Target crop composite high-temperature drought disaster loss detection method and system

Abstract

The invention relates to the technical field of disaster loss detection, in particular to a target crop composite high-temperature drought disaster loss detection method and system. The method comprises the following steps: training machine learning based on target crop per unit yield data and geographic coordinate data of a plurality of grids of a research area and target crop growth factor data of a plurality of dates of the grids to obtain a crop per unit yield prediction model; target crop growth factor data corresponding to the ideal weather scene and the composite high-temperature drought scene are constructed to drive a crop per unit yield prediction model respectively, and target crop per unit yield prediction data corresponding to the ideal weather scene and the composite high-temperature drought scene are obtained; and performing difference processing on the obtained target crop per unit yield prediction data corresponding to the ideal weather scene and the composite high-temperature drought scene to obtain a composite high-temperature drought disaster loss value of the target crop, reflecting the per unit yield loss of the target crop under the composite high-temperature drought stress, and providing a scientific basis for guaranteeing the national food safety.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster loss detection, and particularly to a method, a system, a computer device and a storage medium for detecting the loss of target crops caused by combined high-temperature and drought disasters. Background Art

[0002] Temperature and rainfall are the two most critical meteorological elements affecting the growth of target crops. With the intensification of the global warming trend, meteorological disaster events formed by the combination of temperature and rainfall have become more serious and frequent. Among them, the combined high-temperature and drought disaster is the most prominent, becoming one of the greatest risks threatening the production safety of future target crops (maize, rice and wheat).

[0003] However, the current academic research on combined meteorological disasters is in its infancy. Most research still focuses on evaluating the intensity and frequency of combined meteorological disasters, and there are few studies on quantitatively evaluating the losses of target crops caused by combined meteorological disasters, thus restricting people from taking corresponding agricultural disaster reduction and prevention measures to face the increasingly serious combined high-temperature and drought disasters. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a method, a system, a computer device and a storage medium for detecting the loss of target crops caused by combined high-temperature and drought disasters, construct the data of target crop growth factors corresponding to the ideal weather scenario and the combined high-temperature and drought scenario, combine the pre-trained machine learning model to predict the target crop yield per unit area corresponding to the ideal weather scenario and the combined high-temperature and drought scenario, perform difference processing on the obtained target crop yield per unit area prediction data corresponding to the ideal weather scenario and the combined high-temperature and drought scenario, obtain the loss value of target crops caused by combined high-temperature and drought disasters, reflect the numerical value of the yield loss of target crops under the stress of combined high-temperature and drought, and provide a scientific basis for ensuring national food security.

[0005] In the first aspect, an embodiment of the present application provides a method for detecting the loss of target crops caused by combined high-temperature and drought disasters, including the following steps: Obtain the target crop yield per unit area data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids; Input the target crop yield per unit area data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids into the crop yield per unit area prediction model to be trained for training, and obtain the target crop yield per unit area prediction model; Obtain the geographical coordinate data of several grids in the target area, the ideal target crop growth factor data of several dates corresponding to the ideal weather scenario of the grids, and the stress target crop growth factor data of several dates corresponding to the combined high-temperature and drought scenario of the grids; Input the geographical coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data corresponding to several grids in the target area under the ideal weather scenario; input the geographical coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data corresponding to several grids in the target area under the compound high temperature and drought scenario; Obtain the detection result of the target crop compound high temperature and drought disaster loss in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data.

[0006] In a second aspect, an embodiment of the present application provides a target crop compound high temperature and drought disaster loss detection system, including: A data acquisition module, configured to acquire the target crop yield data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids; A model training module, configured to input the target crop yield data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids into a crop yield prediction model to be trained for training, and obtain a target crop yield prediction model; A scenario construction module, configured to obtain the geographical coordinate data of several grids in the target area, the ideal target crop growth factor data of several dates corresponding to the grids under the ideal weather scenario, and the stress target crop growth factor data of several dates corresponding to the grids under the compound high temperature and drought scenario; A target crop yield prediction module, configured to input the geographical coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data corresponding to several grids in the target area under the ideal weather scenario; input the geographical coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data corresponding to several grids in the target area under the compound high temperature and drought scenario; A target crop loss calculation module, configured to obtain the detection result of the target crop compound high temperature and drought disaster loss in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data.

