Method, apparatus, storage medium, and processor for predicting crop yield

Abstract

Embodiments of the present application provide a method, device, storage medium and processor for predicting crop yield. The method comprises: obtaining a remote sensing image of a crop to be predicted at a first growth period, a first temperature of each day within the first growth period, and a second temperature of each day within a second growth period; determining a predicted biomass of an above-ground part of the crop to be predicted at a harvest period according to the remote sensing image; determining a harvest index correction value of the crop to be predicted according to the first temperature and the second temperature; and determining a yield prediction value of the crop to be predicted according to the predicted biomass of the above-ground part at the harvest period and the harvest index correction value. Through the above technical solution, the predicted biomass is used as a medium for crop yield prediction, which greatly improves the prediction accuracy of crop yield, reduces the prediction error caused by unstable yield, quantifies the influence of temperature on the harvest index of the predicted crop, and further corrects the harvest index, so that the prediction of crop yield is more accurate.

Description

Technical Field

[0001] This application relates to the field of agricultural production, and more specifically to a method, apparatus, storage medium, and processor for predicting crop yield. Background Technology

[0002] Currently, when using remote sensing technology to predict rice yield, a relationship is often established between yield data and remote sensing data to estimate crop yield. However, during the actual growth process of crops, temperature has a significant impact on the final yield. For example, the optimal average temperature for crops during the grain-filling stage is 21-26℃; temperatures exceeding this range can hinder the grain-filling process. If the above method is used to predict crop yield, the hindering effect of temperature on crop growth cannot be directly obtained, leading to an overestimation of crop yield and low prediction accuracy. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, storage medium, and processor for predicting crop yield.

[0004] To achieve the above objectives, a first aspect of this application provides a method for predicting crop yield, comprising: Acquire remote sensing images of the crop to be predicted during its first growth stage, the first temperature of each day during the first growth stage, and the second temperature of each day during the second growth stage; Determine the predicted aboveground biomass of the crop at harvest time based on remote sensing images; The harvest index correction value for the crop to be predicted is determined based on the first temperature and the second temperature. The predicted yield of the crop to be predicted is determined based on the predicted aboveground biomass and harvest index correction values ​​at harvest time.

[0005] In this embodiment of the application, determining the harvest index correction value of the crop to be predicted based on the first temperature and the second temperature includes: determining the first cumulative high temperature and the first high temperature shock intensity of the crop to be predicted during the first growth period, and the second cumulative high temperature and the second high temperature shock intensity during the second growth period, respectively, based on the first temperature and the second temperature. The cumulative high temperature is determined by the temperature of high-temperature days with temperatures higher than a preset temperature during the growth period and the preset temperature. The high temperature shock intensity is the ratio between the cumulative high temperature corresponding to the growth period and the total number of high-temperature days during the growth period. The first cumulative high temperature, the first high temperature shock intensity, the second cumulative high temperature, and the second high temperature shock intensity are input into the harvest index model to determine the predicted harvest index value of the crop to be predicted. The harvest index correction value is then determined based on the predicted harvest index value.

[0006] In this embodiment of the application, determining the harvest index correction value based on the harvest index prediction value includes: determining the harvest index correction value to be zero when the harvest index prediction value is less than or equal to a first preset value; determining the harvest index prediction value as the harvest index correction value when the harvest index prediction value is greater than the first preset value and less than a second preset value; and determining the harvest index correction value as the second preset value when the harvest index prediction value is greater than or equal to the second preset value.

[0007] In this embodiment of the application, the method further includes: obtaining the historical yield value of the historical crop in any two historical harvest years and the historical biomass of the aboveground parts during the harvest period; for each historical harvest year, determining the historical harvest index of the historical crop in the historical harvest year based on the historical yield value and historical biomass; determining the first historical high-temperature day with a temperature greater than a preset temperature during the first growth period of the historical crop in each historical harvest year and the second historical high-temperature day with a temperature greater than a preset temperature during the second growth period; determining the first historical temperature difference between the temperature of each first historical high-temperature day and the preset temperature, and the second historical temperature difference between the temperature of each second historical high-temperature day and the preset temperature; determining the first ratio between the sum of all first historical temperature differences and the total number of days with first historical high temperatures, and the second ratio between the sum of all second historical temperature differences and the total number of days with second historical high temperatures; and constructing a harvest index model based on the first historical temperature, the first ratio, the second historical temperature, the second ratio, and the historical harvest index corresponding to each historical harvest year.

