Technical method and device for automatically forecasting crop yield, water demand and water consumption based on crop model, weather forecast and assimilation algorithm

Abstract

The invention relates to an automatic forecasting technical method and device for crop yield, water demand and water consumption based on a crop model, weather forecast and an assimilation algorithm, and the method comprises the steps: determining observation data of a leaf area index and target meteorological data from a sowing date to a harvesting date according to an obtained forecasting date and to-be-processed data; updating a crop model according to the target meteorological data and the observation data of the leaf area index to obtain an updated model; and forecasting crop information of the forecasting date through the updating model, wherein the crop information comprises at least one of crop yield, water demand information and water consumption information. According to the embodiment of the invention, the crop model can be updated in real time based on the to-be-processed data of the forecast date, so that the advantages of the crop model on the mechanical description of the crop growth process are fully exerted, and the automatic forecast of crop yield, water demand and water consumption at any forecast date is realized.

Description

Technical Field

[0001] The present disclosure relates to the field of farmland ecology, and in particular to a technical method and device for automatically predicting crop yield, water demand and water consumption based on crop models, weather forecasts and assimilation algorithms. Background Art

[0002] The forecast of crop yield and water requirement is one of the important areas in the study of farmland ecosystems. Accurately estimating the final yield and water requirement of crops during the growing season has important guiding significance for farmland water resources management and the implementation of farmland management measures. Summary of the invention

[0003] In view of this, the present disclosure proposes a technical solution for automatic forecasting of crop yield, water requirement and water consumption based on crop models, weather forecasts and assimilation algorithms.

[0004] According to one aspect of the present disclosure, a forecasting method is provided, the method comprising: obtaining a forecast date and data to be processed, the data to be processed comprising historical meteorological data, weather forecast data, and remote sensing reflectivity data; determining, based on the data to be processed, observation data of a leaf area index and target meteorological data between a sowing date and a harvesting date, the forecast date being any date between the sowing date and the harvesting date; updating a crop model based on the target meteorological data and the observation data of the leaf area index to obtain an updated model; and forecasting crop information of the forecast date using the updated model, the crop information comprising at least one of crop yield, water requirement information, and water consumption information.

[0005] In a possible implementation, target meteorological data between the sowing date and the harvesting date are determined based on the data to be processed, including: determining first meteorological data between the sowing date and the forecast date based on the historical meteorological data and the weather forecast data; determining second meteorological data between the forecast date and the first date based on the weather forecast data, the first date being N days later than the forecast date, where N is a positive integer; predicting third meteorological data between the first date and the harvesting date based on the historical meteorological data and the weather forecast data; and concatenating the first meteorological data, the second meteorological data, and the third meteorological data to obtain target meteorological data between the sowing date and the harvesting date.

[0006] In a possible implementation, the third meteorological data between the first date and the harvest date is predicted based on the historical meteorological data and the weather forecast data, including: determining a historically similar year based on the similarity between the downward shortwave radiation data from the sowing date to the forecast date in the weather forecast data and the downward shortwave radiation data of the same period of each year in the historical meteorological data; determining the same period time period corresponding to the historically similar year based on the first date and the harvest date; and determining the historical meteorological data of the same period time period as the third meteorological data between the first date and the harvest date.

[0007] In a possible implementation, the remote sensing reflectance data includes near-infrared band reflectance and red light band reflectance, and the observation data of the leaf area index is determined based on the data to be processed, including: determining the normalized vegetation index based on the near-infrared band reflectance and the red light band reflectance; determining the wide dynamic vegetation index based on the normalized vegetation index and a preset coefficient; determining the observation data of the leaf area index based on the preset maximum leaf area index of the target crop category, the maximum value of the preset wide dynamic vegetation index, the minimum value of the preset wide dynamic vegetation index, and the wide dynamic vegetation index.

[0008] In one possible implementation, the crop model includes an irrigation simulation unit for simulating irrigation time and irrigation water depth, and the method further includes: in response to the water stress coefficient simulated by the crop model being less than a preset threshold, judging whether the current soil moisture content is lower than the field water holding capacity; when the current soil moisture content is lower than the field water holding capacity and the number of irrigations in a preset time period is less than a preset number, determining the irrigation water depth according to the irrigation type, crop root depth, the soil moisture content, and the field water holding capacity, wherein the irrigation type includes sufficient irrigation, insufficient irrigation, and no irrigation.

[0009] In a possible implementation, the target meteorological data includes wind speed, dew point temperature, air temperature, downward shortwave radiation and precipitation at a first preset distance, and the crop model is updated according to the target meteorological data and the observation data of the leaf area index to obtain an updated model, including: determining driving data of the crop model according to the target meteorological data, the driving data including wind speed, water vapor pressure, air temperature, downward shortwave radiation and precipitation at a second preset distance, the second preset distance is smaller than the first preset distance, and the water vapor pressure is determined based on the dew point temperature; updating the parameters of the crop model according to the driving data, and / or updating the state variables and parameters of the crop model according to the observation data of the leaf area index.

[0010] In a possible implementation, the state variables and parameters of the crop model are updated according to the observed data of the leaf area index, including: using a data assimilation method to synchronously update the state variables and parameters of the crop model according to the observed data of the leaf area index and the state variable augmentation matrix with accompanying parameter updates.

[0011] According to another aspect of the present disclosure, a forecasting device is provided, the device comprising: an acquisition module for acquiring a forecast date and data to be processed, the data to be processed comprising historical meteorological data, weather forecast data, and remote sensing reflectivity data; a determination module for determining, based on the data to be processed, observation data of a leaf area index and target meteorological data between a sowing date and a harvesting date, the forecast date being any date between the sowing date and the harvesting date; an update module for updating a crop model based on the target meteorological data and the observation data of the leaf area index to obtain an updated model; and a forecasting module for forecasting crop information of the forecast date through the updated model, the crop information comprising at least one of crop yield, water demand information, and water consumption information.

[0012] In one possible implementation, the determination module is used to: determine the first meteorological data between the sowing date and the forecast date based on the historical meteorological data and the weather forecast data; determine the second meteorological data between the forecast date and the first date based on the weather forecast data, the first date is N days later than the forecast date, and N is a positive integer; predict the third meteorological data between the first date and the harvest date based on the historical meteorological data and the weather forecast data; and concatenate the first meteorological data, the second meteorological data, and the third meteorological data to obtain the target meteorological data between the sowing date and the harvest date.