[0007] In a third aspect, an embodiment of the present application provides a computer device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor; when the computer program is executed by the processor, the steps of the target crop compound high-temperature and drought disaster loss detection method described in the first aspect are implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the target crop compound high-temperature and drought disaster loss detection method described in the first aspect are implemented.

[0009] In an embodiment of the present application, a target crop compound high-temperature and drought disaster loss detection method, system, computer device, and storage medium are provided. The growth factor data of the target crop corresponding to the ideal weather scenario and the compound high-temperature and drought scenario are constructed, and the single yield prediction of the target crop corresponding to the ideal weather scenario and the compound high-temperature and drought scenario is combined with a pre-trained machine learning model. The difference processing is performed on the obtained single yield prediction data of the target crop corresponding to the ideal weather scenario and the compound high-temperature and drought scenario to obtain the target crop compound high-temperature and drought disaster loss value, which reflects the single yield loss value of the target crop under the compound high-temperature and drought stress, providing a scientific basis for ensuring national food security.

[0010] For better understanding and implementation, the present invention will be described in detail below with reference to the accompanying drawings. Description of the Drawings

[0011] Figure 1 It is a schematic flowchart of the target crop compound high-temperature and drought disaster loss detection method provided by an embodiment of the present application; Figure 2 It is a schematic flowchart of S1 in the target crop compound high-temperature and drought disaster loss detection method provided by an embodiment of the present application; Figure 3 It is a schematic flowchart of S3 in the target crop compound high-temperature and drought disaster loss detection method provided by an embodiment of the present application; Figure 4 It is a schematic flowchart of S31 in the target crop compound high-temperature and drought disaster loss detection method provided by an embodiment of the present application; Figure 5 It is a schematic flowchart of S3 in the target crop compound high-temperature and drought disaster loss detection method provided by another embodiment of the present application; Figure 6 It is a schematic flowchart of S5 in the target crop compound high-temperature and drought disaster loss detection method provided by an embodiment of the present application; Figure 7 It is a schematic structural diagram of the target crop compound high-temperature and drought disaster loss detection system provided by an embodiment of the present application; Figure 8 A structural schematic diagram of a computer device provided by an embodiment of the present application. Specific embodiments

[0012] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0013] The terms used in the present application are for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0014] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0015] The data sending end can be a computer device or a mobile terminal device, used to establish a network connection with the data receiving end, capable of encoding the data information sent to the data receiving end, and parsing the data information sent from the data receiving end.

[0016] The data receiving end can be a computer device or a mobile terminal device, used to establish a network connection with the data sending end, capable of encoding the data information sent to the data sending end, and parsing the data information sent from the data sending end.

[0017] Please refer to Figure 1 , Figure 1 A flowchart of a method for detecting the loss of compound high-temperature and drought disasters of target crops provided by an embodiment of the present application. The method includes the following steps: S1: Obtain the target crop yield data, geographic coordinate data of several grids in the study area, and the target crop growth factor data of several dates of these grids.

[0018] The execution entity of the target crop compound high-temperature and drought disaster loss detection method is the detection device of the target crop compound high-temperature and drought disaster loss detection method (hereinafter referred to as the detection device). In an optional embodiment, the detection device can be a computer device, which can be a server, or a server cluster composed of multiple computer devices.

[0019] In this embodiment, the detection device obtains the target crop yield data, geographic coordinate data of several grids in the study area, and the target crop growth factor data of several dates of these grids. Among them, the date is the date during the crop growth season of the target crop, and the crop growth season refers to the time period from the sowing (or transplanting) date to the maturity date of the target crop. The target crop growth factor data includes weather element data and soil property data. The weather element data includes daily average temperature, daily precipitation, daily solar radiation, daily wind speed, and daily relative humidity; the geographic coordinate data includes longitude coordinates and latitude coordinates.