[0008] In this embodiment of the application, determining the predicted aboveground biomass of the crop to be predicted at the harvest period based on remote sensing images includes: preprocessing the remote sensing images to obtain corresponding remote sensing feature values; inputting the remote sensing feature values ​​into a first prediction model to determine the predicted aboveground biomass of the crop to be predicted at the first growth stage, wherein the first prediction model is determined based on historical remote sensing images of historical crops at the first growth stage and historical aboveground biomass; and inputting the predicted aboveground biomass at the first growth stage into a second prediction model to determine the predicted aboveground biomass of the crop to be predicted at the harvest period, wherein the second prediction model is determined based on historical aboveground biomass of historical crops at the first growth stage and historical aboveground biomass at the harvest period.

[0009] In this embodiment of the application, the production forecast is determined by formula (2): (2) in, This refers to the predicted yield of the crop to be predicted in year i. It refers to the predicted aboveground biomass of the crop at harvest time. This refers to the harvest index correction value of the crop to be predicted in year i.

[0010] A second aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned method for predicting crop yield.

[0011] A third aspect of this application provides a processor configured to perform the above-described method for predicting crop yield.

[0012] A fourth aspect of this application provides an apparatus for predicting crop yield, including the processor described above.

[0013] The above-mentioned technical solution determines the predicted biomass of the aboveground part of the crop at the harvest period based on remote sensing images. The predicted biomass is used as a medium for crop yield prediction, which greatly improves the accuracy of crop yield prediction and reduces prediction errors caused by yield instability. At the same time, considering the impact of temperature on crop yield, the influence of temperature on the harvest index of the predicted crop is quantified, and the harvest index is further corrected to make the crop yield prediction more accurate.

[0014] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 The schematic diagram illustrates a process flow diagram of a method for predicting crop yield according to an embodiment of this application; Figure 2 A schematic flowchart of a method for predicting crop yield according to yet another embodiment of this application is shown. Figure 3 The illustration shows example diagrams illustrating the results of determining production forecasts using different methods according to embodiments of this application; Figure 4 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] Figure 1 A schematic flowchart illustrating a method for predicting crop yield according to an embodiment of this application is shown. Figure 1 As shown in one embodiment of this application, a method for predicting crop yield is provided, comprising the following steps: Step 101: Obtain remote sensing images of the crop to be predicted during its first growth stage, the first temperature for each day during the first growth stage, and the second temperature for each day during the second growth stage.

[0018] Step 102: Determine the predicted aboveground biomass of the crop to be predicted at harvest time based on remote sensing images.

[0019] Step 103: Determine the harvest index correction value for the crop to be predicted based on the first temperature and the second temperature.

[0020] Step 104: Determine the predicted yield of the crop to be predicted based on the predicted aboveground biomass and harvest index correction value at harvest time.

[0021] Crops can refer to various plants cultivated in agriculture. For example, crops can refer to field crops such as rice. Crops can be planted in suitable growing areas and can be sown on any day of the sowing period. Crops include multiple growth stages, such as the sowing-booting stage, booting-heading stage, heading-maturity stage, and maturity-harvest stage. When predicting crop yield, the processor first acquires remote sensing images of the crop to be predicted during the first growth stage and the first temperature for each day during the first growth stage, as well as the second temperature for each day during the second growth stage. The first growth stage refers to the booting-heading stage. The second growth stage refers to the heading-maturity stage. The first temperature can refer to the daily maximum temperature of the crop to be predicted during the first growth stage. The second temperature can refer to the daily maximum temperature of the crop to be predicted during the second growth stage.

[0022] The processor can determine the predicted aboveground biomass of the crop at harvest time based on remote sensing images. The predicted aboveground biomass refers to the predicted value of the aboveground biomass of the crop. Aboveground biomass refers to the amount of undecomposed dead plant and animal tissue and its partial decomposition products. The processor can determine the harvest index correction value of the crop based on a first temperature and a second temperature. The harvest index correction value refers to the corrected harvest index. The harvest index is the ratio between the economic yield and biomass of the crop at harvest. The harvest index reflects the ability of a crop population to convert photosynthetic assimilates into economic products and can be used to evaluate the yield level and cultivation effectiveness of crop varieties. After determining the harvest index correction value and the predicted aboveground biomass at harvest time, the processor can determine the predicted yield value of the crop based on the predicted aboveground biomass at harvest time and the harvest index correction value.

