Intelligent agricultural irrigation optimization method and system

Abstract

The invention provides an intelligent agricultural irrigation optimization method and system, and relates to the technical field of agricultural management. The method comprises the following steps: acquiring first irrigation monitoring data of a plurality of sub-irrigation areas in a target planting area, calculating a temperature influence parameter and a humidity influence parameter of each sub-irrigation area, and constructing an irrigation feature vector of each sub-irrigation area; clustering the plurality of sub-irrigation areas to construct a plurality of irrigation area sets, calculating a water demand urgency factor of each irrigation area set and optimizing an initial irrigation scheme to obtain a first target irrigation scheme, and collecting second irrigation monitoring data of the plurality of sub-irrigation areas, and calculating an irrigation gain parameter of each irrigation area set, and optimizing the first target irrigation scheme to generate a second target irrigation scheme. According to the invention, accurate and efficient irrigation water distribution is realized.

Description

Technical Field

[0001] The present invention relates to the field of agricultural management technology, and in particular to an intelligent agricultural irrigation optimization method and system. Background Art

[0002] Agricultural intelligent irrigation technology is an important part of modern agriculture. Rational allocation of water resources in agricultural planting is a key direction to improve water resource utilization and ensure the healthy growth of crops. Some agricultural irrigation processes rely on simple analysis of irrigation monitoring data collected by sensor equipment and adjust irrigation water volume in combination with precipitation forecasts. In this process, if the collected irrigation monitoring data is not analyzed in depth, and the combined effects of multi-dimensional factors such as the impact of temperature changes on evaporation rate, differences in soil types and water retention capacity are ignored, it is easy to fail to accurately analyze the water demand characteristics of crops, and the irrigation strategy may remain in a static stage and lack dynamic adjustment capabilities. In the case of limited water resources, some areas may be under-irrigated or over-irrigated, and the accuracy of water resource allocation needs to be improved. Summary of the invention

[0003] In view of this, the present invention proposes an intelligent agricultural irrigation optimization method and system, which improves the accuracy of irrigation water allocation and realizes the rational use of water resources by performing multi-angle dynamic analysis on the collected irrigation monitoring data and combining water demand characteristics with the allocation mechanism of irrigation gain.

[0004] To achieve the above purpose, the technical solution adopted is as follows:

[0005] A first aspect of the present invention provides an intelligent agricultural irrigation optimization method, comprising:

[0006] Acquire first irrigation monitoring data of multiple sub-irrigation areas in the target planting area, including temperature monitoring data and humidity monitoring data, and extract multiple temperature features and humidity features from the first irrigation monitoring data;

[0007] The temperature influence parameter and humidity influence parameter of each sub-irrigation area are calculated according to the multiple temperature characteristics and humidity characteristics, and the irrigation characteristic vector of each sub-irrigation area is constructed;

[0008] Based on the irrigation feature vectors, cluster analysis is performed on multiple sub-irrigation areas to construct multiple irrigation area sets, and the water demand urgency factor of each irrigation area set is calculated according to multiple groups of first irrigation monitoring data contained in each irrigation area set;

[0009] The initial irrigation plan is optimized according to the water demand urgency factor to obtain a first target irrigation plan, and the target planting area is irrigated based on the first target irrigation plan;

[0010] Collecting second irrigation monitoring data of multiple sub-irrigation areas after irrigating the target planting area based on the first target irrigation scheme, analyzing multiple irrigation area sets based on the second irrigation monitoring data, and generating irrigation gain parameters for each irrigation area set;

[0011] The first target irrigation plan is optimized according to the irrigation gain parameter to generate a second target irrigation plan, and the target planting area is irrigated based on the second target irrigation plan.

[0012] Preferably, the calculation of the temperature-affecting parameter includes:

[0013] The evaporation influence factor and temperature fluctuation factor of each sub-irrigation area in multiple time windows are calculated based on multiple temperature characteristics, where for any time window:

[0014]

[0015] In the formula, E δ represents the evaporation influence factor, α is the curve control parameter, T i is the soil temperature at the i-th moment in the time window, T d is the temperature evaporation threshold, n is the number of soil temperature acquisitions in the time window;

[0016]

[0017] In the formula, B δ represents the temperature fluctuation factor, T m represents the mean soil temperature in the time window, T max , T min are the maximum and minimum values ​​of soil temperature in the time window, respectively;

[0018] The evaporation influence factor is corrected based on the temperature fluctuation factor, and the temperature influence parameters corresponding to multiple time windows are calculated.

[0019] Preferably, the calculation of humidity impact parameters includes:

[0020] The humidity impact factor and humidity fluctuation factor of each sub-irrigation area in multiple time windows are calculated based on multiple humidity characteristics, where for any time window:

[0021]

[0022] In the formula, E δ Represents humidity influence factor, H d Represents the target humidity threshold, H j represents the soil moisture at the jth moment in the time window, H s , H cThey represent the saturated humidity threshold and the dry humidity threshold, respectively, and m is the number of soil moisture collection times in the time window;

[0023]

[0024] Where D δ represents humidity fluctuation factor, H m represents the mean soil moisture in the time window, H max , H min Respectively represent the maximum and minimum values ​​of soil moisture in the time window;

[0025] The humidity influence factor is corrected based on the humidity fluctuation factor, and the humidity influence parameters corresponding to multiple time windows are calculated.