[0020] Since there may be significant differences in the climate conditions and planting methods of different target crops in different regions, in order to ensure the credibility of the machine learning model, specifically, the detection device will use the municipal unit of the target crop as the regional scale for training and testing the machine learning model, and the 1km grid of the target crop within the municipal unit as the grid scale of the training and testing data.

[0021] The soil property data is the soil property data of a 1km grid provided by the Harmonized World Soil Database (HWSD); The weather element data is composed of the daily average temperature, daily precipitation, and daily solar radiation of a 1km grid scale provided by the global meteorological dataset CHELSA-W5E5, and the daily wind speed and daily relative humidity after downscaling the 0.25° ERA5 global climate data to 1km. The weather element data changes with the date and different weather scenarios.

[0022] The geographic coordinate data comes from the centroid position (including longitude and latitude) of the 1km grid of the target crop in the crop growth season data. The crop growth season data comes from the key phenological dates of the target crop at the 1km grid scale provided by the published three major target crop phenological datasets (ChinaCropPhen1km), including the sowing date (or transplanting date), heading date, and maturity date.

[0023] For the target crop yield data, please refer to Figure 2 , Figure 2Schematic flowchart of S1 in the method for detecting the loss of composite high-temperature and drought disasters of target crops provided by an embodiment of the present application, including steps S11 to S12, which are specifically as follows: S11: Obtain the regional-scale yield data of the target crop in the study area, the sum of the vegetation leaf area indices of each grid in the study area, and the average value of the sum of the vegetation leaf area indices of several grids.

[0024] The leaf area index (LAI) of vegetation characterizes the growth status of vegetation, and the larger its value, the more lush the vegetation growth.

[0025] In this embodiment, the detection device obtains the regional-scale yield data of the target crop in the study area, the sum of the vegetation leaf area indices of each grid in the study area, and the average value of the sum of the vegetation leaf area indices of several grids. Specifically, the regional-scale yield data is obtained based on the municipal target crop yield numerical data from 1981 to 2015 provided by national and provincial statistical yearbooks, and the sum of the vegetation leaf area indices of the grids is obtained by adding the daily values of the vegetation leaf area index in the remote sensing data MODIS GLASS during the growth season of the target crop.

[0026] S12: According to the regional-scale yield data of the target crop in the study area, the sum of the vegetation leaf area indices of each grid in the study area, the average value of the sum of the vegetation leaf area indices of several grids, and a preset target crop grid-scale yield calculation algorithm, obtain the target crop yield data of several grids in the study area.

[0027] The target crop grid-scale yield calculation algorithm is:

[0028] In the formula, is the target crop yield data at the grid scale, is the regional-scale yield data of the target crop in the study area. is the sum of the vegetation leaf area indices of a single grid, is the average value of the sum of the vegetation leaf area indices of several grids, and the is the sum of several grids of divided by the number of grids.

[0029] In this embodiment, the detection device obtains the target crop yield data of several grids in the study area according to the regional-scale yield data of the target crop in the study area, the sum of the vegetation leaf area indices of each grid in the study area, the average value of the sum of the vegetation leaf area indices of several grids, and a preset target crop grid-scale yield calculation algorithm.

[0030] S2: Input the target crop yield data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids into the crop yield prediction model to be trained for training, and obtain the target crop yield prediction model.

[0031] In this embodiment, the detection device inputs the target crop yield data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids into the crop yield prediction model to be trained for training, and obtains the target crop yield prediction model. Among them, the crop yield prediction model is a model constructed by training a machine learning model with the weather element data, geographical coordinate data, and soil property data as independent variables and the target crop yield data as the dependent variable.

[0032] The average daily temperature and daily precipitation are the two most important factors affecting the growth of the target crop. In addition, the daily solar radiation, daily wind speed, and daily relative humidity are also meteorological elements affecting the growth of the target crop, and the soil properties and geographical locations at the time of planting each target crop will also affect the growth of the target crop. Specifically, the detection device further divides the target crop yield data, geographical coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids into a training set and a test set according to a ratio of 7:3 for machine learning model training and testing. The machine learning model used is XGBoost, which has a better fitting loss function compared to the traditional gradient boosting decision tree algorithm, can reduce the possible errors, and optimizes the simulation performance of machine learning.