[0013] In a possible implementation, the third meteorological data between the first date and the harvest date is predicted based on the historical meteorological data and the weather forecast data, including: determining a historically similar year based on the similarity between the downward shortwave radiation data from the sowing date to the forecast date in the weather forecast data and the downward shortwave radiation data of the same period of each year in the historical meteorological data; determining the same period time period corresponding to the historically similar year based on the first date and the harvest date; and determining the historical meteorological data of the same period time period as the third meteorological data between the first date and the harvest date.

[0014] In a possible implementation, the remote sensing reflectance data includes near-infrared band reflectance and red light band reflectance, and the determination module is used to: determine a normalized vegetation index based on the near-infrared band reflectance and the red light band reflectance; determine a wide dynamic vegetation index based on the normalized vegetation index and a preset coefficient; determine the observation data of the leaf area index based on a preset maximum leaf area index of the target crop category, a maximum value of a preset wide dynamic vegetation index, a minimum value of a preset wide dynamic vegetation index, and the wide dynamic vegetation index.

[0015] In one possible implementation, the crop model includes an irrigation simulation unit for simulating irrigation time and irrigation water depth, and the device is also used to: in response to the water stress coefficient simulated by the crop model being less than a preset threshold, determine whether the current soil moisture content is lower than the field water holding capacity; when the current soil moisture content is lower than the field water holding capacity and the number of irrigations in a preset time period is less than a preset number, determine the irrigation water depth based on the irrigation type, crop root depth, the soil moisture content, and the field water holding capacity, wherein the irrigation type includes sufficient irrigation, insufficient irrigation, and no irrigation.

[0016] In one possible implementation, the update module is used to: determine the driving data of the crop model based on the target meteorological data, the target meteorological data including wind speed, dew point temperature, air temperature, downward shortwave radiation and precipitation at a first preset distance, and the driving data including wind speed, water vapor pressure, air temperature, downward shortwave radiation and precipitation at a second preset distance, the second preset distance is smaller than the first preset distance, and the water vapor pressure is determined based on the dew point temperature; update the parameters of the crop model based on the driving data, and / or update the state variables and parameters of the crop model based on the observation data of the leaf area index.

[0017] In a possible implementation, the state variables and parameters of the crop model are updated according to the observed data of the leaf area index, including: using a data assimilation method to synchronously update the state variables and parameters of the crop model according to the observed data of the leaf area index and the state variable augmentation matrix with accompanying parameter updates.

[0018] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0019] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0020] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0021] In the forecasting method of the embodiment of the present disclosure, the forecast date and the data to be processed can be obtained, and the data to be processed include historical meteorological data, weather forecast data, and remote sensing reflectivity data; according to the data to be processed, the observation data of the leaf area index and the target meteorological data between the sowing date and the harvesting date are determined, and the forecast date is any date between the sowing date and the harvesting date; the crop model is updated according to the target meteorological data and the observation data of the leaf area index to obtain an updated model; the crop information of the forecast date is forecasted by the updated model, and the crop information includes at least one of crop yield, water demand information, and water consumption information. In this way, since the crop model can be updated in real time based on the data to be processed corresponding to the forecast date, the advantage of the crop model in describing the mechanism of the crop growth process is fully utilized, and the automatic forecast of crop yield, water demand and water consumption can be realized on any forecast date without human intervention.

[0022] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0024] Figure 1 A flowchart of a forecasting method according to an embodiment of the present disclosure is shown.

[0025] Figure 2 A schematic diagram showing the prediction of crop yield under different irrigation conditions according to the prediction method of an embodiment of the present disclosure.

[0026] Figure 3 A schematic diagram showing how to forecast irrigation water demand under different irrigation conditions using a forecasting method according to an embodiment of the present disclosure.

[0027] Figure 4 A schematic diagram showing water consumption forecasting under different irrigation conditions using a forecasting method according to an embodiment of the present disclosure.

[0028] Figure 5 A block diagram of a forecasting device according to an embodiment of the present disclosure is shown.

[0029] Figure 6A block diagram of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0030] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0031] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0032] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0033] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0034] In the related technologies, the crop yield and water demand forecasting models are based on the assumptions of empirical formulas, lacking a mechanistic description of the water-carbon flux coupling process during crop growth, which makes it difficult to accurately describe the changes in crop yield and water demand. In addition, the related technologies require a lot of human intervention, such as measuring the growth of crops during growth, manually downloading existing remote sensing satellite products, etc., and cannot achieve automated integrated processing and real-time rolling forecasting effects, which hinders the large-scale, automated operation of forecasting technology and affects the efficiency of forecasting.

[0035] In view of this, in order to give full play to the advantages of crop models in describing the mechanism of crop growth process and realize rolling update forecasts at any time period during the crop growing season without human intervention, Figure 1 FIG. 5 is a flowchart of a forecasting method according to an embodiment of the present disclosure. Figure 1 As shown, the forecasting method includes:

[0036] In step S11, the forecast date and data to be processed are obtained, wherein the data to be processed include historical meteorological data, weather forecast data, and remote sensing reflectivity data;

[0037] In step S12, based on the data to be processed, the observed data of the leaf area index and the target meteorological data between the sowing date and the harvesting date are determined, and the forecast date is any date between the sowing date and the harvesting date;

[0038] In step S13, the crop model is updated according to the target meteorological data and the observation data of the leaf area index to obtain an updated model;

[0039] In step S14, the crop information of the forecast date is forecasted by the updated model, and the crop information includes at least one of crop yield, water demand information, and water consumption information.

[0040] In a possible implementation, the forecasting method of the embodiment of the present disclosure can be performed by an electronic device such as a terminal device or a server. The terminal device can be any fixed or mobile terminal such as a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server can be a single server or a server cluster composed of multiple servers. Any electronic device can implement the forecasting method of the embodiment of the present disclosure by a processor calling a computer-readable instruction stored in a memory.

[0041] In step S11, the forecast date and the data to be processed can be obtained, such as the data to be processed of the current forecast date of the target area, and the data to be processed includes historical meteorological data, weather forecast data, and remote sensing reflectivity data; wherein, the target area can be an irrigation area to be forecasted at any longitude and latitude, and the forecast date can be any current date after the sowing date and before the harvesting date.

[0042] In a possible implementation, historical meteorological data refers to meteorological data for a long period of time before the forecast date, and may include meteorological data from the crop sowing date to the forecast date in the current growing season, as well as meteorological data for a long period of time (e.g., several years, several decades, etc.) before the sowing date. The historical meteorological data may include: wind speed, dew point temperature, air temperature, downward shortwave radiation, and precipitation. Wind speed and dew point temperature may be hourly scale data, and air temperature, downward shortwave radiation, and precipitation may be daily scale data.