[0026] Preferably, the initial irrigation plan is optimized according to the water demand urgency factor to obtain a first target irrigation plan, including:

[0027] The total irrigation water consumption of the target planting area is optimized according to the water demand urgency factor, and the first target irrigation water consumption of each irrigation area set is determined, where for the hth irrigation area set:

[0028]

[0029] In the formula, Q h represents the first target irrigation water volume of the h-th irrigation area set, F h represents the water demand urgency factor of the h-th irrigation area set, S h represents the irrigation area of ​​the hth irrigation area set, F k represents the water demand urgency factor of the kth irrigation area set, S k represents the irrigated area of ​​the kth irrigation area set, Q z represents the total irrigation water consumption of the target planting area, θ represents the smoothing coefficient;

[0030] For the water demand urgency factor of the irrigation area set, the humidity difference parameter of each sub-irrigation area in the irrigation area set in each time window is calculated, the humidity difference parameter is corrected according to the humidity influence parameter in each time window, and the average of the corrected humidity difference parameters in multiple time windows is calculated to obtain the water demand urgency parameter of each sub-irrigation area. The water demand urgency factor of the irrigation area set is calculated based on multiple water demand urgency parameters of the irrigation area set.

[0031] Preferably, multiple irrigation area sets are analyzed based on the second irrigation monitoring data to generate irrigation gain parameters for each irrigation area set, including:

[0032] Obtaining a first soil moisture of each sub-irrigation area before irrigating the target planting area based on the first target irrigation scheme, and determining a second soil moisture of each sub-irrigation area after irrigating the target planting area based on the first target irrigation scheme according to the second irrigation monitoring data;

[0033] The soil moisture gain value of each sub-irrigation area is calculated according to the first soil moisture and the second soil moisture, the irrigation efficiency parameter of each sub-irrigation area is calculated according to the soil moisture gain value, and the irrigation gain parameter of the irrigation area set is determined according to the soil moisture gain value and the irrigation efficiency parameter:

[0034]

[0035] In the formula, G k represents the irrigation gain parameter of the kth irrigation area set, ΔH a represents the soil moisture gain value of the ath sub-irrigation area in the kth irrigation area set, P a represents the irrigation efficiency parameter of the ath sub-irrigation area in the kth irrigation area set, ω1 and ω2 are the soil moisture gain weight and irrigation efficiency weight, respectively, and b is the number of sub-irrigation areas in the kth irrigation area set.

[0036] Preferably, the first target irrigation scheme is optimized according to the irrigation gain parameter to generate the second target irrigation scheme, including:

[0037] Determine a first allocation weight for each set of irrigation areas according to the first target irrigation scheme, determine a second allocation weight for each set of irrigation areas according to the irrigation gain parameter, optimize each second allocation weight based on the irrigation restriction rule, generate a third allocation weight corresponding to each second allocation weight, and generate a second target irrigation scheme according to the third allocation weight;

[0038] Wherein, each second allocation weight is optimized based on the irrigation restriction rule to generate a third allocation weight corresponding to each second allocation weight, including:

[0039]

[0040] Where W k1 , W k2 and W k3 are the first allocation weight, the second allocation weight and the third allocation weight of the kth irrigation area set respectively, and β and γ are the first restriction parameter and the second restriction parameter respectively.

[0041] Preferably, a DBSCAN algorithm is used to perform cluster analysis on multiple sub-irrigation areas based on the irrigation feature vectors to construct multiple irrigation area sets.

[0042] A second aspect of the present invention provides an intelligent agricultural irrigation optimization system, which is used to implement the above-mentioned intelligent agricultural irrigation optimization method, including:

[0043] A data acquisition module, used to acquire first irrigation monitoring data of multiple sub-irrigation areas in the target planting area, including temperature monitoring data and humidity monitoring data, and extract multiple temperature features and humidity features from the first irrigation monitoring data;

[0044] An irrigation feature extraction module is used to calculate the temperature influence parameter and humidity influence parameter of each sub-irrigation area according to a plurality of temperature features and humidity features, and construct an irrigation feature vector for each sub-irrigation area;

[0045] An irrigation water demand analysis module is used to perform cluster analysis on multiple sub-irrigation areas based on irrigation feature vectors to construct multiple irrigation area sets, and calculate the water demand urgency factor of each irrigation area set according to multiple groups of first irrigation monitoring data contained in each irrigation area set;

[0046] An irrigation management module, used to optimize the initial irrigation plan according to the water demand urgency factor to obtain a first target irrigation plan, and irrigate the target planting area based on the first target irrigation plan;

[0047] An irrigation monitoring module, used for collecting second irrigation monitoring data of multiple sub-irrigation areas after irrigating the target planting area based on the first target irrigation scheme, analyzing multiple irrigation area sets based on the second irrigation monitoring data, and generating irrigation gain parameters for each irrigation area set;

[0048] The irrigation optimization module is used to optimize the first target irrigation plan according to the irrigation gain parameter to generate a second target irrigation plan, and irrigate the target planting area based on the second target irrigation plan.

