A water resources scheduling optimization method based on empirical model

Through the water resource scheduling optimization method based on empirical model, the irrigation volume and the irrigation priority are dynamically adjusted, and the problems of uneven allocation of water resources and inefficient utilization in traditional irrigation systems are solved, and more efficient water resource utilization is achieved.

CN118657349BActive Publication Date: 2024-12-03ANHUI CHENGQIN DATA CO LTD

Patent Information

Application Number
CN202411131941.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-03
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

Traditional irrigation systems use fixed cycles and fixed irrigation volumes, and cannot be dynamically adjusted according to crop growth needs and soil conditions, resulting in uneven allocation of water resources and inefficient utilization.

Method used

The water resource scheduling optimization method based on empirical model is used to collect historical irrigation data and real-time spectral reflection data, build a crop growth coefficient model and soil type index, dynamically adjust the irrigation volume, and combine irrigation priority to allocate water resources to farmland in the irrigation area.

Benefits of technology

It has achieved dynamic adjustment of irrigation volume according to crop growth needs and soil characteristics, optimized water resource allocation, improved the overall water resource allocation efficiency in irrigation areas, and solved the problems of uneven water resource allocation and inefficient utilization efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118657349B_ABST
    Figure CN118657349B_ABST
Patent Text Reader

Abstract

The present invention provides a water resource scheduling optimization method based on an empirical model, and relates to the technical field of irrigation water resource allocation. The present invention collects and analyzes historical irrigation data of each growth stage, combines farmland spectral reflection data and environmental data, constructs a crop growth coefficient model, determines the adjustment coefficient of the crop at different growth stages, collects the type and growth stage of the crop in the current farmland to be irrigated, uses the historical irrigation data to determine the adjustment coefficient, matches the optimal adjustment coefficient corresponding to the growth stage and type of the crop, collects the spectral reflection data and environmental data of the farmland in real time, constructs the current crop adjustment coefficient, generates the crop water requirement in combination with the optimal adjustment coefficient, finally allocates the irrigation water resources of each farmland in the irrigation area in combination with the optimal irrigation amount by setting the irrigation priority, ensures the reasonable allocation of water resources among different farmlands, and optimizes the overall water resource configuration of the irrigation area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of irrigation water resource allocation, and in particular to a water resource scheduling optimization method based on an empirical model. Background Art

[0002] In agricultural production, irrigation water accounts for a large proportion of the total water consumption. The rational scheduling and use of water resources is the key to ensuring high crop yields and efficient use of water resources. In order to meet the needs of crop growth, traditional irrigation systems usually adopt fixed-cycle irrigation methods. This method is simple and easy to implement, but there are obvious problems of uneven water resource distribution and low efficiency.

[0003] In existing irrigation districts, water allocation is often based on fixed irrigation schedules, such as weekly or biweekly irrigation, with a fixed amount of water each time. For example, all fields within an irrigation district may receive the same amount of water each week, regardless of the actual water requirements of crops and differences in soil types. This "one-size-fits-all" irrigation approach ignores the dynamic changes in crop water requirements at different growth stages, as well as the effects of soil texture and organic matter content on water retention capacity. For example, during critical stages of crop growth, such as flowering or fruiting, the demand for water may increase significantly, and traditional irrigation methods cannot provide this flexibility.

[0004] The problems with this fixed and inflexible irrigation method include: first, it is unable to accurately supply water according to the actual growth needs of crops and soil conditions, which may lead to crop water shortage or excessive irrigation, affecting crop growth and yield; second, due to the lack of consideration of different farmland soil types and crop characteristics, water resources are often not optimally allocated, resulting in a waste of water resources; finally, this irrigation method lacks the ability to respond to environmental factors in real time, which makes irrigation decisions out of touch with actual environmental changes, further reducing the efficiency of water resource utilization.

[0005] Therefore, developing an irrigation water resource scheduling method that can dynamically adjust according to crop growth needs, soil conditions, and environmental changes is of great significance for improving water resource utilization efficiency and ensuring agricultural production.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a water resources scheduling optimization method based on an empirical model to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A water resources scheduling optimization method based on an empirical model, the specific steps include:

[0010] Step 1: Divide the growth cycle of crops planted in the farmland into different growth stages, and collect multiple sets of historical irrigation data for each growth stage, wherein the historical irrigation data includes irrigation amount, farmland spectral reflectance data and environmental data of the day before and the day after irrigation;

[0011] Step 2: Construct a crop growth coefficient model, input the historical irrigation data collected at each growth stage, determine the adjustment coefficients of crops at each growth stage, and determine the current crop adjustment coefficients based on the growth stage of the crops planted in the farmland to be irrigated;

[0012] Step 3: Collect the spectral reflectance data and environmental data of the farmland to be irrigated the previous day to form a real-time data set, generate the crop growth stage coefficient based on the real-time data set, build an analysis model based on the crop growth stage coefficient and the current crop adjustment coefficient, and generate the crop water requirement;

[0013] Step 4: Collect multiple groups of soil samples from farmland to be irrigated, analyze the soil samples, obtain soil texture data, organic matter content data and soil effective moisture content data, and generate a soil type index reflecting the soil water retention capacity based on the soil texture data, organic matter content data and soil effective moisture content data;

[0014] Step 5: Build an optimal irrigation amount model based on crop water demand and soil type index, determine the optimal irrigation amount for the farmland to be irrigated based on the area of ​​the farmland to be irrigated, collect the crop types of each farmland to be irrigated in the irrigation area, and determine the irrigation priority based on the soil type index of the farmland;

[0015] Step 6: Obtain the total irrigation water supply in the irrigation area, and allocate irrigation water resources for each farmland in the irrigation area according to the irrigation priority and the optimal irrigation amount of the farmland.

[0016] Furthermore, the irrigation volume is the irrigation water volume per unit area, and the farmland spectral reflectance data includes the reflectance of the near infrared band, the reflectance of the red light band, the reflectance of the red edge band, the reflectance of the blue light band and the reflectance of the short infrared band. The wavelength range of the near infrared band is , the wavelength range of the red light band is , the wavelength range of short infrared band is , the wavelength range of the red edge band is , the wavelength range of the blue light band is The environmental data include the average temperature, average humidity and average light intensity of the farmland environment.

