Intelligent irrigation dynamic decision-making method and equipment

Abstract

The invention relates to the technical field of agricultural irrigation, in particular to an intelligent irrigation dynamic decision-making method and equipment, and constructs an intelligent irrigation fuzzy reasoning and dynamic decision-making method by fusing multi-source remote sensing data and rainfall data and combining water demand characteristics of crops in different growth stages. It can be understood that the method is based on regularly updated remote sensing data, the moisture state of crops is dynamically monitored, and plot-level irrigation decision suggestions are generated. A manager can scientifically formulate an irrigation strategy according to suggestions in combination with the local actual water resource condition and the irrigation system, precise irrigation regulation and control are achieved, and the irrigation efficiency and decision scientificity are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural irrigation, and particularly relates to an intelligent irrigation dynamic decision-making method and device. Background Art

[0002] Intelligent irrigation decision-making technology is of crucial significance for improving water resource utilization efficiency, ensuring crop growth, and increasing agricultural yields. However, there are many limitations in the current existing intelligent irrigation decision-making technologies.

[0003] The current intelligent irrigation decision-making technologies mainly include: irrigation decision-making technology based on soil moisture data: By monitoring the change of soil moisture through sensors and combining with the water requirement law of crops to generate irrigation decision results. Irrigation decision-making technology based on crop growth models and weather forecasts: Based on crop growth models, simulating the water requirements and growth status of crops at different stages, and combining with meteorological data to generate irrigation decision results. Irrigation decision-making technology based on remote sensing data: Based on the spectral information of unmanned aerial vehicle (UAV) remote sensing images and measured moisture data, identifying water deficit areas to generate irrigation decisions; calculating a single index (such as NDVI) based on satellite remote sensing data and combining with the surface energy balance model to predict water consumption and then generate irrigation decisions.

[0004] However, the above intelligent irrigation decision-making technologies generally have the following problems: Poor adaptability: For the irrigation decision-making technology based on soil moisture data, the soil moisture data monitored by the sensor can only reflect the single-point situation and is difficult to represent the moisture condition of the entire field. There are huge differences in water retention, water permeability and other characteristics among different soil types, and the spatial scale of the field varies greatly. This technology cannot dynamically adapt to these changes. For the irrigation decision-making technology based on crop growth models and weather forecasts, the used crop growth models are relatively complex and require a large number of parameters to be input. However, some parameters are difficult to accurately obtain under different regions and planting conditions, and parameter calibration has certain difficulties, which is prone to generate many uncertainties, resulting in poor adaptability in different environments. For the irrigation decision-making technology based on remote sensing data, UAV remote sensing data is easily affected by the environment. For example, windy and rainy weather will affect the flight stability of the UAV and the quality of data collection, and the complexity of data processing is relatively high. When satellite remote sensing data is combined with the evapotranspiration model, both data at two scales rely on the support of ground measured data. Under the differences in terrain, climate and other conditions in different regions, the applicability is poor and the application range is limited.

[0005] Poor accuracy and stability: Irrigation decision-making technology based on soil moisture data relies on sensor accuracy, but sensors are easily affected by multiple factors such as temperature and soil texture. For example, in a high temperature environment, sensors may have errors, resulting in deviations in the acquired soil moisture data, which in turn leads to erroneous irrigation decision results. Irrigation decision-making technology based on crop growth models and weather forecasts relies on weather data and parameter calibration accuracy. However, weather forecast data itself has uncertainties, and the complexity of model parameterization will also introduce cumulative errors, which may eventually lead to incorrect irrigation decision results. Irrigation decision-making technology based on remote sensing data relies on high-resolution remote sensing images at the drone scale, but weather factors can seriously affect data quality. For example, cloud cover can cause image information to be missing. At the satellite scale, a single index combined with a surface energy balance model is usually used. The data lag problem is not solved, and real-time performance is limited, which may lead to irrigation decision errors.

[0006] Difficult to promote: Most existing technologies require soil sensors, drones, or model development and optimization. These devices and software require regular maintenance and updates, which not only consumes a lot of manpower and material resources, but also requires professional technicians to operate. Model development also requires a lot of manpower for research and debugging, which increases the implementation cost to a certain extent and limits the promotion and application of these technologies. Summary of the invention

[0007] In view of this, the purpose of the present invention is to provide an intelligent irrigation dynamic decision-making method and device to solve the problems of poor adaptability, poor accuracy and stability, and difficulty in promotion of intelligent irrigation decision-making in the prior art.

