Intelligent irrigation control method and system based on meteorological information

Abstract

The invention discloses an intelligent irrigation control method and system based on meteorological information, and relates to the technical field of irrigation control, an area to be irrigated is divided into a plurality of sub-areas, and future rainfall (first rainfall) is predicted through a preset meteorological early warning model; acquiring water absorption data of each sub-region, calculating a water absorption coefficient, and determining absorbable rainfall (second rainfall) in combination with the first rainfall; and judging the water consumption of each sub-region according to the crop growth data and the historical data, and comparing the water consumption with the second rainfall. If the water consumption is greater than the second rainfall, the sub-region needs to be irrigated; according to the method, the soil water content of each sub-region can be finely judged, and whether rainfall meets the water demand or not is evaluated, so that whether irrigation is needed or not is judged, excessive irrigation and water resource waste are avoided, meanwhile, it is ensured that crops obtain enough water, water resource management is optimized, and the crop growth effect and agricultural production efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of irrigation control, and in particular to an intelligent irrigation control method and system based on meteorological information. Background Art

[0002] Irrigation technology based on meteorological information refers to an intelligent technology that uses real-time or predicted meteorological data, such as rainfall, temperature, humidity, wind speed, evapotranspiration, etc., to dynamically analyze the water demand of crops, thereby scientifically formulating irrigation plans. This technology, through the coordinated work of sensors, meteorological stations and data processing systems, combined with soil moisture monitoring and crop growth models, can accurately control irrigation time and water volume, avoid over-irrigation or waste of water resources, improve agricultural production efficiency, and reduce negative impacts on the environment. It is an important means of saving water and increasing efficiency in modern agriculture;

[0003] In existing technologies, when rainfall is predicted through meteorological information, the predicted rainfall often covers a larger area. However, different small areas in the entire area may have different water absorption. This error may cause the system to overestimate the soil moisture content in certain small areas. In fact, these areas may be short of water due to poor water absorption or insufficient local rainfall, thereby delaying necessary irrigation operations. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and provide an intelligent irrigation control method and system based on meteorological information.

[0005] In a first aspect of the present invention, a method for intelligent irrigation control based on meteorological information is first proposed, the method comprising:

[0006] The entire area to be irrigated is recorded as the target area, and the target area is divided into several sub-areas, and the rainfall in the target area within a preset time in the future is predicted as the first rainfall by a preset meteorological early warning model;

[0007] Acquire water absorption data of each sub-area, calculate a water absorption coefficient based on the water absorption data, and determine the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall; the water absorption data includes a plant coverage coefficient, a slope steepness coefficient, and a soil permeability coefficient;

[0008] Obtain the crop growth data corresponding to each sub-region, and determine the amount of water required for each sub-region based on the crop growth data and historical crop growth data;

[0009] The water consumption is compared with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated.

[0010] Optionally, the plant coverage factor includes:

[0011] Obtain satellite images of each sub-area, extract the reflectance values ​​of the near-infrared band and the red light band from the satellite images, and obtain the vegetation index NDVI of the corresponding pixels. The calculation formula is: In the formula, NIR and RED are the reflectance values ​​of the near infrared band and the red light band respectively;

[0012] Send multiple laser pulses to each sub-area, obtain the flight time of the first echo and the flight time of the last echo, and calculate the average height of vegetation in each sub-area. The calculation formula is: Where SD is the average height of vegetation, c is the speed of light, tw and te are the flight time of the first echo and the flight time of the last echo, respectively;

[0013] Calculate the plant cover factor FG using the following formula: FG = NDVI·SD.

