation sequence of the grid, the precipitation sequence of the measured stations around the grid, the station distance, and the environmental covariate sequence are used as the input of the random forest spatial interpolation model to predict the precipitation sequence of the grid point. The predicted precipitation sequences of each grid point are integrated to finally form a new set of precipitation product data.

[0010] The present invention also provides a multi-source satellite precipitation product fusion device combining sliding quartet permutation and random forest spatial interpolation, comprising:

[0011] The data preprocessing module is used to obtain multi-source satellite precipitation products, multi-source environmental covariate data, and daily precipitation data at measured sites, and resample the multi-source precipitation products and environmental covariate data to the same temporal and spatial resolution;

[0012] The weighted average module of multi-source precipitation products is used to obtain the time series of multi-source satellite precipitation products for each grid point on the watershed surface based on a unified spatiotemporal resolution, combine any four precipitation product sequences to construct a sample combination set, estimate the error variance and error covariance of the four precipitation sequences in each sample combination within each sliding window period based on the sliding quartet permutation analysis method, perform arithmetic averaging on the error variance and error covariance of the same precipitation products in different sample combinations, obtain the error variance of multi-source precipitation products and the error covariance between products, construct an error matrix based on the product error variance and the error covariance between products, calculate the weight coefficient of each product, and then calculate the satellite precipitation sequence after weighted average;

[0013] The random forest spatial interpolation model training module is used to construct a sample set on a grid with measured stations, taking the measured station precipitation as the dependent variable, and the weighted average satellite precipitation sequence, multi-source environmental covariate sequence, and the surrounding measured station precipitation sequence and station distance as independent variables, divide the sample set into training samples and validation samples, and train the random forest spatial interpolation model;

[0014] The precipitation prediction module is used to predict the precipitation sequence of the grid point on the grid without measured sites based on the trained random forest spatial interpolation model, using the weighted average satellite precipitation sequence of the grid, the precipitation sequence of measured sites around the grid, the site distance, and the environmental covariate sequence as the input of the random forest spatial interpolation model, and integrate the predicted precipitation sequences of each grid point to finally form a new set of precipitation product data.

[0015] The present invention also provides a computer device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation as described above are implemented.

[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the multi-source satellite precipitation product fusion method combining sliding quartet permutation with random forest spatial interpolation as described above are implemented.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] The present invention obtains the multi-source precipitation product sequence of each grid point on the watershed surface, constructs a sample combination set, estimates the error variance and error covariance of the precipitation sequence in each sample combination set within the sliding window period based on the sliding quartet permutation analysis technology, constructs an error characteristic matrix and calculates the weight coefficient of each precipitation product based on it, and then calculates the satellite precipitation after weighted averaging, which can grasp the error time-varying characteristics of the original precipitation product, and introduces the measured precipitation information through the random forest spatial interpolation model to achieve more accurate prediction. The present invention overcomes the shortcomings of the current satellite precipitation product fusion field that the measured information cannot be integrated, and the problem that the fusion effect is affected by the quality of the original product when the satellite precipitation product and the measured precipitation are fused by machine learning, which is of great significance for improving the fusion accuracy of satellite precipitation products. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention is a flow chart of a multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0021] like Figure 1 As shown, a multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation includes the following steps:

[0022] Step (1), obtaining multi-source satellite precipitation products, multi-source environmental covariate data and daily precipitation data of measured sites, resampling the multi-source precipitation products and environmental covariate data to the same spatiotemporal resolution;

[0023] In an embodiment of the present invention, the Ili River Basin in Xinjiang is taken as the study area, and data from 2010 to 2020 of six satellite precipitation products including ERA5-Land, SM2RAIN, CHIPRS, CMORPH, IMERG, and PERSIANN-CDR are collected. At the same time, elevation data with a resolution of 90m provided by SRTM data are collected, and the slope, aspect, and Tpi data are calculated using the elevation data. The surface temperature data and NDVI data provided by the MODIS satellite and the 10m wind speed and wind direction data provided by ERA5-Land are collected. The above data have different temporal and spatial resolutions. For problems with different spatial scales, the bilinear interpolation method is used to unify the different spatial resolutions to 0.1 degrees. For problems with different time scales, the next-day scale is summed and calculated, and the 8-day average data provided by MODIS is determined to be equal to the 8-day average for the daily average within 8 days. Finally, the collected multi-source satellite precipitation product data and environmental covariate data are unified into a spatiotemporal scale of 0.1 degrees and a daily scale. There are 22 measuring stations in the study area, and the measured daily precipitation data of these 22 stations from 2011 to 2019 were collected from the hydrological yearbook.