[0043] Optionally, the source of historical meteorological data may include meteorological agencies, meteorological service companies, meteorological data open platforms, etc. The embodiments of the present disclosure do not limit the source of historical meteorological data. For example, historical meteorological data can use the application programming interface (API) provided by the meteorological data open platform to achieve automatic data download and obtain the 0.1°×0.1° meteorological reanalysis data set of land surface elements released by the meteorological data open platform.

[0044] In a possible implementation, the weather forecast data may cover all meteorological inputs from the forecast date to a few days after the forecast date (e.g., 10 days after the forecast date), and may include hourly wind speed, downward shortwave radiation, air temperature, dew point temperature, and precipitation. The weather forecast data may be provided by a weather forecast center and may be updated in real time. The embodiments of the present disclosure do not limit the source of the weather forecast data.

[0045] In a possible implementation, the remote sensing reflectance data may be reflectance product data provided by the Moderate Resolution Imaging Spectroradiometer (MODIS) (eg, MOD09Q1.061, with a spatial resolution of 250 m×250 m and a temporal resolution of 8 days).

[0046] In step S12, the observation data of the leaf area index can be determined based on the remote sensing reflectivity data in the acquired data to be processed; and the target meteorological data between the sowing date and the harvesting date can be determined based on the historical meteorological data, weather forecast data, and remote sensing reflectivity data included in the data to be processed.

[0047] Optionally, the Leaf Area Index (LAI), also known as the leaf area coefficient, refers to the multiple of the total area of ​​plant leaves per unit land area to the land area, for example, Leaf Area Index = Total Leaf Area / Land Area. The Leaf Area Index is related to the density and structure (e.g., single layer or multilayer) of the vegetation, the biological properties of trees (e.g., branching angle, leaf attachment angle, shade tolerance, etc.) and environmental conditions (e.g., light, moisture, soil nutrient status, etc.), and is an indicator of the vegetation's utilization of light energy and canopy structure. The remote sensing reflectance data in the data to be processed can be converted into observation data of the leaf area index based on a calibration method measured at the site or a preset neural network model. The embodiments of the present disclosure do not limit the method for determining the observation data of the leaf area index.

[0048] Optionally, the acquired historical meteorological data and weather forecast data can be scaled, and the hourly scale data in the acquired historical meteorological data and weather forecast data can be converted into daily scale data, and the target meteorological data from the sowing date to the first date (e.g., N days after the forecast data) can be determined based on the daily scale historical meteorological data and weather forecast data. And, the meteorological data between the first date and the harvest date can be obtained using the similar historical year method. For example, a time period can be selected (e.g., between the sowing date and the forecast date), and the downward shortwave radiation in the forecast year in this time period is regarded as a vector, and the angle between this vector and the downward shortwave radiation vector in the same period of the historical meteorological data is calculated. The year with the smallest angle is selected as the historical similar year. The historical meteorological data in the same period of the historical similar year can be used as the target meteorological data from the first date to the harvest date.

[0049] In step S13, the crop model can be updated according to the target meteorological data and the observation data of the leaf area index to obtain an updated model. The specific updating method may include trial and error method, data assimilation method, automatic optimization software and other methods to enhance the accuracy and reliability of the crop model. The embodiments of the present disclosure do not limit the updating method of the crop model.

[0050] Among them, the crop model is also called the crop growth simulation model, which uses crop science and agricultural systems science, combined with crop physiological and ecological characteristics, field meteorological conditions, soil physical and chemical conditions, water and fertilizer conditions and other agricultural measures to quantitatively and dynamically simulate crop growth and development, yield formation, and response to different changes in the external environment for different types of crops. The crop model can quantify the crop growth system, different physiological growth processes and their interrelationships, reduce the workload of field experiments, and avoid repeating the same or similar scientific experiments in different test areas.

[0051] For example, the crop model can be a dynamic explanatory model that can simulate the target crop on a daily basis and simulate the growth and development process of the target crop under potential meteorological, soil, water and nutrient conditions.

[0052] In step S14, crop information is forecasted by updating the model, and the crop information may include at least one of crop yield, water requirement information, and water consumption information corresponding to any forecast date.

[0053] Optionally, the disclosed embodiment may integrate automated processing technology to reduce the cost of human intervention. Users only need to customize the forecast date, and the pre-written program code can automatically download and process historical meteorological data, weather forecast data, and remote sensing reflectivity data, and automatically run crop models and model update methods such as data assimilation based on the above data to achieve automated forecasts of crop yield, water demand, and water consumption.

[0054] Through steps S11 to S14, since the crop model can be updated in real time according to the pending data corresponding to the forecast date, the advantage of the crop model in describing the mechanistic nature of the crop growth process can be fully utilized, and automatic forecasts of crop yield, water demand and water consumption can be achieved on any forecast date without human intervention.

[0055] The following is an exemplary description of the forecasting method in the embodiment of the present disclosure.

[0056] Assume that a winter wheat experimental farmland in a certain area is selected, the sowing date is October 20, 2023, the forecast date is set to May 3, 2024, and the harvest date is set to June 15, 2024. In step S11, the meteorological data can be automatically downloaded using the meteorological data loading program written in the scripting language Python through the API provided by the meteorological data open source platform. The acquired historical meteorological data may include historical long-term meteorological data (for example, 1950 to 2023), and the acquired weather forecast data may include meteorological data between the sowing date and N days after the forecast date (for example, October 10, 2023 to May 13, 2024).

[0057] The meteorological data corresponding to the historical meteorological data may include hourly wind speed and dew point temperature data, daily temperature, downward shortwave radiation and precipitation data. The meteorological data corresponding to the weather forecast data may include hourly wind speed, dew point temperature data, temperature, downward shortwave radiation and precipitation data.

[0058] Synchronously, in step S11, a remote sensing data loading program written in the sample language Python can be used to automatically retrieve available remote sensing reflectance data between the sowing date and the forecast date. The remote sensing reflectance data may include the reflectance of the red light band (620-670nm) and the reflectance of the near infrared band (841-876nm).

[0059] In a possible implementation, in step S12, determining the target meteorological data between the sowing date and the harvesting date based on the data to be processed may include: determining the first meteorological data between the sowing date and the forecast date based on the historical meteorological data and the weather forecast data; determining the second meteorological data between the forecast date and the first date based on the weather forecast data, the first date being N days later than the forecast date, where N is a positive integer; predicting the third meteorological data between the first date and the harvesting date based on the historical meteorological data and the weather forecast data; and concatenating the first meteorological data, the second meteorological data, and the third meteorological data to obtain the target meteorological data between the sowing date and the harvesting date.