[0014] Optionally, the slope steepness coefficient includes:

[0015] Obtain digital elevation model (DEM) data of each sub-area, and extract all pixel points from the digital elevation model (DEM) data;

[0016] For each pixel point, calculate its slope value. The slope refers to the elevation change between the point and the surrounding neighboring pixels. The slope is calculated using the following formula:

[0017]

[0018] In the formula, S i,j is the slope value at the pixel point (i, j); ΔZ is the elevation difference between the pixel point and its neighboring pixels in the vertical direction; ΔX is the horizontal distance between the pixel point and its neighboring pixels in the horizontal direction, usually taken as 1 pixel unit; ΔY is the horizontal distance between the pixel point and its neighboring pixels in another horizontal direction;

[0019] Scan the entire digital elevation model (DEM), extract the slope data of the area, and find the maximum slope value S max ;

[0020] For each pixel (i, j), calculate the slope steepness coefficient a i,j , the calculation formula is:

[0021] The mean of the slope steepness coefficients of all the pixels in the sub-region is calculated to obtain the slope steepness coefficient of the corresponding sub-region.

[0022] Optionally, calculating the water absorption coefficient according to the water absorption data, and determining the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall includes:

[0023] The plant coverage coefficient, slope steepness coefficient and soil permeability coefficient of each sub-area are normalized and mapped to [0, 1], and the water absorption coefficient TG is calculated. The calculation formula is: In the formula, sx, sd and sv are the normalized plant coverage coefficient, slope steepness coefficient and soil permeability coefficient respectively;

[0024] The rainfall that can be absorbed by each sub-area is determined according to the water absorption coefficient and the first rainfall as the second rainfall.

[0025] Optionally, determining the rainfall that can be absorbed by each sub-area as the second rainfall according to the water absorption coefficient and the first rainfall includes:

[0026] The second rainfall is calculated using the formula WPU=EFR·TG; wherein WPU is the second rainfall, EFR is the first rainfall, and TG is the water absorption coefficient.

[0027] Optionally, obtaining crop growth data corresponding to each sub-region, and determining the amount of water required for each sub-region according to the crop growth data and historical crop growth data includes:

[0028] Obtain the current growth status data of crops in each sub-region, and obtain the historical growth status data of crops in different growth stages, and determine the amount of water required for each sub-region based on the crop planting area of ​​each sub-region, specifically:

[0029] Marking the historical growth status data of the crop at each different growth stage as target historical data;

[0030] Preprocess the current crop growth status data and target historical data;

[0031] Construct a distance matrix, in which each element is the distance between the crop growth status data point at the current stage and the target historical data point;

[0032] The dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the crop growth status data sequence at the current stage and the target historical data sequence;

[0033] According to the calculated shortest path, the volatility data series and the target historical data series are aligned;

[0034] According to the aligned fluctuation data sequence and historical data sequence, the similarity between them is calculated;

[0035] The target historical data corresponding to the maximum similarity is used as the final matching historical data, and the growth stage corresponding to the final matching historical data is used as the current growth stage of the crop;

[0036] The preset water requirement corresponding to the current growth stage of the crop is obtained, and the planting area of ​​the crop in the sub-region is obtained, and the preset water requirement and the planting area are multiplied after removing the unit to obtain the water consumption required for each sub-region.

[0037] In a second aspect of the present invention, an intelligent irrigation control system based on meteorological information is provided, the system comprising:

[0038] The first rainfall module: the entire area to be irrigated is recorded as the target area, and the target area is divided into several sub-areas, and the rainfall in the target area within a preset time in the future is predicted as the first rainfall through a preset meteorological early warning model;

[0039] Second rainfall module: obtain water absorption data of each sub-area, calculate water absorption coefficient according to the water absorption data, and determine the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall; the above water absorption data include plant coverage coefficient, slope steepness coefficient and soil permeability coefficient;

[0040] Water consumption module: obtains the crop growth data corresponding to each sub-region, and determines the water consumption required for each sub-region based on the crop growth data and historical crop growth data;

[0041] Irrigation control module: compares the water consumption with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated.