[0033] S3: Obtain the geographical coordinate data of several grids in the target area, the ideal target crop growth factor data of several dates corresponding to the ideal weather scenario of the grids, and the stress target crop growth factor data of several dates corresponding to the compound high-temperature and drought scenario of the grids.

[0034] The ideal weather scenario is used to indicate that the target crop in the grid has not suffered from high-temperature heat damage or experienced a meteorological drought event during the crop growth season, and the compound high-temperature and drought scenario is used to indicate that the target crop in the grid has suffered from a disaster event in which high-temperature heat damage and meteorological drought occur simultaneously on one or more dates during the crop growth season.

[0035] In this embodiment, the detection device obtains the geographical coordinate data of several grids in the target area, the ideal target crop growth factor data of several dates corresponding to the ideal weather scenario for the grids, and the stress target crop growth factor data of several dates corresponding to the composite high-temperature and drought scenario for the grids. Among them, the ideal target crop growth factor data is used to indicate the growth factor data of the target crop on the dates corresponding to the ideal weather scenario. The stress target crop growth factor data is used to indicate the growth factor data of the target crop on the dates corresponding to the composite high-temperature and drought scenario.

[0036] For the ideal target crop growth factor data, please refer to Figure 3 , Figure 3 which is a schematic flowchart of S3 in the method for detecting the loss of composite high-temperature and drought disasters of target crops provided by an embodiment of the present application, including steps S31 to S32, as follows: S31: Obtain the target crop growth factor data of several dates of several grids in the target area, the relative threshold of high-temperature heat damage, and the relative threshold of meteorological drought.

[0037] In this embodiment, the detection device obtains the target crop growth factor data of several dates of several grids in the target area, the relative threshold of high-temperature heat damage, and the relative threshold of meteorological drought.

[0038] For the relative threshold of high-temperature heat damage and the relative threshold of meteorological drought, please refer to Figure 4 , Figure 4 which is a schematic flowchart of S31 in the method for detecting the loss of composite high-temperature and drought disasters of target crops provided by an embodiment of the present application, including step S311, as follows: S311: According to the daily average temperature and daily precipitation in the target crop growth factor data of several dates of several grids in the research area, respectively construct a daily average temperature time series and a daily precipitation time series, and extract the value of the preset first quantile of the daily average temperature time series as the relative threshold of high-temperature heat damage, and the value of the preset second quantile of the daily precipitation time series as the relative threshold of meteorological drought.

[0039] Considering the actual situation that the absolute thresholds of disaster-causing temperatures for high-temperature heat damage and the absolute thresholds of disaster-causing rainfall for meteorological drought vary greatly for different crops in different regions, in this embodiment, the relative thresholds of disaster-causing temperatures for high-temperature heat damage and the relative thresholds of disaster-causing rainfall for meteorological drought will be extracted according to the definition of extreme weather. Extreme weather refers to an abnormal weather phenomenon in a certain area that significantly deviates from its historical average state during the same period, and generally uses a certain percentile as the judgment standard for significant deviation.

[0040] In this embodiment, the detection device constructs a daily average temperature time series and a daily precipitation time series respectively according to the daily average temperature and daily precipitation in the target crop growth factor data of several grids in the research area for several dates, and extracts the value of a preset first quantile of the daily average temperature time series as the relative threshold of high-temperature heat damage, and the value of a preset second quantile of the daily precipitation time series as the relative threshold of meteorological drought. Specifically, the first quantile can be set to the 90% quantile, and the second quantile can be set to 10%.

[0041] S32: Traverse the daily average temperature and daily precipitation in the target crop growth factor data. If the daily average temperature is higher than the relative threshold of high-temperature heat damage, replace the value of the daily average temperature with the relative threshold of high-temperature heat damage; if the daily precipitation is lower than the relative threshold of meteorological drought, replace the value of the daily precipitation with the relative threshold of meteorological drought, so as to obtain the ideal target crop growth factor data of several grids in the target area for several dates corresponding to the ideal weather scenario.