[0008] According to a first aspect of an embodiment of the present invention, there is provided a smart irrigation dynamic decision-making method, comprising: Get the boundary of the target plot, and obtain the sentinel-2 L2A remote sensing data of the target plot on the current date and the same period in history according to the boundary of the target plot; Generate a vector mask file according to sentinel-2 L2A remote sensing data, remove data of interference pixels in the sentinel-2 L2A remote sensing data according to the vector mask file, and calculate the normalized vegetation index of the target plot using the denoised sentinel-2 L2A remote sensing data; Get the Sentinel-3 level-2 LST data and precipitation data corresponding to the sentinel-2 L2A remote sensing data of the same period in history; reproject the Sentinel-3 level-2 LST data to the coordinate system of the corresponding sentinel-2 L2A remote sensing data; resample the Sentinel-3 level-2 LST data and precipitation data to the preset resolution; According to the denoised Sentinel-2 L2A remote sensing data of the current date and the same historical period, calculate the moisture status index of each pixel; according to the normalized difference vegetation index of the current date and the same historical period, calculate the vegetation status index of each pixel; according to the land surface temperature data in the Sentinel-3 level-2 LST data of the current date and the same historical period, calculate the temperature status index of each pixel; According to the growth stage of the crops on the current date, obtain the linguistic variables of the moisture status index, vegetation status index, and temperature status index of each pixel; According to the linguistic variables corresponding to the moisture status index, vegetation status index, and temperature status index respectively, obtain the irrigation decision level of each pixel; According to the irrigation decision levels of all pixels in the target plot, generate the irrigation decision for the target plot; according to the precipitation data in the past and the predicted precipitation data in the future of the current date, generate a decision prompt.

[0009] Preferably, before obtaining the Sentinel-2 L2A remote sensing data of the same historical period, it further includes: downloading the Sentinel-2 L2A remote sensing data of any 2 days from the crop vigorous growth period of each year in the preset historical time period; After calculating the normalized difference vegetation index of the target plot according to the downloaded Sentinel-2 L2A remote sensing data, it further includes: if the normalized difference vegetation index of the target plot is greater than or equal to the planting determination threshold, obtain the Sentinel-2 L2A remote sensing data of the remaining days of that year.

[0010] Preferably, after obtaining the Sentinel-2 L2A remote sensing data, it further includes: According to the SLC band data of the Sentinel-2 L2A remote sensing data, calculate the proportion of cloud, snow, and ice coverage area. If the proportion of cloud, snow, and ice coverage area is less than or equal to the preset threshold, mark the Sentinel-2 L2A remote sensing data as valid data, otherwise, consider it as invalid data.

[0011] Preferably, according to the denoised Sentinel-2 L2A remote sensing data of the current date and the same historical period, calculating the moisture status index of each pixel includes: According to the near-infrared band reflectance and short-wave infrared band reflectance of each pixel in the denoised Sentinel-2 L2A remote sensing data of the current date and the same historical period, calculate the normalized difference moisture index of each pixel; According to the normalized difference moisture index of each pixel on the current date, the maximum and minimum values of the normalized difference moisture index in the same historical period, calculate the moisture status index of each pixel.

[0012] Preferably, according to the normalized difference vegetation index (NDVI) of the current date and the historical same period, calculate the vegetation status index of each pixel, including: Calculate the vegetation status index of each pixel according to the NDVI of each pixel on the current date, the maximum and minimum values of the NDVI in the historical same period.

[0013] Preferably, according to the land surface temperature data of the current date and the historical same period, calculate the temperature status index of each pixel, including: Calculate the temperature status index of each pixel according to the land surface temperature data of each pixel on the current date, the maximum and minimum values of the land surface temperature data in the historical same period.

[0014] Preferably, generate a decision prompt, including: If the irrigation decision for the target plot is that irrigation is required, then according to the precipitation data, determine whether there is effective precipitation within a preset time period before and after the current date. If so, after generating the irrigation decision, generate a decision prompt that irrigation is not required due to the occurrence of precipitation.

[0015] Preferably, generating a decision prompt further includes: Obtain the irrigation operation data that the user has executed; If the irrigation decision for the target plot is that irrigation is required, then according to the irrigation operation data, determine whether an irrigation operation has been executed within a preset time period before the current date. If so, after generating the irrigation decision, generate a decision prompt that irrigation is not required due to the execution of the irrigation operation.

[0016] Preferably, the method further includes: If there is no effective precipitation within a preset time period before and after the current date, then retrieve the predicted precipitation data for the next 3 days based on the current date from the meteorological prediction database, and determine whether there is effective precipitation according to the predicted precipitation data; if there is effective precipitation within the next 3 days, generate a decision prompt that irrigation is not required due to the predicted future precipitation.

[0017] According to the second aspect of the embodiments of the present invention, provide an intelligent irrigation dynamic decision-making device, including: A main controller, and a memory connected to the main controller; The memory stores program instructions therein; The main controller is used to execute the program instructions stored in the memory and execute the method described in any one of the above.