[0024] Step (2), obtaining the multi-source precipitation product sequence of each grid point on the watershed surface, constructing a sample combination set, estimating the error variance and error covariance of the precipitation sequence in each sample combination over time based on the sliding quartet permutation analysis technique, constructing an error characteristic matrix and using it to calculate the product weight matrix, performing weighted averaging according to the product weights, and obtaining the weighted average satellite precipitation data;

[0025] In the embodiment of the present invention, based on the six satellite precipitation products P1, P2, ..., P6 (representing ERA5-Land, SM2RAIN, CHIPRS, CMORPH, IMERG, and PERSIANN-CDR, respectively) after spatiotemporal resampling in step (1), six precipitation time series (P 1,1 , P 1,2 ,…,P 1,t )、(P 2,1 , P 2,2 ,…,P 2,t ),…,(P 6,1 , P 6,2 ,…,P 6,t ). Where t represents the total length of time, P 1,1 represents the precipitation value of the first precipitation product at the first moment, P 1,t It represents the precipitation value of the first precipitation product at the tth moment. For these 6 time series, any 4 of them can be combined to obtain 15 sample combinations. The 4 sequences in each sample combination are recorded as (W1, W2, ..., W t)、(X1,X2,…,X t )、(Y1,Y2,…,Y t )、(Z1,Z2,…,Z t ).

[0026] Assuming that each sliding window period is 101 days, if it is necessary to obtain the weighted average precipitation during the period of t days to t+k days, it is necessary to collect multi-source precipitation products during the period of t-50 days to t+k+50 days. In view of the need to obtain the weighted average precipitation during the period of 20110101-20191231 in the embodiment, the first sliding window period should be 20101112-20110220.

[0027] Taking 20101112-20110220 as the first sliding window period, the four precipitation sequences in each sample combination within the sliding window period are (W1, W2, …, W 101 )、(X1,X2,…,X 101 )、(Y1,Y2,…,Y 101 )、(Z1,Z2,…,Z 101 ), construct a column vector

[0028] Taking the grid point with the central coordinates of (82°E, 47°N) as an example, the W, X, Y, and Z vectors of the sample combination including ERA5-Land, SM2RAIN, CHIRPS, and CMORPH in the window period of 20101112-20110220 are shown in Table 1.

[0029] Table 1 W, X, Y, Z vector results

[0030]

[0031] Calculate the covariance between vectors

[0032] The covariance matrix B and coefficient matrix A are constructed using the covariance calculated above:

[0033]

[0034] According to the least squares solution of the four-fold permutation analysis method, by solving the equation A*U=B, the error characteristic matrix U can be obtained (the error characteristic matrix is ​​used to calculate the error variance of each vector and the error covariance between vectors). The solution method is as follows:

[0035]

[0036] where β W , βX , β Y , β Z Respectively represent the magnitude conversion coefficients of W, X, Y, and Z series relative to the unknown true precipitation series, C pp is the variance of the unknown precipitation true value sequence, C εWεW , C εXεX , C εYεY , C εZεZ Respectively represent the error variance of the W, X, Y, and Z series without magnitude conversion, C εYεZ Represents the error covariance between Y and Z without magnitude reduction.

[0037] Based on the error characteristic matrix U, the error variance of W, X, Y, and Z during the sliding window period can be calculated The error covariance between Y and Z is

[0038] In the example of the present invention, taking the grid point with the central coordinates of (82°E, 47°N) as an example, the calculation results of the error variance and error covariance of the W, X, Y, and Z vectors of the sample combination including ERA5-Land, SM2RAIN, CHIRPS, and CMORPH in the window period of 20101112-20110220 are shown in Table 2.