[0049] The present invention has the following beneficial effects:

[0050] The present invention analyzes the collected temperature and humidity monitoring data of the target planting area, extracts temperature and humidity related features, uses a clustering algorithm to perform feature analysis and partitioning on multiple sub-irrigation areas, constructs a set of areas with similar irrigation needs, and realizes dynamic optimization management of irrigation partitions; adopts the water urgency factor in combination with the area of ​​the irrigation area to design the first target irrigation plan, and realizes the precise allocation of irrigation water; by collecting the second irrigation monitoring data after the execution of the first target irrigation plan, quantifies the dynamic impact of temperature and humidity on irrigation demand, calculates the irrigation gain parameter, and performs feedback optimization on the plan from the perspective of irrigation effect, generates a second target irrigation plan, and dynamically adjusts the irrigation plan, thereby realizing precise and efficient irrigation water allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of a flow chart of an intelligent agricultural irrigation optimization method provided in an embodiment of the present invention.

[0052] Figure 2 A schematic diagram of the structure of an intelligent agricultural irrigation optimization system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make those skilled in the art better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] See also Figure 1 The embodiment of the present invention provides an intelligent agricultural irrigation optimization method, comprising the following steps:

[0055] Step S10: Acquire first irrigation monitoring data of multiple sub-irrigation areas in the target planting area, including temperature monitoring data and humidity monitoring data, and extract multiple temperature features and humidity features from the first irrigation monitoring data.

[0056] In this embodiment, for multiple sub-irrigation areas in the target planting area, real-time monitoring can be performed through a sensor network to obtain the first irrigation monitoring data of each sub-irrigation area, which at least includes temperature monitoring data and humidity monitoring data, and characterizes the changes in the temperature and humidity of the soil in the planting area. After preprocessing the collected data and removing outliers and noise, multiple temperature features and humidity features, such as mean features, range features, fluctuation features, etc., are extracted from the first irrigation monitoring data for subsequent in-depth analysis.

[0057] Step S20: Calculate the temperature influence parameter and humidity influence parameter of each sub-irrigation area according to the multiple temperature characteristics and humidity characteristics, and construct an irrigation feature vector for each sub-irrigation area.

[0058] In this embodiment, the temperature and humidity characteristics extracted are used to calculate the temperature and humidity influence parameters of each sub-irrigation area. Specifically, the nonlinear evaporation potential and volatility characteristics of temperature are combined to quantify the impact of temperature on regional water demand, and multiple temperature influence parameters of each sub-irrigation area are calculated. In addition, the current humidity state and the critical range of humidity are combined to evaluate the absorption of water in different regions, and multiple humidity influence parameters of each sub-irrigation area are calculated. Finally, the temperature influence parameters and humidity influence parameters are combined into a multidimensional feature vector to construct an irrigation feature vector for each sub-irrigation area, which is used to characterize the comprehensive irrigation characteristics in different regions.

[0059] Step S30: cluster analysis is performed on the multiple sub-irrigation areas based on the irrigation feature vectors to construct multiple irrigation area sets, and the water demand urgency factor of each irrigation area set is calculated according to the multiple groups of first irrigation monitoring data contained in each irrigation area set.

[0060] In this embodiment, a clustering algorithm is used to analyze the feature vectors of multiple sub-irrigation areas, and the target planting area is divided based on the irrigation characteristics according to the similarity, so as to cluster the sub-irrigation areas with similar irrigation characteristics. For example, a DBSCAN algorithm is used to perform cluster analysis on multiple sub-irrigation areas based on the irrigation feature vectors, and finally multiple irrigation area sets are obtained. The areas in each irrigation area set have similar irrigation characteristics, which is convenient for unified management. According to the first irrigation monitoring data corresponding to the multiple sub-irrigation areas in the irrigation area set, the water demand urgency factor in each irrigation area set is calculated by comprehensively considering the water demand urgency and the lack of humidity, reflecting the urgent demand of the set for irrigation water resources.

[0061] Step S40: Optimize the initial irrigation plan according to the water demand urgency factor to obtain a first target irrigation plan, and irrigate the target planting area based on the first target irrigation plan.

[0062] In this embodiment, a water resource allocation model is designed based on the water urgency factor of each set of irrigation areas and the total available irrigation water volume, and the initial irrigation plan, i.e., the irrigation plan formulated based on artificial experience, is optimized to generate a first target irrigation plan to achieve accurate allocation of water to each area, give priority to sets with high water urgency factors, and reasonably allocate water resources according to the degree of water demand to ensure efficient use of water resources.

[0063] Step S50, collecting second irrigation monitoring data of multiple sub-irrigation areas after irrigating the target planting area based on the first target irrigation plan, analyzing multiple irrigation area sets based on the second irrigation monitoring data, and generating irrigation gain parameters for each irrigation area set.