[0018] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: It can be understood that the technical solution shown in the present invention integrates multi-source data, introduces fuzzy reasoning, and flexibly outputs through the input of multiple variables. It is more applicable to agricultural scenarios under different technical and environmental conditions and has stronger generalization ability. Facing different growth stages of crops, this technical solution more conforms to the growth law of crops by precisely designing the linguistic variables and membership functions in fuzzy reasoning, can better handle the uncertainty and complexity of water demand, and at the same time constructs dynamic rules to utilize precipitation data to correct the influence of the lag of remote sensing data on irrigation decision-making in real time, improving the dynamics and accuracy of irrigation decision-making. Relying on remote sensing satellite data and precipitation data, it intelligently provides plot-level irrigation decision-making suggestions without sensor deployment, manual sampling, and regular equipment calibration, significantly reducing the costs of hardware investment and long-term operation and maintenance. Moreover, managers can flexibly adjust in combination with the actual water resource situation and irrigation system, enhancing the scientificity and flexibility of irrigation decision-making and making it easier to promote and use.

[0019] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present invention and, together with the specification, are used to explain the principles of the present invention.

[0021] Figure 1 is a schematic diagram of the steps of an intelligent irrigation dynamic decision-making method shown according to an exemplary embodiment; Figure 2 is a flowchart of data acquisition and preprocessing shown according to an exemplary embodiment; Figure 3 is a flowchart of an intelligent irrigation dynamic decision-making system for a corn plot shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0023] In one embodiment, Figure 1 is a schematic diagram of the steps of an intelligent irrigation dynamic decision-making method shown according to an exemplary embodiment. Refer to Figure 1 , a method for intelligent irrigation dynamic decision-making is provided, including: Step S11, obtaining the boundary of the target plot, and obtaining the sentinel-2 L2A remote sensing data of the target plot on the current date and the same period in history according to the boundary of the target plot.

[0024] Step S12: Generate a vector mask file according to the sentinel-2 L2A remote sensing data, remove the data of the interfering pixels in the sentinel-2 L2A remote sensing data according to the vector mask file, and calculate the normalized vegetation index of the target plot using the denoised sentinel-2 L2A remote sensing data.

[0025] Step S13, obtaining the Sentinel-3 level-2 LST data and precipitation data corresponding to the sentinel-2 L2A remote sensing data of the same period in history; reprojecting the Sentinel-3 level-2 LST data to the coordinate system corresponding to the sentinel-2 L2A remote sensing data; and resampling the Sentinel-3 level-2 LST data and precipitation data to a preset resolution.

[0026] Step S14, calculate the moisture state index of each pixel according to the denoised sentinel-2 L2A remote sensing data of the current date and the same period in history; calculate the vegetation state index of each pixel according to the normalized vegetation index of the current date and the same period in history; calculate the temperature state index of each pixel according to the surface temperature data in the Sentinel-3 level-2 LST data of the current date and the same period in history.

[0027] Step S15: according to the growth period of crops on the current date, the water state index linguistic variable, the vegetation state index linguistic variable and the temperature state index linguistic variable of each pixel are obtained.

[0028] Step S16: derive the irrigation decision level of each pixel according to the linguistic variables corresponding to the water state index, the vegetation state index and the temperature state index.

[0029] Step S17: Generate an irrigation decision for the target plot based on the irrigation decision levels of all pixels in the target plot; and generate a decision prompt based on the past precipitation data of the current date and the future predicted precipitation data.

[0030] It can be understood that the technical solution shown in the present invention integrates multi-source data, introduces fuzzy reasoning, and flexibly outputs through the input of multiple variables, making it more suitable for agricultural scenarios under different technical and environmental conditions and having stronger generalization ability. For different growth stages of crops, this technical solution more conforms to the growth law of crops by precisely designing the linguistic variables and membership functions in fuzzy reasoning, can better handle the uncertainty and complexity of water requirements, and at the same time constructs dynamic rules to utilize precipitation data to correct in real time the influence of the lag of remote sensing data on irrigation decision-making, improving the dynamics and accuracy of irrigation decision-making. Relying on remote sensing satellite data and precipitation data, it intelligently provides plot-level irrigation decision-making suggestions without sensor deployment, manual sampling, and regular equipment calibration, significantly reducing the costs of hardware investment and long-term operation and maintenance. Moreover, managers can flexibly adjust in combination with the actual water resource situation and irrigation system, enhancing the scientificity and flexibility of irrigation decision-making and making it easier to promote and use.

[0031] In specific practice, the technical solution shown in this embodiment can be specifically divided into three stages, namely: data acquisition and preprocessing, key feature extraction, and intelligent irrigation fuzzy reasoning decision generation.

[0032] Data acquisition and preprocessing are reflected in steps S11, S12, and S13. In a preferred embodiment, the specific process of data acquisition and preprocessing can be referred to Figure 2 .

[0033] First, obtain the boundary of the target plot, and obtain the sentinel-2 L2A remote sensing data of the target plot on the current date according to the boundary of the target plot. At this time, it is necessary to determine whether the sentinel-2 L2A remote sensing data is valid data, which is judged according to the proportion of the cloud, snow, and ice coverage area.

[0034] It should be noted that the SLC band data (scene classification map) is obtained, and according to the SLC band data of the sentinel-2 L2A remote sensing data, the proportion of the cloud, snow, and ice coverage area is calculated. If the proportion of the cloud, snow, and ice coverage area is less than or equal to the preset threshold, the sentinel-2 L2A remote sensing data is marked as valid data, otherwise, it is regarded as invalid data.

