An irrigation system that automatically adjusts the amount of rainwater collected from corn for irrigation

Abstract

The present application provides an irrigation system for automatically adjusting the amount of rainwater collected and supplementary irrigation for corn, and relates to the field of agricultural irrigation technology. The system includes: a corn monitoring module, which obtains characteristic data of corn growth status and characteristic data of corn cultivation soil; an irrigation cultivation association module, which receives a corn irrigation cultivation association plan for a predetermined future time zone window; a growth environment prediction module, which obtains a predicted corn growth environment; a corn supplementary irrigation prediction module, which obtains a predicted supplementary irrigation amount; a supplementary irrigation optimization module, which obtains a corn supplementary irrigation optimization plan based on an embedded supplementary irrigation optimization algorithm; and a rainwater collection supplementary irrigation module, which irrigates corn according to the corn supplementary irrigation optimization plan. The present application solves the technical problem of low irrigation quality due to the lack of accurate real-time monitoring and supplementary irrigation prediction in the prior art. By integrating multiple sensors and algorithms, the growth status and soil conditions of corn are monitored in real time, and accurate irrigation management is performed according to the future environment, thereby achieving the technical effect of improving irrigation quality.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural irrigation, and in particular to an irrigation system that automatically adjusts the amount of rainwater collected and supplemented irrigation for corn. Background Art

[0002] In recent years, agricultural irrigation technology has used big data, artificial intelligence, the Internet of Things and other information technologies to provide real-time irrigation according to the water consumption patterns of crops, thereby achieving on-site interception and off-season utilization of precipitation resources, and effectively increasing the grain production capacity of dryland farmland. However, there are still some problems, including insufficient real-time monitoring of crop growth status and limited intelligent prediction capabilities, resulting in low effective utilization coefficients of irrigation water.

[0003] In summary, the existing technology suffers from the technical problem of low irrigation quality due to the lack of accurate real-time monitoring and irrigation prediction. Summary of the invention

[0004] The purpose of this application is to provide an irrigation system that automatically adjusts the amount of rainwater collected for corn irrigation, so as to solve the technical problem of low irrigation quality due to the lack of accurate real-time monitoring and irrigation prediction in the prior art.

[0005] In view of the above problems, the present application provides an irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation, wherein the system comprises: a corn monitoring module, the corn monitoring module is used to obtain corn growth status characteristic data and corn cultivation soil characteristic data; an irrigation cultivation association module, the irrigation cultivation association module is used to receive a corn irrigation cultivation association scheme for a predetermined future time zone window; a growth environment prediction module, the growth environment prediction module is used to predict the corn growth environment based on the predetermined future time zone window to obtain a predicted corn growth environment; a corn irrigation prediction module, the The corn supplementary irrigation prediction module predicts the supplementary irrigation amount based on the corn growth status characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association plan and the predicted corn growth environment to obtain the predicted supplementary irrigation amount; the supplementary irrigation optimization module, the supplementary irrigation optimization module performs corn supplementary irrigation optimization based on the embedded supplementary irrigation optimization algorithm and the predicted supplementary irrigation amount to obtain the corn supplementary irrigation optimization plan; the rainwater collection and supplementary irrigation module, the rainwater collection and supplementary irrigation module irrigates corn according to the corn supplementary irrigation optimization plan, wherein the rainwater collection and supplementary irrigation module includes a rainwater collection module and an automatic irrigation module.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The invention adopts a corn monitoring module for obtaining corn growth state characteristic data and corn cultivation soil characteristic data; an irrigation cultivation association module for receiving a corn irrigation cultivation association scheme of a predetermined future time zone window; a growth environment prediction module for predicting the corn growth environment based on the predetermined future time zone window to obtain a predicted corn growth environment; a corn supplementary irrigation prediction module predicts the supplementary irrigation amount based on the corn growth state characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association scheme and the predicted corn growth environment to obtain a predicted supplementary irrigation amount; a supplementary irrigation optimization module performs corn supplementary irrigation optimization based on the embedded supplementary irrigation optimization algorithm and the predicted supplementary irrigation amount to obtain a corn supplementary irrigation optimization scheme; a rainwater collection supplementary irrigation module performs corn irrigation according to the corn supplementary irrigation optimization scheme, wherein the rainwater collection supplementary irrigation module includes a rainwater collection module and an automatic irrigation module. That is to say, by integrating multiple sensors and algorithms, the growth state and soil conditions of corn are monitored in real time, and accurate irrigation management is performed according to the predicted future environment, thereby achieving the technical effect of improving irrigation quality.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a schematic diagram of the structure of an irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation in this application;