[0064] In this embodiment, after executing the first target irrigation scheme, the second irrigation monitoring data of each sub-irrigation area is collected through sensors, including data such as humidity changes after irrigation, to reflect the soil moisture absorption state. The improvement of soil moisture by irrigation is analyzed through the data before and after irrigation, and the irrigation gain parameter of each irrigation area set is calculated to quantitatively characterize the effect of irrigation after adopting the first target irrigation scheme.

[0065] Step S60: Optimize the first target irrigation plan according to the irrigation gain parameter to generate a second target irrigation plan, and irrigate the target planting area based on the second target irrigation plan.

[0066] In this embodiment, based on the irrigation gain parameter, the first target irrigation scheme is feedback optimized to achieve redistribution of water in different areas based on irrigation efficiency and humidity improvement. For example, the amount of water allocated to the set of areas with high irrigation gain is appropriately increased to give full play to the benefits of water resources, and local water replenishment optimization is performed on the set of areas with poor humidity uniformity. By dynamically adjusting the weight distribution ratio of the irrigation scheme, it is ensured that the optimized second target irrigation scheme can not only meet the needs of high water demand areas, but also improve the overall irrigation efficiency. After performing irrigation operations according to the second target irrigation scheme, the next round of monitoring and optimization feedback loop can be entered to achieve better irrigation effects and realize efficient and accurate irrigation management of the target planting area.

[0067] In an optional implementation process, for the calculation of the temperature influence parameters in step S20, the soil temperature data in multiple time windows are analyzed to dynamically quantify the impact of temperature on evaporation potential and water demand, and the temperature influence parameters of each sub-irrigation area are calculated.

[0068] Specifically, the evaporation impact factor and temperature fluctuation factor of each sub-irrigation area in multiple time windows are calculated according to multiple temperature characteristics. For any time window, the calculation formula of the evaporation impact factor is as follows:

[0069]

[0070] In the formula, E δ represents the evaporation influencing factor, which is used to quantify the comprehensive effect of soil temperature on evaporation rate. α is the curve control parameter, which is used to adjust the nonlinear sensitivity of the model. i is the soil temperature at the i-th moment in the time window, T d is the temperature evaporation threshold, which indicates the temperature threshold that begins to significantly affect evaporation. It can be determined based on empirical knowledge. For example, for most crops, the evaporation rate begins to increase significantly when the temperature is greater than 25°C. At this time, the temperature evaporation threshold can be set to 25°C. n is the number of soil temperature collection times in the time window, which represents the sample size for calculation.

[0071] The temperature fluctuation factor calculation formula is as follows:

[0072]

[0073] In the formula, B δ Represents the temperature fluctuation factor, which is used to describe the fluctuation characteristics of soil temperature within the time window. M represents the mean soil temperature in the time window, T max 、T min are the maximum and minimum values ​​of soil temperature in the time window, respectively, reflecting the extreme range of temperature change in the time window.

[0074] After calculating the evaporation influencing factors and temperature fluctuation factors of each sub-irrigation area in multiple time windows in the above method, the temperature fluctuation factor is included in the analysis of the evaporation influencing factor. The evaporation influencing factor is corrected based on the temperature fluctuation factor to increase the contribution weight of the area with violent fluctuations to evaporation. Finally, the temperature influence parameters corresponding to the multiple time windows are calculated. A parameter sequence is formed according to the temperature influence parameters corresponding to the multiple time windows, which is used to measure the temporal impact of soil temperature changes on irrigation conditions.

[0075] In an optional implementation process, for the calculation of the humidity impact parameters in step S20, the soil moisture data within the time window is dynamically analyzed, and the humidity impact parameters of each sub-irrigation area are calculated in combination with the critical state of soil moisture demand during crop growth to reflect the impact of humidity status on irrigation demand.

[0076] The calculation of humidity-affected parameters includes:

[0077] The humidity impact factor and humidity fluctuation factor of each sub-irrigation area in multiple time windows are calculated according to multiple humidity characteristics, wherein for any time window, the calculation formula of the humidity impact factor is as follows;

[0078]

[0079] In the formula, E δ Represents the humidity impact factor, which is used to quantify the deviation between the current humidity state and the target humidity. d Represents the target humidity threshold, indicating the optimal humidity level for crop growth, H j represents the soil moisture at the jth moment in the time window, m is the number of times the soil moisture is collected in the time window, and H s , H c They represent the saturation humidity threshold and the dry humidity threshold respectively, indicating the critical state of the crops' humidity demand. The saturation humidity threshold represents the upper limit of the crops' demand for soil humidity, and the dry humidity threshold represents the lower limit of the crops' minimum demand for humidity. Too high or too low soil humidity will affect the production of crops. The saturation humidity threshold and the dry humidity threshold can be reasonably set according to the production needs of crops, and are not specifically limited here.

[0080] The calculation formula of humidity fluctuation factor is as follows:

[0081]

[0082] Where D δ Represents the humidity fluctuation factor, which is used to describe the fluctuation characteristics of soil moisture within the time window. mrepresents the mean soil moisture in the time window, H max , H min They represent the maximum and minimum values ​​of soil moisture in the time window respectively. The larger the humidity fluctuation factor finally calculated is, the greater the change of soil moisture in the time window is and the stronger the volatility is.

