Agricultural flood disaster risk assessment system and method based on heterogeneous data fusion

Abstract

The present invention discloses an agricultural flood disaster risk assessment system and method based on heterogeneous data fusion, which belongs to the field of data processing. The present invention monitors and obtains crop flood disaster related data and crop growth status related data, constructs a flood disaster risk feature vector generation model, imports the monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector, constructs a flood disaster risk assessment model, imports the flood disaster risk feature vector into the flood disaster risk assessment model to perform risk assessment, constructs a crop damage degree assessment model, imports the flood disaster risk assessment result into the crop damage degree assessment model to assess the crop damage degree, judges the risk of flood disaster occurrence through a deep learning model, and assesses the damage degree to crops, so as to provide more accurate decision support for disaster prevention and control and agricultural production.

Description

Technical Field

[0001] The invention belongs to the field of data processing, and specifically relates to an agricultural flood disaster risk assessment system and method based on heterogeneous data fusion. Background Art

[0002] Due to global climate change and the frequent occurrence of extreme weather events, floods and waterlogging are posing an increasing threat to agricultural production. Floods and waterlogging not only lead to a deterioration of the growing environment for crops and a decrease in yields, but can even lead to large-scale crop failures, causing serious impacts on food security and the rural economy. Therefore, accurate assessment and early warning of the risks of agricultural floods and waterlogging are of great significance for disaster prevention and control and loss reduction.

[0003] At present, traditional flood disaster risk assessment methods mainly rely on a single data source and simple statistical models, which have the following shortcomings: (1) A single data source cannot fully reflect the complex causes of flood disasters and their multidimensional impacts on agriculture; (2) Traditional models cannot fully capture the complex nonlinear relationships in multi-source spatiotemporal data, resulting in low accuracy in risk assessment and early warning; (3) There is a lack of effective integration and processing of real-time data, making it difficult to provide accurate risk warnings in a timely manner.

[0004] The present invention aims to develop a system and method for agricultural flood disaster risk assessment based on heterogeneous data fusion, which analyzes the relevant data affecting flood disasters and crop growth in real time and uses deep learning models to judge the risk of flood disasters and evaluate the degree of damage to crops, thereby realizing dynamic assessment and spatial simulation of agricultural flood disasters, and providing more accurate decision-making support for disaster prevention and control and agricultural production. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes an agricultural flood disaster risk assessment system and method based on heterogeneous data fusion. The present invention monitors and obtains crop flood disaster related data and crop growth status related data, constructs a flood disaster risk feature vector generation model, imports the monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector, constructs a flood disaster risk assessment model, imports the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment, constructs a crop damage degree assessment model, imports the flood disaster risk assessment results into the crop damage degree assessment model to assess the crop damage degree, judges the risk of flood disasters through a deep learning model, and assesses the degree of damage to crops, so as to provide more accurate decision support for disaster prevention and control and agricultural production.

[0006] To achieve the above object, the present invention provides the following technical solutions: A system and method for agricultural flood disaster risk assessment based on heterogeneous data fusion, which includes the following specific steps: Monitor and obtain data related to crop flood disasters and crop growth status; Construct a flood disaster risk feature vector generation model, and import the monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector; Construct a flood disaster risk assessment model, and import the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment; Construct a crop damage assessment model, and import the flood disaster risk assessment results into the crop damage assessment model to assess the extent of crop damage.

[0007] It should be specifically explained here that the monitoring and acquisition of crop flood disaster-related data and crop growth status-related data includes the following specific steps: S11, obtain standardized vegetation index through satellite remote sensing and soil moisture data through sensors; S12. Obtain rainfall, air humidity, crop growth stage and river water level data through monitoring stations; S13. Obtain historical flood disaster data through historical flood disaster records.