[0011] Figure 2 A flow chart of obtaining an optimal solution for corn irrigation in an irrigation system that automatically adjusts the amount of corn rainwater collection and irrigation is provided in this application.

[0012] Explanation of the reference numerals: corn monitoring module 11 , irrigation cultivation association module 12 , growth environment prediction module 13 , corn supplementary irrigation prediction module 14 , supplementary irrigation optimization module 15 , rainwater collection supplementary irrigation module 16 . DETAILED DESCRIPTION

[0013] This application provides an irrigation system that automatically adjusts the amount of rainwater collected for corn irrigation, solving the technical problem of low irrigation quality due to the lack of accurate real-time monitoring and irrigation prediction in the prior art. By integrating multiple sensors and algorithms, the growth status and soil conditions of corn are monitored in real time, and accurate irrigation management is performed according to the predicted future environment, achieving the technical effect of improving irrigation quality.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] Please refer to the attached Figure 1 The present application provides an irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation, wherein the system comprises:

[0016] The corn monitoring module 11 is used to obtain corn growth status characteristic data and corn cultivation soil characteristic data.

[0017] Specifically, the corn monitoring module can realize real-time monitoring of the growth status and cultivation soil of corn by integrating a variety of sensors and technical means. The monitoring of growth status characteristic data usually involves image recognition technology, spectral analysis technology, laser scanning technology or machine vision technology. For example, through image recognition technology, cameras or drones can be installed in the field to analyze the appearance characteristics of corn to determine the growth stage of corn, and the shape, size and color of corn cobs can be analyzed to evaluate the development and maturity of the fruit; spectral analysis technology can be used to measure the spectrum reflected by corn leaves through a chlorophyll meter or spectrometer to calculate the chlorophyll content; using laser scanning technology or machine vision technology, the laser scanner emits a laser beam, and the height of the plant is determined by measuring the time from the laser beam from emission to reflection. Machine vision technology calculates the size and number of leaves by analyzing the captured images, thereby estimating the leaf area; through visual recognition, infrared imaging or other remote sensing technologies, it is possible to monitor pests and diseases on corn plants, and timely discover and intervene.

[0018] Corn cultivation soil characteristic data involves monitoring soil moisture, temperature, pH value and nutrient content. Soil moisture is the direct factor that determines the timing and amount of irrigation, while soil temperature and pH value affect the availability of nutrients in the soil. The content of soil nutrients, such as nitrogen, phosphorus, potassium, etc., is the key source of nutrition for the healthy growth of corn. Through real-time monitoring and data collection, accurate information on corn growth and soil conditions can be obtained, and the irrigation amount can be accurately adjusted according to the actual water demand of corn and the moisture condition of the soil to avoid excessive or insufficient irrigation.

[0019] The irrigation and cultivation association module 12 is used to receive a corn irrigation and cultivation association plan for a predetermined future time zone window.

[0020] Specifically, a detailed irrigation plan is developed based on information such as future weather forecasts, corn growth stages, soil conditions, and expected environmental conditions. At the same time, a series of cultivation measures closely related to corn irrigation will also be considered, including deep plowing, increased fertilizer application, intertillage and weeding, etc., aimed at optimizing corn growth conditions. For example, deep plowing is to improve soil structure, increase soil permeability and water retention capacity, and promote the in-depth development of the root system through mechanical deep plowing before corn planting or during growth; increased fertilizer application is to apply nitrogen, phosphorus, potassium and other fertilizers, as well as trace element fertilizers according to soil nutrient test results and corn growth needs to provide sufficient nutrition for the soil; intertillage and weeding is to weed and loosen the soil during corn growth to reduce soil moisture evaporation, maintain soil moisture, and ensure that water and fertilizer can be more effectively absorbed by corn plants. The future time zone window usually refers to a specific time range used to predict and plan future activities or events. In the corn irrigation system, the scheduled future time zone window refers to a scheduled future time period, which can be one day, one week or longer. During this period, the irrigation and cultivation association module predicts the needs of corn growth based on various data (such as weather forecast, soil moisture, crop water requirement, etc.), thereby formulating and adjusting the corn irrigation plan. In addition, the future time zone window can also be adjusted according to real-time monitoring data and environmental changes to adapt to changing external conditions. By receiving the corn irrigation and cultivation association plan, it is ensured that corn grows under the best environmental conditions.