[0083] After calculating the humidity influence factor and humidity fluctuation factor in each time window in the above way, the humidity influence factor is corrected based on the humidity fluctuation factor, and the irrigation demand weight of the area with large humidity fluctuation is adjusted by the humidity fluctuation factor, so as to calculate the humidity influence parameters corresponding to multiple time windows respectively, and form the corresponding time series, which is used to measure the temporal impact of soil moisture changes on irrigation conditions.

[0084] In an optional implementation process, for the generation of the first target irrigation plan in step S40, the initial irrigation plan is optimized by the water urgency factor to obtain the first target irrigation water volume for each set of irrigation areas. The calculation process takes into account the area and water demand of the irrigation area and adopts a dynamic allocation formula to achieve accurate allocation of irrigation resources.

[0085] Specifically, the initial irrigation plan is optimized according to the water demand urgency factor to obtain the first target irrigation plan, including:

[0086] The total irrigation water consumption of the target planting area is optimized according to the water demand urgency factor, and the first target irrigation water consumption of each irrigation area set is determined, where for the hth irrigation area set:

[0087]

[0088] In the formula, Q h represents the first target irrigation water volume of the h-th irrigation area set, F h The water demand urgency factor of the h-th irrigation area set is used to characterize the urgency of the demand for irrigation water resources in the area of ​​the set. h represents the irrigation area of ​​the hth irrigation area set, F k represents the water demand urgency factor of the kth irrigation area set, S k represents the irrigated area of ​​the kth irrigation area set, Q z represents the total irrigation water consumption in the target planting area, and θ represents the smoothing coefficient, which is used to adjust the distribution difference and avoid excessive fluctuations in weight distribution.

[0089] For the calculation of the water demand urgency factor of the irrigation area set, the humidity difference parameter of each sub-irrigation area in the irrigation area set in each time window is first calculated. Specifically, the difference between the target humidity threshold and the mean humidity in the time window is calculated, so as to characterize the difference between the humidity state of the sub-irrigation area in the time window and the target humidity threshold through the humidity difference parameter, and quantify the degree of water demand.

[0090] Then, the humidity influence parameter calculated previously is introduced to correct the humidity difference parameter, and the influence of the dynamic change of humidity on the water demand is considered. The humidity difference parameter is corrected according to the humidity influence parameter in each time window, and the average of the humidity difference parameters in multiple corrected time windows is obtained to obtain the water demand urgency parameter of each sub-irrigation area, reflecting the water demand status over a period of time. Finally, the water demand urgency factor of the irrigation area set is calculated according to the multiple water demand urgency parameters of the irrigation area set, for example, the average of multiple water demand urgency parameters is taken as the water demand urgency factor. This is to comprehensively characterize the degree of demand for water resources for crops in the areas involved in the irrigation area set.

[0091] The above scheme combines the water demand urgency factor, the irrigation area and the total water resources, and optimizes the irrigation scheme through a refined allocation formula. The dynamic calculation of the water demand urgency factor not only takes into account the humidity difference within the time window, but also improves the accuracy of allocation by correcting the humidity influencing factor. This scheme can effectively improve irrigation efficiency and reduce water waste under the condition of limited irrigation resources, providing data support for the optimization of modern smart agricultural irrigation.

[0092] In an optional implementation process, in order to analyze the effect of the irrigation plan after execution, the second irrigation monitoring data is used to generate irrigation gain parameters for each irrigation area set for multiple irrigation area sets in the target planting area.

[0093] Specifically, multiple irrigation area sets are analyzed based on the second irrigation monitoring data to generate irrigation gain parameters for each irrigation area set, including:

[0094] The first soil moisture of each sub-irrigation area before the target planting area is irrigated based on the first target irrigation scheme is obtained, and the second soil moisture of each sub-irrigation area after the target planting area is irrigated based on the first target irrigation scheme is determined according to the second irrigation monitoring data.

[0095] After the first soil moisture and the second soil moisture are collected by the monitoring device, the soil moisture gain value of each sub-irrigation area is calculated according to the first soil moisture and the second soil moisture, and the irrigation efficiency parameter of each sub-irrigation area is calculated according to the soil moisture gain value. Among them, the soil moisture gain value can be specifically the difference between the second soil moisture and the first soil moisture, which is used to measure the improvement of soil moisture by irrigation, and the irrigation efficiency parameter can be specifically the soil moisture gain value and the actual irrigation water volume of the sub-irrigation area, which is used to indicate the improvement effect of each unit of water volume on soil moisture after irrigation.

[0096] After determining the soil moisture gain value and the irrigation efficiency parameter, the irrigation gain parameter of the irrigation area set is determined according to the soil moisture gain value and the irrigation efficiency parameter:

[0097]

[0098] In the formula, G k represents the irrigation gain parameter of the kth irrigation area set, which is used to measure the overall irrigation effect of the irrigation area set. a represents the soil moisture gain value of the ath sub-irrigation area in the kth irrigation area set, P a It represents the irrigation efficiency parameter of the ath sub-irrigation area in the kth irrigation area set. ω1 and ω2 are the soil moisture gain weight and irrigation efficiency weight, respectively. They can be dynamically adjusted according to the irrigation target and reasonably adjusted according to the actual emphasis on humidity improvement and water resource efficiency. b is the number of sub-irrigation areas in the kth irrigation area set.