[0017] Furthermore, the logic for constructing the crop growth coefficient model is:

[0018] Generate the vegetation index, chlorophyll index and moisture index of the crop on that day based on the daily farmland spectral reflectance data in the historical irrigation data;

[0019] The historical crop growth coefficient is generated by combining the vegetation index, chlorophyll index and moisture index corresponding to each day in the historical irrigation data, as well as the corresponding average temperature, average humidity and average light intensity;

[0020] The irrigation amount of each set of historical irrigation data is associated with the historical crop growth coefficient corresponding to the farmland spectral reflectance data and environmental data on the day before and after irrigation to form an environmental factor data set. The formed environmental factor data set is:

[0021]

[0022] in, Indicates Among the crops, The first growth stage The environmental factor data set consists of a group of historical data. , and Respectively represent Among the crops, The first growth stage The historical crop growth coefficient and irrigation amount of the previous day and the next day in the historical irrigation data of the group;

[0023] According to multiple sets of environmental factor data sets corresponding to the same crop type and the same growth stage, the environmental factor data set with the largest irrigation effect index is screened out, and the irrigation amount corresponding to the environmental factor data set is set as the optimal irrigation reference amount. The logic for generating the irrigation effect index is as follows:

[0024]

[0025] in, Indicates Among the crops, The first growth stage The irrigation effect index of the environmental factor data set composed of a group of historical data;

[0026] The crop growth coefficient model is constructed to determine the adjustment coefficient for the crop type and growth stage. The formula is as follows:

[0027]

[0028] in, Indicates Category, in The adjustment factor for crops at different growth stages is Indicates Category, in The optimal irrigation reference amount for crops at each growth stage is: Indicates the historical crop growth coefficient of the day before irrigation in the environmental factor dataset corresponding to the optimal irrigation reference amount, A number indicating the type of crop being grown. Indicates the number of the generation phase, Indicates the number of historical data.

[0029] Furthermore, the vegetation index, chlorophyll index and moisture index of the corresponding crops are generated based on the following formula:

[0030]

[0031]

[0032]

[0033] in, , and represent vegetation index, chlorophyll index and moisture index respectively. , , , and They represent the reflectivity of the near infrared band, the reflectivity of the red light band, the reflectivity of the red edge band, the reflectivity of the blue light band and the reflectivity of the short infrared band respectively;

[0034] The historical crop growth coefficient is generated based on the vegetation index, chlorophyll index and moisture index, as well as the average temperature, average humidity and average light intensity, according to the following formula:

[0035]

[0036] in, represents the historical crop growth coefficient, , and They represent the average temperature, average humidity and average light intensity of the farmland environment respectively.

[0037] Furthermore, according to the growth stage of the crops planted in the farmland to be irrigated, the logic for determining the current crop adjustment coefficient is as follows:

[0038] The adjustment coefficients of various growth stages of various types of crops constructed based on historical irrigation data are traversed, and the adjustment coefficients generated by historical irrigation data of the same crop type and growth stage are found, and defined as the current crop adjustment coefficients.

[0039] Furthermore, the specific logic of generating crop growth stage coefficients based on the real-time data set is as follows:

[0040] The vegetation index, chlorophyll index and moisture index of crops are generated based on the spectral reflectance data of the farmland to be irrigated the previous day in the real-time data set. The formula is as follows:

[0041]

[0042]

[0043]

[0044] in, , and They represent the determination of vegetation index, chlorophyll index and moisture index respectively. , , , , They respectively represent the reflectance of the near infrared band, the reflectance of the red band, the reflectance of the red edge band, the reflectance of the blue band and the reflectance of the short infrared band in the spectral reflectance data of the farmland to be irrigated the previous day in the real-time data set;

[0045] The crop growth stage coefficient is generated based on the vegetation index, chlorophyll index, moisture index, and environmental data in the real-time data set. The formula is as follows:

[0046]

[0047] in, represents the crop growth stage coefficient, , and They respectively represent the average temperature, average humidity and average light intensity in the environmental data of the farmland to be irrigated the previous day in the real-time dataset.

[0048] Furthermore, the analytical model is constructed to generate the formula based on which the crop water requirement is:

[0049]

[0050] in, Indicates the water requirement of crops, which is used to reflect the water requirement per unit area of ​​crops. represents the crop growth stage coefficient, Indicates the current crop adjustment factor.

[0051] Further, the method for generating the soil type index is:

[0052] At least five collection points are set in the farmland to be irrigated, and all the collection points are arranged in a straight line with the same spacing between adjacent collection points. The same amount of soil samples are collected at each collection point, and the soil depth of all soil samples is the same. The soil texture data, organic matter content data and soil effective moisture content data of all collected soil samples are analyzed to generate the soil type index, and the formula is as follows:

[0053]

[0054] in, represents the soil type index, , and Respectively represent Soil texture data, organic matter content data and soil effective moisture content data of each collection point, Indicates the number of the sampling point. Indicates the number of collection points, ;

[0055] The soil texture data is generated based on the formula:

[0056]

[0057] in, and Respectively The relative content of clay and silt in the soil samples from the collection points , are the clay weight coefficient and the silt weight coefficient respectively. , ;

[0058] The organic matter content data are the mass percentage of organic components in the soil samples, and the soil effective moisture content data are the volume percentage of water in the soil samples.

[0059] Furthermore, the logic for determining the optimal irrigation amount for the farmland to be irrigated is:

[0060]

[0061] in, represents the optimal irrigation amount for the farmland to be irrigated, Indicates the water requirement of crops. represents the soil type index, Represents the area of ​​farmland to be irrigated.

[0062] Furthermore, the method of collecting the crop types of each farmland to be irrigated in all irrigation areas and determining the irrigation priority in combination with the soil type index of the farmland is as follows;

[0063] Type weights are assigned based on the types of crops grown in the farmland, where crop types include food crops, cash crops, vegetable crops, fruit crops, and other crops. The type weights of food crops are , the type weight of cash crops is , the type weight of vegetable crops is , the type weights of fruit crops and other crops are , ,and ;

[0064] The priority is generated based on the type weight of the crop type grown on the farmland and the soil type index of the farmland soil, based on the formula:

[0065]

[0066] in, Indicates the first The priority of the farmland, and Respectively represent the first The type weight of the farmland and the soil type index of the soil, Indicates the number of the farmland to be irrigated in the irrigation area. , It indicates the total number of farmlands to be irrigated in the irrigation area;

[0067] The logic for allocating irrigation water resources to each farmland in the irrigation area is:

[0068]

[0069] in, Indicates the first The amount of water allocated to each farmland, Indicates the first The optimal irrigation amount for a piece of farmland, It represents the total amount of irrigation water in the irrigation area. Indicates the first The area of ​​farmland.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] The present invention collects and analyzes historical irrigation data of each growth stage, combines farmland spectral reflectance data and environmental data, constructs a crop growth coefficient model, determines the adjustment coefficient of crops at different growth stages, collects the types and growth stages of crops in the current farmland to be irrigated, uses historical irrigation data to determine the adjustment coefficient, matches the optimal adjustment coefficient corresponding to the growth stage and type of the crop, and makes the current crop adjustment coefficient the optimal solution for the current specific conditions. The subsequent irrigation amount allocation can dynamically adjust the crop water demand according to the actual growth needs of the crop.