[0039] Table 2 Calculation results of error variance and error covariance

[0040]

[0041] The error variance and error covariance calculated for the same precipitation product in the 15 sample combinations were averaged (for example, the first sample combination included ERA5-Land, SM2RAIN, CHIRPS, and CMORPH, and the second sample combination included ERA5-Land, SM2RAIN, CHIRPS, and IMERG. Then, by taking the arithmetic average of the error variances of ERA5-Land obtained in the two sample combinations, it was determined that the arithmetic average represented the error variance of the ERA5-Land product). Finally, the error variance of each precipitation product was obtained. and the inter-product error covariance Constructing the error matrix Weight coefficient λ of each product i (i=1~m) is calculated by the following formula: E ij represents the element in the i-th row and j-th column of the error matrix. The weighted average precipitation data on the 51st day (i.e. 20110101) is

[0042] In the example of the present invention, for the grid point with the central coordinates of (82°E, 47°N), the weights of the six precipitation products in the window period of 20101112-20110220 are shown in Table 3.

[0043] Table 3 Weight coefficients of various precipitation products

[0044]

[0045] Then add one day to the initial date of the sliding window period, that is, take 20101113-20110221 as the new window period, repeat the above steps to calculate the error variance of precipitation products within the window period and the error covariance between products, construct the error matrix to calculate the weight coefficient of each product, and the weighted average precipitation data of the 51st day (i.e. 20110102) within the window period is The window period is continuously moved forward until the weighted average precipitation at each time point is obtained, and finally the weighted average precipitation sequence is obtained.

[0046] Step (3), on the grid with measured stations, the measured station precipitation is used as the dependent variable, and the weighted average satellite precipitation data, multi-source environmental covariate data, and the surrounding measured station precipitation and station distance are used as independent variables to construct a sample set, divide it into training samples and validation samples, and use the random forest spatial interpolation model for training;

[0047] The random forest spatial interpolation model is based on the random forest model. It considers the spatial autocorrelation between the observations by considering the n observations near the prediction point and the distances from these observation locations to the prediction location as additional covariates in the random forest. Its input is the estimated precipitation of the precipitation product at the prediction point, environmental covariate data, the observed precipitation near the prediction point, and the distance from the observation point to the prediction point. The output is the actual precipitation at the prediction point. Its expression is as follows:

[0048] z(L p )=f(P(L p ),En(L p ),z(L1),d1,z(L2),d2,...,z(L k ),d k )

[0049] Where: z(L p ) is the predicted point L p The actual precipitation at p ) is the precipitation product at the prediction point L o Estimated precipitation at p ) is the predicted point L pThe environmental covariate sequence at includes longitude, latitude, elevation, slope, aspect, terrain position index, surface temperature, normalized difference vegetation index NDVI, 10m wind speed, 10m wind direction. z(L1), z(L2), …, z(L k ) is the measured precipitation at the k nearest observation locations near the prediction point, d1, d2, …, d k That is, the distance between the k nearest observation positions near the prediction point and the prediction point.

[0050] Further, step (3) comprises:

[0051] Based on the collected measured precipitation data, for each measured site j (j = 1 to n, n is the total number of measured sites), extract the measured precipitation P_obs at each moment of the site j,t , construct the dependent variable vector;

[0052] Extract the weighted average precipitation P_merge corresponding to the grid at the same time in step (2) of the station j,t , environment variables (longitude lon j , latitude lat j , Elevation j , Slope j , Slope Aspect j , Terrain Position Index Tpi j , land surface temperature LST j,t , Normalized Difference Vegetation Index NDVI j,t 、10m wind speed j,t 、10m Wind direction j,t ), and the measured precipitation P_obs_near1 at the k nearest measured points near the grid point at the same time t , P_obs_near2 t , ..., P_obs_neark t , and the corresponding site distances D_obs_near1, D_obs_near2, …, D_obs_neark to construct the independent variable matrix;

[0053] In the example of the present invention, k is set to 10, that is, the influence of precipitation at the 10 closest measured points near the target grid point on the target grid point is considered. The results of the independent variable and dependent variable matrices are shown in Table 4.

[0054] Table 4 Independent variable and dependent variable matrix

[0055]

[0056] Table 4 (Continued) Independent variable and dependent variable matrix

[0057]

[0058]

[0059] Furthermore, the independent variable and dependent variable data samples are divided into training samples and validation samples according to ten-fold cross validation. The model parameters of the random forest spatial interpolation model, including the number of node segmentation variables mtry, the minimum node size min.node.size, and the observation-to-sample ratio sample.fraction in the decision tree, are randomly sampled, and the random forest spatial interpolation model is trained under each parameter combination condition. The optimal parameter combination is selected based on the minimum sum of squared errors of the validation data set to obtain the trained random forest spatial interpolation model.