[0099] By calculating the irrigation gain parameters in the above way, the irrigation improvement effect can be quantified to comprehensively evaluate the water resource utilization efficiency and guide subsequent optimization decisions.

[0100] In an optional implementation process, in step S60, in order to further optimize the first target irrigation plan, the first allocation weight is dynamically adjusted according to the irrigation gain parameters of each irrigation area set to generate a second allocation weight, and on this basis, the irrigation restriction rule is further optimized to generate a third allocation weight. Finally, the second target irrigation plan is formed based on the third allocation weight to achieve accurate and efficient irrigation water allocation.

[0101] Specifically, the first target irrigation plan is optimized according to the irrigation gain parameter to generate the second target irrigation plan, including

[0102] A first allocation weight for each set of irrigation areas is determined according to the first target irrigation scheme, and a second allocation weight for each set of irrigation areas is determined according to the irrigation gain parameter, wherein the second allocation weight can be specifically generated by normalizing the irrigation gain parameter of each set of irrigation areas, and is used to determine the weight for allocating water resources from the perspective of irrigation gain, that is, the performance of each set of irrigation areas in actual irrigation effects.

[0103] On the basis of calculating the second allocation weight, the weight range is adjusted through the irrigation restriction rule to avoid overly aggressive water allocation due to drastic changes in irrigation gain parameters, ensure the stability of allocation, and finally generate the third allocation weight. Specifically:

[0104]

[0105] Where W k1 , W k2 and W k3 are the first allocation weight, the second allocation weight and the third allocation weight of the kth irrigation area set, respectively; β and γ are the first restriction parameter and the second restriction parameter, respectively; wherein the first restriction parameter is usually used to limit the lower limit of the weight, indicating the minimum variation range of the second allocation weight, for example, the value is 0.8; the second restriction parameter is usually used to limit the upper limit of the weight, indicating the maximum variation range of the second allocation weight, for example, the value is 1.2.

[0106] In the above manner, each second allocation weight is optimized based on the irrigation restriction rule to generate a third allocation weight corresponding to each second allocation weight. A second target irrigation plan is generated according to the third allocation weight. In this process, multiple third allocation weights can be normalized first to ensure that the sum of the weight allocations is equal to 1, so that the allocated water volume of each irrigation area set is calculated according to the normalized third allocation weights to generate the corresponding second target irrigation plan, so as to better meet the water demand of multiple area sets and realize efficient agricultural irrigation under limited water resources.

[0107] The present invention analyzes the collected temperature and humidity monitoring data of the target planting area, extracts temperature and humidity related features, uses a clustering algorithm to perform feature analysis and partitioning on multiple sub-irrigation areas, constructs a set of regions with similar irrigation needs, and realizes dynamic optimization management of irrigation partitions; uses the water urgency factor combined with the area of ​​the irrigation area to design the first target irrigation plan, and realizes the precise allocation of irrigation water; collects the second irrigation monitoring data after the first target irrigation plan is executed, quantifies the dynamic impact of temperature and humidity on irrigation demand, calculates the irrigation gain parameter, and optimizes the plan from the perspective of irrigation effect, generates the second target irrigation plan, and dynamically adjusts the irrigation plan, realizing accurate and efficient irrigation water allocation. The present invention significantly improves the scientificity and efficiency of agricultural irrigation through the comprehensive application of multi-dimensional monitoring data, accurate feature extraction, dynamic allocation weight adjustment, and closed-loop optimization feedback, and has significant technical advantages in improving crop growth quality, reducing water resource waste, and realizing efficient agricultural irrigation management.

[0108] See also Figure 2 The embodiment of the present invention further provides an intelligent agricultural irrigation optimization system for implementing the above-mentioned intelligent agricultural irrigation optimization method, the system comprising:

[0109] A data acquisition module, used to acquire first irrigation monitoring data of multiple sub-irrigation areas in the target planting area, including temperature monitoring data and humidity monitoring data, and extract multiple temperature features and humidity features from the first irrigation monitoring data;

[0110] An irrigation feature extraction module is used to calculate the temperature influence parameter and humidity influence parameter of each sub-irrigation area according to a plurality of temperature features and humidity features, and construct an irrigation feature vector for each sub-irrigation area;

[0111] The calculation of temperature-affected parameters includes:

[0112] The evaporation influence factor and temperature fluctuation factor of each sub-irrigation area in multiple time windows are calculated based on multiple temperature characteristics, where for any time window:

[0113]

[0114] In the formula, E δ represents the evaporation influence factor, α is the curve control parameter, T i is the soil temperature at the i-th moment in the time window, T d is the temperature evaporation threshold, n is the number of soil temperature acquisitions in the time window;

[0115]

[0116] In the formula, Bδ represents the temperature fluctuation factor, T m represents the mean soil temperature in the time window, T max 、T min are the maximum and minimum values ​​of soil temperature in the time window, respectively;

[0117] The evaporation influence factor is corrected based on the temperature fluctuation factor, and the temperature influence parameters corresponding to multiple time windows are calculated.