[0072] The present invention constructs the current crop adjustment coefficient by collecting the spectral reflectance data and environmental data of the farmland in real time, and generates the crop water requirement in combination with the optimal adjustment coefficient. The crop water requirement can be used to indicate the optimal water requirement for crop growth under the current crop type and growth stage. The soil type index reflecting the soil water retention capacity is generated by collecting soil samples and analyzing their texture, organic matter content and effective water content. The introduction of the soil type index enables the irrigation system to construct an optimal irrigation amount model and generate the optimal irrigation amount according to the soil characteristics of different farmlands by combining the soil type index and the crop water requirement.

[0073] Finally, the present invention sets irrigation priorities and allocates irrigation water resources for each farmland in the irrigation area in combination with the optimal irrigation amount, thereby ensuring the rational distribution of water resources among different farmlands, further optimizing the overall water resource allocation of the irrigation area, and effectively solving the problems of uneven water resource distribution and low utilization efficiency in traditional irrigation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0075] Figure 2 This is a schematic diagram of the composition of historical irrigation data in the present invention. DETAILED DESCRIPTION

[0076] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0077] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0078] Example:

[0079] See also Figure 1 to Figure 2 , the present invention provides a technical solution:

[0080] A water resources scheduling optimization method based on an empirical model, the specific steps include:

[0081] Step 1: Divide the growth cycle of crops planted in the farmland into different growth stages, and collect multiple sets of historical irrigation data for each growth stage, wherein the historical irrigation data include irrigation amount, farmland spectral reflectance data and environmental data one day before and one day after irrigation.

[0082] In this embodiment, the types of crops planted in the farmland in the irrigation area are divided into food crops, cash crops, vegetable crops, fruit crops and other crops, and the growth stages of the planted crops are divided into sowing period, seedling period, growth period, flowering period, fruit development period, maturity period and harvest period. The irrigation amount is the irrigation water volume per unit area, and the unit is cubic meter per square meter. The calculation is obtained by dividing the volume of the total irrigation water by the area of ​​the farmland. The spectral reflectance data of the farmland include the reflectance of the near-infrared band, the reflectance of the red light band, the reflectance of the red edge band, the reflectance of the blue light band and the reflectance of the short infrared band. The wavelength range of the near-infrared band is , the wavelength range of the red light band is , the wavelength range of the short infrared band is , the wavelength range of the red edge band is , the wavelength range of the blue light band is The environmental data include the average temperature, average humidity and average light intensity of the farmland environment.

[0083] The spectral reflectance data of farmland is obtained through a hyperspectral sensor installed on a drone. The instrument emits light of a specific wavelength to the farmland and measures the intensity of the reflected light to calculate the reflectance. The average temperature, average humidity and average light intensity of the farmland environment refer to the average levels of temperature, humidity and light intensity in the farmland within a certain time range.

[0084] The average temperature refers to the arithmetic mean of all temperature readings recorded in the farmland within a certain period of time. If the temperature is measured every hour in a day, then the temperature readings of 24 hours are added together and then divided by 24 to obtain the average temperature of the day. The average humidity refers to the arithmetic mean of all humidity readings recorded in the farmland within a certain period of time. The calculation method is similar to the average temperature: all humidity readings in this time period are added together and then divided by the total number of readings. The average light intensity refers to the arithmetic mean of all light intensity readings recorded in the farmland within a certain period of time. The calculation method is still to add all light intensity readings in this time period and then divide by the total number of readings. In order to obtain an accurate average value, multiple measurement points can be set in the farmland, especially in large areas of farmland, to ensure that the data can represent the conditions of the entire farmland. It can also be collected through an automatic weather station or environmental monitoring system installed in the farmland. These systems can continuously record temperature, humidity and light intensity and automatically calculate the average value. In this embodiment, the time period of environmental data is days, and the farmland spectral reflectance data is collected at 12 noon.

[0085] Step 2: Construct a crop growth coefficient model, input the historical irrigation data collected at each growth stage, determine the adjustment coefficient for each growth stage of the crop, and determine the current crop adjustment coefficient based on the growth stage of the crop planted in the farmland to be irrigated.

[0086] In this embodiment, the logic for constructing the crop growth coefficient model is:

[0087] The vegetation index, chlorophyll index and moisture index of the crops of the day are generated based on the daily farmland spectral reflectance data in the historical irrigation data. By analyzing the spectral reflectance data, the growth and health status of the crops can be monitored in real time. The vegetation index is used to evaluate the health status of the crops. The higher the vegetation index, the better the vegetation coverage and the better the crop health status. The chlorophyll index is an indicator used to estimate the chlorophyll content in the leaves of the crops. Chlorophyll is a key pigment for photosynthesis in plants, and its content directly affects the photosynthetic efficiency and growth status of the plants. The higher the chlorophyll index value, the higher the chlorophyll content, the stronger the photosynthesis ability of the crops, and the better the health status. The moisture index is an indicator used to evaluate the moisture content of the crops. Water is one of the important limiting factors for plant growth. The higher the moisture index value, the higher the moisture content of the crops and the lower the water stress.

[0088] The historical crop growth coefficient is generated by combining the corresponding vegetation index, chlorophyll index and moisture index of each day in the historical irrigation data, as well as the corresponding average temperature, average humidity and average light intensity. The historical crop growth coefficient specifically reflects the comprehensive assessment of crop growth conditions within a specific time range. It takes into account the impact of environmental factors on the vegetation index, chlorophyll index and moisture index, as well as the crop growth and health conditions represented by these indices themselves. By calculating the historical crop growth coefficient, a comprehensive indicator can be obtained, which can more accurately reflect the actual growth of crops under specific environmental conditions.

[0089] The introduction of average temperature, average humidity and average illuminance is mainly to correct or standardize the vegetation index, chlorophyll index and moisture index to eliminate the potential impact of these environmental variables on the crop growth index. For example, high temperature may cause a decrease in the moisture index, even if the actual moisture conditions have not changed. Similarly, changes in illuminance may also affect the chlorophyll index readings. By combining the average values ​​of these environmental factors, we can more accurately assess the true growth status of crops under these conditions, rather than simply relying on changes in a single index, making the generated historical crop growth coefficient more reliable and practical.

[0090] The irrigation amount of each set of historical irrigation data is associated with the historical crop growth coefficient corresponding to the farmland spectral reflectance data and environmental data on the day before and after irrigation to form an environmental factor data set. The formed environmental factor data set is:

[0091]

[0092] in, Indicates Among the crops, The first growth stage The environmental factor data set consists of a group of historical data. , and Respectively represent Among the crops, The first growth stage The historical crop growth coefficient and irrigation amount of the previous day and the next day in the set of historical irrigation data are collected. Multiple sets of historical irrigation data are collected at each growth stage of each crop type.

[0093] According to multiple sets of environmental factor data sets corresponding to the same crop type and the same growth stage, the environmental factor data set with the largest irrigation effect index is screened out, and the irrigation amount corresponding to the environmental factor data set is set as the optimal irrigation reference amount. The logic for generating the irrigation effect index is as follows:

[0094]

[0095] in, Indicates Among the crops, The first growth stage The irrigation effect index of the environmental factor data set composed of a group of historical data.