[0060] In the example of the present invention, the parameter results of the trained random forest spatial interpolation model are shown in Table 5.

[0061] Table 5 Random forest spatial interpolation model parameters

[0062]

[0063] Step (4), based on the constructed random forest spatial interpolation model, on the grid without measured stations, the weighted average satellite precipitation data of the grid, the measured station precipitation around the grid and the station distance, and the environmental covariate data are used as model inputs, and the predicted precipitation of the grid point is output. The predicted precipitation sequences of each grid point are integrated to finally form a new set of precipitation product data;

[0064] Furthermore, the specific steps of step (4) are as follows: for any grid without a measured station, extract the weighted average precipitation P_merge of step (2) on the grid t , environmental variables (longitude lon, latitude lat, elevation Elevation, slope Slope, aspect Aspect, terrain position index Tpi, surface temperature LST t , Normalized Difference Vegetation Index NDVI t 、10m wind speed t 、10m Wind direction t ), and the measured precipitation P_obs_near1 at the k nearest measured points near the grid point at the same time t , P_obs_near2 t , ..., P_obs_neark t, and the corresponding station distances D_obs_near1, D_obs_near2, …, D_obs_neark, construct an independent variable matrix; use this independent variable matrix as the input of the random forest spatial interpolation model trained in step (3), output the predicted precipitation sequence at the grid point, integrate the predicted precipitation sequences P_predict of each grid point, and finally form a new set of precipitation product data.

[0065] In the example of the present invention, the independent variable matrix of the grid without measured stations and the predicted precipitation results output by the random forest spatial interpolation model are shown in Table 6.

[0066] Table 6 Independent variable matrix of grids without measured stations and partial results of predicted precipitation

[0067]

[0068] Table 6 (Continued) Independent variable matrix of grids without actual measurement stations and partial results of predicted precipitation

[0069]

[0070]

[0071] The present invention adopts Pearson correlation coefficient, root mean square error RMSE, detection rate POD, false alarm rate FAR and Heidke skill score HSS, which are common evaluation indicators of precipitation products, to evaluate the fusion effect of a proposed multi-source satellite daily-scale precipitation product fusion method combining a sliding quartet permutation analysis technology with a random forest spatial interpolation model.

[0072] In the examples of the present invention, the calculation results of the evaluation indicators are shown in Table 7. The results are presented in the form of mean value ± standard deviation. The mean value is the arithmetic mean of the precipitation product evaluation indicators at different measured sites, and the standard deviation is the standard deviation of the precipitation product evaluation indicators at different measured sites.

[0073] Table 7 Evaluation indicators of original products and fusion products

[0074]

[0075]

[0076] According to the results in Table 7, it can be seen that after the fusion method proposed in the present invention is used to fuse precipitation products from different sources, the precipitation simulation accuracy is significantly improved: the correlation coefficient is increased to above 0.70, the RMSE is reduced to below 2.5, the POD is increased to above 0.95, the FAR is reduced to below 0.47, and the HSS is increased to above 0.55.

[0077] Based on the same technical concept as the method embodiment, another embodiment of the present invention further provides a multi-source satellite precipitation product fusion device combining sliding quartet permutation and random forest spatial interpolation, comprising:

[0078] The data preprocessing module is used to obtain multi-source satellite precipitation products, multi-source environmental covariate data, and daily precipitation data at measured sites, and resample the multi-source precipitation products and environmental covariate data to the same temporal and spatial resolution;

[0079] The weighted average module of multi-source precipitation products is used to obtain the time series of multi-source satellite precipitation products for each grid point on the watershed surface based on a unified spatiotemporal resolution, combine any four precipitation product sequences to construct a sample combination set, estimate the error variance and error covariance of the four precipitation sequences in each sample combination within each sliding window period based on the sliding quartet permutation analysis method, perform arithmetic averaging on the error variance and error covariance of the same precipitation products in different sample combinations, obtain the error variance of multi-source precipitation products and the error covariance between products, construct an error matrix based on the product error variance and the error covariance between products, calculate the weight coefficient of each product, and then calculate the satellite precipitation sequence after weighted average;