[0060] For example, assuming the forecast date is May 3, 2024, the first date is May 13, 2024, which is 10 days later than the forecast date May 3, 2024 (for example, N=10), which is the latest date that the weather forecast can predict. The sowing date is October 20, 2023, and the harvesting date is June 15, 2024.

[0061] In this scenario, the historical meteorological data are the real meteorological data recorded from January 1, 1950 to May 3, 2024, among which wind speed and dew point temperature can be hourly scale data, and air temperature, downward shortwave radiation, and precipitation can be daily scale data;

[0062] Weather forecast data are the predicted meteorological data recorded from October 20, 2023 to May 13, 2024, among which wind speed, downward shortwave radiation, air temperature, dew point temperature and precipitation can be on an hourly scale;

[0063] The remote sensing reflectance data is a collection of data collected by a moderate resolution imaging spectrometer from January 1, 1950 to May 3, 2024. For example, data may be collected every 8 days.

[0064] Among them, since there are hourly scale data and daily scale data in historical meteorological data and weather forecast data, in order to facilitate calculation, the hourly scale data in the two can be upscaled to daily scale data. For example, the dew point temperature at the hourly scale can be averaged, and the average dew point temperature can be used as the dew point temperature at the daily scale; for another example, the wind speed at the hourly scale can be averaged, and the average wind speed can be used as the wind speed at the daily scale; for another example, the downward shortwave radiation at the hourly scale can be summed, and the summed result can be used as the downward shortwave radiation at the daily scale; for another example, the precipitation at the hourly scale can be summed, and the summed result can be used as the precipitation at the daily scale; for another example, the maximum and minimum values ​​of the temperature at the hourly scale can be taken, and the temperature range obtained by the maximum and minimum values ​​can be used as the temperature at the daily scale.

[0065] Since there are both historical meteorological data and weather forecast data in the period from October 20, 2023 to May 3, 2024, the real meteorological data from October 20, 2023 to May 3, 2024 can be extracted from the historical meteorological data, and the predicted meteorological data from October 20, 2023 to May 3, 2024 can be extracted from the weather forecast data. Then, the historical meteorological data and weather forecast data from October 20, 2023 to May 3, 2024 can be weighted summed to obtain the first meteorological data from the sowing date of October 20, 2023 to the forecast date of May 3, 2024.

[0066] Since the period from May 3, 2024 to May 13, 2024 is a future period after the forecast date, there is no historical meteorological data, and the weather forecast data for the period from May 3, 2024 to May 13, 2024 can be directly used as the second meteorological data. Among them, May 13, 2024 is the first date, which is 10 days later than the forecast date (N=10). The specific time of the first date can be determined by the latest number of days N predicted by the weather forecast data in the future. The embodiments of the present disclosure do not limit the specific values ​​of N and the first date, and can be set according to the actual application scenario.

[0067] Since there is neither historical meteorological data nor weather forecast data from May 13, 2024 to June 15, 2024, the third meteorological data between the first date May 13, 2024 and the harvest date June 15, 2024 can be predicted based on the historical meteorological data and weather forecast data.

[0068] In a possible implementation, the third meteorological data between the first date and the harvest date is predicted based on the historical meteorological data and the weather forecast data, including: determining a historically similar year based on the similarity between the downward shortwave radiation data from the sowing date to the forecast date in the weather forecast data and the downward shortwave radiation data of the same period of each year in the historical meteorological data; determining the same period time period corresponding to the historically similar year based on the first date and the harvest date; and determining the historical meteorological data of the same period time period as the third meteorological data between the first date and the harvest date.

[0069] For example, a long series of historical meteorological data can be obtained, and the third meteorological data between the first date and the harvest date can be predicted using the similar historical year method. In the example, assuming that the harvest date of winter wheat is June 15, 2024, the meteorological data time period obtained by the similar historical year method is May 13, 2024 to June 15, 2024.

[0070] Specifically, the data for the period from October 20, 2023 to May 3, 2024 can be extracted from the downward shortwave radiation data of the weather forecast data, and the downward shortwave radiation data in this time period can be regarded as vector a. Vector a can represent the downward shortwave radiation in the forecast year, and the angle θ between vector a and the downward shortwave radiation vector b in the same period (October 20 to May 3) in the historical meteorological data period (1950 to 2023) is calculated, and the year with the smallest angle θ is selected as the historical similarity year.

[0071]

[0072] Among them, θ is the angle between vector a and vector b; vector a represents the downward shortwave radiation vector of the forecast year, and b represents the downward shortwave radiation vector of the historical year.

[0073] In the example, it is assumed that the smallest angle θ comes from 2011, that is, the angle θ between the downward shortwave radiation vector from October 20, 2010 to May 3, 2011 in the historical meteorological data and the downward shortwave radiation vector from October 20, 2023 to May 3, 2024 is the smallest, and the two are most similar. Therefore, the historical meteorological data from May 13, 2011 to June 15, 2011 can be used as the third meteorological data from May 13, 2024 to June 15, 2024.

[0074] By splicing the first meteorological data from the sowing date October 20, 2023 to the forecast date May 3, 2024, the second meteorological data from the forecast date May 3, 2024 to the first date May 13, 2024, and the third meteorological data from the first date May 13, 2024 to the harvesting date June 15, 2024, we can obtain the target meteorological data between the sowing date October 20, 2023 and the harvesting date June 15, 2024.

[0075] In this way, as long as the user customizes the forecast date, the forecast method of the disclosed embodiment can automatically download and process historical meteorological data, weather forecast data and remote sensing reflectivity data, and accurately derive the target meteorological data from the sowing date to the harvesting date based on the above data, which is conducive to the subsequent automatic operation of the crop model and data assimilation algorithm, and realizes accurate forecasting of crop yield, water demand and water consumption.

[0076] In a possible implementation, in step S12, the remote sensing reflectance data includes near-infrared band reflectance and red light band reflectance, and the observation data of the leaf area index is determined according to the data to be processed, including: determining the normalized vegetation index according to the near-infrared band reflectance and the red light band reflectance; determining the wide dynamic vegetation index according to the normalized vegetation index and a preset coefficient; determining the observation data of the leaf area index according to the preset maximum leaf area index of the target crop category, the maximum value of the preset wide dynamic vegetation index, the minimum value of the preset wide dynamic vegetation index, and the wide dynamic vegetation index.

[0077] Exemplarily, the ground near-infrared band reflectivity and red light band reflectivity obtained in step S11 can be used to calculate the leaf area index of the crop.