[0023] The above-mentioned technical solution determines the predicted biomass of the aboveground part of the crop at the harvest period based on remote sensing images. The predicted biomass is used as a medium for crop yield prediction, which greatly improves the accuracy of crop yield prediction and reduces prediction errors caused by yield instability. At the same time, considering the impact of temperature on crop yield, the influence of temperature on the harvest index of the predicted crop is quantified, and the harvest index is further corrected to make the crop yield prediction more accurate.

[0024] In one embodiment, determining the harvest index correction value of the crop to be predicted based on the first temperature and the second temperature includes: determining the first cumulative high temperature and the first high temperature shock intensity of the crop to be predicted during the first growth period, and the second cumulative high temperature and the second high temperature shock intensity during the second growth period, respectively, wherein the cumulative high temperature is determined based on the temperature of high-temperature days with temperatures higher than a preset temperature during the growth period and the preset temperature, and the high temperature shock intensity is the ratio between the cumulative high temperature corresponding to the growth period and the total number of high-temperature days during the growth period; inputting the first cumulative high temperature, the first high temperature shock intensity, the second cumulative high temperature, and the second high temperature shock intensity into the harvest index model to determine the predicted harvest index value of the crop to be predicted; and determining the harvest index correction value based on the predicted harvest index value.

[0025] Temperature affects crop growth to varying degrees, thus influencing the prediction of subsequent crop yields. Therefore, when determining the harvest index correction value for a crop to be predicted, the processor can first determine the first cumulative high-temperature temperature and the first high-temperature shock intensity of the crop during its first growth period based on a first temperature. Specifically, in one embodiment, the processor can determine multiple first high-temperature days during the first growth period where the temperature of the crop to be predicted is higher than a preset temperature, and can determine the temperature difference between the temperature of each first high-temperature day and the preset temperature. The processor can determine the sum of all temperature differences as the first cumulative high-temperature temperature of the crop to be predicted during its first growth period. Then, the processor can determine the ratio between the first cumulative high-temperature temperature and the number of days with first high-temperature days as the first high-temperature shock intensity of the crop to be predicted during its first growth period. The first cumulative high-temperature temperature is determined based on the temperature of the first high-temperature days during the first growth period that are higher than the preset temperature and the preset temperature. The first high-temperature shock intensity is the ratio between the first cumulative high-temperature temperature corresponding to the first growth period and the total number of days with first high-temperature days during the first growth period. The preset temperature can be customized according to actual conditions. For example, the preset temperature can be 35°C. That is, if the temperature on a certain day is greater than 35℃, then that day can be designated as a high-temperature day.

[0026] The processor can determine the second cumulative high-temperature temperature and the second high-temperature shock intensity of the crop to be predicted during its second growth period based on the second temperature. Specifically, in one embodiment, the processor can determine a plurality of second high-temperature days during the second growth period of the crop to be predicted where the temperature is higher than a preset temperature, and can determine the temperature difference between the temperature of each second high-temperature day and the preset temperature. The processor can determine the sum of all temperature differences as the second cumulative high-temperature temperature of the crop to be predicted during its second growth period. Then, the processor can determine the ratio between the second cumulative high-temperature temperature and the number of days with second high-temperature days as the second high-temperature shock intensity of the crop to be predicted during its second growth period. The second cumulative high-temperature temperature is determined based on the temperature of the second high-temperature days during the second growth period that are higher than the preset temperature and the preset temperature. The second high-temperature shock intensity is the ratio between the second cumulative high-temperature temperature corresponding to the second growth period and the total number of days with second high-temperature days during the second growth period.

[0027] The processor can input the first accumulated high temperature, the first high temperature shock intensity, the second accumulated high temperature, and the second high temperature shock intensity into the harvest index model to determine the predicted harvest index value for the crop to be predicted. The harvest index model is a mathematical model that can be constructed based on the historical temperatures of the crop during its first and second growth stages. Once the predicted harvest index value for the crop to be predicted is determined, the processor can determine a harvest index correction value based on the predicted harvest index value.