[0096] The irrigation effect index reflects the actual growth of crops, that is, the change in the health status of crops, between the day before and the day after irrigation. The larger the irrigation effect index, the better the irrigation effect, and the corresponding irrigation amount is more suitable for crops of this type and growth stage.

[0097] The crop growth coefficient model is constructed to determine the adjustment coefficient for the crop type and growth stage. The formula is as follows:

[0098]

[0099] in, Indicates Category, in The adjustment factor for crops at different growth stages is Indicates Category, in The optimal irrigation reference amount for crops at each growth stage is: Indicates the historical crop growth coefficient of the day before irrigation in the environmental factor dataset corresponding to the optimal irrigation reference amount, A number indicating the type of crop being grown. Indicates the number of the generation phase, Indicates the number of historical data.

[0100] The adjustment factor reflects the relative relationship between the optimal irrigation reference amount and the historical crop growth coefficient of the day before irrigation for a specific crop type and growth stage. This coefficient is calculated by comparing the maximum irrigation effect with the maximum historical crop growth coefficient of the day before irrigation. The larger the value of the adjustment coefficient, the greater the crop growth promotion effect of the optimal irrigation reference amount relative to the historical crop growth coefficient of the day before irrigation for a given crop type and growth stage. This coefficient reflects the degree of optimization of irrigation amount for crop growth under specific conditions. The adjustment coefficient provides a quantitative indicator to help determine what irrigation amount can most effectively promote crop growth under specific crop types and growth stages.

[0101] In this embodiment, the vegetation index, chlorophyll index and moisture index of the corresponding crop are generated based on the following formula:

[0102]

[0103]

[0104]

[0105] in, , and represent vegetation index, chlorophyll index and moisture index respectively. , , , and They respectively represent the reflectivity of the near-infrared band, the reflectivity of the red light band, the reflectivity of the red edge band, the reflectivity of the blue light band and the reflectivity of the short infrared band.

[0106] The vegetation index, chlorophyll index and moisture index are constructed by analyzing the differences in spectral reflectance in different bands. Because different substances have different reflection and absorption characteristics for light of different wavelengths, vegetation has a higher reflectance in the near-infrared band and a stronger absorption in the red light band. Therefore, by comparing the difference in reflectance between these two bands, the biomass and growth vitality of vegetation can be quantified. The higher the vegetation index, the better the vegetation coverage and the more vigorous the growth. The change in chlorophyll reflectance in the red-edge band and the blue-light band is related to the chlorophyll content. The change in chlorophyll will affect the reflectance in the red-edge band. The chlorophyll relative content is evaluated by the chlorophyll index, thereby understanding the photosynthesis efficiency of crops. Water has a strong absorption characteristic in the short-infrared band. The moisture content of vegetation can be evaluated by the moisture index. The higher the moisture index value, the higher the moisture content.

[0107] The historical crop growth coefficient is generated based on the vegetation index, chlorophyll index and moisture index, as well as the average temperature, average humidity and average light intensity, according to the following formula:

[0108]

[0109] in, represents the historical crop growth coefficient, , and They represent the average temperature, average humidity and average light intensity of the farmland environment respectively.

[0110] The historical crop growth coefficient combines the vegetation index, chlorophyll index and moisture index with environmental factors to calibrate the impact of environmental factors on these indices, thereby more accurately reflecting the actual growth status of crops. The logical relationship of this calibration is based on the impact of environmental factors on crop physiological processes and growth characteristics.

[0111] Temperature affects the growth rate and metabolic activity of crops. Higher temperatures can promote photosynthesis and the transport of nutrients, thereby increasing the vegetation index. Temperature affects the synthesis and degradation of chlorophyll. Higher temperatures are conducive to the accumulation of chlorophyll and increase the chlorophyll index. Temperature affects transpiration and water loss. Higher temperatures can cause rapid evaporation of water, reduce the moisture content of soil and crops, and thus reduce the moisture index. Since the actual scenario is crop planting, extreme temperatures are not considered.

[0112] Humidity affects the water absorption and transpiration of crops. Higher humidity helps maintain the water balance of crops and supports healthy growth, thereby improving the vegetation index. Humidity affects the water status of leaves, which in turn affects the synthesis of chlorophyll. Higher humidity conditions are conducive to the accumulation of chlorophyll and increase the chlorophyll index. Humidity directly affects the moisture content of soil and crops. High humidity can reduce water evaporation and maintain a higher moisture index; low humidity may cause rapid water loss and reduce the moisture index.

[0113] Light is the energy source for photosynthesis, which directly affects the growth of crops and the accumulation of biomass. Sufficient light can improve the vegetation index, while insufficient light may lead to growth stunting. Light directly affects the synthesis of chlorophyll. Sufficient light is conducive to the accumulation of chlorophyll and improves the chlorophyll index. Insufficient light may lead to a decrease in chlorophyll content. Light intensity indirectly affects the use and loss of water by affecting photosynthesis and transpiration. Strong light will increase transpiration and lead to rapid water loss.

[0114] The vegetation index reflects the growth status and biomass of vegetation, the chlorophyll index reflects the chlorophyll content and the photosynthesis efficiency of crops, and the moisture index reflects the moisture status of crops and soil. Therefore, the vegetation index is calculated by dividing To correct the influence of environmental factors, the vegetation index can more accurately reflect the state of vegetation itself. The chlorophyll index is calculated by dividing To eliminate the influence of environmental factors on chlorophyll content, the chlorophyll index can more purely reflect the actual content of chlorophyll. The moisture index is multiplied by and divided by To correct the impact of environmental factors on water status, so that the moisture index can more accurately reflect the moisture status of crops and soil.

[0115] By separating and correcting the impact of environmental factors on the vegetation index, chlorophyll index and moisture index, these indices can more truly reflect the growth status of crops without interference from environmental factors, and the historical crop growth coefficient can more accurately represent the actual growth conditions of crops.

[0116] In this embodiment, the logic for determining the current crop adjustment coefficient according to the growth stage of the crops planted in the farmland to be irrigated is:

[0117] The adjustment coefficients of various growth stages of various types of crops constructed based on historical irrigation data are traversed, and the adjustment coefficients generated by historical irrigation data of the same crop type and growth stage are found, and defined as the current crop adjustment coefficients.

[0118] By collecting the types and growth stages of crops and using historical irrigation data to determine the adjustment coefficient, the optimal adjustment coefficient corresponding to the growth stage and type of crops can be accurately matched. This will facilitate the subsequent determination of what irrigation amount can most effectively promote crop growth based on the optimal adjustment coefficient, ensure that the irrigation plan matches the actual needs of the crops, improve the accuracy and efficiency of irrigation, and find the current crop adjustment coefficient. In essence, it is to find historical irrigation data that fully matches the current crop type and growth stage, which can ensure that the adjustment coefficient is the optimal solution for the current specific conditions.