[0035] Calculate the proportion of the cloud, snow / ice coverage area (CSI), and the formula is as follows:

[0036]

[0037]

[0038] Among them, is the proportion of the cloud, snow / ice coverage area in the corn plot, and the unit is %; is the number of pixels marked as cloud in the SCL scene classification map; is the number of pixels marked as snow or ice in the SCL; is the total number of pixels within the corn plot.

[0039] By judging the size relationship between the proportion of cloud, snow / ice coverage area (CSI) and the preset threshold, the validity of sentinel-2 L2A remote sensing data is determined: Assume the preset threshold is 50%, and the judgment conditions are as follows: If CSI ≤ 50%, then retain the sentinel-2 L2A remote sensing data of the corn plot, mark it as valid data, and form a vector mask file Plot_No_CSI for denoising and subsequent index calculation. The vector mask file defines the spatial range through geometric figures such as points, lines, and polygons. When processing remote sensing data related to corn plots, a polygon vector mask will be constructed based on the corn plot boundary to accurately delineate the target area. At the same time, the vector mask file will mark the pixel area of valid data and set the pixel area covered by cloud, snow / ice to invisible / not passing. The vector mask file is overlaid with the sentinel-2 L2A remote sensing data to achieve data screening and denoising.

[0040] If CSI > 50%, it indicates that the plot is greatly affected by cloud, snow / ice and does not meet the requirements of subsequent calculations. Then terminate the calculation at this time, no longer perform subsequent steps, and mark the remote sensing data of this period as invalid data.

[0041] When the remote sensing data of the current date is valid data, extract the date of the sentinel-2 L2A remote sensing data, that is, year, month, and day.

[0042] After that, obtain the sentinel-2 L2A remote sensing data of the same historical period. It should be noted that first, select 2 days of sentinel-2 L2A remote sensing data for download from each year's crop growth vigorous period within the preset historical time period (which can be the past 6 years).

[0043] Assume the year of the remote sensing data of the current date is 2024, then obtain 2 days of sentinel-2 L2A remote sensing data from the past 6 years (2018 - 2023) during the crop growth vigorous period (taking corn as an example, the corn growth vigorous period is from July 1st to July 31st). Similarly, it is necessary to judge the validity of the sentinel-2 L2A remote sensing data through the proportion of cloud, snow / ice coverage area (CSI).

[0044] When judged to be valid, combine the sentinel-2 L2A remote sensing data with the vector mask file to calculate the normalized difference vegetation index of the plot after removing the interference pixels. The calculation formula is as follows:

[0045] Among them, is the normalized difference vegetation index of the corn plot; and are the reflectances of the near-infrared and red light bands of the i-th pixel respectively (obtained from Sentinel-2 L2A remote sensing data). is the total number of effective pixels within the corn plot (invalid pixels are excluded according to the vector mask file Plot_No_CSI).

[0046] If the normalized difference vegetation index of the target plot is greater than or equal to the planting determination threshold, the Sentinel-2 L2A remote sensing data of the same historical period of that year is obtained. If, during the acquisition of the remote sensing data of the same historical period, the data of the same historical date does not exist or is unavailable, the remaining available Sentinel-2 L2A remote sensing data within 5 days before and after will be queried day by day as the Sentinel-2 L2A remote sensing data of the same historical period.

[0047] For example, assuming that the planting determination threshold is 0.35, if the of the Sentinel-2 L2A remote sensing data for 2 days in 2018 are both lower than the set planting determination threshold of 0.35, it indicates that corn was not planted in this plot in 2018, and the other Sentinel-2 and Sentinel-3 data for 2018 will not be downloaded. On the contrary, if the of the Sentinel-2 L2A remote sensing data for 2 days in 2019 are both higher than the set planting determination threshold of 0.35, it indicates that corn was planted in this plot in 2019, and the remote sensing data of the same historical period of that year can be downloaded continuously.

[0048] Preferably, it is possible to repeatedly determine whether corn was planted each year from 2018 to 2023, save the years in which corn was planted to the planting year statistical table, and obtain the Sentinel-2 L2A remote sensing data of the same historical period according to the valid historical years saved in the planting year statistical table. For each obtained Sentinel-2 L2A remote sensing data, it is necessary to judge its validity through the cloud, snow / ice coverage area ratio (CSI) and eliminate the invalid data.

[0049] It can be understood that by designing the non-planting year detection function for screening, only the data of the planting years is downloaded, avoiding the processing of invalid data to optimize computing resources. At the same time, the SCL is used to remove noise, improving the data accuracy and processing efficiency.

[0050] After the above processing, the Sentinel-3 level-2 LST data and precipitation data in the preset historical time period are downloaded. It is necessary to process the three types of data to make the three data sources consistent in time and space and achieve multi-source remote sensing data fusion. Specifically: Reproject the Sentinel-3 level-2 LST data to the coordinate system consistent with the sentinel-2 L2A remote sensing data; Resample the Sentinel-3 level-2 LST data and precipitation data to the preset resolution (e.g., 10m).