[0008] It should be specifically explained here that the construction of the flood disaster risk feature vector generation model and the importation of monitoring data into the flood disaster risk feature vector generation model to generate the flood disaster risk feature vector include the following specific steps: S21, substituting the expected rainfall at the next moment into the rainfall deviation calculation formula to calculate the rainfall deviation at the next moment, wherein the rainfall deviation calculation formula at the moment t+1 is: ,in, is the expected rainfall at time t+1, To exclude the historical average rainfall of extreme weather, The standard deviation of rainfall to exclude extreme weather; S22, substituting the real-time upstream river water level into the calculation formula of the downstream river water level at the next moment to calculate the downstream river water level at the next moment, wherein the calculation formula of the downstream river water level at the moment t+1 is: ,in, and is the empirical coefficient, is the upstream river water level at time t, and the river water level at the next moment is substituted into the river water level deviation calculation formula to calculate the river water level deviation. The river water level deviation calculation formula at time t+1 is: ,in, is the river water level at time t+1, To average river levels excluding extreme weather conditions, The standard deviation of river levels to exclude extreme weather conditions; S23, substituting the air humidity at the next moment into the air humidity deviation calculation formula to calculate the air humidity deviation at the next moment, wherein the air humidity deviation calculation formula at the moment t+1 is: ,in, is the air humidity at time t+1, To exclude the average air humidity during extreme weather conditions, To exclude the standard deviation of air humidity in extreme weather; S24, substituting the soil moisture at the next moment into the normalized soil moisture calculation formula to calculate the normalized soil moisture at the next moment, wherein the normalized soil moisture calculation formula at the moment t+1 is: ,in, is the soil moisture at time t+1, To exclude the mean soil moisture value of extreme weather, In order to exclude the standard deviation of soil moisture in extreme weather, the soil and crop data and normalized soil moisture were substituted into the crop fixed soil index calculation formula to calculate the crop fixed soil index. The crop fixed soil index calculation formula at time t+1 is: , is the shear strength of the soil, is the crop root enhancement coefficient, Z is the crop root density, and T is the crop tensile strength; S25. Substitute the standardized vegetation index, rainfall deviation, river water level deviation, air humidity deviation and crop fixed soil index into the characteristic vector generation formula to generate a flood disaster risk characteristic vector, where the flood disaster risk characteristic vector at time t+1 is: ,in, It is a standardized vegetation index obtained through satellite remote sensing monitoring.

[0009] It should be specifically explained here that the construction of the flood disaster risk assessment model and the importation of the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment include the following specific steps: S31. Construct a flood disaster risk assessment model based on a long short-term memory neural network, construct an initialization network, set the number of input layer nodes to 5, corresponding to the standardized vegetation index, rainfall deviation, river water level deviation, air humidity deviation and crop fixed soil index, set the number of hidden layer nodes to 10, used to capture the time dependency of features, set the number of output layer nodes to 1, corresponding to the flood disaster risk assessment value, and at the same time, initialize the weights and biases for the connections from the input layer to the hidden layer and from the hidden layer to the output layer. The weights and biases are parameters to be optimized in the network; S32, bringing the input flood disaster risk feature vector into the hidden layer output calculation formula hidden layer output; S321, the calculation formula of the forget gate in the hidden layer is: ,in, is the logistic activation function, is the forget gate weight matrix, is the bias term of the forget gate, is the hidden state at time t, is the input feature vector at time t+1; S322, the calculation formula of the input gate in the hidden layer is: , ,in, is the logistic activation function, is the output of the input gate, is the candidate memory cell state, is the input gate weight matrix, is the memory unit weight matrix, and is bias; S323, the calculation formula for updating the unit state in the hidden layer is: ,in, is the cell state at time t+1, is the unit state at time t; S324, the calculation formula of the output gate in the hidden layer is: , ,in, is the logistic activation function, is the output of the output gate, is the hidden state output, is the bias, is the output gate weight matrix; S33, substituting the output data of the hidden layer into the calculation formula of the output layer to calculate the flood disaster risk assessment value at the current moment, wherein the calculation formula of the output layer is: ,in, is the logistic activation function; S34. The gradient of the loss function for each weight and bias in the network is calculated through the back-propagation algorithm. The gradient is the partial derivative of the loss function with respect to each weight and bias, and then the Adam optimization algorithm is used to update the weights and biases.