[0119] Step 3: Collect the spectral reflectance data and environmental data of the farmland to be irrigated the day before to form a real-time data set, generate the crop growth stage coefficient based on the real-time data set, build an analysis model based on the crop growth stage coefficient and the current crop adjustment coefficient, and generate the crop water requirement.

[0120] The specific logic for generating crop growth stage coefficients based on real-time data sets is:

[0121] The vegetation index, chlorophyll index and moisture index of crops are generated based on the spectral reflectance data of the farmland to be irrigated the previous day in the real-time data set. The formula is as follows:

[0122]

[0123]

[0124]

[0125] in, , and They represent the determination of vegetation index, chlorophyll index and moisture index respectively. , , , , They respectively represent the reflectance of the near infrared band, the reflectance of the red band, the reflectance of the red edge band, the reflectance of the blue band and the reflectance of the short infrared band in the spectral reflectance data of the farmland to be irrigated the previous day in the real-time data set;

[0126] The crop growth stage coefficient is generated based on the vegetation index, chlorophyll index, moisture index, and environmental data in the real-time data set. The formula is as follows:

[0127]

[0128] in, represents the crop growth stage coefficient, , and The average temperature, average humidity and average light intensity in the environmental data of the farmland to be irrigated the previous day in the real-time data set are respectively represented; the crop growth stage coefficient combines the vegetation index, chlorophyll index and moisture index with the environmental data in the real-time data set to calibrate the impact of environmental factors on these indexes, thereby more accurately reflecting the real-time growth status of the crop.

[0129] In the real-time data set, the generation logic of judging the vegetation index, judging the chlorophyll index and judging the moisture index is the same as the logic of generating the vegetation index, chlorophyll index and moisture index of the corresponding crops from the historical irrigation data. In the real-time data set, the logic of generating the crop growth stage coefficient is the same as the logic of generating the historical crop growth coefficient in the historical irrigation data. However, the processing of real-time data is different in purpose, application and data source.

[0130] The reason for the similarity is that historical irrigation data provides experience-based references, while real-time data sets provide current feedback. In order to effectively combine the two, the same evaluation criteria and calculation methods need to be used to ensure consistency in the analysis results.

[0131] The operation of generating crop growth stage coefficients using real-time data sets is complementary to the previous process of determining adjustment coefficients based on historical irrigation data. The historical data processing step relies on past irrigation data, while this step relies on the current real-time data set. The real-time data provides specific information about current crop and environmental conditions. The purpose of the historical data processing step is to determine an adjustment coefficient based on historical experience so that it can be applied under similar conditions. The purpose of this step is to generate a crop growth stage coefficient that reflects the current crop growth status and environmental conditions based on the current real-time data. The adjustment coefficient generated by the historical data processing step can be applied to similar historical conditions, while the crop growth stage coefficient generated by the real-time data is directly applied to the current irrigation decision. The historical data processing provides an experience-based benchmark, while the real-time data processing provides real-time calibration.

[0132] In this embodiment, the analysis model is constructed to generate the formula based on which the crop water requirement is:

[0133]

[0134] in, Indicates the water requirement of crops, which is used to reflect the water requirement per unit area of ​​crops. represents the crop growth stage coefficient, Indicates the current crop adjustment factor.

[0135] Crop water requirement indicates the water requirement per unit area of ​​crops, in cubic meters per square meter. The crop growth stage coefficient reflects the water demand of the crop at the current growth stage. It is a coefficient adjusted according to the crop growth stage to ensure the appropriate amount of water is provided at different stages.

[0136] The current crop adjustment coefficient indicates the degree of optimization of crop water requirement for crop growth under the current crop type and growth stage. The crop water requirement is the amount of irrigation water that can bring greater crop growth promotion effect relative to the crop growth stage coefficient of the day before irrigation. The current crop adjustment coefficient is a quantitative indicator based on historical data. It helps determine which crop water requirement can most effectively promote crop growth under the crop type and growth stage in the real-time data set, and helps to achieve precise irrigation, which can not only meet the growth needs of crops, but also avoid waste of water resources.

[0137] Step 4: Collect multiple groups of soil samples from farmland to be irrigated, analyze the soil samples, obtain soil texture data, organic matter content data and soil effective moisture content data, and generate a soil type index reflecting the soil water retention capacity based on the soil texture data, organic matter content data and soil effective moisture content data.

[0138] In this embodiment, the method for generating the soil type index is:

[0139] At least five collection points are set up in the farmland to be irrigated, and all the collection points are arranged in a straight line with the same spacing between adjacent collection points. An equal amount of soil samples are collected at each collection point, and all soil samples are collected at the same soil depth. The collected samples are consistent in depth. Such a setting helps to ensure the representativeness and uniformity of the samples and reduce errors caused by geographical differences.

[0140] The soil texture data, organic matter content data and soil effective moisture content data of all collected soil samples were analyzed to generate the soil type index based on the formula:

[0141]

[0142] in, represents the soil type index, , and Respectively represent Soil texture data, organic matter content data and soil effective moisture content data of each collection point, Indicates the number of the sampling point. Indicates the number of collection points, , respectively, calculate the sum of soil texture data, organic matter content data and soil effective moisture content data at the collection points, and divide the average of soil texture data, organic matter content data and soil effective moisture content data by the number of collection points.

[0143] The soil texture data is generated based on the formula:

[0144]

[0145] in, and Respectively The relative content of clay and silt in the soil samples from the collection points , are the clay weight coefficient and the silt weight coefficient respectively. , ;

[0146] The organic matter content data are the mass percentage of organic components in the soil samples, and the soil effective moisture content data are the volume percentage of water in the soil samples.

[0147] The larger the soil type index is, the stronger the soil water retention capacity is. The value ranges of soil texture data, organic matter content data and soil effective moisture content data are all from 0 to 1. The range of is 0 to π / 2, so the value range of soil type index is 0 to 1. The reason for using sine function for fitting is that in the range of 0 to π / 2, the sine function is monotonically increasing, ensuring that the soil type index increases with the increase of soil texture, organic matter content and effective moisture content data. The sine function provides a nonlinear mapping method that can capture the complex relationship between soil characteristic data. When the soil texture data, organic matter content data and soil effective moisture content data are too high, due to the saturation effect, the effect of their increase on the soil type index becomes lower and lower, and eventually tends to be stable.

[0148] Soil texture is determined by the ratio of soil particles of different sizes. Clay and silt have an important influence on the physical properties of soil. Clay has the largest specific surface area and can absorb and retain a large amount of water. Therefore, soils with high clay content usually have a higher water retention capacity. The specific surface area of ​​silt is smaller than that of clay, but larger than that of sand, so they can also provide a certain water retention capacity. Soils with high silt content usually have a moderate water retention capacity. Because clay has a more significant effect on the structure and water retention capacity of the soil, .