[0042] In this embodiment, the detection device traverses the daily average temperature and daily precipitation in the target crop growth factor data. If the daily average temperature is higher than the relative threshold of high-temperature heat damage, replace the value of the daily average temperature with the relative threshold of high-temperature heat damage; if the daily precipitation is lower than the relative threshold of meteorological drought, replace the value of the daily precipitation with the relative threshold of meteorological drought, so as to obtain the ideal target crop growth factor data of several grids in the target area for several dates corresponding to the ideal weather scenario, ensuring that the daily average temperature and daily precipitation data during the crop growth season calculated will not cause high-temperature heat damage and meteorological drought events, that is, forming the ideal weather scenario of the target crop during the crop growth season.

[0043] For the stress target crop growth factor data, please refer to Figure 5 , Figure 5 which is the flowchart of S3 in the target crop compound high-temperature and drought disaster loss detection method provided by another embodiment of this application, including steps S33~S34, specifically as follows: S33: Based on the relative threshold of high-temperature heat damage and the relative threshold of meteorological drought, obtain the compound high-temperature and drought disaster event record data of the target area.

[0044] In this embodiment, the detection device obtains the compound high-temperature and drought disaster event record data of the target area based on the relative threshold of high-temperature heat damage and the relative threshold of meteorological drought, where the compound high-temperature and drought disaster event record data includes the daily average temperature and daily precipitation for several dates when the compound high-temperature and drought disaster occurs.

[0045] S34: According to the recorded data of the compound high-temperature and drought disaster event, replace the values of the daily average temperature and daily precipitation on the corresponding dates in the ideal target crop growth factor data of several grids in the target area on the corresponding dates in the ideal weather scenario with the values of the daily average temperature and daily precipitation on the corresponding dates in the recorded data of the compound high-temperature and drought disaster event, so as to obtain the stress target crop growth factor data of several grids in the target area on the corresponding dates in the compound high-temperature and drought scenario.

[0046] In this embodiment, the detection device replaces the values of the daily average temperature and daily precipitation on the corresponding dates in the ideal target crop growth factor data of several grids in the target area on the corresponding dates in the ideal weather scenario with the values of the daily average temperature and daily precipitation on the corresponding dates in the recorded data of the compound high-temperature and drought disaster event, so as to obtain the stress target crop growth factor data of several grids in the target area on the corresponding dates in the compound high-temperature and drought scenario, so as to ensure that the designed compound high-temperature and drought weather scenario can comprehensively cover all possible situations; other meteorological elements remain unchanged.

[0047] S4: Input the geographical coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data of several grids in the target area corresponding to the ideal weather scenario; input the geographical coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data of several grids in the target area corresponding to the compound high-temperature and drought scenario.

[0048] In this embodiment, the detection device inputs the geographical coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data of several grids in the target area corresponding to the ideal weather scenario; inputs the geographical coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data of several grids in the target area corresponding to the compound high-temperature and drought scenario.

[0049] S5: Obtain the detection result of the compound high-temperature and drought disaster loss of the target crop in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data.

[0050] In this embodiment, the detection device obtains the detection result of the composite high-temperature and drought disaster loss of the target crop in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data.

[0051] Please refer to Figure 6 , Figure 6 which is a schematic flowchart of S5 in the method for detecting the composite high-temperature and drought disaster loss of the target crop provided by an embodiment of the present application, including step S51, specifically as follows: S51: Perform a difference operation on the ideal target crop yield prediction data corresponding to the ideal weather scenario and the stress target crop yield prediction data corresponding to the high-temperature heat damage scenario for the same grid in the target area, to obtain the target crop loss values of several grids in the target area, which are used as the detection result of the composite high-temperature and drought disaster loss of the target crop.