[0042] Beneficial effects of the present invention:

[0043] The present invention proposes an intelligent irrigation control method and system based on meteorological information, which records the entire area to be irrigated as a target area, divides the target area into several sub-areas, and predicts the rainfall in the target area within a preset time in the future as a first rainfall through a preset meteorological early warning model; obtains water absorption data of each sub-area, calculates a water absorption coefficient according to the water absorption data, and determines the rainfall that can be absorbed by each sub-area as a second rainfall in combination with the first rainfall; obtains crop growth data corresponding to each sub-area, and judges the water consumption required for each sub-area according to the crop growth data and historical crop growth data, compares the water consumption with the second rainfall, and if the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated, and can more precisely judge the soil moisture content of the small area, and evaluate whether the rainfall can cover the water demand of the small area, so as to judge whether the small area needs to be irrigated again. This method helps to reasonably adjust the irrigation amount, avoid over-irrigation and waste of water resources, and ensure that crops get enough water supply, optimize water resource management, and improve crop growth effect and agricultural production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below in conjunction with the accompanying drawings.

[0045] Figure 1 It is a flow chart of an intelligent irrigation control method based on meteorological information;

[0046] Figure 2 The framework diagram of an intelligent irrigation control system based on meteorological information. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0049] The embodiment of the present invention provides an intelligent irrigation control method based on meteorological information. Figure 1 , Figure 1 A flow chart of an intelligent irrigation control method based on meteorological information provided by an embodiment of the present invention. The method comprises the following steps:

[0050] The entire area to be irrigated is recorded as the target area, and the target area is divided into several sub-areas, and the rainfall in the target area within a preset time in the future is predicted as the first rainfall by a preset meteorological early warning model;

[0051] Acquire water absorption data of each sub-area, calculate a water absorption coefficient based on the water absorption data, and determine the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall; the water absorption data include plant coverage coefficient, slope steepness coefficient and soil permeability coefficient;

[0052] Obtain the crop growth data corresponding to each sub-region, and determine the amount of water required for each sub-region based on the crop growth data and historical crop growth data;

[0053] The water consumption is compared with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated.

[0054] An intelligent irrigation control method based on meteorological information provided by an embodiment of the present invention can accurately judge the soil moisture content of a small area and evaluate whether the rainfall can cover the water demand of the small area, so as to judge whether the small area needs to be irrigated again. This method helps to reasonably adjust the irrigation amount, avoid excessive irrigation and waste of water resources, and ensure that crops get enough water supply, optimize water resource management, and improve crop growth effects and agricultural production efficiency.

[0055] In one embodiment, the rainfall in the target area within the preset time in the future is predicted as the first rainfall by using a preset meteorological warning model. Specifically, it can include using multi-source data such as historical meteorological data, meteorological satellite information, meteorological radar, and numerical weather forecast models, combined with precipitation intensity models and local climate characteristics in meteorology to predict rainfall; in the prediction process, multiple factors can be considered, such as temperature system, humidity, air pressure and wind speed, which will affect the occurrence and intensity of precipitation. In addition, according to the seasonal changes of the region, topography (such as altitude and mountain distribution, etc.) and historical rainfall data, multivariate regression analysis can be performed using machine learning algorithms to further improve the accuracy of rainfall prediction. Finally, the rainfall obtained according to these calculations is used as the first rainfall as the basis for irrigation decision-making; it should be noted that the preset time is set by professionals according to the actual situation, and no specific elaboration or limitation is made.

[0056] In one embodiment, the plant cover factor includes:

[0057] Obtain satellite images of each sub-area, extract the reflectance values ​​of the near-infrared band and the red light band from the satellite images, and obtain the vegetation index NDVI of the corresponding pixels. The calculation formula is: In the formula, NIR and RED are the reflectance values ​​of the near infrared band and the red light band respectively;

[0058] Send multiple laser pulses to each sub-area, obtain the flight time of the first echo and the flight time of the last echo, and calculate the average height of vegetation in each sub-area. The calculation formula is: Where SD is the average height of vegetation, c is the speed of light, tw and te are the flight time of the first echo and the flight time of the last echo, respectively;

[0059] Calculate the plant cover factor FG using the following formula: FG = NDVI·SD.