[0051] After the data acquisition and preprocessing are completed, the key feature extraction stage is carried out.

[0052] Key feature extraction is to calculate the moisture status index, vegetation status index and temperature status index based on the obtained sentinel-2 L2A remote sensing data and Sentinel-3 level-2 LST data.

[0053] It should be noted that the moisture status index (WCI) is mainly calculated through the normalized difference moisture index (NDMI) and is used to evaluate the moisture content of corn. Calculating the moisture status index of each pixel includes: Calculating the normalized difference moisture index of each pixel according to the near-infrared band reflectance and short-wave infrared band reflectance of each pixel in the denoised sentinel-2 L2A remote sensing data on the current date and the historical same period; Calculating the moisture status index of each pixel according to the normalized difference moisture index of each pixel on the current date, the maximum and minimum values of the normalized difference moisture index in the historical same period. The calculation formula is as follows: 00

[0054] Among them, is the normalized difference moisture index of the pixel on this date in the current year; 、 are respectively the minimum and maximum values within the historical same period of this pixel; is the near-infrared band reflectance of the pixel; is the short-wave infrared band reflectance of the pixel. is the moisture status index of the pixel.

[0055] It should be noted that the vegetation condition index (VCI) mainly represents the relative measure of the growth condition of corn. The higher the VCI value, the better the vegetation growth condition. Calculating the vegetation condition index of each pixel includes: The vegetation status index of each pixel is calculated based on the normalized difference vegetation index (NDVI) of the current date of each pixel, the maximum and minimum values of the NDVI in the same historical period. The calculation formula is as follows: 00

[0056] Wherein, is the normalized difference vegetation index of the pixel on the date of the current year; and are respectively the minimum and maximum values within the same historical period of the pixel. is the vegetation status index of the pixel.

[0057] It should be noted that the land surface temperature condition index (LSTCI) reflects the degree of stress on maize by temperature by comparing the difference between the land surface temperature of the current year on this date and the temperature data of the same historical period. Calculating the land surface temperature condition index of each pixel includes: The land surface temperature condition index of each pixel is calculated based on the land surface temperature data of the current date of each pixel, the maximum and minimum values of the land surface temperature data in the same historical period. The calculation formula is as follows: 00

[0058] Wherein, is the land surface temperature of the pixel on the date of the current year, in °C. The land surface temperature in the Sentinel-3 level-2 LST data needs to be converted to degrees Celsius; and are respectively the minimum and maximum values within the same historical period of the pixel, in °C. is the land surface temperature condition index of the pixel.

[0059] After the extraction of key features is completed, it enters the intelligent irrigation fuzzy inference decision-making stage, which includes steps S15, S16 and S17.

[0060] In step S15, according to the growth period of the crops on the current date, the linguistic variables of the water status index, the vegetation status index and the land surface temperature condition index of each pixel are obtained.

[0061] Preferably, in combination with the growth period of the crops on the current date, the linguistic variables of the water status index, the vegetation status index and the land surface temperature condition index of each pixel are obtained by referring to the pre-constructed linguistic variable database.

[0062] In specific practice, taking corn as an example, by designing an intelligent irrigation fuzzy inference system, the linguistic variables and membership functions of input variables at different corn growth stages are constructed, a linguistic variable database is built, and the linguistic variables of the water status index, vegetation status index, and temperature status index of each pixel are obtained.

[0063] The water demand intensity of corn varies at different growth stages. During the seedling period from sowing to jointing, the plants are small, and the overall water demand is not high. In this stage, attention should be paid to not having too much water, as it is not conducive to strong seedlings. From jointing to tasseling, the growth enters a vigorous stage, the temperature gradually rises, and the evapotranspiration rate also accelerates, resulting in a larger overall water consumption. From tasseling to filling, the water demand is relatively high. The metabolism during this period is relatively vigorous, and the water demand intensity is high. Only sufficient water can meet the needs of growth and development, and this is also a key stage for yield formation. Entering the filling and maturity stage, when the grains are basically fixed, the water consumption decreases.

[0064] Based on the water demand characteristics of corn throughout its growth period, for the three key indices, namely the water status index (WCI), vegetation status index (VCI), and temperature status index (LSTCI), the corresponding linguistic variables are constructed respectively. The membership functions all select trigonometric functions. The reference for the linguistic variable database is shown in Table 1.

[0065] Table 1 Comparison Table of Linguistic Variables

[0066] Since trigonometric functions are selected as the membership functions in this embodiment, and the triangular membership functions require intersections in the range.

[0067] Through the constructed linguistic variables and membership functions of input variables at different corn growth stages, combined with the growth stage of the crops on the current date, and the calculated water status index, vegetation status index, and temperature status index on the current date, the corresponding linguistic variables can be obtained.