[0021] The growth environment prediction module 13 is used to predict the corn growth environment based on the predetermined future time zone window to obtain a predicted corn growth environment.

[0022] Specifically, using historical data and current meteorological data, soil conditions, corn growth status and other comprehensive information, combined with future weather forecasts, the growth environment of corn in a predetermined future time period is predicted, including but not limited to environmental factors such as temperature, humidity, wind speed, and precipitation probability. A prediction model can be established, using a large amount of historical data as a reference, including weather data, soil moisture records, crop growth conditions, etc. in the past few years, to analyze these data, identify the laws and trends of corn growth, and predict the degree of impact of different environmental conditions on corn growth. Predict the state of the corn growth environment based on weather forecasts and soil conditions in the future time zone window. For example, it is predicted that the temperature will rise and the soil moisture will decrease in the next few days, at which time corn needs more water to maintain normal growth; or it is predicted that there may be continuous rainfall in the next few days, at which time the need for irrigation needs to be reduced. Through prediction, the irrigation system can be adjusted in advance to ensure that corn grows under the best environmental conditions and improve irrigation efficiency.

[0023] The corn supplementary irrigation prediction module 14 is used to predict the supplementary irrigation amount based on the corn growth state characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association plan and the predicted corn growth environment to obtain the predicted supplementary irrigation amount.

[0024] Specifically, the characteristic data of corn growth status include the current growth stage of the crop, chlorophyll content, plant height, leaf area and fruit development, etc., reflecting the health status and growth progress of corn plants. The characteristic data of corn cultivation soil include soil moisture, temperature, pH value and nutrient content, which directly affect the growth of corn roots and water absorption efficiency. The corn irrigation cultivation association scheme includes irrigation plans based on factors such as weather forecasts, soil conditions and crop water requirements. Predicting the growth environment of corn involves predicting the growth environment of corn based on weather conditions and soil moisture changes in the future. Combining these data as input, the future water requirement of corn is predicted through mathematical models or machine learning algorithms to obtain the predicted irrigation amount, that is, the amount of water recommended by the system to be supplemented for corn in the future time zone window. By comprehensively considering multiple factors, the system can provide more accurate irrigation suggestions, dynamically adjust the irrigation plan according to real-time and predicted data, and promptly respond to changes in corn growth and changes in external environmental conditions to achieve precise irrigation and improve water resource utilization efficiency.

[0025] The supplementary irrigation optimization module 15 is used to perform corn supplementary irrigation optimization based on the embedded supplementary irrigation optimization algorithm and the predicted supplementary irrigation amount to obtain a corn supplementary irrigation optimization plan.

[0026] Specifically, the predicted irrigation amount is calculated based on the characteristic data of corn growth status, soil characteristic data, irrigation cultivation association scheme and predicted corn growth environment. The irrigation optimization algorithm combines the predicted irrigation amount with other related data to form an optimization problem to find the best irrigation strategy to meet the growth needs of corn while considering the constraints of irrigation equipment. Through the irrigation optimization algorithm, one or more irrigation schemes are obtained. These schemes are solutions that meet the constraints of the optimization problem, including the best irrigation time, frequency and water volume parameters, which can guide the actual irrigation operation. The irrigation optimization algorithm is a decision support tool that can analyze the predicted irrigation amount and other related data, such as corn growth status, soil characteristics, irrigation equipment parameters, etc., to determine the best irrigation strategy. The optimal irrigation scheme is found based on mathematical models, machine learning algorithms or optimization algorithms, such as genetic algorithms, particle swarm optimization, etc. Based on the embedded irrigation optimization algorithm, the irrigation strategy is automatically adjusted according to the actual water demand of corn and future environmental conditions to achieve the best irrigation effect.