[0078] For example, the normalized vegetation index can be determined based on the near-infrared band reflectance and red light band reflectance contained in the remote sensing reflectance data, that is:

[0079]

[0080] In formula (2), NIR represents the reflectance of the near infrared band, R represents the reflectance of the red light band, and NDVI represents the normalized vegetation index. The normalized vegetation index NDVI is the ratio of the difference and sum of the near infrared band reflectance NIR and the red light band reflectance R. The normalized vegetation index can be used to detect vegetation growth status, vegetation coverage, and eliminate some radiation errors.

[0081] The normalized difference vegetation index NDVI is determined by formula (2), and the wide dynamic range vegetation index WDRVI can be determined according to the normalized difference vegetation index NDVI and the preset coefficient α, that is:

[0082]

[0083] In formula (3), WDRVI represents the wide dynamic range vegetation index, NDVI represents the normalized difference vegetation index, and α represents a preset empirical coefficient, for example, α is 0.2. The embodiment of the present disclosure does not limit the specific value of the empirical coefficient α, and it can be set according to the actual application scenario. In this way, by enhancing the dynamic range and using the same band as the normalized difference vegetation index NDVI, the wide dynamic range vegetation index WDRVI can more reliably characterize the physiological and phenological characteristics of crops.

[0084] The wide dynamic range vegetation index WDRVI is determined by formula (3), which can be calculated based on the preset maximum leaf area index LAI of the target crop category. max , preset the maximum value of wide dynamic vegetation index WDRVI max , preset the minimum value of wide dynamic vegetation index WDRVI min , the wide dynamic vegetation index WDRVI, determines the observation data LAI of the leaf area index, namely:

[0085]

[0086] In formula (4), the maximum value of the wide dynamic vegetation index WDRVI is preset max , is the maximum value of the wide dynamic range vegetation index WDRVI calculated from the maximum value of the normalized difference vegetation index NDVI. For example, take WDRVI max It is 0.4776.

[0087] Preset minimum value of wide dynamic vegetation index WDRVI min , is the minimum value of the wide dynamic range vegetation index WDRVI calculated from the minimum value of the normalized difference vegetation index NDVI. For example, take WDRVI max It is -0.6090.

[0088] Preset maximum leaf area index LAI maxIndicates the influencing factor of the type of crops planted. The value can change according to the different crops planted. Specifically, land use data can be obtained to determine the types of crops planted in the study area based on the land use data. For example, if the target crop in the study area is winter wheat, LAI max The value can be 7.0cm 2 / cm 2 .

[0089] In this way, the remote sensing reflectance data can be converted into an indicator reflecting the growth status of the crop canopy, namely, the leaf area index, based on the calibration method of the site measurement. The latest leaf area index (for example, the leaf area index closest to the forecast date) obtained by processing formula (2) to formula (4) will be assimilated into the crop model as an observation value.

[0090] In a possible implementation, in step S13, the target meteorological data includes wind speed, dew point temperature, air temperature, downward shortwave radiation and precipitation at a first preset distance, and the crop model is updated according to the target meteorological data and the observation data of the leaf area index to obtain an updated model, including: determining driving data of the crop model according to the target meteorological data, the driving data including wind speed, water vapor pressure, air temperature, downward shortwave radiation and precipitation at a second preset distance, the second preset distance is smaller than the first preset distance, and the water vapor pressure is determined based on the dew point temperature; updating the parameters of the crop model according to the driving data, and / or updating the state variables and parameters of the crop model according to the observation data of the leaf area index.

[0091] Among them, the state variable is a state quantity output in the crop model, such as the leaf area index output by the crop model, which changes with time and is related to the value at the previous moment. The parameter refers to at least one of the multiple parameters input into the crop model, such as crop parameters, soil parameters, farmland management parameters, etc.

[0092] For example, assuming that the first preset distance is 10 meters and the second preset distance is 2 meters, the wind speed at 10 meters in the driving data can be determined according to the wind speed at 2 meters included in the target meteorological data, that is:

[0093] W 2 =0.74795×W 10 (5)

[0094] Among them, W 2 Indicates the wind speed at 2 meters above the ground (m / s), W 10It indicates the wind speed (m / s) at 10 meters from the ground surface. It should be understood that the embodiments of the present disclosure are only arranged with the first preset distance being 10 meters and the second preset distance being 2 meters, wherein the second preset distance is smaller than the first preset distance, the first preset distance can be determined by the acquired meteorological data, and the second preset distance can be determined by the crop height, and the first preset distance and the second preset distance can be specifically set according to the actual application scenario, and the embodiments of the present disclosure do not impose specific restrictions on this.

[0095] The water vapor pressure in the driving data can be calculated from the dew point temperature of the target meteorological data, that is:

[0096]

[0097] Where VP represents the water vapor pressure (Pa) in the driving data; T d Indicates the dew point temperature (°C) in the target weather data.

[0098] In this way, the wind speed at the first preset distance from the ground in the target meteorological data can be replaced by the wind speed at the second preset distance from the ground, the dew point temperature in the target meteorological data can be replaced by the water vapor pressure, and the air temperature, downward shortwave radiation and precipitation in the target meteorological data can be retained, so that the driving data used to update the crop model in real time can be obtained. For example, whenever the forecast date changes, the corresponding driving data will also change, so that the crop model can be updated with the latest driving data so that the crop model can more accurately predict crop information.

[0099] In a possible implementation, the crop model is constructed based on driving data, crop growth parameter files, soil parameter files, and farmland management files. The crop growth parameter files are used to provide crop growth parameters (such as accumulated temperature, specific leaf area, maximum carbon assimilation rate, etc.) for the crop model; the soil parameter files are used to provide soil parameters (such as saturated moisture content, initial moisture content, etc.) for the crop model; and the farmland management files are used to provide farmland management parameters (such as sowing / germination date, harvest date, irrigation date, water depth, etc.) for the crop model.

[0100] In a possible implementation, the crop model includes an irrigation simulation unit for simulating irrigation time and irrigation water depth, and the method further includes: in response to the water stress coefficient simulated by the crop model being less than a preset threshold, determining whether the current soil moisture content is lower than the field water holding capacity; when the current soil moisture content is lower than the field water holding capacity and the number of irrigations in the preset time period is less than the preset number, determining the irrigation water depth according to the irrigation type, the crop root depth, the soil moisture content, and the field water holding capacity, wherein the irrigation type includes sufficient irrigation, insufficient irrigation, and no irrigation. For example, sufficient irrigation is 100% irrigation, no irrigation is 0% irrigation, and insufficient irrigation is any other proportion of irrigation other than 100% and 0%.