[0060] It should be noted that by acquiring satellite images of each sub-area, especially data from the near-infrared band and the red light band, high-resolution remote sensing satellites (such as Landsat, Sentinel-2) or sensors carried by drones are usually used. The reflectance values ​​of these bands are extracted through image processing technology to calculate the vegetation index; in addition, the flight time of the first echo and the flight time of the last echo are calculated from the LiDAR echo, and the data is corrected according to the ground control points to ensure measurement accuracy;

[0061] It should be noted that the plant coverage coefficient of a sub-region is used to measure the degree to which a sub-region is covered by plants. The greater the degree of plant coverage, the less rainfall the sub-region can absorb, because vegetation coverage will cause rainfall to be first absorbed by the leaves and stems of plants, and some water will evaporate back into the atmosphere through evaporation, reducing the amount of water that penetrates into the soil; in addition, higher plant coverage will also increase ground water evaporation and plant water demand, further reducing the amount of water available in the soil. Therefore, the plant coverage coefficient is negatively correlated with the soil's water absorption capacity. The higher the coverage, the lower the soil's water absorption; based on this characteristic, when making irrigation decisions, it is necessary to take into account the interception and evaporation effects of plant coverage on precipitation, and reasonably adjust the irrigation amount of each sub-region to avoid untimely irrigation.

[0062] The benefit of calculating the plant coverage coefficient of a sub-region for irrigation control of the sub-region is that it can provide accurate water demand data, making irrigation decisions more scientific and efficient. By understanding the degree of plant coverage in different sub-regions, the rainfall water absorption capacity and evaporation water demand of each region can be effectively predicted, thereby avoiding the waste of water resources due to over-irrigation and preventing the growth of crops from being affected by insufficient irrigation. The calculation of the plant coverage coefficient can help identify which areas need more water support and which areas can reduce irrigation to ensure the rational allocation of water resources. Through this refined irrigation control, not only the water efficiency of agricultural production is improved, but also unnecessary environmental burdens are reduced, ultimately achieving the goal of water saving and efficiency improvement. In addition, this irrigation control method based on plant coverage coefficient can give priority to areas with higher water demand in the case of drought or insufficient precipitation, avoid uneven crop growth caused by uneven irrigation, and improve the overall yield and quality of crops.

[0063] In one embodiment, the slope steepness factor includes:

[0064] First, obtain the digital elevation model (DEM) data of each sub-region and extract all the pixels from the DEM data; DEM can be obtained through satellite remote sensing or aerial laser radar (LiDAR) technology, which provides the ground elevation information of each pixel in the region;

[0065] For each pixel point, calculate its slope value. The slope refers to the elevation change between the point and the surrounding neighboring pixels. The slope is calculated using the following formula:

[0066]

[0067] In the formula, S i,j is the slope value at the pixel point (i, j); ΔZ is the elevation difference between the pixel point and its neighboring pixels in the vertical direction; ΔX is the horizontal distance between the pixel point and its neighboring pixels in the horizontal direction, usually taken as 1 pixel unit; ΔY is the horizontal distance between the pixel point and its neighboring pixels in another horizontal direction;

[0068] The specific calculation method depends on the selection of the neighborhood. Usually, the slope is calculated using the elevation difference of a 3x3 neighborhood or a larger area. The slope value can be expressed in radians or degrees, and is usually converted to an angle as: θ i，j =arctan(S i,j ),θ i，j is the slope angle at (i, j);

[0069] In order to calculate the slope steepness coefficient, it is necessary to determine the maximum slope value in the sub-area; the maximum slope value S can be found by scanning the slope data of the entire area. max ;

[0070] For each pixel (i, j), calculate the slope steepness coefficient a i,j , the calculation formula is:

[0071] The mean of the slope steepness coefficients of all the pixels in the sub-region is calculated to obtain the slope steepness coefficient of the corresponding sub-region.

[0072] It should be noted that the slope steepness coefficient is used to measure the steepness of the slope of the sub-region. The larger the slope steepness coefficient, the smaller the rainfall that can be absorbed by the sub-region, because the steep slope area often leads to rapid water loss and weak water penetration into the soil; in areas with steeper slopes, most of the rainfall water is lost in the form of runoff and cannot be effectively penetrated and absorbed by the soil. The steeper slope increases the flow rate of water on the surface, reduces the retention time of water, and further reduces the water storage capacity of the soil; therefore, the larger the slope steepness coefficient, the worse the sub-region's ability to absorb precipitation. When making irrigation decisions, it is necessary to increase the amount of irrigation water accordingly to avoid untimely irrigation.