[0052] In this embodiment, the detection device performs a difference operation on the ideal target crop yield prediction data corresponding to the ideal weather scenario and the stress target crop yield prediction data corresponding to the high-temperature heat damage scenario for the same grid in the target area, to obtain the target crop loss values of several grids in the target area, which are used as the detection result of the composite high-temperature and drought disaster loss of the target crop.

[0053] Construct the target crop growth factor data corresponding to the ideal weather scenario and the composite high-temperature and drought scenario, combine with the pre-trained machine learning model to predict the target crop yield corresponding to the ideal weather scenario and the composite high-temperature and drought scenario, perform a difference operation on the obtained target crop yield prediction data corresponding to the ideal weather scenario and the composite high-temperature and drought scenario, to obtain the composite high-temperature and drought disaster loss value of the target crop, which reflects the target crop yield loss value under the composite high-temperature and drought stress, and provides a scientific basis for ensuring national food security.

[0054] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of the system for detecting the composite high-temperature and drought disaster loss of the target crop provided by an embodiment of the present application. This device can implement all or part of the system for detecting the composite high-temperature and drought disaster loss of the target crop through software, hardware, or a combination of both. The system 7 includes: A data acquisition module 71, configured to acquire the target crop yield data, geographic coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids; A model training module 72, configured to input the target crop yield data, geographic coordinate data of several grids in the research area, and the target crop growth factor data of several dates of the grids into the crop yield prediction model to be trained for training, to obtain the target crop yield prediction model; A scenario construction module 73, configured to obtain the geographical coordinate data of a plurality of grids in a target area, the ideal target crop growth factor data of the grids on a plurality of dates corresponding to an ideal weather scenario, and the stress target crop growth factor data of the grids on a plurality of dates corresponding to a combined high temperature and drought scenario; A target crop yield prediction module 74, configured to input the geographical coordinate data of a plurality of grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data corresponding to the plurality of grids in the target area under the ideal weather scenario; input the geographical coordinate data of the plurality of grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data corresponding to the plurality of grids in the target area under the combined high temperature and drought scenario; A target crop loss calculation module 75, configured to obtain the detection result of the combined high temperature and drought disaster loss of the target crop in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data.

[0055] In an embodiment of the present application, a data acquisition module is used to acquire target crop yield data, geographic coordinate data of several grids in a research area, and target crop growth factor data of several dates of the grids; a model training module inputs the target crop yield data, geographic coordinate data of several grids in the research area, and target crop growth factor data of several dates of the grids into a crop yield prediction model to be trained for training to obtain a target crop yield prediction model; a scenario construction module acquires geographic coordinate data of several grids in a target area, ideal target crop growth factor data of several dates corresponding to an ideal weather scenario of the grids, and stress target crop growth factor data of several dates corresponding to a combined high-temperature and drought scenario of the grids; a target crop yield prediction module inputs the geographic coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain ideal target crop yield prediction data corresponding to the ideal weather scenario of several grids in the target area; inputs the geographic coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain stress target crop yield prediction data corresponding to the combined high-temperature and drought scenario of several grids in the target area; a target crop loss calculation module obtains a target crop combined high-temperature and drought disaster loss detection result according to the ideal target crop yield prediction data and the stress target crop yield prediction data. By constructing target crop growth factor data corresponding to an ideal weather scenario and a combined high-temperature and drought scenario, and combining a pre-trained machine learning model to predict the target crop yield corresponding to the ideal weather scenario and the combined high-temperature and drought scenario, and performing difference processing on the obtained target crop yield prediction data corresponding to the ideal weather scenario and the combined high-temperature and drought scenario to obtain a target crop combined high-temperature and drought disaster loss value, which reflects the target crop yield loss value under the combined high-temperature and drought stress, providing a scientific basis for ensuring national food security.

[0056] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a computer device provided by an embodiment of the present application. The computer device 8 includes: a processor 81, a memory 82, and a computer program 83 stored on the memory 82 and executable on the processor 81; the computer device can store multiple instructions, and the instructions are suitable for being loaded and executed by the processor 81 to perform the method steps of the above Figures 1 to 6 shown embodiment. The specific execution process can refer to the specific description of the Figures 1 to 6 shown embodiment and will not be elaborated here.