[0118] Calculation of humidity-affected parameters, including:

[0119] The humidity impact factor and humidity fluctuation factor of each sub-irrigation area in multiple time windows are calculated based on multiple humidity characteristics, where for any time window:

[0120]

[0121] In the formula, E δ Represents humidity influence factor, H d Represents the target humidity threshold, H j represents the soil moisture at the jth moment in the time window, H s , H c They represent the saturated humidity threshold and the dry humidity threshold, respectively, and m is the number of soil moisture collection times in the time window;

[0122]

[0123] Where D δ represents humidity fluctuation factor, H m represents the mean soil moisture in the time window, H max , H min Respectively represent the maximum and minimum values ​​of soil moisture in the time window;

[0124] The humidity influence factor is corrected based on the humidity fluctuation factor, and the humidity influence parameters corresponding to multiple time windows are calculated.

[0125] An irrigation water demand analysis module is used to perform cluster analysis on multiple sub-irrigation areas based on irrigation feature vectors to construct multiple irrigation area sets, and calculate the water demand urgency factor of each irrigation area set according to multiple groups of first irrigation monitoring data contained in each irrigation area set;

[0126] An irrigation management module, used to optimize the initial irrigation plan according to the water demand urgency factor to obtain a first target irrigation plan, and irrigate the target planting area based on the first target irrigation plan;

[0127] An irrigation monitoring module, used for collecting second irrigation monitoring data of multiple sub-irrigation areas after irrigating the target planting area based on the first target irrigation scheme, analyzing multiple irrigation area sets based on the second irrigation monitoring data, and generating irrigation gain parameters for each irrigation area set;

[0128] The irrigation optimization module is used to optimize the first target irrigation plan according to the irrigation gain parameter to generate a second target irrigation plan, and irrigate the target planting area based on the second target irrigation plan.

[0129] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A smart agricultural irrigation optimization method, characterized in that: include: Acquire first irrigation monitoring data of multiple sub-irrigation areas in the target planting area, including temperature monitoring data and humidity monitoring data, and extract multiple temperature features and humidity features from the first irrigation monitoring data; The temperature influence parameter and humidity influence parameter of each sub-irrigation area are calculated according to the multiple temperature characteristics and humidity characteristics, and the irrigation characteristic vector of each sub-irrigation area is constructed; Based on the irrigation feature vectors, cluster analysis is performed on multiple sub-irrigation areas to construct multiple irrigation area sets, and the water demand urgency factor of each irrigation area set is calculated according to multiple groups of first irrigation monitoring data contained in each irrigation area set; The initial irrigation plan is optimized according to the water demand urgency factor to obtain a first target irrigation plan, and the target planting area is irrigated based on the first target irrigation plan; Collecting second irrigation monitoring data of multiple sub-irrigation areas after irrigating the target planting area based on the first target irrigation scheme, analyzing multiple irrigation area sets based on the second irrigation monitoring data, and generating irrigation gain parameters for each irrigation area set; The first target irrigation plan is optimized according to the irrigation gain parameter to generate a second target irrigation plan, and the target planting area is irrigated based on the second target irrigation plan.

2. The intelligent agricultural irrigation optimization method according to claim 1, characterized in that: Calculation of temperature-affected parameters, including: The evaporation influence factor and temperature fluctuation factor of each sub-irrigation area in multiple time windows are calculated based on multiple temperature characteristics, where for any time window: In the formula, E δ represents the evaporation influence factor, α is the curve control parameter, T i is the soil temperature at the i-th moment in the time window, T d is the temperature evaporation threshold, n is the number of soil temperature acquisitions in the time window; In the formula, B δ represents the temperature fluctuation factor, T m represents the mean soil temperature in the time window, T max , T min are the maximum and minimum values ​​of soil temperature in the time window, respectively; The evaporation influence factor is corrected based on the temperature fluctuation factor, and the temperature influence parameters corresponding to multiple time windows are calculated.

3. The intelligent agricultural irrigation optimization method according to claim 2, characterized in that: Calculation of humidity-affected parameters, including: The humidity impact factor and humidity fluctuation factor of each sub-irrigation area in multiple time windows are calculated based on multiple humidity characteristics, where for any time window: In the formula, E δ Represents humidity influence factor, H d Represents the target humidity threshold, H j represents the soil moisture at the jth moment in the time window, H s , H c They represent the saturated humidity threshold and the dry humidity threshold, respectively, and m is the number of soil moisture collection times in the time window; Where D δ represents humidity fluctuation factor, H m represents the mean soil moisture in the time window, H max , H min Respectively represent the maximum and minimum values ​​of soil moisture in the time window; The humidity influence factor is corrected based on the humidity fluctuation factor, and the humidity influence parameters corresponding to multiple time windows are calculated.