[0073] In one implementation, the benefit of calculating the slope steepness coefficient of a sub-region for irrigation control of the sub-region is that it can accurately reflect the water loss rate and infiltration capacity under different slope conditions, thereby providing more detailed data support for irrigation management. By understanding the slope characteristics of each sub-region, it is possible to predict the water distribution after precipitation, avoid over-reliance on rainfall water infiltration in areas with steeper slopes, and reduce water waste due to runoff. In addition, the calculation of the slope steepness coefficient helps determine which areas require more irrigation water to compensate for soil water loss and ensure that the water needs of crops throughout the growing season are fully met. In short, this data can effectively optimize irrigation plans, improve the efficiency of water resource utilization, avoid uneven or excessive irrigation, and promote the sustainable development of agricultural production.

[0074] In one embodiment, the soil permeability coefficient is used to measure the soil's ability to penetrate water, that is, the rate at which water penetrates through the soil surface into the groundwater layer; the coefficient is usually obtained through field tests (such as square permeability test, double ring permeability test, etc.), measuring the depth or rate of water penetration within a certain period of time; different types of soil (such as sand, clay, loam, etc.) have different permeability coefficients, usually the permeability coefficient of sand is larger, while the permeability coefficient of clay is smaller; generally speaking, the value range of the soil permeability coefficient is 0.1-100cm / h (centimeter per hour), and the specific value is affected by factors such as soil particle composition, structure, humidity and organic matter content. The larger the soil permeability coefficient, the stronger the permeability of water in the soil, and the soil can more effectively absorb and store precipitation, reducing surface runoff; conversely, soil with a smaller permeability coefficient is prone to water loss, affecting irrigation efficiency. Therefore, understanding and accurately calculating the soil permeability coefficient is crucial to optimizing irrigation decisions and improving water resource utilization efficiency.

[0075] It should be noted that the smaller the soil permeability coefficient of each sub-area, the smaller the rainfall that can be absorbed by the sub-area, because the smaller the soil permeability coefficient means that the water infiltrates the soil more slowly, and the precipitation water is more likely to form runoff on the surface, and it is difficult to store it deep in the soil. Soil with poor permeability usually has a short water retention time, making it difficult to effectively store water for crop absorption, resulting in rapid loss of surface water. Therefore, in such areas, although the rainfall may be large, the amount of water that can actually penetrate and be absorbed by crops is small, and the irrigation amount needs to be adjusted more accurately to ensure that the soil obtains enough water and avoid waste.

[0076] In one embodiment, calculating the water absorption coefficient according to the water absorption data and determining the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall includes:

[0077] The plant coverage coefficient, slope steepness coefficient and soil permeability coefficient of each sub-area are normalized and mapped to [0, 1], and the water absorption coefficient TG is calculated. The calculation formula is: In the formula, sx, sd and sv are the normalized plant coverage coefficient, slope steepness coefficient and soil permeability coefficient respectively;

[0078] The second rainfall is calculated using the formula WPU=EFR·TG; wherein WPU is the second rainfall, and EFR is the first rainfall.

[0079] It should be noted that normalization is to adjust the data value to a uniform range, usually between 0 and 1, to eliminate the impact of different dimensions and scales on the analysis results. The common implementation method is minimum-maximum normalization, that is, by subtracting the minimum value from the data and then dividing it by the range of the data (maximum value minus minimum value). In this way, all data will be adjusted to between 0 and 1, so that data of different scales can participate equally in subsequent analysis and calculation.