[0101] In the example, the crop model WOFOST (World Food Studies) can be used, which can simulate the growth and evapotranspiration of the target crop. An irrigation simulation unit can be added to the crop model to simulate and predict the irrigation water requirement of the target crop, for example, including simulating and predicting the irrigation time and irrigation water depth.

[0102] Optionally, for the simulation of irrigation time, a preset threshold α can be set as a water stress threshold (also called an irrigation threshold). When the water stress coefficient simulated in the crop model on a certain day is lower than α, irrigation is triggered, and when it is greater than or equal to α, no irrigation is performed. In the example, the preset threshold α can be taken as 0.90. Irrigation can be triggered only when the water stress coefficient simulated by the crop model is lower than 0.90, and the amount of irrigation after the irrigation is triggered needs to be judged later.

[0103] Optionally, for the simulation of irrigation depth, when irrigation is triggered, it can be determined whether the current soil moisture content θ is lower than the field water holding capacity θ fc , when soil moisture content θ ≥ field water holding capacity θ fc When the soil moisture content θ < field water holding capacity θ fc Irrigation is needed at this time. The irrigation water depth I (cm) on that day can be expressed as:

[0104] I=IC×RD×(θ fc -θ) (7)

[0105] Among them, IC is a value between 0 and 1, indicating different irrigation types. For example, IC is 1 when fully irrigated, 0.5 when 50% insufficient irrigation, and 0 when no irrigation; RD represents the crop root depth (cm) of the day, which is calculated from the crop model; the soil moisture content θ is given by the crop model simulation results; in the example, it is assumed that the field water holding capacity θ fcAccording to the actual measured value of the site, it is taken as 0.30. It can provide crop yield and water demand forecasts under three different actual irrigation needs, namely, full irrigation (completely sufficient irrigation, IC = 1), 50% insufficient irrigation (only irrigated to 50% of the sufficient irrigation, IC = 0.5) and no irrigation (no irrigation, IC = 0).

[0106] In order to better meet actual needs, the number of irrigations can be limited. For example, when the current soil moisture content θ is lower than the field water holding capacity θ fc , and the number of irrigations in the preset time period is less than the preset number, the irrigation water depth I is determined according to formula (7).

[0107] For example, winter wheat will be irrigated at most once between the greening stage (e.g., in late February or early March) and the jointing stage (e.g., in mid-April), and the preset number of irrigations during this period can be set to 1; winter wheat will also be irrigated at most once between the jointing stage and the maturity stage (e.g., in late May or early June), and the preset number of irrigations during this period can also be set to 1. In this way, the following restrictions can be imposed in the crop model: there is at most one irrigation between February 20 and April 15, and at most one irrigation between April 16 and June 1.

[0108] In this way, the disclosed embodiment modifies the crop model and adds a simulation unit for irrigation water demand. The simulation unit can realize the forecast of crop yield, water demand and water consumption under different irrigation conditions (such as sufficient irrigation, insufficient irrigation and no irrigation, etc.), which is more in line with the actual situation of the irrigation area and can provide a scientific basis for agricultural water management and farmland decision-making.

[0109] In a possible implementation, after the crop model is constructed, the driving data corresponding to the current forecast date may be input into the crop model, and the parameters of the crop model may be updated using the driving data to obtain an updated crop model.

[0110] In a possible implementation, the state variables and parameters of the crop model are updated according to the observed data of the leaf area index, including: using a data assimilation method to update the state variables and parameters of the crop model according to the observed data of the leaf area index and an augmented matrix of state variables with accompanying parameter updates.

[0111] For example, data assimilation refers to a method of integrating new observation data during the dynamic operation of the crop model while considering the errors in the observation data and prediction data of the leaf area index. Within the forecast framework of the crop model, the state variables of the crop model (such as the state variables output by the crop model for representing the leaf area index) can be assimilated by continuously integrating direct or indirect observation data of different sources and different resolutions with discrete distribution in time and space through the data assimilation algorithm, and the parameters of the crop model can be automatically adjusted to improve the estimation accuracy of the state variables output by the crop model and improve the prediction ability of the crop model.

[0112] Among them, the assimilation algorithm may include sequential data assimilation method (such as Kalman filter method, ensemble Kalman filter method, particle filter method, etc.) and continuous data assimilation method. The embodiments of the present disclosure do not limit the category of the assimilation algorithm.

[0113] Optionally, assuming that the data assimilation method adopts the ensemble Kalman filter method (EnKF), the ensemble Kalman filter method and the crop model can be combined with the state variable augmented matrix method with parameter update to achieve the synchronous update of the model state variables and parameters. The specific formula is as follows:

[0114] K=PH T (HPH T +R) -1 (8)

[0115]

[0116] In the example, formula (8) and formula (9) can represent the update process of the ensemble Kalman filter method, and the observed value at the current moment can be used to correct the predicted (prior) value to obtain the analyzed (posterior) value at the current moment. represents the posterior state variable matrix of leaf area index; represents the prior state variable matrix of leaf area index; y t,i The observed variable matrix y representing the leaf area index can be determined based on formulas (2) to (4): t,i ; The superscript a represents the analysis (posterior) value, and the superscript f represents the prediction (prior) value; t represents the tth time step; i represents the i-th crop model in the crop model set, and the model parameters of each crop model (such as crop growth parameters, soil parameters, and farmland management parameters) can be fine-tuned; K is the Kalman gain matrix; P is the covariance matrix of the prior state variables of the leaf area index; H is the conversion matrix between the state variables of the leaf area index and the observed values; R represents the covariance matrix of the observed variables.

[0117] It can be seen from formula (8) and formula (9) that in the calculation process, the data assimilation method can comprehensively consider the errors between the simulation results output by the crop model and the leaf area index observation data based on remote sensing reflectance data.

[0118] In practical applications, if the understanding of the intrinsic mechanism of target crop growth is not very complete, as the crop model is driven, it will be affected by the imperfect calibration of crop parameters, and the error accumulation will gradually increase. The correction of the crop model simulation process by introducing the assimilation algorithm is not accurate and reliable enough.

[0119] In order to further improve the accuracy and reliability of crop model forecasting, formula (10) can be used in combination with the state variable augmented matrix method with parameter update to achieve synchronous update of model state variables and parameters.