[0028] In one embodiment, determining the harvest index correction value based on the harvest index forecast includes: determining the harvest index correction value to be zero when the harvest index forecast is less than or equal to a first preset value; determining the harvest index forecast as the harvest index correction value when the harvest index forecast is greater than the first preset value and less than a second preset value; and determining the harvest index correction value as the second preset value when the harvest index forecast is greater than or equal to the second preset value.

[0029] The processor can further refine the predicted harvest index value to obtain a corrected harvest index value for the crop to be predicted. Specifically, the processor can compare the predicted harvest index value with a first preset value and a second preset value. The first and second preset values ​​can be customized according to actual conditions. For example, the first preset value can be 0.1, and the second preset value can be 0.65. If the predicted harvest index value is less than or equal to the first preset value, the processor can determine the corrected harvest index value to be zero. That is, in this case, the crop to be predicted may experience a complete crop failure, i.e., the yield may be zero. If the predicted harvest index value is greater than the first preset value but less than the second preset value, the processor can determine the predicted harvest index value as the corrected harvest index value. That is, in this case, no correction is required for the predicted harvest index value. If the predicted harvest index value is greater than or equal to the second preset value, the processor can determine the corrected harvest index value to be the second preset value.

[0030] Specifically, in one embodiment, the harvest index forecast can be corrected using the following formula:

[0031] Here, HI refers to the harvest index forecast. This refers to the harvest index correction value.

[0032] In one embodiment, the method further includes: obtaining historical yield values ​​of historical crops in any two historical harvest years and historical aboveground biomass at the harvest period; for each historical harvest year, determining a historical harvest index of the historical crop based on the historical yield value and historical biomass; determining the first historical high-temperature day with a temperature greater than a preset temperature during the first growth period of the historical crop in each historical harvest year and the second historical high-temperature day with a temperature greater than a preset temperature during the second growth period; determining a first historical temperature difference between the temperature of each first historical high-temperature day and the preset temperature, and a second historical temperature difference between the temperature of each second historical high-temperature day and the preset temperature; determining a first ratio between the sum of all first historical temperature differences and the total number of first historical high-temperature days, and a second ratio between the sum of all second historical temperature differences and the total number of second historical high-temperature days; and constructing a harvest index model based on the first historical temperature, the first ratio, the second historical temperature, the second ratio, and the historical harvest index corresponding to each historical harvest year.

[0033] Before forecasting yield, the processor can first construct a harvest index model. Specifically, the processor can first obtain the historical yield values ​​and historical biomass of the crop at any two historical harvest years. The historical crop can refer to a crop that has already been harvested, such as field crops like rice. For each historical harvest year, the processor can determine the historical harvest index of the historical crop for that year based on the historical yield value and historical biomass. The historical crop can be sown on any historical sowing day within the historical sowing period; therefore, different historical sowing days will result in different harvest days, leading to different crop harvest indices. Furthermore, even if the historical crop was sown on the same historical sowing day, it could be planted in different regions, resulting in different harvest indices. Therefore, for each historical harvest year, there can be multiple historical yield values ​​and multiple corresponding historical biomass values, and thus, multiple determined historical harvest indices.

[0034] The processor can determine the first historical high-temperature day with a temperature exceeding a preset temperature during the first growth period of each historical harvest year, and the second historical high-temperature day with a temperature exceeding the preset temperature during the second growth period. Then, the processor can further determine the first historical temperature difference between the temperature of each first historical high-temperature day and the preset temperature, and the second historical temperature difference between the temperature of each second historical high-temperature day and the preset temperature. The preset temperature can be customized according to actual conditions. For example, the preset temperature can be 35℃. The processor can further determine a first ratio between the sum of all first historical temperature differences and the total number of first historical high-temperature days, and a second ratio between the sum of all second historical temperature differences and the total number of second historical high-temperature days. The sum of all first historical temperature differences can refer to the historical cumulative high temperature during the first growth period of the historical crop, and the first ratio can refer to the historical high-temperature impact intensity during the first growth period of the historical crop. The sum of all second historical temperature differences can refer to the historical cumulative high temperature during the second growth period of the historical crop, and the second ratio can refer to the historical high-temperature impact intensity during the second growth period of the historical crop.