[0057] Among them, the processor 81 may include one or more processing cores. The processor 81 uses various interfaces and lines to connect various parts within the server. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 82, and by invoking the data in the memory 82, it executes various functions of the target crop complex high-temperature and drought disaster loss detection system 7 and processes data. Optionally, the processor 81 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 81 may integrate a combination of one or several of the central processing unit 81 (CPU), graphics processing unit 81 (GPU), and modem. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the touch display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 81 and may be implemented separately by a single chip.

[0058] Among them, the memory 82 may include random access memory 82 (RAM), and may also include read-only memory 82 (ROM). Optionally, the memory 82 includes a non-transitory computer-readable storage medium. The memory 82 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 82 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store the data involved in the above-mentioned various method embodiments. Optionally, the memory 82 may also be at least one storage device located far from the aforementioned processor 81.

[0059] The embodiment of the present application also provides a storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by the processor to perform the Figures 1 to 6 method steps of the embodiments shown above. The specific execution process can refer to the Figures 1 to 6 specific description of the embodiments shown above, and will not be elaborated here.

[0060] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0061] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0063] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division, and there can be other division methods 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0064] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] In addition, in each embodiment of the present invention, each functional unit may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0066] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it may also be completed by a computer program instructing relevant hardware. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments may be implemented. Among them, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate form, etc.

[0067] The present invention is not limited to the above-mentioned embodiments. If various changes or deformations to the present invention do not deviate from the spirit and scope of the present invention, and if these changes and deformations fall within the scope of the claims of the present invention and equivalent technical scope, then the present invention also intends to include these changes and deformations.

Claims

1. A method for detecting target crop compound high temperature drought disaster losses, characterized in that: The following steps are involved: Obtaining target crop yield data, geographic coordinate data of a plurality of grids in a study area and target crop growth factor data of a plurality of dates of the grids; Inputting the target crop yield per unit area data, geographic coordinate data of a plurality of grids in the study area and the target crop growth factor data of a plurality of dates in the grids into the crop yield prediction model to be trained, thereby obtaining the target crop yield prediction model; Obtaining geographic coordinate data of a plurality of grids in a target area, ideal target crop growth factor data of the grids on a plurality of dates corresponding to an ideal weather scenario, and stress target crop growth factor data of the grids on a plurality of dates corresponding to a composite high temperature drought scenario; Inputting the geographic coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data corresponding to the several grids in the target area under the ideal weather scenario; inputting the geographic coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data corresponding to the several grids in the target area under the composite high temperature and drought scenario; The target crop compound high temperature and drought disaster loss detection result in the target area is obtained according to the ideal target crop yield prediction data and the stressed target crop yield prediction data.

2. The target crop composite high temperature drought disaster loss detection method according to claim 1, characterized in that: The target crop yield data of several grids in the study area are obtained by the following steps: Obtaining regional scale yield data of the target crop in the study area, the sum of the vegetation leaf area index of each grid in the study area, and the average of the sum of the vegetation leaf area index of several grids; According to the regional scale yield data of the target crop in the study area, the sum of the vegetation leaf area index of each grid in the study area, the average of the sum of the vegetation leaf area index of several grids and the preset target crop grid scale yield calculation algorithm, the target crop yield data of several grids in the study area are obtained.

3. The target crop composite high temperature drought disaster loss detection method according to claim 1, characterized in that: The target crop growth factor data includes weather element data and soil property data; the weather element data includes daily average temperature, daily precipitation, solar radiation, daily wind speed and daily relative humidity; the geographic coordinate data includes longitude coordinates and latitude coordinates.