[0120] In formula (10), β i represents the parameter matrix, represents the state variable augmentation matrix with the parameter matrix β, H x represents the identity matrix, H * Representation and The matching transformation matrix can be substituted into formula (7) and formula (8) to obtain H=H * , realizing sequential assimilation of ensemble Kalman filter based on accompanying parameter update, synchronously updating state variables and parameters of crop model, and improving the accuracy of crop model forecast.

[0121] It should be understood that the parameters selected in this example may include: wilting coefficient (SMW), accumulated temperature from germination to flowering stage (TSUM1) and leaf physiological cycle (SPAN) at 35°C, and the embodiments of the present disclosure are not limited to this. Regarding other data assimilation methods with parameter updates such as particle filtering, reference may be made to the ensemble Kalman filter method with parameter updates illustrated in the above formulas (8) to (10), which will not be described in detail here.

[0122] The ensemble Kalman filter method with parameter update can realize real-time update of remote sensing observations. This data assimilation method with parameter update can also synchronously update the state variables and parameters of the crop model, improving the accuracy of crop model forecasting.

[0123] In a possible implementation, the crop model may also include an automated forecasting module for automated forecasting simulation of crop yield and water requirement (evapotranspiration and irrigation), allowing user-defined variables as shown in the following table:

[0124] Table 1

[0125]

[0126] In this way, the user can customize the longitude and latitude of the forecast area, the forecast date, the model parameters, etc. After the user completes the customization according to Table 1, the program code written according to the forecasting method of the embodiment of the present disclosure can be run to realize the forecast of crop yield and water demand (evapotranspiration and irrigation water demand) in a given area.

[0127] In this way, the forecasting method of the embodiment of the present disclosure can support richer user-defined items, including the latitude and longitude coordinates of the simulation area, forecast date, modified model parameters, etc., thereby enhancing the robustness and applicability of the forecasting method.

[0128] In step S14, crop information may be forecasted by updating the model, and the crop information may include at least one of crop yield, water requirement information, and water consumption information corresponding to any forecast date.

[0129] Figure 2 A schematic diagram showing crop yield prediction under different irrigation conditions according to a prediction method according to an embodiment of the present disclosure is shown as follows: Figure 2 As shown, for crop yield, under sufficient irrigation, insufficient irrigation (eg 50% insufficient irrigation) and no irrigation conditions, the predicted results are 487 kg / mu, 482 kg / mu and 403 kg / mu respectively.

[0130] Figure 3 A schematic diagram showing how the forecasting method according to an embodiment of the present disclosure forecasts irrigation water demand under different irrigation conditions is shown in FIG. Figure 3 As shown, for crop water demand information, the predicted irrigation date is May 8, the sufficient irrigation volume is 78 cubic meters per mu, and the insufficient irrigation volume is 39 cubic meters per mu.

[0131] Figure 4 A schematic diagram showing water consumption forecasting under different irrigation conditions according to the forecasting method of an embodiment of the present disclosure is shown as follows: Figure 4 As shown, for crop water consumption information (evapotranspiration), under sufficient irrigation, insufficient irrigation and no irrigation conditions, the predicted results are 324 mm, 313 mm and 290 mm respectively.

[0132] It can be seen that the embodiments of the present disclosure can accurately predict the yield, irrigation water requirement and water consumption at the end of the crop growing season according to the established region and forecast date within the crop growing season, and can provide forecast results under different irrigation conditions to meet actual agricultural water management needs.

[0133] The disclosed embodiment can be based on crop models, weather forecast data and data assimilation methods to simultaneously forecast crop yield, water demand and water consumption, and realize automatic forecasting of the final yield of target crops, irrigation water demand (including irrigation time and irrigation water depth) and total crop water consumption (evapotranspiration) during the growing season. Among them, through the automatic processing of historical meteorological data, weather forecast data and remote sensing reflectivity data, combined with the crop model and the data assimilation method framework of the ensemble Kalman filter method with parameter updates, the forecast of the final yield at the end of the season, irrigation water demand and total water consumption (evapotranspiration) can be realized within the crop growing season. The disclosed embodiment also provides different assimilation algorithms and forecast simulations under different irrigation conditions.

[0134] In addition, the disclosed embodiments can use automation technology to closely combine crop models with remote sensing observations through data assimilation methods, and make full use of remote sensing observation information to synchronously update the state variables of the crop model (for example, the state variables output by the crop model to represent the leaf area index) and other model parameters, thereby increasing the reliability of the crop model forecast results. This integrated automated forecasting framework achieves fully automated forecasts of crop yield, water demand, and water consumption on a given forecast date, reducing the cost of human intervention. Simultaneously, the forecasting method of the disclosed embodiments also supports forecast simulations under different irrigation conditions, which is more in line with the actual needs of the irrigation area and can provide a scientific basis for agricultural water management and decision-making.

[0135] Figure 5 A block diagram of a forecasting device according to an embodiment of the present disclosure is shown as follows: Figure 5 As shown, the device comprises:

[0136] An acquisition module 51 is used to acquire a forecast date and data to be processed, wherein the data to be processed includes historical meteorological data, weather forecast data, and remote sensing reflectivity data;

[0137] A determination module 52 is used to determine the observed data of the leaf area index and the target meteorological data between the sowing date and the harvesting date according to the data to be processed, wherein the forecast date is any date between the sowing date and the harvesting date;

[0138] An updating module 53, used for updating the crop model according to the target meteorological data and the observation data of the leaf area index to obtain an updated model;

[0139] The forecasting module 54 is used to forecast the crop information of the forecast date by using the updated model, wherein the crop information includes at least one of crop yield, water requirement information, and water consumption information.

[0140] In one possible implementation, the determination module 52 is used to: determine the first meteorological data between the sowing date and the forecast date based on the historical meteorological data and the weather forecast data; determine the second meteorological data between the forecast date and the first date based on the weather forecast data, the first date being N days later than the forecast date, where N is a positive integer; predict the third meteorological data between the first date and the harvest date based on the historical meteorological data and the weather forecast data; and concatenate the first meteorological data, the second meteorological data, and the third meteorological data to obtain the target meteorological data between the sowing date and the harvest date.

[0141] In a possible implementation, the third meteorological data from the first date to the harvest date is predicted based on the historical meteorological data and the weather forecast data, including: determining a historically similar year based on the similarity between the downward shortwave radiation from the sowing date to the forecast date in the weather forecast data and the downward shortwave radiation in the same period of each year in the historical meteorological data; determining the same period time period corresponding to the historically similar year based on the first date and the harvest date; and determining the historical meteorological data for the same period time period as the third meteorological data from the first date to the harvest date.