[0035] The processor can construct a harvest index model based on the first historical temperature, first ratio, second historical temperature, second ratio, and historical harvest index corresponding to each historical harvest year for historical crops. Here, the harvest index model refers to a mathematical model. Furthermore, the processor can determine the heat tolerance weight value and high-temperature shock calibration value of historical crops based on the first historical temperature, first ratio, second historical temperature, and second ratio corresponding to each historical harvest year, and then correct the crop's harvest index based on these heat tolerance weight values ​​and high-temperature shock calibration values.

[0036] Taking the historical crop Meixiangzhan 2 as an example, Table 1 shows the historical harvest index of Meixiangzhan 2 in 2020, 2021, and 2022. Table 2 shows the cumulative daily high temperature and high temperature shock intensity of Meixiangzhan 2 in 2020, 2021, and 2022. Tg1 refers to the number of days with a maximum daily temperature greater than 35℃ during the booting-heading stage of Meixiangzhan 2, and Tg2 refers to the number of days with a maximum daily temperature greater than 35℃ during the heading-maturity stage of Meixiangzhan 2. This refers to the cumulative high temperature on high-temperature days during the booting-heading stage. , This refers to the cumulative high temperature on high-temperature days during the heading-to-maturity period. . This refers to the intensity of high-temperature shock during the booting to heading stage. , This refers to the intensity of high-temperature shock during the heading and maturity stages. The processor can construct a harvest index model based on the cumulative high temperature, high temperature shock intensity, and harvest index of high-temperature days during the heading-booting stage in 2020 and 2021, as well as the cumulative high temperature, high temperature shock intensity, and harvest index of high-temperature days during the heading-maturity stage.

[0037] Furthermore, the constructed harvest index model can be used to predict the harvest index of Meixiangzhan 2 in 2022. For example, Table 3 shows the simulated and actual harvest index values ​​for Meixiangzhan 2 in 2022. The processor can determine the weight value of the heat resistance of the Meixiangzhan 2 rice variety and the impact calibration value of high temperature relative to rice growth using data from 2020, 2021, and 2022, and then adjust the predicted harvest index based on these weight values ​​and impact calibration values.

[0038] Table 1. Historical Harvest Index of Meixiangzhan No. 2 in 2020 / 2021 / 2022

[0039] Table 2. Daily cumulative high temperature and high temperature shock intensity of Meixiangzhan No. 2 in 2020 / 2021 / 2022

[0040] Table 3. Simulated harvest index values ​​for Meixiangzhan No. 2 in 2020 / 2021 / 2022

[0041] In one embodiment, determining the predicted aboveground biomass of a crop to be predicted at harvest time based on remote sensing images includes: preprocessing the remote sensing images to obtain corresponding remote sensing feature values; inputting the remote sensing feature values ​​into a first prediction model to determine the predicted aboveground biomass of the crop to be predicted at the first growth stage, the first prediction model being determined based on historical remote sensing images of historical crops at the first growth stage and historical aboveground biomass; and inputting the predicted aboveground biomass at the first growth stage into a second prediction model to determine the predicted aboveground biomass of the crop to be predicted at harvest time, the second prediction model being determined based on historical aboveground biomass of historical crops at the first growth stage and historical aboveground biomass at harvest time.

[0042] The processor can preprocess remote sensing images to obtain corresponding remote sensing feature values. These feature values ​​include vegetation indices, texture features, and band indices. The processor can input these feature values ​​into a first prediction model to determine the predicted aboveground biomass of the crop during its first growth stage. The first prediction model is determined based on historical remote sensing images and historical biomass of the crop during its first growth stage. Specifically, processing historical remote sensing images yields historical remote sensing feature values. Then, traditional regression equations can be used to analyze these historical feature values ​​and historical biomass to construct the first prediction model. Traditional regression equations include linear equations, exponential functions, and logarithmic functions. Historical remote sensing feature values ​​include historical vegetation indices, historical texture features, and historical band indices. For example, if historical vegetation indices are obtained after processing historical remote sensing images, an aboveground biomass inversion model based on the vegetation indices can be constructed, i.e., the first prediction model.