[0080] In one embodiment, obtaining the crop growth data corresponding to each sub-region and determining the amount of water required for each sub-region according to the crop growth data and historical crop growth data includes:

[0081] Obtain the current growth status data of crops in each sub-region, and obtain the historical growth status data of crops in different growth stages, and determine the amount of water required for each sub-region based on the crop planting area of ​​each sub-region, specifically:

[0082] Marking the historical growth status data of the crop at each different growth stage as target historical data;

[0083] Preprocess the current crop growth status data and target historical data;

[0084] Construct a distance matrix, in which each element is the distance between the crop growth status data point at the current stage and the target historical data point;

[0085] The dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the crop growth status data sequence at the current stage and the target historical data sequence;

[0086] According to the calculated shortest path, the volatility data series and the target historical data series are aligned;

[0087] According to the aligned fluctuation data sequence and historical data sequence, the similarity between them is calculated;

[0088] The target historical data corresponding to the maximum similarity is used as the final matching historical data, and the growth stage corresponding to the final matching historical data is used as the current growth stage of the crop;

[0089] The preset water requirement corresponding to the current growth stage of the crop is obtained, and the planting area of ​​the crop in the sub-region is obtained, and the preset water requirement and the planting area are multiplied after removing the unit to obtain the water consumption required for each sub-region.

[0090] It should be noted that the crop growth status data of each sub-region includes the key physiological and environmental parameters of crops in different growth periods, which can reflect the current growth status of crops. These data usually cover different characteristics of crops during their growth cycle, such as crop height, leaf area index (LAI), root development, photosynthetic rate, flowering and fruiting conditions, and physiological maturity. In addition, it also includes environmental factors such as soil moisture, temperature, precipitation, light intensity, and atmospheric humidity. These data are usually collected through remote sensing technology, ground sensors, drones, and other means, and can reflect the growth dynamics of crops in real time.

[0091] The growth stage of crops refers to the different stages of crops from sowing to maturity, divided according to their physiological characteristics. Generally speaking, the growth stage of crops can be divided into several stages, such as germination, seedling, jointing, flowering, filling and maturity. Each growth stage has its own unique growth characteristics and water requirements. The germination stage is mainly the seed germination and seedling growth stage, with low water demand; while the filling and maturity stages are the key stages of crop growth, and crops need more water to maintain growth and promote fruit formation. Therefore, according to the growth stage and related data of crops, their water requirements can be reasonably predicted, so as to formulate more accurate irrigation plans.

[0092] It should be noted that the preset water demand corresponding to the current growth stage of the crop is usually scientifically set based on the water demand of the crop variety and changes in environmental conditions. The water demand for each growth stage is different. For example, in the germination period, the water demand of the crop is relatively low, mainly used to promote seed germination and seedling growth; in the jointing and flowering periods, the crop enters a rapid growth stage, and the water demand increases significantly, mainly used to support the rapid growth of the plant and the formation of reproductive organs; in the filling period, the water demand of the crop reaches a peak, especially for crops such as rice, wheat, and corn. The water demand at this stage directly affects the yield and quality. For example, the water demand of rice during the flowering and filling periods may reach 100-150 mm per hectare per day, while the water demand in the early growth period may be only 30-50 mm. The water demand of different crops at different stages may be adjusted according to factors such as climatic conditions and soil moisture. Therefore, combined with the specific crop growth stage and actual environmental conditions, reasonable prediction and adjustment of water demand is an important basis for formulating irrigation plans.

[0093] In one implementation, the benefits of determining the amount of water required for each sub-region by the above method are that, first, this dynamic matching method based on the current growth state of the crop and historical data can more accurately reflect the water demand of crops in each sub-region at different growth stages, avoiding the use of static or generalized water estimation methods. By comparing the current crop growth stage and the historical growth state through the dynamic programming algorithm, the fluctuations and changes in crop growth can be effectively captured to ensure that the adjustment of water consumption is more in line with actual needs. Secondly, combined with the planting area of ​​the crop, the calculated water consumption not only takes into account the growth characteristics of the crop, but also quantitatively evaluates the actual planting conditions of the region. This method can formulate personalized irrigation plans according to the crop types and growth environments of different sub-regions, avoid excessive or insufficient irrigation, optimize the use of water resources, improve the utilization efficiency of water resources, and reduce waste. In addition, by calculating the similarity and selecting the most matching historical data, the irrigation amount can be adjusted according to the historical climate and growth law, further improving the accuracy of the prediction and the scientific nature of the decision.