[0068] It can be understood that for different growth stages of corn (sowing - jointing, jointing - tasseling, tasseling - filling, filling - maturity), a growth - stage - oriented fuzzy rule base is constructed. Through dynamic rule design combined with crop growth laws, the irrigation decision results of the intelligent irrigation dynamic decision - making model for corn fields are more scientific and adaptable.

[0069] Step S16: According to the linguistic variables corresponding to the water status index, vegetation status index, and temperature status index respectively, obtain the irrigation decision level of each pixel.

[0070] In specific practice, a rule base for maize irrigation decision-making levels based on fuzzy inference is designed. Based on the measured data of the soil volume water content in the 0-60 cm root zone of maize during the whole growth period in multiple regions and combined with expert experience, 27 fuzzy rules are constructed as the rule base for maize irrigation decision-making levels. See Table 2. For example, if the linguistic variable of the moisture status index is low, the linguistic variable of the temperature status index is low, and the linguistic variable of the vegetation status index is low, then the irrigation decision-making level belongs to high.

[0071] Table 2 Table of the rule base for maize irrigation decision-making levels

[0072] Through the constructed rule base for maize irrigation decision-making levels, the irrigation decision-making level of each pixel can be obtained according to the linguistic variables corresponding to the moisture status index, vegetation status index, and temperature status index respectively.

[0073] Step S17: Generate the irrigation decision for the target plot according to the irrigation decision-making levels of all pixels in the target plot.

[0074] In specific practice, pixel-level fuzzy inference and plot-level decision aggregation are carried out. Using the Mamdani model, the growth period and key features of the current date are used as input variables, and combined with the "rule base for irrigation decision-making levels" to deduce the fuzzy set of the irrigation decision-making level. Immediately afterwards, the centroid method is used to defuzzify it to obtain the defuzzified value of each pixel, and it is mapped into the corresponding irrigation decision category according to the predefined numerical range. Based on this, the proportion of pixels in the plot whose irrigation decision category is "irrigation required" is counted. If it exceeds 60%, the plot is marked as "irrigation required"; if 30% ≤ proportion < 60%, the plot is marked as "basically satisfied"; if the proportion is less than 30%, the plot is marked as "no irrigation required".

[0075] Thus, the staff can use an intelligent irrigation dynamic decision-making method constructed to generate irrigation decisions.

[0076] In practical applications, an intelligent irrigation dynamic decision-making method shown in this embodiment can be integrated into an intelligent irrigation dynamic decision-making system for the convenience of users.

[0077] See Figure 3 , the specific execution process of the intelligent irrigation dynamic decision-making for maize plots is as follows: Before starting the intelligent irrigation dynamic decision-making system for maize plots, the required user data should be obtained in advance, including the starting date of maize planting in the plot, plot boundary information (latitude and longitude), the time of the user's irrigation farming operations, and the expected harvest date.

[0078] Start the system. First, compare the corn sowing start date input by the user with the current date. If the user enters data before sowing and the current date is earlier than the sowing date, the system will pause until it automatically restarts when the current date is the same as the filled sowing date. If the current date is the sowing date or after it, the model will run normally. Obtain the databases required by the system, including the corn growth period database and meteorological prediction data. Based on the current date and the plot boundary information (latitude and longitude), retrieve the information in the corn growth period database for matching to obtain the actual growth period of the corn on the current date. Start entering the "data acquisition and preprocessing stage". After the execution of this stage, detect whether there is valid data output. If there is no data, it means that there may be no Sentinel-2 L2A product data on that day (limited by the satellite revisit cycle) or the cloud cover does not meet the requirements and the data cannot be used, then terminate the system and restart the system again the next day; if there is data, continue to execute the "key feature extraction stage", and input the extracted feature results and growth period information into the "intelligent irrigation fuzzy inference stage" for fuzzy inference and judgment to generate irrigation decisions.

[0079] After generating the irrigation decision for the target plot, generate a decision prompt based on the precipitation data in the past and the predicted precipitation data in the future of the current date.

[0080] If the irrigation decision output by the intelligent irrigation dynamic decision system is "basically satisfied", then finally output to the user the decision prompt of "Under the current conditions, the corn on this plot grows well, temporarily no irrigation is required, it is recommended to continuously monitor".

[0081] If the irrigation decision output by the "intelligent irrigation fuzzy inference system" is "no irrigation required", then finally output to the user the decision prompt of "At this stage of this plot, the corn growth is in a state of sufficient moisture and no irrigation measures need to be implemented".

[0082] It should be noted that generating a decision prompt includes: if the irrigation decision for the target plot is that irrigation is required, then according to the precipitation data, judge whether there is effective precipitation in the preset time period before and after the current date. If so, after generating the irrigation decision, generate a decision prompt of not requiring irrigation due to the occurrence of precipitation.

[0083] Generating a decision prompt also includes: obtaining the irrigation operation data already executed by the user; if the irrigation decision for the target plot is that irrigation is required, then judge whether an irrigation operation has been performed in the preset time period before the current date according to the irrigation operation data. If so, after generating the irrigation decision, generate a decision prompt of not requiring irrigation due to the execution of the irrigation operation.