[0043] Given the predicted aboveground biomass of the crop under prediction during its first growth stage, the processor can input this predicted aboveground biomass into a second prediction model to determine the predicted aboveground biomass at harvest. The second prediction model is determined based on the historical aboveground biomass of crops during their first growth stage and at harvest. Specifically, multiple stepwise regression and sensitivity factor screening can be used to construct a multi-temporal aboveground biomass prediction model, i.e., the second prediction model, using the historical aboveground biomass during the first growth stage and at harvest.

[0044] In one embodiment, the production forecast is determined by formula (2): (2) in, This refers to the predicted yield of the crop to be predicted in year i. It refers to the predicted aboveground biomass of the crop at harvest time. This refers to the harvest index correction value of the crop to be predicted in year i.

[0045] In one embodiment, such as Figure 2 The diagram shows a flowchart of another method for predicting crop yield.

[0046] When predicting crop yield, the processor first acquires remote sensing image data before the heading stage (first growth stage), the daily maximum temperature during the booting-heading stage (first growth stage) (first temperature), and the daily maximum temperature during the heading-maturity stage (second growth stage) (second temperature). Then, the processor processes the remote sensing image data to obtain remote sensing feature data. This remote sensing feature data may include vegetation data, texture features, and band indices. The processor further inputs the remote sensing feature data into an inversion model (first prediction model) to obtain the current biomass (predicted aboveground biomass during the first growth stage). The processor can then input the current biomass into a harvest biomass prediction model (second prediction model) to obtain the predicted aboveground biomass at harvest. After determining the daily maximum temperature during the booting-heading stage and the heading-maturity stage, the number of days with temperatures above 35°C can be determined, and the cumulative high temperature daydays (HGDD) (first and second cumulative high temperature daydays) can be calculated. Next, the processor can determine the high-temperature shock intensity AHGDD (first high-temperature shock intensity and second high-temperature shock intensity). Specifically, the processor can determine the high-temperature shock intensity of the booting-heading period (first high-temperature shock intensity) by the ratio between the cumulative high temperature during the booting-heading period and the number of days with temperatures above 35°C during the booting-heading period. The processor can determine the high-temperature shock intensity of the heading-maturity period (second high-temperature shock intensity) by the ratio between the cumulative high temperature during the heading-maturity period and the number of days with temperatures above 35°C during the heading-maturity period. Then, the processor can input the cumulative high temperature HGDD and the high-temperature shock intensity AHGDD into the harvest index correction model (harvest index model) to obtain the predicted value of the harvest index. Then, the harvest index is further adjusted to obtain the corrected value of the harvest index. After determining the predicted aboveground biomass and the corrected value of the harvest index at harvest time, the processor can input the predicted aboveground biomass and the corrected value of the harvest index at harvest time into the yield prediction model (…). This is used to obtain crop yield forecasts.

[0047] like Figure 3 As shown in the figure, an example graph illustrates the results of determining yield predictions using different methods. It is evident that the yield prediction model constructed using aboveground biomass is more sensitive to heat stress and exhibits higher yield accuracy.

[0048] The above-mentioned technical solution determines the predicted biomass of the aboveground part of the crop at the harvest period based on remote sensing images. The predicted biomass is used as a medium for crop yield prediction, which greatly improves the accuracy of crop yield prediction and reduces prediction errors caused by yield instability. At the same time, considering the impact of temperature on crop yield, the influence of temperature on the harvest index of the predicted crop is quantified, and the harvest index is further corrected to make the crop yield prediction more accurate.

[0049] Figure 1-2 This is a flowchart illustrating a method for predicting crop yield in one embodiment. It should be understood that, although... Figure 1-2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1-2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0050] In one embodiment, a storage medium is provided on which a program is stored, which, when executed by a processor, implements the above-described method for predicting crop yield.

[0051] In one embodiment, a processor is provided for running a program, wherein the program executes the method described above for predicting crop yield.

[0052] In one embodiment, an apparatus for predicting crop yield is provided, including the processor described above.

[0053] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data such as yield forecasts. The network interface A02 communicates with external terminals via a network connection. When the processor A01 executes the computer program B02, it implements a method for predicting crop yields.