[0094] In one embodiment, the water consumption is compared with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated; if the water consumption is not greater than the second rainfall, the corresponding sub-area does not need to be irrigated.

[0095] It should be noted that if the water consumption of a sub-region is greater than the second rainfall, it means that the rainfall in the sub-region cannot meet the water demand for crop growth, so irrigation is needed to supplement water to ensure the water supply required for crop growth.

[0096] If the water use is not greater than the second rainfall amount, it means that the precipitation in the sub-area is sufficient to meet the water demand of crops, or the precipitation is close to being sufficient and no additional irrigation is needed.

[0097] In one implementation, this method helps to reasonably adjust the irrigation amount, avoid over-irrigation and waste of water resources, while ensuring that crops receive adequate water supply, optimizing water resource management, and improving crop growth effects and agricultural production efficiency.

[0098] Based on the same inventive concept, the embodiment of the present invention also provides an intelligent irrigation control system based on meteorological information. Figure 2 , Figure 2 A framework diagram of an intelligent irrigation control system based on meteorological information provided by an embodiment of the present invention, the system includes:

[0099] The first rainfall module: the entire area to be irrigated is recorded as the target area, and the target area is divided into several sub-areas, and the rainfall in the target area within a preset time in the future is predicted as the first rainfall through a preset meteorological early warning model;

[0100] Second rainfall module: obtain water absorption data of each sub-area, calculate water absorption coefficient according to the water absorption data, and determine the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall; the above water absorption data include plant coverage coefficient, slope steepness coefficient and soil permeability coefficient;

[0101] Water consumption module: obtains the crop growth data corresponding to each sub-region, and determines the water consumption required for each sub-region based on the crop growth data and historical crop growth data;

[0102] Irrigation control module: compares the water consumption with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated.

[0103] An intelligent irrigation control system based on meteorological information provided by an embodiment of the present invention can, through the above method, make a relatively precise judgment on the soil moisture content of a small area, and evaluate whether the rainfall can cover the water demand of the small area, so as to judge whether the small area needs to be irrigated again. This method helps to reasonably adjust the irrigation amount, avoid over-irrigation and waste of water resources, and at the same time ensure that crops get enough water supply, optimize water resource management, and improve crop growth effects and agricultural production efficiency.

[0104] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be used to artificially limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent irrigation control method based on meteorological information, characterized in that: The following steps are involved: The entire area to be irrigated is recorded as the target area, and the target area is divided into several sub-areas, and the rainfall in the target area within a preset time in the future is predicted as the first rainfall by a preset meteorological early warning model; Acquire water absorption data of each sub-area, calculate a water absorption coefficient based on the water absorption data, and determine the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall; the water absorption data includes a plant coverage coefficient, a slope steepness coefficient, and a soil permeability coefficient; Obtain the crop growth data corresponding to each sub-region, and determine the amount of water required for each sub-region based on the crop growth data and historical crop growth data; The water consumption is compared with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated.

2. The intelligent irrigation control method based on meteorological information according to claim 1, characterized in that: The plant cover factor includes: Obtain satellite images of each sub-area, extract the reflectance values ​​of the near-infrared band and the red light band from the satellite images, and obtain the vegetation index NDVI of the corresponding pixels. The calculation formula is: In the formula, NIR and RED are the reflectance values ​​of the near infrared band and the red light band respectively; Send multiple laser pulses to each sub-area, obtain the flight time of the first echo and the flight time of the last echo, and calculate the average height of vegetation in each sub-area. The calculation formula is: Where SD is the average height of vegetation, c is the speed of light, tw and te are the flight time of the first echo and the flight time of the last echo, respectively; Calculate the plant cover factor FG using the following formula: FG = NDVI·SD.