[0010] It should be specifically explained that the construction of the crop damage assessment model and the introduction of the flood disaster risk assessment results into the crop damage assessment model to assess the crop damage include the following specific steps: S41, importing historical flood disaster data into the risk assessment model to generate a risk threshold, and substituting the current flood disaster risk assessment value into the risk level assessment formula, wherein the risk level assessment formula is: ,in, is the risk threshold, is the risk assessment value at time t+1, is the sensitivity parameter, obtained by fitting historical data; S42. Substituting the flood disaster risk assessment value into the crop damage degree formula to calculate the crop damage degree assessment value, wherein the crop damage degree calculation formula is: ,in, is the crop growth stage factor, i.e., the disaster resistance weight of crops in different growth cycles; S43. Substituting the assessed value of the degree of damage to crops into a calculation formula for the yield after damage to crops to calculate the yield after damage to crops, wherein the calculation formula for the yield after damage to crops is: ,in, is the expected yield of crops under non-disaster conditions, It is the predicted value of the degree of damage to crops; S44. Divide the crop planting area The high-resolution grid is used to calculate the risk assessment level, crop damage degree and post-damage yield of each grid, and generate flood risk value distribution map, crop damage degree distribution map and crop yield distribution map after damage.

[0011] A system for assessing agricultural flood disaster risk based on heterogeneous data fusion is implemented based on the above-mentioned method for assessing agricultural flood disaster risk based on heterogeneous data fusion, and specifically includes: A data acquisition module is used to acquire data related to crop flood disasters and crop growth status; A flood disaster risk feature vector generation module, used to generate a flood disaster risk feature vector; Flood disaster risk assessment module, used to assess flood disaster risks; The crop damage assessment module is used to assess the extent of crop damage.

[0012] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned agricultural flood disaster risk assessment method based on heterogeneous data fusion by calling the computer program stored in the memory.

[0013] A computer-readable storage medium, characterized in that it stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned agricultural flood disaster risk assessment method based on heterogeneous data fusion.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention monitors and obtains crop flood disaster-related data and crop growth status-related data, constructs a flood disaster risk feature vector generation model, imports the monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector, constructs a flood disaster risk assessment model, imports the flood disaster risk feature vector into the flood disaster risk assessment model to perform risk assessment, constructs a crop damage degree assessment model, imports the flood disaster risk assessment result into the crop damage degree assessment model to assess the crop damage degree, determines the risk of flood disaster occurrence through a deep learning model, and assesses the degree of damage to crops, thereby providing more accurate decision support for disaster prevention and control and agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the overall process of the agricultural flood disaster risk assessment method based on heterogeneous data fusion of the present invention; Figure 2 This is a flow chart of constructing a flood disaster risk assessment model based on a long short-term memory neural network in the present invention; Figure 3 It is a schematic diagram of the overall framework of the agricultural flood disaster risk assessment system based on heterogeneous data fusion of the present invention. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0017] Example 1 See also Figure 1-Figure 2 The present invention provides an embodiment: an agricultural flood disaster risk assessment method based on heterogeneous data fusion, which includes the following specific steps: Monitor and obtain data related to crop flood disasters and crop growth status; Construct a flood disaster risk feature vector generation model, and import the monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector; Construct a flood disaster risk assessment model, and import the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment; Construct a crop damage assessment model, and import the flood disaster risk assessment results into the crop damage assessment model to assess the extent of crop damage.