[0149] The organic matter content data indicates the mass percentage of organic components in the soil sample. Organic matter provides cementing materials, allowing soil particles to form a more stable and loose structure, thereby increasing the porosity and water holding capacity of the soil. Organic matter also has strong water absorption and can absorb and retain large amounts of water. Therefore, the higher the organic matter content in the soil, the stronger its water retention capacity. The effective moisture content of the soil refers to the volume percentage of water in the soil that is available for plants to absorb and utilize. Soil with a high effective moisture content can provide plants with a more stable water supply. The effective moisture content of the soil directly reflects the actual water supply capacity of the soil. The higher the effective moisture content, the more moisture the soil can retain after rainfall or irrigation, so the more moisture the plants can use, and the stronger the water retention capacity of the soil.

[0150] Step 5: Construct an optimal irrigation amount model based on crop water demand and soil type index, determine the optimal irrigation amount for the farmland to be irrigated based on the area of ​​the farmland to be irrigated, collect the crop types of each farmland to be irrigated in the irrigation area, and determine the irrigation priority based on the soil type index of the farmland.

[0151] In this embodiment, the logic for determining the optimal irrigation amount for the farmland to be irrigated is:

[0152]

[0153] in, represents the optimal irrigation amount for the farmland to be irrigated, Indicates the water requirement of crops. represents the soil type index, Represents the area of ​​farmland to be irrigated.

[0154] Crop water requirement is the amount of irrigation water that can bring greater crop growth promotion effect relative to the crop growth stage coefficient of the day before irrigation. Crop water requirement is the basis of the optimal irrigation amount. It directly reflects the crop's demand for water at different growth stages. The higher the crop water requirement, the higher the optimal irrigation amount to ensure that the crop can obtain enough water to support its growth.

[0155] The soil type index reflects the water retention capacity of the soil. The lower the soil type index, the worse the soil's water retention capacity, so more irrigation water is needed to replenish the water lost due to insufficient soil water retention. On the contrary, if the soil type index is high, it means that the soil has a better water retention capacity and the irrigation amount can be reduced because the soil can retain water more effectively. The farmland area is a necessary parameter for calculating the total irrigation amount. The larger the area, the greater the total irrigation amount. Therefore, the farmland area is a factor that directly affects the total irrigation amount.

[0156] By dividing the crop water requirement by the soil type index, the actual amount of water required by the crop per unit area can be obtained, and then multiplied by the farmland area, the total irrigation amount required for the entire farmland can be obtained. This embodiment not only takes into account the water requirement of the crop, but also takes into account the characteristics of the soil, so as to more accurately match the actual water requirement of the crop. By introducing the soil type index, the irrigation amount can be adjusted according to the water retention capacity of different soils, which helps to achieve the rational allocation and efficient use of water resources, avoid excessive irrigation and water waste, and ensure that crops get enough water to support their growth and development.

[0157] Furthermore, the method of collecting the crop types of each farmland to be irrigated in all irrigation areas and determining the irrigation priority in combination with the soil type index of the farmland is as follows;

[0158] Type weights are assigned based on the types of crops grown in the farmland, including food crops, cash crops, vegetable crops, fruit crops and other crops. Type weights are assigned based on the types of crops grown in the farmland, including food crops, cash crops, vegetable crops, fruit crops and other crops. The type weights of food crops are , the type weight of cash crops is , the type weight of vegetable crops is , the type weights of fruit crops and other crops are , ,and .

[0159] Furthermore, the type weights of crop types are specifically distributed as follows: the type weight of grain crops is 0.35, the type weight of cash crops is 0.25, the type weight of vegetable crops is 0.2, and the type weight of fruit crops and other crops is 0.1.

[0160] The larger the weight, the more important this type of crop is in the irrigation priority. When determining the irrigation priority, different weights are given to different crop types, reflecting the importance, value and urgency of water demand of these crops in agricultural production and social economy. Therefore, food crops have the largest weight, which is set to 0.35, because ensuring food supply is the top priority at present. Cash crops such as oilseeds and fiber crops contribute greatly to the economy, especially in terms of export and industrial raw material supply. Therefore, the weight of cash crops is 0.25.

[0161] Vegetable crops are also very important for people's daily diet, but compared with food crops, their demand is not as urgent and their economic benefits are not high. The weight of vegetable crops is lower than that of food crops and cash crops. Fruit crops and other crops may include a variety of diversified crops, which play an important role in maintaining ecological diversity and environmental balance. However, these crops have lower demand for water resources, and their economic value and social demand are not as significant as other crops, so their weight is the lowest.

[0162] Step 6: Obtain the total irrigation water supply in the irrigation area, and allocate irrigation water resources for each farmland in the irrigation area according to the irrigation priority and the optimal irrigation amount of the farmland.

[0163] The priority is generated based on the type weight of the crop type grown on the farmland and the soil type index of the farmland soil, based on the formula:

[0164]

[0165] in, Indicates the first The priority of the farmland, and Respectively represent the first The type weight of the farmland and the soil type index of the soil, Indicates the number of the farmland to be irrigated in the irrigation area. , It indicates the total number of farmlands to be irrigated in the irrigation area.

[0166] By combining the type weights of crop types and the soil type index, it can be ensured that with limited irrigation resources, water resources can be fairly and efficiently allocated according to the specific needs and importance of different farmlands. The type weights reflect the water needs of different crops and their importance in agricultural production, while the soil type index reflects the water retention capacity of the soil. By multiplying the two, a priority score that comprehensively considers crop needs and soil conditions can be obtained to determine which farmlands need irrigation the most.

[0167] Priority indicates the irrigation priority of farmland. The higher the value, the higher the priority of the farmland in the allocation of irrigation resources, that is, the more it needs to be irrigated first. If a piece of farmland is planted with crops with a higher type weight (such as grain crops), then its type weight will be higher. The soil type index reflects the water retention capacity of the soil. The higher the index means the stronger the water retention capacity of the soil, because better soil conditions mean that the demand for irrigation of crops may be reduced, but at the same time, irrigation water can be used more efficiently.

[0168] In the case of limited resources, it is necessary to ensure that water resources can be used efficiently. By combining the importance of crop types and soil conditions, it can be ensured that those farmlands that need water the most are irrigated first, thereby improving the overall water resource utilization efficiency. The correlation between type weights and soil type indexes and farmland irrigation priorities is to ensure that under limited irrigation resources, resources can be reasonably allocated according to the actual needs of crops and soil conditions to achieve maximum benefits of agricultural production and effective use of resources.

[0169] Furthermore, the logic for allocating irrigation water resources to each farmland in the irrigation area is as follows:

[0170]

[0171] in, Indicates the first The amount of water allocated to each farmland, Indicates the first The optimal irrigation amount for a piece of farmland, It represents the total amount of irrigation water in the irrigation area. Indicates the first The area of ​​farmland, Indicates the number of the farmland to be irrigated in the irrigation area. , It indicates the total number of farmlands to be irrigated in the irrigation area.