[0054] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0055] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring remote sensing images of the crop to be predicted during its first growth stage, a first temperature for each day during the first growth stage, and a second temperature for each day during the second growth stage; determining the predicted aboveground biomass of the crop to be predicted at the harvest stage based on the remote sensing images; determining a harvest index correction value for the crop to be predicted based on the first and second temperatures; and determining the predicted yield value of the crop to be predicted based on the predicted aboveground biomass and the harvest index correction value at the harvest stage.

[0056] In one embodiment, determining the harvest index correction value of the crop to be predicted based on the first temperature and the second temperature includes: determining the first cumulative high temperature and the first high temperature shock intensity of the crop to be predicted during the first growth period, and the second cumulative high temperature and the second high temperature shock intensity during the second growth period, respectively, wherein the cumulative high temperature is determined based on the temperature of high-temperature days with temperatures higher than a preset temperature during the growth period and the preset temperature, and the high temperature shock intensity is the ratio between the cumulative high temperature corresponding to the growth period and the total number of high-temperature days during the growth period; inputting the first cumulative high temperature, the first high temperature shock intensity, the second cumulative high temperature, and the second high temperature shock intensity into the harvest index model to determine the predicted harvest index value of the crop to be predicted; and determining the harvest index correction value based on the predicted harvest index value.

[0057] In one embodiment, determining the harvest index correction value based on the harvest index forecast includes: determining the harvest index correction value to be zero when the harvest index forecast is less than or equal to a first preset value; determining the harvest index forecast as the harvest index correction value when the harvest index forecast is greater than the first preset value and less than a second preset value; and determining the harvest index correction value as the second preset value when the harvest index forecast is greater than or equal to the second preset value.

[0058] In one embodiment, the method further includes: obtaining historical yield values ​​of historical crops in any two historical harvest years and historical aboveground biomass at the harvest period; for each historical harvest year, determining a historical harvest index of the historical crop based on the historical yield value and historical biomass; determining the first historical high-temperature day with a temperature greater than a preset temperature during the first growth period of the historical crop in each historical harvest year and the second historical high-temperature day with a temperature greater than a preset temperature during the second growth period; determining a first historical temperature difference between the temperature of each first historical high-temperature day and the preset temperature, and a second historical temperature difference between the temperature of each second historical high-temperature day and the preset temperature; determining a first ratio between the sum of all first historical temperature differences and the total number of first historical high-temperature days, and a second ratio between the sum of all second historical temperature differences and the total number of second historical high-temperature days; and constructing a harvest index model based on the first historical temperature, the first ratio, the second historical temperature, the second ratio, and the historical harvest index corresponding to each historical harvest year.

[0059] In one embodiment, determining the predicted aboveground biomass of a crop to be predicted at harvest time based on remote sensing images includes: preprocessing the remote sensing images to obtain corresponding remote sensing feature values; inputting the remote sensing feature values ​​into a first prediction model to determine the predicted aboveground biomass of the crop to be predicted at the first growth stage, the first prediction model being determined based on historical remote sensing images and historical aboveground biomass of historical crops at the first growth stage; and inputting the predicted aboveground biomass at the first growth stage into a second prediction model to determine the predicted aboveground biomass of the crop to be predicted at harvest time, the second prediction model being determined based on historical aboveground biomass of historical crops at the first growth stage and historical aboveground biomass at harvest time.

[0060] In one embodiment, the production forecast is determined by formula (2): (2) in, This refers to the predicted yield of the crop to be predicted in year i. It refers to the predicted aboveground biomass of the crop at harvest time. This refers to the harvest index correction value of the crop to be predicted in year i.

[0061] This application also provides a computer program product that, when executed on a data processing device, is adapted to execute a program having method steps for predicting crop yield.