[0027] The rainwater collection and irrigation module 16 is used to irrigate corn according to the corn irrigation optimization scheme, wherein the rainwater collection and irrigation module includes a rainwater collection module and an automatic irrigation module.

[0028] Specifically, corn irrigation is carried out according to the obtained corn supplementary irrigation optimization scheme, and theoretical calculations are converted into practical operations. The rainwater collection and supplementary irrigation module includes a rainwater collection module and an automated irrigation module, which work together to ensure that corn obtains the most suitable irrigation conditions. The rainwater collection module usually includes a rainwater collector, a water storage facility, and a processing system, which is responsible for collecting and storing natural precipitation, such as rainwater, snowmelt, etc., to supplement the irrigation water source. The rainwater collector can be installed on rainwater collection facilities such as roofs and ground to collect rainwater. The water storage facility stores rainwater through storage facilities such as water tanks or reservoirs. The processing system is used to purify and process the collected rainwater to ensure that the collected water meets the irrigation water quality standards. The automated irrigation module is responsible for performing actual irrigation operations according to the corn supplementary irrigation optimization scheme, including sprinkler irrigation, drip irrigation or other irrigation systems, and adjusting the irrigation strategy as needed to achieve precise irrigation of corn. The rainwater collection and supplementary irrigation module realizes precise irrigation management of corn through the collaborative work of the rainwater collection module and the automated irrigation module. By collecting and storing rainwater through the rainwater collection module, we can reduce dependence on traditional water sources and achieve conservation and rational use of water resources.

[0029] Further, the corn monitoring module 11 in the system is also used for:

[0030] According to the corn monitoring module, a corn monitoring image set is obtained; according to the enhanced processing algorithm embedded in the corn monitoring module, the corn monitoring image set is enhanced to obtain a corn monitoring enhanced image set; the corn growth status integrated detection channel in the corn monitoring module is activated, wherein the corn growth status integrated detection channel includes P corn growth status feature recognition channels corresponding to P corn growth status characteristic indicators, and P is a positive integer greater than 1; the corn monitoring enhanced image set is input into the P corn growth status feature recognition channels to obtain P corn growth status feature recognition results; and the P corn growth status feature recognition results are integrated to generate the corn growth status feature data.

[0031] Specifically, cameras or drones are installed in farmland to obtain corn monitoring image sets. These images can provide important information about the growth status of corn, such as plant height, leaf area, fruit development, pest and disease conditions, etc. Due to the complexity and uncontrollability of the outdoor environment, it may be affected by factors such as lighting conditions, weather conditions, and occlusions, and there may be problems such as noise and uneven lighting, which will lead to a decrease in image quality and affect subsequent analysis and identification. In order to improve the quality of the image, the corn monitoring module has an embedded enhancement processing algorithm to enhance the corn monitoring image set to obtain a corn monitoring enhanced image set. The enhancement processing includes denoising, contrast enhancement, color correction, sharpening and other technologies.

[0032] The integrated detection channel of corn growth state is activated, including P corn growth state feature recognition channels corresponding to P corn growth state feature indicators, where P is a positive integer greater than 1. Each recognition channel is specifically targeted at a specific growth state feature indicator, such as plant height, leaf area, fruit development, pest and disease status, etc. The recognition channel is based on machine learning or deep learning algorithms, such as convolutional neural network (CNN) or support vector machine (SVM), and can automatically recognize and extract specific feature indicators from images by learning and analyzing image data. The corn monitoring enhanced image set is input into the P recognition channels, and each channel will analyze the image set, extract information related to the corresponding feature indicators, and obtain P corn growth state feature recognition results to reflect the current growth state of the corn plant. In order to obtain more comprehensive and accurate corn growth state feature data, it is necessary to fuse these P recognition results. The fusion process involves data fusion algorithms, such as weighted average, maximum value selection, minimum value selection, etc. Comprehensively consider the recognition results of all channels to generate a comprehensive corn growth state feature data set. This data set will contain multiple key feature indicators, which can more comprehensively reflect the growth status of corn plants.