[0172] The allocation of water resources in the irrigation area takes into account both the optimal irrigation amount of each farmland and the relative importance and area of ​​each farmland. The allocation of water resources is more fair and efficient, and can meet the actual needs of different farmlands. At the same time, taking into account the water resource limitations of the entire irrigation area, the optimal irrigation amount is the irrigation amount calculated based on the crop water requirement, soil type index and farmland area, which reflects the actual irrigation needs of each farmland. The product of the irrigation priority of each farmland and its area reflects the relative importance and actual size of the farmland. By dividing this product by the sum of the products of the priorities and areas of all farmlands, the relative allocation ratio of each farmland can be obtained. The relative allocation ratio of each farmland is multiplied by the total irrigation water volume in the irrigation area to obtain the amount of water that should theoretically be allocated to each farmland.

[0173] use The function ensures that the actual amount of water allocated to each farmland will not exceed its optimal irrigation amount, nor will it exceed the theoretical allocation amount calculated based on priority and area. That is, the actual amount of water allocated to each farmland is the minimum between its optimal irrigation amount and the theoretical allocation amount calculated based on priority and area. Under limited water resources, it can ensure that the allocation of water resources not only meets the actual needs of the farmland, but also takes into account the relative importance and area of ​​the farmland, as well as the water resource limitations of the entire irrigation area. It can ensure that key farmlands get enough water resources while avoiding waste of water resources.

[0174] By taking the priority and area of ​​farmland into consideration, it is ensured that water resource allocation is not only based on the needs of farmland, but also takes into account the actual size and importance of farmland, so that a more equitable and efficient water resource allocation can be achieved between different farmlands. The strategy of minimizing allocation is adopted to ensure that the actual amount of water allocated to each farmland does not exceed its optimal irrigation amount, nor does it exceed the theoretical allocation calculated based on priority and area. This helps to avoid over-allocation of water resources, optimize the use of water resources, allow dynamic adjustment of water resource allocation according to the actual needs and priorities of different farmlands, and enhance the flexibility and adaptability of the irrigation system. This is of great significance for coping with different climatic conditions, crop needs and soil types.

[0175] This embodiment comprehensively considers multiple factors such as farmland priority, area, and optimal irrigation amount to calculate the actual amount of water allocated to each farmland. This precision and comprehensive consideration makes water resource allocation more efficient and reasonable, and can better adapt to and meet the actual needs of different farmlands, thereby improving the performance and economic benefits of the irrigation system as a whole.

[0176] In this embodiment, the area of ​​farmland is uniformly expressed in square meters, the amount of irrigation water is uniformly expressed in cubic meters, clay particles are the smallest part of soil particles, with a diameter of less than 0.002 mm, and the diameter of powder particles is between 0.002 mm and 0.05 mm. Organic components refer to organic matter derived from organisms in the soil, including humus, organic residues and microorganisms, etc. The units of measured temperature and humidity are degrees Celsius and relative humidity, respectively, and the unit of light intensity is lux.

[0177] In this embodiment, the classification of crop types is mainly based on the purpose of the crops. For example, food crops are mainly used for direct human consumption or as staple food raw materials, cash crops are mainly used for industrial processing, such as textiles, sugar making, oil extraction, etc., vegetable crops are mainly for direct human consumption and provide nutrients such as vitamins and minerals, fruit tree crops mainly provide fruits that can be eaten directly or processed, and other crops include medicinal plants, spice crops, and ornamental plants. This classification is helpful for research and development based on the needs of different crop types. In this embodiment, the crop growth stages are divided into sowing period, seedling period, growth period, flowering period, fruit development period, maturity period and harvest period, which are based on the natural process and physiological changes of crop growth.

[0178] This embodiment constructs a crop growth coefficient model by collecting and analyzing historical irrigation data at each growth stage, combining farmland spectral reflectance data and environmental data, and can accurately determine the adjustment coefficient of crops at different growth stages. By collecting the type and growth stage of the crops currently to be irrigated, the adjustment coefficient is determined using historical irrigation data, and the optimal adjustment coefficient corresponding to the growth stage and type of the crop is accurately matched, so that the current crop adjustment coefficient is the optimal solution for the current specific conditions. The subsequent irrigation amount allocation can dynamically adjust the crop water demand according to the actual growth needs of the crop.

[0179] This embodiment constructs the current crop adjustment coefficient by real-time collection of spectral reflectance data and environmental data of farmland, and generates crop water requirement in combination with the optimal adjustment coefficient. The crop water requirement can be used to indicate the optimal water requirement for crop growth under the current crop type and growth stage. A soil type index reflecting the soil's water retention capacity is generated by collecting soil samples and analyzing their texture, organic matter content, and effective moisture content. The introduction of the soil type index enables the irrigation system to construct an optimal irrigation amount model and generate the optimal irrigation amount based on the soil characteristics of different farmlands by combining the soil type index and crop water requirement.

[0180] The final embodiment sets irrigation priorities and allocates irrigation water resources for each farmland in the irrigation area in combination with the optimal irrigation amount, thereby ensuring the rational distribution of water resources among different farmlands, further optimizing the overall water resource allocation of the irrigation area, and effectively solving the problems of uneven water resource distribution and low utilization efficiency in traditional irrigation methods.