[0084] If there is no effective precipitation within a preset time period before and after the current date, retrieve the predicted precipitation data for the next 3 days based on the current date from the meteorological prediction database, and determine whether there is effective precipitation according to the predicted precipitation data; if there is effective precipitation within the next 3 days, generate a decision prompt that irrigation is not required due to the predicted future precipitation.

[0085] In specific practice, if the output result of the "Intelligent Irrigation Fuzzy Inference System" is "irrigation is required", retrieve the precipitation data processed in the "Data Acquisition and Preprocessing Stage". Due to the certain lag in obtaining remote sensing satellite data products, it is necessary to check the precipitation data between two dates. If there is effective precipitation (i.e., daily precipitation > 3 mm) or the user has performed an irrigation operation, the intelligent control fuzzy inference judgment result is adjusted, and finally, a decision prompt "It is monitored that the plot needs irrigation on YYYY-MM-DD (satellite shooting date), but due to subsequent precipitation or irrigation operations, it is recommended to continue monitoring and irrigation is not required for the time being" is output to the user. If there is no effective precipitation, continue to retrieve the predicted precipitation data for the next 3 days based on the current date from the meteorological prediction database. If there is no effective precipitation within the predicted 3 days and the user has not performed an irrigation operation, a decision prompt "It is recommended to start irrigation on YYYY-MM-DD_1 (i.e., the current date)" is finally output to the user. Otherwise, the user is prompted "It is monitored that the plot needs irrigation on YYYY-MM-DD, but there will be precipitation within the next 3 days. It is recommended to continue observing and irrigation is not required for the time being".

[0086] Execute the intelligent irrigation dynamic decision system for corn plots once a day, dynamically output irrigation decision suggestions at the plot scale, and stop running the system until the harvest date.

[0087] This embodiment constructs a dynamic, multi-level, and multi-scale decision logic, from pixel-level fuzzy inference to plot-level decision aggregation. At the same time, it corrects the lag of remote sensing data, combines multi-dimensional conditional judgments of historical precipitation, weather forecasts, and user irrigation operations, generates personalized suggestions, realizes the integrated optimization of dynamic decision-making and user feedback, improves the real-time performance and accuracy of irrigation decision-making, and helps users achieve precise and efficient irrigation optimization.

[0088] The technical solution shown in the present invention, compared with the prior art: Stronger generalization ability: In the prior art, it all depends on ground sensors, unmanned aerial vehicle equipment, on-site measured data, or crop growth models. The accuracy and representativeness of its data sources and the complexity of crop growth models make it difficult to adapt to different environmental conditions. However, in the present invention, by integrating multi-source data, it avoids relying on a single data source. In addition, a fuzzy inference system is introduced. Compared with the traditional method that relies on fixed thresholds, the fuzzy inference system flexibly outputs through the input of multiple variables, is more suitable for agricultural scenarios under different technical conditions and environmental conditions, and has stronger generalization ability.

[0089] Higher precision: Most of the irrigation decision-making methods in the prior art are general-purpose and do not consider the water demand characteristics of specific crops at different growth stages. This invention is oriented to different growth periods of corn. By precisely designing the linguistic variables and membership functions in the fuzzy inference system, it better conforms to the crop growth law. The introduction of the fuzzy inference system can better handle the uncertainty and complexity of water demand. At the same time, a dynamic rule is constructed to correct the impact of the lag of remote sensing data on irrigation decision-making in real time, improving the dynamics and precision of irrigation decision-making.

[0090] Stronger application and promotion: This invention relies on remote sensing satellite data and meteorological data, and uses an intelligent irrigation dynamic decision-making model for corn plots to intelligently provide plot-level irrigation decision-making suggestions. There is no need for sensor deployment, manual sampling, and regular equipment calibration, significantly reducing the costs of hardware investment and long-term operation and maintenance. Moreover, managers can flexibly adjust according to the actual water resource situation and irrigation system, enhancing the scientificity and flexibility of irrigation decision-making and making it easier to promote and use.

[0091] In another embodiment, an intelligent irrigation dynamic decision-making device is provided, including: A main controller, and a memory connected to the main controller; The memory, in which program instructions are stored; The main controller is used to execute the program instructions stored in the memory and execute the method described in any one of the above.

[0092] It can be understood that the same or similar parts in the above embodiments can be referred to each other. For the content not detailed in some embodiments, reference can be made to the same or similar content in other embodiments.

[0093] It should be noted that in the description of the present invention, terms such as "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "a plurality" refers to at least two.

[0094] Any process or method description in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of executable instructions including one or more steps for implementing a specific logical function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a manner that is not shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the involved functions, which should be understood by those skilled in the technical field to which the embodiments of the present invention belong.

[0095] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0096] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0097] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0098] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disk, etc.