[0080] The random forest spatial interpolation model training module is used to construct a sample set on a grid with measured stations, taking the measured station precipitation as the dependent variable, and the weighted average satellite precipitation sequence, multi-source environmental covariate sequence, and the surrounding measured station precipitation sequence and station distance as independent variables, divide the sample set into training samples and validation samples, and train the random forest spatial interpolation model;

[0081] The precipitation prediction module is used to predict the precipitation sequence of the grid point on the grid without measured sites based on the trained random forest spatial interpolation model, using the weighted average satellite precipitation sequence of the grid, the precipitation sequence of measured sites around the grid, the site distance, and the environmental covariate sequence as the input of the random forest spatial interpolation model, and integrate the predicted precipitation sequences of each grid point to finally form a new set of precipitation product data.

[0082] It should be understood that the multi-source satellite precipitation product fusion device combining sliding quartet permutation and random forest spatial interpolation in the embodiment of the present invention can realize all the technical solutions in the above method embodiment, and the functions of its various functional modules can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can refer to the relevant description in the above embodiment, which will not be repeated here.

[0083] The present invention also provides a computer device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation as described above are implemented.

[0084] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the multi-source satellite precipitation product fusion method combining sliding quartet permutation with random forest spatial interpolation as described above are implemented.

[0085] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices (systems), computer equipment or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0086] The present invention is described with reference to a flowchart of a method according to an embodiment of the present invention. It should be understood that each process in the flowchart and a combination of processes in the flowchart can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A device that specifies functions in a process or multiple processes.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A function specified in a process or multiple processes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 The steps of a specified function in a process or multiple processes.

Claims

1. A multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation, characterized in that: The following steps are involved: (1) Obtain multi-source satellite precipitation products, multi-source environmental covariate data, and daily precipitation data at measured sites, and resample the multi-source precipitation products and environmental covariate data to the same temporal and spatial resolution; (2) Based on a unified spatiotemporal resolution, the time series of multi-source satellite precipitation products at each grid point on the basin surface are obtained, and any four precipitation product sequences are combined to construct a sample combination set. The error variance and error covariance of the four precipitation sequences in each sample combination within each sliding window period are estimated based on the sliding quartet permutation analysis method. The error variance and error covariance of the same precipitation products in different sample combinations are arithmetic averaged to obtain the error variance of the multi-source precipitation products and the error covariance between products. An error matrix is ​​constructed based on the product error variance and the error covariance between products, and the weight coefficient of each product is calculated to obtain the satellite precipitation sequence after weighted average. (3) On the grid with measured stations, the measured station precipitation is used as the dependent variable, and the weighted average satellite precipitation series, multi-source environmental covariate series, and the surrounding measured station precipitation series and station distance are used as independent variables. A sample set is constructed, divided into training samples and validation samples, and the random forest spatial interpolation model is trained; (4) Based on the trained random forest spatial interpolation model, on the grid without measured stations, the weighted average satellite precipitation sequence of the grid, the precipitation sequence of the measured stations around the grid, the station distance, and the environmental covariate sequence are used as the input of the random forest spatial interpolation model to predict the precipitation sequence of the grid point. The predicted precipitation sequences of each grid point are integrated to finally form a new set of precipitation product data.

2. The method according to claim 1, characterized in that In the step (1), the multi-source precipitation products and environmental covariate data are resampled to the same spatiotemporal resolution, including: The bilinear interpolation method is used to unify the data of different spatial resolutions to the same resolution, and the data of the next-day scale are accumulated and summed to unify to the daily scale.

3. The method according to claim 1, characterized in that In step (2), the method for constructing the precipitation sample combination set is as follows: Based on the m satellite precipitation products P1, P2, ..., P after spatiotemporal resampling in step (1), m , at each grid point on the basin surface, we get m precipitation time series (P 1,1 , P 1,2 ,…,P 1,t )、(P 2,1 , P 2,2 ,…,P 2,t ),…,(P m,1 , P m,2 ,…,P m,t ), t is the total length of time, and any four of these m time series can be combined to obtain C m 4 There are four sample combinations, and the four sequences in each sample combination are represented as (W1, W2, ..., W t )、(X1,X2,…,X t )、(Y1,Y2,…,Y t )、(Z1,Z2,…,Z t ).