4. The intelligent agricultural irrigation optimization method according to claim 3, characterized in that: The initial irrigation plan is optimized according to the water demand urgency factor to obtain the first target irrigation plan, including: The total irrigation water consumption of the target planting area is optimized according to the water demand urgency factor, and the first target irrigation water consumption of each irrigation area set is determined, where for the hth irrigation area set: In the formula, Q h represents the first target irrigation water volume of the h-th irrigation area set, F h represents the water demand urgency factor of the h-th irrigation area set, S h represents the irrigation area of ​​the hth irrigation area set, F k represents the water demand urgency factor of the kth irrigation area set, S k represents the irrigated area of ​​the kth irrigation area set, Q z represents the total irrigation water consumption of the target planting area, θ represents the smoothing coefficient; For the water demand urgency factor of the irrigation area set, the humidity difference parameter of each sub-irrigation area in the irrigation area set in each time window is calculated, the humidity difference parameter is corrected according to the humidity influence parameter in each time window, and the average of the corrected humidity difference parameters in multiple time windows is calculated to obtain the water demand urgency parameter of each sub-irrigation area. The water demand urgency factor of the irrigation area set is calculated based on multiple water demand urgency parameters of the irrigation area set.

5. The intelligent agricultural irrigation optimization method according to claim 4, characterized in that: Analyze multiple irrigation area sets based on the second irrigation monitoring data to generate irrigation gain parameters for each irrigation area set, including: Obtaining a first soil moisture of each sub-irrigation area before irrigating the target planting area based on the first target irrigation scheme, and determining a second soil moisture of each sub-irrigation area after irrigating the target planting area based on the first target irrigation scheme according to the second irrigation monitoring data; The soil moisture gain value of each sub-irrigation area is calculated according to the first soil moisture and the second soil moisture, the irrigation efficiency parameter of each sub-irrigation area is calculated according to the soil moisture gain value, and the irrigation gain parameter of the irrigation area set is determined according to the soil moisture gain value and the irrigation efficiency parameter: In the formula, G k represents the irrigation gain parameter of the kth irrigation area set, ΔH a represents the soil moisture gain value of the ath sub-irrigation area in the kth irrigation area set, P a represents the irrigation efficiency parameter of the ath sub-irrigation area in the kth irrigation area set, ω1 and ω2 are the soil moisture gain weight and irrigation efficiency weight, respectively, and b is the number of sub-irrigation areas in the kth irrigation area set.

6. The intelligent agricultural irrigation optimization method according to claim 5, characterized in that: The first target irrigation plan is optimized according to the irrigation gain parameter to generate a second target irrigation plan, including: Determine a first allocation weight for each set of irrigation areas according to the first target irrigation scheme, determine a second allocation weight for each set of irrigation areas according to the irrigation gain parameter, optimize each second allocation weight based on the irrigation restriction rule, generate a third allocation weight corresponding to each second allocation weight, and generate a second target irrigation scheme according to the third allocation weight; Wherein, each second allocation weight is optimized based on the irrigation restriction rule to generate a third allocation weight corresponding to each second allocation weight, including: Where W k1 , W k2 and W k3 are the first allocation weight, the second allocation weight and the third allocation weight of the kth irrigation area set respectively, and β and γ are the first restriction parameter and the second restriction parameter respectively.

7. The intelligent agricultural irrigation optimization method according to claim 1, characterized in that: Based on the irrigation feature vector, the DBSCAN algorithm was used to perform cluster analysis on multiple sub-irrigation areas, and multiple irrigation area sets were constructed.

8. An intelligent agricultural irrigation optimization system, characterized in that: The system is used to implement the intelligent agricultural irrigation optimization method according to any one of claims 1 to 7, comprising: A data acquisition module, used to acquire first irrigation monitoring data of multiple sub-irrigation areas in the target planting area, including temperature monitoring data and humidity monitoring data, and extract multiple temperature features and humidity features from the first irrigation monitoring data; An irrigation feature extraction module is used to calculate the temperature influence parameter and humidity influence parameter of each sub-irrigation area according to a plurality of temperature features and humidity features, and construct an irrigation feature vector for each sub-irrigation area; An irrigation water demand analysis module is used to perform cluster analysis on multiple sub-irrigation areas based on irrigation feature vectors to construct multiple irrigation area sets, and calculate the water demand urgency factor of each irrigation area set according to multiple groups of first irrigation monitoring data contained in each irrigation area set; An irrigation management module, used to optimize the initial irrigation plan according to the water demand urgency factor to obtain a first target irrigation plan, and irrigate the target planting area based on the first target irrigation plan; An irrigation monitoring module, used for collecting second irrigation monitoring data of multiple sub-irrigation areas after irrigating the target planting area based on the first target irrigation scheme, analyzing multiple irrigation area sets based on the second irrigation monitoring data, and generating irrigation gain parameters for each irrigation area set; The irrigation optimization module is used to optimize the first target irrigation plan according to the irrigation gain parameter to generate a second target irrigation plan, and irrigate the target planting area based on the second target irrigation plan.

Images