[0142] In a possible implementation, the remote sensing reflectance data includes near-infrared band reflectance and red light band reflectance, and the determination module 52 is used to: determine the normalized vegetation index based on the near-infrared band reflectance and the red light band reflectance; determine the wide dynamic vegetation index based on the normalized vegetation index and a preset coefficient; determine the observation data of the leaf area index based on the preset maximum leaf area index of the target crop category, the maximum value of the preset wide dynamic vegetation index, the minimum value of the preset wide dynamic vegetation index, and the wide dynamic vegetation index.

[0143] In one possible implementation, the crop model includes an irrigation simulation unit for simulating irrigation time and irrigation water depth, and the device is also used to: in response to the water stress coefficient simulated by the crop model being less than a preset threshold, determine whether the current soil moisture content is lower than the field water holding capacity; when the current soil moisture content is lower than the field water holding capacity and the number of irrigations in a preset time period is less than a preset number, determine the irrigation water depth based on the irrigation type, crop root depth, the soil moisture content, and the field water holding capacity, wherein the irrigation type includes sufficient irrigation, insufficient irrigation, and no irrigation.

[0144] In one possible implementation, the update module 53 is used to: determine the driving data of the crop model based on the target meteorological data, the target meteorological data including the wind speed, dew point temperature, air temperature, downward shortwave radiation and precipitation at a first preset distance, and the driving data including the wind speed, water vapor pressure, air temperature, downward shortwave radiation and precipitation at a second preset distance, the second preset distance is smaller than the first preset distance, and the water vapor pressure is determined based on the dew point temperature; update the parameters of the crop model based on the driving data, and / or update the state variables and parameters of the crop model based on the observation data of the leaf area index.

[0145] In a possible implementation, the state variables and parameters of the crop model are updated according to the observed data of the leaf area index, including: using a data assimilation method to synchronously update the state variables and parameters of the crop model according to the observed data of the leaf area index and the state variable augmentation matrix with accompanying parameter updates.

[0146] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0147] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0148] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0149] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0150] Figure 6 1 is a block diagram showing an electronic device according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Figure 6, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0151] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0152] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0153] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0154] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0155] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0156] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0157] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0158] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0159] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0160] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0161] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A forecasting method, characterized in that: The method comprises: Obtaining forecast date and data to be processed, wherein the data to be processed includes historical meteorological data, weather forecast data, and remote sensing reflectivity data; Determine the observed data of the leaf area index and the target meteorological data between the sowing date and the harvesting date according to the data to be processed, wherein the forecast date is any date between the sowing date and the harvesting date; updating the crop model according to the target meteorological data and the observation data of the leaf area index to obtain an updated model; The crop information of the forecast date is forecasted by the updated model, wherein the crop information includes at least one of crop yield, water demand information, and water consumption information.

2. The method according to claim 1, characterized in that Determine the target meteorological data from the sowing date to the harvesting date according to the data to be processed, including: Determine first meteorological data between a sowing date and a forecast date according to the historical meteorological data and the weather forecast data; Determine, according to the weather forecast data, second meteorological data between the forecast date and a first date, wherein the first date is N days later than the forecast date, where N is a positive integer; Predicting third meteorological data from the first date to the harvest date based on the historical meteorological data and the weather forecast data; The first meteorological data, the second meteorological data, and the third meteorological data are spliced ​​to obtain target meteorological data between the sowing date and the harvesting date.

3. The method according to claim 2, characterized in that Predicting third meteorological data from the first date to the harvest date based on the historical meteorological data and the weather forecast data, including: Determine a historical similar year based on the similarity between the downward shortwave radiation data from the sowing date to the forecast date in the weather forecast data and the downward shortwave radiation data of the same period of each year in the historical meteorological data; Determining the same period of time corresponding to the historically similar year according to the first date and the harvest date; The historical meteorological data for the same period of time is determined as the third meteorological data between the first date and the harvest date.

4. The method according to claim 1, characterized in that: The remote sensing reflectance data includes near infrared band reflectance and red light band reflectance. According to the data to be processed, the observation data of the leaf area index is determined, including: Determining a normalized vegetation index according to the near-infrared band reflectance and the red light band reflectance; Determining a wide dynamic vegetation index according to the normalized vegetation index and a preset coefficient; The observation data of the leaf area index is determined according to the preset maximum leaf area index of the target crop category, the maximum value of the preset wide dynamic vegetation index, the minimum value of the preset wide dynamic vegetation index, and the wide dynamic vegetation index.

5. The method according to claim 1, characterized in that The crop model includes an irrigation simulation unit for simulating irrigation time and irrigation water depth, and the method further includes: In response to the water stress coefficient simulated by the crop model being less than a preset threshold, determining whether the current soil moisture content is lower than the field water holding capacity; When the current soil moisture content is lower than the field water holding capacity and the number of irrigations in the preset time period is less than the preset number, the irrigation water depth is determined according to the irrigation type, crop root depth, the soil moisture content, and the field water holding capacity, wherein the irrigation type includes sufficient irrigation, insufficient irrigation, and no irrigation.

6. The method according to claim 1, characterized in that The target meteorological data includes wind speed, dew point temperature, air temperature, downward shortwave radiation and precipitation at a first preset distance. The crop model is updated according to the target meteorological data and the observation data of the leaf area index to obtain an updated model, including: determining driving data of the crop model according to the target meteorological data, the driving data comprising wind speed, water vapor pressure, air temperature, downward shortwave radiation and precipitation at a second preset distance, the second preset distance being smaller than the first preset distance, the water vapor pressure being determined based on the dew point temperature; The parameters of the crop model are updated according to the driving data, and / or the state variables and parameters of the crop model are updated according to the observation data of the leaf area index.

7. The method according to claim 6, characterized in that Updating the state variables and parameters of the crop model according to the observed data of the leaf area index includes: By using the data assimilation method, the state variables and parameters of the crop model are synchronously updated according to the observed data of the leaf area index and the state variable augmented matrix with parameter updates.

8. A forecasting device, characterized in that: The device comprises: An acquisition module, used to acquire the forecast date and data to be processed, wherein the data to be processed includes historical meteorological data, weather forecast data, and remote sensing reflectivity data; A determination module, used for determining the observed data of the leaf area index and the target meteorological data between the sowing date and the harvesting date according to the data to be processed, wherein the forecast date is any date between the sowing date and the harvesting date; An updating module, used for updating the crop model according to the target meteorological data and the observation data of the leaf area index to obtain an updated model; A forecasting module is used to forecast the crop information of the forecast date through the updated model, wherein the crop information includes at least one of crop yield, water demand information, and water consumption information.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 7 when executing the instructions stored in the memory.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images