[0099] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0100] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. An intelligent irrigation dynamic decision-making method, characterized in that, include: Get the boundary of the target plot, and obtain the sentinel-2 L2A remote sensing data of the target plot on the current date and the same period in history according to the boundary of the target plot; Generate a vector mask file according to sentinel-2 L2A remote sensing data, remove data of interference pixels in the sentinel-2 L2A remote sensing data according to the vector mask file, and calculate the normalized vegetation index of the target plot using the denoised sentinel-2 L2A remote sensing data; Get the Sentinel-3 level-2 LST data and precipitation data corresponding to the sentinel-2 L2A remote sensing data of the same period in history; reproject the Sentinel-3 level-2 LST data to the coordinate system of the corresponding sentinel-2 L2A remote sensing data; resample the Sentinel-3 level-2 LST data and precipitation data to the preset resolution; The moisture state index of each pixel is calculated based on the denoised sentinel-2 L2A remote sensing data of the current date and the same period in history; the vegetation state index of each pixel is calculated based on the normalized vegetation index of the current date and the same period in history; the temperature state index of each pixel is calculated based on the surface temperature data in the Sentinel-3 level-2 LST data of the current date and the same period in history; According to the crop growth period on the current date, the water state index linguistic variable, vegetation state index linguistic variable and temperature state index linguistic variable of each pixel are obtained; According to the linguistic variables corresponding to the water state index, vegetation state index and temperature state index, the irrigation decision level of each pixel is obtained; The irrigation decision of the target plot is generated according to the irrigation decision level of all pixels in the target plot; the decision prompt is generated according to the past precipitation data of the current date and the future predicted precipitation data.

2. The method according to claim 1, characterized in that Before obtaining the sentinel-2 L2A remote sensing data of the same period in history, it also includes: downloading sentinel-2 L2A remote sensing data of any two days in the preset historical time period during the peak period of crop growth each year; After calculating the normalized vegetation index of the target plot according to the downloaded sentinel-2 L2A remote sensing data, the method further includes: if the normalized vegetation index of the target plot is greater than or equal to the planting determination threshold, acquiring the sentinel-2 L2A remote sensing data of the remaining days of the year.

3. The method according to claim 1, wherein After acquiring sentinel-2 L2A remote sensing data, it also includes: According to the SLC band data of sentinel-2 L2A remote sensing data, the proportion of cloud, snow and ice coverage area is calculated. If the proportion of cloud, snow and ice coverage area is less than or equal to the preset threshold, the sentinel-2 L2A remote sensing data is marked as valid data, otherwise, it is regarded as invalid data.

4. The method according to claim 1, characterized in that, Based on the denoised sentinel-2 L2A remote sensing data of the current date and the same period in history, the water status index of each pixel is calculated, including: Calculate the normalized difference moisture index for each pixel based on the reflectance of the near-infrared band and the short-wave infrared band of the denoised Sentinel-2 L2A remote sensing data for the current date and the same period in history. Calculate the moisture status index for each pixel based on the normalized difference moisture index of each pixel for the current date, the maximum and minimum values of the normalized difference moisture index in the same period in history.

5. The method according to claim 1, wherein Calculate the vegetation status index for each pixel based on the normalized difference vegetation index for the current date and the same period in history, including: Calculate the vegetation status index for each pixel based on the normalized difference vegetation index of each pixel for the current date, the maximum and minimum values of the normalized difference vegetation index in the same period in history.

6. The method according to claim 1, characterized in that Calculate the temperature status index for each pixel based on the land surface temperature data for the current date and the same period in history, including: Calculate the temperature status index for each pixel based on the land surface temperature data of each pixel for the current date, the maximum and minimum values of the land surface temperature data in the same period in history.

7. The method according to claim 1, characterized in that Generate decision prompts, including: If the irrigation decision for the target plot is that irrigation is required, then based on the precipitation data, determine whether there is effective precipitation within a preset time period before the current date. If so, after generating the irrigation decision, generate a decision prompt that irrigation is not required due to the occurrence of precipitation.

8. The method according to claim 7, characterized in that, Also include: Obtain the irrigation operation data already executed by the user; If the irrigation decision for the target plot is that irrigation is required, then based on the irrigation operation data, determine whether an irrigation operation has been performed within a preset time period before the current date. If so, after generating the irrigation decision, generate a decision prompt that irrigation is not required due to the execution of the irrigation operation.

9. The method according to claim 7, characterized in that Also include: If there is no effective precipitation within a preset time period before the current date, then retrieve the predicted precipitation data for the next 3 days based on the current date from the meteorological prediction database, and determine whether there is effective precipitation based on the predicted precipitation data; if there is effective precipitation within the next 3 days, then generate a decision prompt that irrigation is not required due to the expected future precipitation.

10. An intelligent irrigation dynamic decision-making device, characterized in that, Include: A main controller, and a memory connected to the main controller; The memory, in which program instructions are stored; The main controller is used to execute the program instructions stored in the memory and execute the method according to any one of claims 1 to 9.

Images