[0033] The enhanced processing algorithm is a specially designed algorithm to improve the quality and recognizability of images. It eliminates or reduces noise and uneven lighting in the image through operations such as denoising, contrast enhancement, sharpening, and color adjustment, and enhances the details and clarity of the image. The integrated detection channel refers to a system that contains multiple corn growth status feature recognition channels, each of which is responsible for identifying and extracting a specific corn growth status feature indicator. These channels can work simultaneously to collaboratively identify and extract multiple feature indicators, thereby improving the efficiency and accuracy of monitoring. Through the embedded enhanced processing algorithm and integrated detection channel, the corn monitoring module can improve the efficiency and accuracy of image processing and reduce manual intervention.

[0034] Further, the corn monitoring module 11 in the system is also used for:

[0035] Preprocessing is performed on the corn monitoring image set to obtain a first corn monitoring image processing result, wherein the preprocessing includes image color conversion and image size adjustment; multi-scale decomposition is performed on the first corn monitoring image processing result to obtain a second corn monitoring image processing result; inverse normalization is performed on the second corn monitoring image processing result to obtain a third corn monitoring image processing result; contrast enhancement is performed on the third corn monitoring image processing result to generate a fourth corn monitoring image processing result; scale reconstruction is performed on the fourth corn monitoring image processing result to generate the corn monitoring enhanced image set.

[0036] Specifically, the corn monitoring image set is subjected to image color conversion and image size adjustment to improve the visual effect of the image and enhance the accuracy of the analysis. Color conversion converts the image from the RGB color space to a format more suitable for analysis, such as HSV or Lab color space. Size adjustment reduces the amount of calculation by reducing the image size or adjusts the image ratio to better meet the needs of subsequent processing. Based on this, the first corn monitoring image processing result is obtained. The preprocessed image has a unified color space and a size suitable for subsequent processing. According to the spatial frequency information to be captured, Gaussian filters of different sizes are selected. The larger the filter, the more low-frequency information can be captured. Gaussian filters of different sizes are applied at different scales to decompose the image into sub-images of different scales, each sub-image corresponding to a specific spatial frequency range. The sub-images at different scales are combined to form a multi-scale decomposition result, generating the second corn monitoring image processing result. After the multi-scale decomposition, the image pixel value is converted from the normalized space back to the original pixel value to obtain the third corn monitoring image processing result. According to the inverse normalized image, contrast enhancement processing is performed, and the important features in the image are highlighted through Laplace transform and transformation function techniques, noise and blur are reduced, and the image is clearer, so as to obtain the fourth corn monitoring image processing result. Finally, scale reconstruction is performed to recombine the sub-images after multi-scale decomposition to generate a complete image. In this way, the detail information brought by multi-scale decomposition can be retained, and more information can be provided for subsequent feature recognition. Through scale reconstruction, a corn monitoring enhanced image set is generated. By performing preprocessing, multi-scale decomposition, inverse normalization, contrast enhancement and scale reconstruction on the corn monitoring image set, a set of high-quality corn monitoring enhanced image sets can be obtained, which has higher clarity, better feature extraction ability and more suitable numerical range.

[0037] Further, the corn monitoring module 11 in the system is also used for:

[0038] According to the corn monitoring module, corn cultivation soil monitoring data is obtained; according to the corn cultivation soil monitoring data, data cleaning is performed to generate the corn cultivation soil characteristic data.

[0039] Specifically, the corn monitoring module monitors key parameters such as soil moisture, temperature, pH value, electrical conductivity (EC), and nutrient content in real time through soil sensors, soil moisture sensors, soil temperature sensors, and soil pH sensors installed in farmland, and obtains corn cultivation soil monitoring data. Due to factors such as sensor errors, environmental interference, and data transmission errors, there are noise, outliers, or other data quality problems in the soil monitoring data during the collection process, and the data needs to be cleaned to ensure the accuracy and reliability of the data. Data cleaning includes removing outliers, filling missing data, and correcting data errors. The cleaned data generates characteristic data of corn cultivation soil. These characteristic data are key parameters that describe the state and quality of the soil, and usually include soil moisture, soil temperature, pH value, EC value, and main nutrient content. The corn cultivation soil monitoring data is obtained through the corn monitoring module, and data cleaning and feature extraction are performed to achieve a more accurate assessment of the soil condition.