3. The intelligent irrigation control method based on meteorological information according to claim 1, characterized in that: The slope steepness coefficient includes: Obtain digital elevation model (DEM) data of each sub-area, and extract all pixel points from the digital elevation model (DEM) data; For each pixel point, calculate its slope value. The slope refers to the elevation change between the point and the surrounding neighboring pixels. The slope is calculated using the following formula: In the formula, S i,j is the slope value at the pixel point (i, j); ΔZ is the elevation difference between the pixel point and its neighboring pixels in the vertical direction; ΔX is the horizontal distance between the pixel point and its neighboring pixels in the horizontal direction, usually taken as 1 pixel unit; ΔY is the horizontal distance between the pixel point and its neighboring pixels in another horizontal direction; Scan the entire digital elevation model (DEM), extract the slope data of the area, and find the maximum slope value S max ; For each pixel (i, j), calculate the slope steepness coefficient a i,j , the calculation formula is: The mean of the slope steepness coefficients of all the pixels in the sub-region is calculated to obtain the slope steepness coefficient of the corresponding sub-region.

4. The intelligent irrigation control method based on meteorological information according to claim 1, characterized in that: The water absorption coefficient is calculated according to the water absorption data, and the rainfall that can be absorbed by each sub-area is determined as the second rainfall in combination with the first rainfall, including: The plant coverage coefficient, slope steepness coefficient and soil permeability coefficient of each sub-area are normalized and mapped to [0, 1], and the water absorption coefficient TG is calculated. The calculation formula is: In the formula, sx, sd and sv are the normalized plant coverage coefficient, slope steepness coefficient and soil permeability coefficient respectively; The rainfall that can be absorbed by each sub-area is determined according to the water absorption coefficient and the first rainfall as the second rainfall.

5. The intelligent irrigation control method based on meteorological information according to claim 4 is characterized in that: Determining the rainfall that can be absorbed by each sub-area as the second rainfall according to the water absorption coefficient and the first rainfall includes: The second rainfall is calculated using the formula WPU=EFR·TG; wherein WPU is the second rainfall, EFR is the first rainfall, and TG is the water absorption coefficient.

6. The intelligent irrigation control method based on meteorological information according to claim 1, characterized in that: Obtain the crop growth data corresponding to each sub-region, and determine the water consumption required for each sub-region based on the crop growth data and historical crop growth data, including: Obtain the current growth status data of crops in each sub-region, and obtain the historical growth status data of crops in different growth stages, and determine the amount of water required for each sub-region based on the crop planting area of ​​each sub-region, specifically: Marking the historical growth status data of the crop at each different growth stage as target historical data; Preprocess the current crop growth status data and target historical data; Construct a distance matrix, in which each element is the distance between the crop growth status data point at the current stage and the target historical data point; The dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the crop growth status data sequence at the current stage and the target historical data sequence; According to the calculated shortest path, the volatility data series and the target historical data series are aligned; According to the aligned fluctuation data sequence and historical data sequence, the similarity between them is calculated; The target historical data corresponding to the maximum similarity is used as the final matching historical data, and the growth stage corresponding to the final matching historical data is used as the current growth stage of the crop; The preset water requirement corresponding to the current growth stage of the crop is obtained, and the planting area of ​​the crop in the sub-region is obtained, and the preset water requirement and the planting area are multiplied after removing the unit to obtain the water consumption required for each sub-region.

7. An intelligent irrigation control system based on meteorological information, used to implement the intelligent irrigation control method based on meteorological information as described in any one of claims 1 to 6, characterized in that: The system comprises: The first rainfall module: the entire area to be irrigated is recorded as the target area, and the target area is divided into several sub-areas, and the rainfall in the target area within a preset time in the future is predicted as the first rainfall through a preset meteorological early warning model; Second rainfall module: obtain water absorption data of each sub-area, calculate water absorption coefficient according to the water absorption data, and determine the rainfall that can be absorbed by each sub-area as the second rainfall in combination with the first rainfall; the above water absorption data include plant coverage coefficient, slope steepness coefficient and soil permeability coefficient; Water consumption module: obtains the crop growth data corresponding to each sub-region, and determines the water consumption required for each sub-region based on the crop growth data and historical crop growth data; Irrigation control module: compares the water consumption with the second rainfall. If the water consumption is greater than the second rainfall, the corresponding sub-area needs to be irrigated.

Images