[0062] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0068] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0070] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting crop yield, characterized in that, The method includes: Acquire remote sensing images of the crop to be predicted during its first growth stage, the first temperature for each day during the first growth stage, and the second temperature for each day during the second growth stage; Determine the predicted aboveground biomass of the crop to be predicted at harvest time based on the remote sensing images; The harvest index correction value of the crop to be predicted is determined based on the first temperature and the second temperature. The predicted yield of the crop to be predicted is determined based on the predicted aboveground biomass at harvest time and the harvest index correction value. The step of determining the harvest index correction value of the crop to be predicted based on the first temperature and the second temperature includes: determining the first cumulative high temperature and the first high temperature shock intensity of the crop to be predicted during the first growth period, and the second cumulative high temperature and the second high temperature shock intensity during the second growth period, respectively, based on the first temperature and the second temperature. The cumulative high temperature is the sum of the differences between the daily maximum temperature of all high-temperature days and a preset temperature; the high temperature shock intensity is the ratio between the cumulative high temperature corresponding to the growth period and the total number of high-temperature days within the growth period; inputting the first cumulative high temperature, the first high temperature shock intensity, the second cumulative high temperature, and the second high temperature shock intensity into the harvest index model to determine the predicted harvest index value of the crop to be predicted; and determining the harvest index correction value based on the predicted harvest index value. The step of determining the harvest index correction value based on the harvest index prediction value includes: determining the harvest index correction value to be zero when the harvest index prediction value is less than or equal to a first preset value; determining the harvest index prediction value as the harvest index correction value when the harvest index prediction value is greater than the first preset value and less than a second preset value; and determining the harvest index correction value as the second preset value when the harvest index prediction value is greater than or equal to the second preset value. The step of determining the predicted aboveground biomass of the crop to be predicted at the harvest period based on the remote sensing image includes: preprocessing the remote sensing image to obtain corresponding remote sensing feature values; inputting the remote sensing feature values ​​into a first prediction model to determine the predicted aboveground biomass of the crop to be predicted at the first growth stage, wherein the first prediction model is determined based on historical remote sensing images of historical crops at the first growth stage and historical aboveground biomass; and inputting the predicted aboveground biomass at the first growth stage into a second prediction model to determine the predicted aboveground biomass of the crop to be predicted at the harvest period, wherein the second prediction model is determined based on historical aboveground biomass of historical crops at the first growth stage and historical aboveground biomass at the harvest period. The harvest index forecast is corrected using the following formula: In the formula, HI refers to the predicted harvest index. This refers to the harvest index correction value; The first growth period refers to the heading-booting period, the second growth period refers to the booting-maturity period, the harvest period is after the second growth period, and the harvest index correction value refers to the ratio between the economic yield and the biological yield of the crop at harvest after correction. Wherein, the first temperature refers to the highest daily temperature of the crop to be predicted during its first growth period, and the second temperature refers to the highest daily temperature of the crop to be predicted during its second growth period.

2. The method for predicting crop yield according to claim 1, characterized in that, The method further includes: Obtain the historical yield values ​​of historical crops for any two historical harvest years and the historical aboveground biomass at harvest time; For each historical harvest year, a historical harvest index for the historical crop in that historical harvest year is determined based on the historical yield value and historical biomass. The first historical high-temperature day with a temperature greater than a preset temperature during the first growth period of each historical harvest year and the second historical high-temperature day with a temperature greater than the preset temperature during the second growth period of the historical crop are determined. Determine the first historical temperature difference between the daily maximum temperature of each first historical high temperature day and the preset temperature, and the second historical temperature difference between the daily maximum temperature of each second historical high temperature day and the preset temperature; Determine a first ratio between the sum of all first historical temperature differences and the total number of first historical high-temperature days, and a second ratio between the sum of all second historical temperature differences and the total number of second historical high-temperature days; A harvest index model is constructed based on the first historical high temperature cumulative temperature, the first historical high temperature impact intensity, the second historical high temperature cumulative temperature, the second historical high temperature impact intensity, and the historical harvest index corresponding to each historical harvest year.

3. The method for predicting crop yield according to claim 1, characterized in that, The predicted output value is determined by formula (2): （2） in, This refers to the predicted yield of the crop to be predicted in year i. This refers to the predicted aboveground biomass of the crop to be predicted at harvest time. This refers to the harvest index correction value of the crop to be predicted in year i.

4. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, the instruction causes the processor to be configured to perform the method for predicting crop yield according to any one of claims 1 to 3.

5. A processor, characterized in that, It is configured to perform the method for predicting crop yield as described in any one of claims 1 to 3.

6. A device for predicting crop yield, characterized in that, The device includes the processor according to claim 5.

Images