[0018] In this embodiment, it should be specifically explained that monitoring and obtaining crop flood disaster-related data and crop growth status-related data includes the following specific steps: S11, obtain standardized vegetation index through satellite remote sensing and soil moisture data through sensors; S12. Obtain rainfall, air humidity, crop growth stage and river water level data through monitoring stations; S13. Obtain historical flood disaster data through historical flood disaster records.

[0019] In this embodiment, it should be specifically explained that constructing a flood disaster risk feature vector generation model and importing monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector includes the following specific steps: S21, substituting the expected rainfall at the next moment into the rainfall deviation calculation formula to calculate the rainfall deviation at the next moment, wherein the rainfall deviation calculation formula at the moment t+1 is: ,in, is the expected rainfall at time t+1, To exclude the historical average rainfall of extreme weather, The standard deviation of rainfall to exclude extreme weather; S22, substituting the real-time upstream river water level into the calculation formula of the downstream river water level at the next moment to calculate the downstream river water level at the next moment, wherein the calculation formula of the downstream river water level at the moment t+1 is: ,in, and is the empirical coefficient, is the upstream river water level at time t, and the river water level at the next moment is substituted into the river water level deviation calculation formula to calculate the river water level deviation. The river water level deviation calculation formula at time t+1 is: ,in, is the river water level at time t+1, To average river levels excluding extreme weather conditions, The standard deviation of river levels to exclude extreme weather conditions; S23, substituting the air humidity at the next moment into the air humidity deviation calculation formula to calculate the air humidity deviation at the next moment, wherein the air humidity deviation calculation formula at the moment t+1 is: ,in, is the air humidity at time t+1, To exclude the average air humidity during extreme weather conditions, To exclude the standard deviation of air humidity in extreme weather; S24, substituting the soil moisture at the next moment into the normalized soil moisture calculation formula to calculate the normalized soil moisture at the next moment, wherein the normalized soil moisture calculation formula at the moment t+1 is: ,in, is the soil moisture at time t+1, To exclude the mean soil moisture value of extreme weather, In order to exclude the standard deviation of soil moisture in extreme weather, the soil and crop data and normalized soil moisture were substituted into the crop fixed soil index calculation formula to calculate the crop fixed soil index. The crop fixed soil index calculation formula at time t+1 is: , is the shear strength of the soil, is the crop root enhancement coefficient, that is, the efficiency coefficient of enhancing the soil shear strength, Z is the crop root density, obtained by the root scanner, and T is the crop tensile strength, where the soil shear strength is obtained according to the literature, and the crop root enhancement coefficient and crop tensile strength are obtained according to the crop root experiment; S25. Substitute the standardized vegetation index, rainfall deviation, river water level deviation, air humidity deviation and crop fixed soil index into the characteristic vector generation formula to generate a flood disaster risk characteristic vector, where the flood disaster risk characteristic vector at time t+1 is: ,in, It is a standardized vegetation index obtained through satellite remote sensing monitoring.

[0020] In this embodiment, it should be specifically explained that constructing a flood disaster risk assessment model and importing the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment includes the following specific steps: S31. Construct a flood disaster risk assessment model based on a long short-term memory neural network, construct an initialization network, set the number of input layer nodes to 5, corresponding to the standardized vegetation index, rainfall deviation, river water level deviation, air humidity deviation and crop fixed soil index, set the number of hidden layer nodes to 10, used to capture the time dependency of features, set the number of output layer nodes to 1, corresponding to the flood disaster risk assessment value, and at the same time, initialize the weights and biases for the connections from the input layer to the hidden layer and from the hidden layer to the output layer. The weights and biases are parameters to be optimized in the network; S32, bringing the input flood disaster risk feature vector into the hidden layer output calculation formula hidden layer output; S321, the calculation formula of the forget gate in the hidden layer is: ,in, is the logistic activation function, is the forget gate weight matrix, is the bias term of the forget gate, is the hidden state at time t, is the input feature vector at time t+1; S322, the calculation formula of the input gate in the hidden layer is: , ,in, is the logistic activation function, is the output of the input gate, is the candidate memory cell state, is the input gate weight matrix, is the memory unit weight matrix, and is bias; S323, the calculation formula for updating the unit state in the hidden layer is: ,in, is the cell state at time t+1, is the unit state at time t; S324, the calculation formula of the output gate in the hidden layer is: , ,in, is the logistic activation function, is the output of the output gate, is the hidden state output, is the bias, is the output gate weight matrix; S33, substituting the output data of the hidden layer into the calculation formula of the output layer to calculate the flood disaster risk assessment value at the current moment, wherein the calculation formula of the output layer is: ,in, is the logistic activation function; S34. The gradient of the loss function for each weight and bias in the network is calculated through the back-propagation algorithm. The gradient is the partial derivative of the loss function with respect to each weight and bias, and then the Adam optimization algorithm is used to update the weights and biases.