4. The target crop composite high temperature drought disaster loss detection method according to claim 3, characterized in that: The ideal target crop growth factor data of the grid on several dates corresponding to the ideal weather scenario are obtained by the following steps: Obtaining target crop growth factor data, high temperature heat damage relative thresholds, and meteorological drought relative thresholds for a number of dates in a number of grids in the target area; The daily average temperature and daily precipitation in the target crop growth factor data are traversed; if the daily average temperature is higher than the high temperature heat damage relative threshold, the value of the daily average temperature is replaced by the high temperature heat damage relative threshold; if the daily precipitation is lower than the meteorological drought relative threshold, the value of the daily precipitation is replaced by the meteorological drought relative threshold, and the ideal target crop growth factor data of several grids in the target area on several dates corresponding to ideal weather scenarios are obtained.

5. The target crop composite high temperature drought disaster loss detection method according to claim 4, characterized in that: The growth factor data of the stress target crops on the grid on several dates corresponding to the composite high temperature and drought scenario are obtained by the following steps: Based on the high temperature heat damage relative threshold and the meteorological drought relative threshold, obtaining the composite high temperature drought disaster event record data of the target area, wherein the composite high temperature drought disaster event record data includes the daily average temperature and daily precipitation on several dates when the composite high temperature drought disaster occurs; According to the composite high temperature and drought disaster event record data, the values ​​of daily average temperature and daily precipitation on corresponding dates in the ideal target crop growth factor data of several grids in the target area on several dates corresponding to the ideal weather scenarios are respectively replaced with the values ​​of daily average temperature and daily precipitation on corresponding dates in the composite high temperature and drought disaster event record data, so as to obtain the stress target crop growth factor data of several grids in the target area on several dates corresponding to the composite high temperature and drought scenarios.

6. The target crop composite high temperature drought disaster loss detection method according to claim 5, characterized in that: The high temperature heat damage relative threshold and the meteorological drought relative threshold are obtained by the following steps: According to the daily average temperature and daily precipitation in the target crop growth factor data of several dates in several grids of the study area, a daily average temperature time series and a daily precipitation time series are constructed respectively, and the value of the preset first quantile of the daily average temperature time series is extracted as the relative threshold of high temperature heat damage, and the value of the preset second quantile of the daily precipitation time series is extracted as the relative threshold of meteorological drought.

7. The target crop composite high temperature drought disaster loss detection method according to claim 6, characterized in that: The method of obtaining the target crop compound high temperature drought disaster loss detection result in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data comprises the following steps: The ideal target crop yield prediction data corresponding to the ideal weather scenario and the stressed target crop yield prediction data corresponding to the compound high temperature and drought scenario of the same grid in the target area are subjected to difference processing to obtain the target crop loss values ​​of several grids in the target area as the target crop compound high temperature and drought disaster loss detection result.

8. A target crop composite high temperature drought disaster loss detection system, characterized in that: include: A data acquisition module, used to obtain target crop yield data, geographic coordinate data of a plurality of grids in a study area and target crop growth factor data of a plurality of dates of the grids; A model training module, for inputting the target crop yield data and geographic coordinate data of a plurality of grids in the study area and the target crop growth factor data of a plurality of dates of the grids into the crop yield prediction model to be trained, so as to obtain the target crop yield prediction model; A scenario construction module is used to obtain geographic coordinate data of a plurality of grids in a target area, ideal target crop growth factor data of the grids on a plurality of dates corresponding to an ideal weather scenario, and stress target crop growth factor data of the grids on a plurality of dates corresponding to a composite high temperature drought scenario; The target crop yield prediction module is used to input the geographic coordinate data of several grids in the target area and the ideal target crop growth factor data into the target crop yield prediction model to obtain the ideal target crop yield prediction data corresponding to the several grids in the target area under the ideal weather scenario; input the geographic coordinate data of several grids in the target area and the stress target crop growth factor data into the target crop yield prediction model to obtain the stress target crop yield prediction data corresponding to the several grids in the target area under the composite high temperature drought scenario; The target crop loss calculation module is used to obtain the target crop compound high temperature drought disaster loss detection result in the target area according to the ideal target crop yield prediction data and the stress target crop yield prediction data.

9. A computer device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the target crop composite high temperature and drought disaster loss detection method as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the target crop combined high temperature and drought disaster loss detection method as described in any one of claims 1 to 7 are implemented.

Images