[0181] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0182] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0183] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A water resources scheduling optimization method based on empirical model, characterized in that: The specific steps include: Step 1: Divide the growth cycle of crops planted in the farmland into different growth stages, and collect multiple sets of historical irrigation data for each growth stage, wherein the historical irrigation data includes irrigation amount, environmental data, and farmland spectral reflectance data of the day before and the day after irrigation; Step 2: Construct a crop growth coefficient model, input the historical irrigation data collected at each growth stage, determine the adjustment coefficients of crops at each growth stage, and determine the current crop adjustment coefficients based on the growth stage of the crops planted in the farmland to be irrigated; Step 3: Collect environmental data and spectral reflectance data of the farmland to be irrigated the previous day to form a real-time data set, generate crop growth stage coefficients based on the real-time data set, build an analysis model based on the crop growth stage coefficients and the current crop adjustment coefficients, and generate crop water requirements; Step 4: Collect multiple groups of soil samples from farmland to be irrigated, analyze the soil samples, obtain soil texture data, organic matter content data and soil effective moisture content data, and generate a soil type index reflecting the soil water retention capacity based on the soil texture data, organic matter content data and soil effective moisture content data; Step 5: Build an optimal irrigation amount model based on crop water demand and soil type index, determine the optimal irrigation amount for the farmland to be irrigated based on the area of ​​the farmland to be irrigated, collect the crop types of each farmland to be irrigated in the irrigation area, and determine the irrigation priority based on the soil type index of the farmland; Step 6: Obtain the total water supply for irrigation in the irrigation area, and allocate irrigation water resources for each farmland in the irrigation area according to the irrigation priority and the optimal irrigation amount of the farmland; The irrigation volume is the irrigation water volume per unit area. The farmland spectral reflectance data includes the reflectance of the near infrared band, the reflectance of the red light band, the reflectance of the red edge band, the reflectance of the blue light band and the reflectance of the short infrared band. The wavelength range of the near infrared band is , the wavelength range of the red light band is , the wavelength range of short infrared band is , the wavelength range of the red edge band is , the wavelength range of the blue light band is , the environmental data include the average temperature, average humidity and average light intensity of the environment in which the farmland is located; The logic behind constructing the crop growth coefficient model is: Generate the vegetation index, chlorophyll index and moisture index of the crop on that day based on the daily farmland spectral reflectance data in the historical irrigation data; The historical crop growth coefficient is generated by combining the vegetation index, chlorophyll index and moisture index corresponding to each day in the historical irrigation data, as well as the corresponding average temperature, average humidity and average light intensity; The irrigation amount, environmental data, and historical crop growth coefficients corresponding to the farmland spectral reflectance data of each set of historical irrigation data on the day before and the day after irrigation are associated to form an environmental factor data set. The formed environmental factor data set is: in, Indicates Among the crops, The first growth stage The environmental factor data set consists of a group of historical data. , and Respectively represent Among the crops, The first growth stage The historical crop growth coefficient and irrigation amount of the previous day and the next day in the historical irrigation data of the group; According to multiple sets of environmental factor data sets corresponding to the same crop type and the same growth stage, the environmental factor data set with the largest irrigation effect index is screened out, and the irrigation amount corresponding to the environmental factor data set is set as the optimal irrigation reference amount. The logic for generating the irrigation effect index is as follows: in, Indicates Among the crops, The first growth stage The irrigation effect index of the environmental factor data set composed of a group of historical data; The crop growth coefficient model is constructed to determine the adjustment coefficient for the crop type and growth stage. The formula is as follows: in, Indicates Category, in The adjustment factor for crops at different growth stages is Indicates Category, in The optimal irrigation reference amount for crops at each growth stage is: Indicates the historical crop growth coefficient of the day before irrigation in the environmental factor dataset corresponding to the optimal irrigation reference amount, A number indicating the type of crop being grown. Indicates the number of the generation phase, Indicates the number of historical data; The vegetation index, chlorophyll index and moisture index of the corresponding crops are generated based on the following formula: in, , and represent vegetation index, chlorophyll index and moisture index respectively. , , , and They represent the reflectivity of the near infrared band, the reflectivity of the red light band, the reflectivity of the red edge band, the reflectivity of the blue light band and the reflectivity of the short infrared band respectively; The historical crop growth coefficient is generated based on the vegetation index, chlorophyll index and moisture index, as well as the average temperature, average humidity and average light intensity, according to the following formula: in, represents the historical crop growth coefficient, , and They represent the average temperature, average humidity and average light intensity of the farmland environment respectively; According to the growth stage of the crops planted in the farmland to be irrigated, the logic for determining the current crop adjustment coefficient is: Traverse the adjustment coefficients of each growth stage of each type of crop constructed based on historical irrigation data, find the adjustment coefficient generated by historical irrigation data of the same crop type and the same growth stage, and define it as the current crop adjustment coefficient; The specific logic for generating crop growth stage coefficients based on real-time data sets is: The vegetation index, chlorophyll index and moisture index of crops are generated based on the spectral reflectance data of the farmland to be irrigated the previous day in the real-time data set. The formula is as follows: in, , and They represent the determination of vegetation index, chlorophyll index and moisture index respectively. , , , , They respectively represent the reflectance of the near infrared band, the reflectance of the red band, the reflectance of the red edge band, the reflectance of the blue band and the reflectance of the short infrared band in the spectral reflectance data of the farmland to be irrigated the previous day in the real-time data set; The crop growth stage coefficient is generated based on the vegetation index, chlorophyll index, moisture index, and environmental data in the real-time data set. The formula is as follows: in, represents the crop growth stage coefficient, , and They respectively represent the average temperature, average humidity and average light intensity in the environmental data of the farmland to be irrigated the previous day in the real-time dataset.

2. The water resource scheduling optimization method based on the empirical model according to claim 1 is characterized in that: The analytical model is constructed to generate the formula based on crop water requirement: in, Indicates the water requirement of crops, which is used to reflect the water requirement per unit area of ​​crops. represents the crop growth stage coefficient, Indicates the current crop adjustment factor.

3. The water resource scheduling optimization method based on the empirical model according to claim 1 is characterized in that: The method to generate the soil type index is: At least five collection points are set in the farmland to be irrigated, and all the collection points are arranged in a straight line with the same spacing between adjacent collection points. The same amount of soil samples are collected at each collection point, and the soil depth of all soil samples is the same. The soil texture data, organic matter content data and soil effective moisture content data of all collected soil samples are analyzed to generate the soil type index, and the formula is as follows: in, represents the soil type index, , and Respectively represent Soil texture data, organic matter content data and soil effective moisture content data of each collection point, Indicates the number of the sampling point. Indicates the number of collection points, ; The soil texture data is generated based on the formula: in, and Respectively The relative content of clay and silt in the soil samples from the collection points , are the clay weight coefficient and the silt weight coefficient respectively. , ; The organic matter content data are the mass percentage of organic components in the soil samples, and the soil effective moisture content data are the volume percentage of water in the soil samples.

4. The water resource scheduling optimization method based on the empirical model according to claim 1 is characterized in that: The logic for determining the optimal amount of irrigation for the farmland to be irrigated is: in, represents the optimal irrigation amount for the farmland to be irrigated, Indicates the water requirement of crops. represents the soil type index, Represents the area of ​​farmland to be irrigated.

5. The water resources scheduling optimization method based on empirical model according to claim 1 is characterized in that: The method of collecting the crop types of each farmland to be irrigated in all irrigation areas and combining the soil type index of the farmland to determine the irrigation priority is: Type weights are assigned based on the types of crops grown in the farmland, where crop types include food crops, cash crops, vegetable crops, fruit crops, and other crops. The type weights of food crops are , the type weight of cash crops is , the type weight of vegetable crops is , the type weights of fruit crops and other crops are , ,and ; The priority is generated based on the type weight of the crop type grown on the farmland and the soil type index of the farmland soil, based on the formula: in, Indicates the first The priority of the farmland, and Respectively represent the first The type weight of the farmland and the soil type index of the soil, Indicates the number of the farmland to be irrigated in the irrigation area. , It indicates the total number of farmlands to be irrigated in the irrigation area; The logic for allocating irrigation water resources to each farmland in the irrigation area is: in, Indicates the first The amount of water allocated to each farmland, Indicates the first The optimal irrigation amount for a piece of farmland, It represents the total amount of irrigation water in the irrigation area. Indicates the first The area of ​​farmland.

Citation Information

Patent Citations

  • Intelligent garden water and fertilizer irrigation optimization method and system

    CN117751742A

  • Methods and systems for irrigation guidance

    US20200214231A1

Cited By

  • Irrigation resource allocation optimization system based on environmental perception

    CN122366929A