[0021] In this embodiment, it should be specifically explained that constructing a crop damage degree assessment model and importing the flood disaster risk assessment results into the crop damage degree assessment model to assess the crop damage degree includes the following specific steps: S41, importing historical flood disaster data into the risk assessment model to generate a risk threshold, and substituting the current flood disaster risk assessment value into the risk level assessment formula, wherein the risk level assessment formula is: ,in, is the risk threshold, is the risk assessment value at time t+1, is the sensitivity parameter, obtained by fitting historical data; S42. Substituting the flood disaster risk assessment value into the crop damage degree formula to calculate the crop damage degree assessment value, wherein the crop damage degree calculation formula is: ,in, is the crop growth stage factor, that is, the disaster resistance weight of crops in different growth cycles, which is obtained by fitting the historical data of crop growth; S43. Substituting the assessed value of the degree of damage to crops into a calculation formula for the yield after damage to crops to calculate the yield after damage to crops, wherein the calculation formula for the yield after damage to crops is: ,in, is the expected yield of crops under non-disaster conditions, It is the predicted value of the degree of damage to crops; S44. Divide the crop planting area The high-resolution grid is used to calculate the risk assessment level, crop damage degree and post-damage yield of each grid, and generate flood risk value distribution map, crop damage degree distribution map and crop yield distribution map after damage.

[0022] It should be noted here that the empirical coefficient for calculating the downstream river water level is and The value of is obtained as follows: obtain 500 sets of upstream and downstream river water level data, substitute the upstream and downstream river water level data into the downstream water level calculation formula, fit the formula by the least squares method, minimize the sum of squares of the error between the predicted value and the actual value, and output the empirical coefficient and ; It should be noted here that the risk threshold in the risk level assessment formula and sensitivity parameters The value of is obtained as follows: obtain the historical flood disaster data of the target area, substitute the historical data into the flood disaster risk assessment model to calculate the flood disaster risk assessment value, obtain the threshold and level judgment of these flood disaster risk assessment values ​​by experts, and set the risk threshold and sensitivity parameters.

[0023] Example 2 like Figure 3 As shown, the agricultural flood disaster risk assessment system based on heterogeneous data fusion is implemented based on the above-mentioned agricultural flood disaster risk assessment method based on heterogeneous data fusion, and specifically includes a data acquisition module, a flood disaster risk feature vector generation module, a flood disaster risk assessment module and a crop damage degree assessment module. The data acquisition module is used to obtain crop flood disaster related data and crop growth status related data, the flood disaster risk feature vector generation module is used to generate flood disaster risk feature vectors, the flood disaster risk assessment module is used to assess flood disaster risks, and the crop damage degree assessment module is used to assess the degree of crop damage.

[0024] Example 3 This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned agricultural flood disaster risk assessment method based on heterogeneous data fusion by calling the computer program stored in the memory.

[0025] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a multimedia image quality evaluation method based on scene recognition provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface for data input and output. This embodiment will not be described in detail here.