4. The method according to claim 1, characterized in that: In step (2), the error variance and error covariance of the four precipitation sequences in each sample combination within each sliding window period are estimated based on the sliding four-fold permutation analysis method, and the estimation method is as follows: Assume that the duration of each sliding window is S, and the four precipitation sequences within the sliding window are (W1, W2, …, W S )、(X1,X2,…,X S )、(Y1,Y2,…,Y S )、(Z1,Z2,…,Z S ), construct a column vector Calculate the covariance between vectors The covariance matrix B and the coefficient matrix A are constructed using the covariance calculated above: According to the least squares solution of the four-fold permutation analysis method, the error characteristic matrix U is obtained by solving the equation A*U=B. The solution method is as follows: Where: β W , β X , β Y , β Z Respectively represent the magnitude conversion coefficients of W, X, Y, and Z series relative to the unknown true precipitation series, C pp is the variance of the unknown precipitation true value sequence, C εWεW , C εXεX , C εYεY , C εZεZ Respectively represent the error variance of the W, X, Y, and Z series without magnitude reduction, C εYεZ Represents the error covariance between Y and Z without magnitude reduction; According to the calculated error characteristic matrix U, the error variances of the four sequences W, X, Y, and Z during the sliding window period are calculated as follows: and the error covariance between Y and Z is 5. The method according to claim 1, characterized in that In step (2), the error matrix is ​​expressed as: in represents the error variance of each precipitation product, Represents the error covariance between products, and the weight coefficient λ of each product i Calculated by the following formula: E ij represents the element in the i-th row and j-th column of the error matrix. The weighted average precipitation data of the k-th day is 6. The method according to claim 1, characterized in that In the step (3), the environmental covariate data include longitude, latitude, elevation, slope, aspect, terrain position index, surface temperature, normalized difference vegetation index NDVI, 10m wind speed, and 10m wind direction data.

7. The method according to claim 1, characterized in that In step (3), the random forest spatial interpolation model expression is as follows: z(L p )=f(P(L p ),En(L p ),z(L1),d1,z(L2),d2,…,z(L k ),d k ) Where: z(L p ) is the predicted point L p The actual precipitation at p ) is the precipitation product at the prediction point L o Estimated precipitation at p ) is the predicted point L p The sequence of environmental covariates at , z(L1), z(L2), …, z(L k ) is the measured precipitation at the k nearest observation locations near the prediction point, d1, d2, …, d k is the distance between the predicted point and the k nearest observation positions near the predicted point.

8. A multi-source satellite precipitation product fusion device combining sliding quartet permutation and random forest spatial interpolation, characterized in that: include: The data preprocessing module is used to obtain multi-source satellite precipitation products, multi-source environmental covariate data, and daily precipitation data at measured sites, and resample the multi-source precipitation products and environmental covariate data to the same temporal and spatial resolution; The weighted average module of multi-source precipitation products is used to obtain the time series of multi-source satellite precipitation products for each grid point on the watershed surface based on a unified spatiotemporal resolution, combine any four precipitation product sequences to construct a sample combination set, estimate the error variance and error covariance of the four precipitation sequences in each sample combination within each sliding window period based on the sliding quartet permutation analysis method, perform arithmetic averaging on the error variance and error covariance of the same precipitation products in different sample combinations, obtain the error variance of multi-source precipitation products and the error covariance between products, construct an error matrix based on the product error variance and the error covariance between products, calculate the weight coefficient of each product, and then calculate the satellite precipitation sequence after weighted average; The random forest spatial interpolation model training module is used to construct a sample set on a grid with measured stations, taking the measured station precipitation as the dependent variable, and the weighted average satellite precipitation sequence, multi-source environmental covariate sequence, and the surrounding measured station precipitation sequence and station distance as independent variables, divide the sample set into training samples and validation samples, and train the random forest spatial interpolation model; The precipitation prediction module is used to predict the precipitation sequence of the grid point on the grid without measured sites based on the trained random forest spatial interpolation model, using the weighted average satellite precipitation sequence of the grid, the precipitation sequence of measured sites around the grid, the site distance, and the environmental covariate sequence as the input of the random forest spatial interpolation model, and integrate the predicted precipitation sequences of each grid point to finally form a new set of precipitation product data.

9. A computer device, characterized in that: include: one or more processors; Memory; And one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-source satellite precipitation product fusion method combining sliding quartet permutation and random forest spatial interpolation as described in any one of claims 1 to 7 are implemented.

Images