[0026] Example 4 This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon; When the computer program runs on a computer device, the computer device executes the above-mentioned agricultural flood disaster risk assessment method based on heterogeneous data fusion.

[0027] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0028] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0029] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0030] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by 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 invention 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. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0031] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0032] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0033] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one way of division, and there may be other ways of division in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0034] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0035] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0036] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0037] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Agricultural flood disaster risk assessment method based on heterogeneous data fusion, characterized by: It includes the following specific steps: Monitor and obtain data related to crop flood disasters and crop growth status; Construct a flood disaster risk feature vector generation model, and import the monitoring data into the flood disaster risk feature vector generation model to generate a flood disaster risk feature vector; Construct a flood disaster risk assessment model, and import the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment; Construct a crop damage assessment model, and import the flood disaster risk assessment results into the crop damage assessment model to assess the extent of crop damage.

2. The agricultural flood disaster risk assessment method based on heterogeneous data fusion according to claim 1 is characterized in that: The monitoring and acquisition of crop flood disaster related data and crop growth status related data includes the following specific steps: S11, obtain standardized vegetation index through satellite remote sensing and soil moisture data through sensors; S12. Obtain rainfall, air humidity, crop growth stage and river water level data through monitoring stations; S13. Obtain historical flood disaster data through historical flood disaster records.

3. The agricultural flood disaster risk assessment method based on heterogeneous data fusion as claimed in claim 2 is characterized in that: The construction of the flood disaster risk feature vector generation model and the importation of monitoring data into the flood disaster risk feature vector generation model to generate the flood disaster risk feature vector include the following specific steps: S21, substituting the expected rainfall at the next moment into the rainfall deviation calculation formula to calculate the rainfall deviation at the next moment, wherein the rainfall deviation calculation formula at the moment t+1 is: ,in, is the expected rainfall at time t+1, To exclude the historical average rainfall of extreme weather, The standard deviation of rainfall to exclude extreme weather; S22, substituting the real-time upstream river water level into the calculation formula of the downstream river water level at the next moment to calculate the downstream river water level at the next moment, wherein the calculation formula of the downstream river water level at the moment t+1 is: ,in, and is the empirical coefficient, is the upstream river water level at time t, and the river water level at the next moment is substituted into the river water level deviation calculation formula to calculate the river water level deviation. The river water level deviation calculation formula at time t+1 is: ,in, is the river water level at time t+1, To average river levels excluding extreme weather conditions, The standard deviation of river levels to exclude extreme weather conditions; S23, substituting the air humidity at the next moment into the air humidity deviation calculation formula to calculate the air humidity deviation at the next moment, wherein the air humidity deviation calculation formula at the moment t+1 is: ,in, is the air humidity at time t+1, To exclude the average air humidity during extreme weather conditions, To exclude the standard deviation of air humidity in extreme weather; S24, substituting the soil moisture at the next moment into the normalized soil moisture calculation formula to calculate the normalized soil moisture at the next moment, wherein the normalized soil moisture calculation formula at the moment t+1 is: ,in, is the soil moisture at time t+1, To exclude the mean soil moisture value of extreme weather, In order to exclude the standard deviation of soil moisture in extreme weather, the soil and crop data and normalized soil moisture were substituted into the crop fixed soil index calculation formula to calculate the crop fixed soil index. The crop fixed soil index calculation formula at time t+1 is: , is the shear strength of the soil, is the crop root enhancement coefficient, Z is the crop root density, and T is the crop tensile strength; S25. Substitute the standardized vegetation index, rainfall deviation, river water level deviation, air humidity deviation and crop fixed soil index into the characteristic vector generation formula to generate a flood disaster risk characteristic vector, where the flood disaster risk characteristic vector at time t+1 is: ,in, is the Standardized Vegetation Index.

4. The agricultural flood disaster risk assessment method based on heterogeneous data fusion as claimed in claim 3 is characterized in that: The construction of the flood disaster risk assessment model and the introduction of the flood disaster risk feature vector into the flood disaster risk assessment model for risk assessment include the following specific steps: S31. Construct a flood disaster risk assessment model based on a long short-term memory neural network, construct an initialization network, set the number of input layer nodes to 5, corresponding to the standardized vegetation index, rainfall deviation, river water level deviation, air humidity deviation and crop fixed soil index, set the number of hidden layer nodes to 10, set the number of output layer nodes to 1, corresponding to the flood disaster risk assessment value, and at the same time, initialize the weights and biases for the connections from the input layer to the hidden layer and from the hidden layer to the output layer. The weights and biases are the parameters to be optimized in the network; S32, bringing the input flood disaster risk feature vector into the hidden layer output calculation formula hidden layer output; S321, the calculation formula of the forget gate in the hidden layer is: ,in, is the logistic activation function, is the forget gate weight matrix, is the bias term of the forget gate, is the hidden state at time t, is the input feature vector at time t+1; S322, the calculation formula of the input gate in the hidden layer is: , ,in, is the logistic activation function, is the output of the input gate, is the candidate memory cell state, is the input gate weight matrix, is the memory unit weight matrix, and is bias; S323, the calculation formula for updating the unit state in the hidden layer is: ,in, is the cell state at time t+1, is the unit state at time t; S324, the calculation formula of the output gate in the hidden layer is: , ,in, is the logistic activation function, is the output of the output gate, is the hidden state output, is the bias, is the output gate weight matrix; S33, substituting the hidden layer output data into the calculation formula of the output layer to calculate the flood disaster risk assessment value at the current moment, wherein the calculation formula of the output layer is: ,in, is the logistic activation function; S34. The gradient of the loss function for each weight and bias in the network is calculated through the back-propagation algorithm. The gradient is the partial derivative of the loss function with respect to each weight and bias, and then the Adam optimization algorithm is used to update the weights and biases.

5. The agricultural flood disaster risk assessment method based on heterogeneous data fusion according to claim 4 is characterized in that: The construction of the crop damage assessment model and the introduction of the flood disaster risk assessment results into the crop damage assessment model to assess the crop damage degree include the following specific steps: S41, importing historical flood disaster data into the risk assessment model to generate a risk threshold, and substituting the current flood disaster risk assessment value into the risk level assessment formula, wherein the risk level assessment formula is: ,in, is the risk threshold, is the risk assessment value at time t+1, is the sensitivity parameter; S42. Substituting the flood disaster risk assessment value into the crop damage degree formula to calculate the crop damage degree assessment value, wherein the crop damage degree calculation formula is: ,in, It is the factor of crop growth stage; S43. Substituting the assessed value of the degree of damage to crops into a calculation formula for the yield after damage to crops to calculate the yield after damage to crops, wherein the calculation formula for the yield after damage to crops is: ,in, is the expected yield of crops under non-disaster conditions, It is the predicted value of the degree of damage to crops; S44. Divide the crop planting area The high-resolution grid is used to calculate the risk assessment level, crop damage degree and yield after damage for each grid, and generate flood risk value distribution map, crop damage degree distribution map and crop yield distribution map after damage.

6. An agricultural flood disaster risk assessment system based on heterogeneous data fusion, which is implemented based on the agricultural flood disaster risk assessment method based on heterogeneous data fusion as claimed in any one of claims 1 to 5, and is characterized in that: Specifically include: A data acquisition module is used to acquire data related to crop flood disasters and crop growth status; A flood disaster risk feature vector generation module, used to generate a flood disaster risk feature vector; Flood disaster risk assessment module, used to assess flood disaster risks; The crop damage assessment module is used to assess the extent of crop damage.

7. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the agricultural flood disaster risk assessment method based on heterogeneous data fusion as described in any one of claims 1 to 5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the agricultural flood disaster risk assessment method based on heterogeneous data fusion as described in any one of claims 1 to 5.

Images