[0040] Furthermore, the corn supplementary irrigation prediction module 14 in the system is also used for:

[0041] Loading corn growth status characteristic data records, corn cultivation soil characteristic data records, corn irrigation cultivation associated scheme records, corn growth environment records and corn supplementary irrigation amount records; activating W corn supplementary irrigation learning channels, wherein W is a positive integer greater than 1; based on the corn growth status characteristic data records, the corn cultivation soil characteristic data records, the corn irrigation cultivation associated scheme records, the corn growth environment records and the corn supplementary irrigation amount records, according to the W corn supplementary irrigation learning channels, building the corn supplementary irrigation prediction module; inputting the corn growth status characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation associated scheme and the predicted corn growth environment into the corn supplementary irrigation prediction module to generate the predicted supplementary irrigation amount.

[0042] Specifically, the data records of corn growth status characteristics, corn cultivation soil characteristics, corn irrigation and cultivation association schemes, corn growth environment and corn supplementary irrigation are collected and loaded into the system to analyze the growth status and soil conditions of corn, predict the future growth environment, and formulate and implement irrigation plans based on the irrigation and cultivation association schemes and supplementary irrigation records. W corn supplementary irrigation learning channels are activated. These channels are modules specially designed to learn and optimize corn supplementary irrigation strategies. Each channel contains one or more machine learning models, which automatically learn and adjust irrigation strategies by analyzing historical data and real-time data. Using W corn supplementary irrigation learning channels, a corn supplementary irrigation prediction module is built. Each learning channel uses different learning algorithms, such as neural networks, support vector machines, random forests, etc. These learning channels can work simultaneously or independently, and the learning parameters can be adjusted as needed to adapt to different learning tasks. The supplementary irrigation needs of corn are predicted by combining historical data and real-time data using machine learning algorithms and statistical models. Collect corn growth status characteristic data records, corn cultivation soil characteristic data records, corn irrigation cultivation related plan records, corn growth environment records, clean and preprocess these data, and use the processed data to train the prediction module. During the training process, the internal parameters are continuously adjusted to minimize the prediction error. After the training is completed, the module predicts the corn supplementary irrigation demand based on the input data. Through continuous learning and adjustment, the corn supplementary irrigation prediction module can adapt to different growth environments and conditions and achieve precise irrigation management.

[0043] Furthermore, the corn supplementary irrigation prediction module 14 in the system is also used for:

[0044] The method comprises the following steps: taking the corn growth state characteristic data record, the corn cultivation soil characteristic data record, the corn irrigation cultivation associated scheme record and the corn growth environment record as input data, taking the corn supplementary irrigation amount record as output data, performing supervised learning on the W corn supplementary irrigation learning channels, and generating W corn supplementary irrigation predictors that meet the corn supplementary irrigation prediction accuracy constraint; collecting the output information of the W corn supplementary irrigation predictors to obtain corn supplementary irrigation integrated learning data; taking the corn supplementary irrigation integrated learning data as input information, and taking the corn supplementary irrigation amount record as output information, training a corn supplementary irrigation prediction integrated model that meets the corn supplementary irrigation prediction accuracy constraint; merging the W corn supplementary irrigation predictors as parallel independent nodes to generate a corn supplementary irrigation prediction processing layer; merging the corn supplementary irrigation prediction processing layer with the input layer of the corn supplementary irrigation prediction integrated model to generate the corn supplementary irrigation prediction module.

[0045] Specifically, corn growth state characteristic data records, corn cultivation soil characteristic data records, corn irrigation cultivation association scheme records, and corn growth environment records are collected, and these data are cleaned and preprocessed. The processed data is input into the module to output the corn supplementary irrigation volume record. W corn supplementary irrigation learning channels are supervised and learned, and each channel uses a different learning algorithm to improve the generalization ability and prediction accuracy of the model. Through supervised learning, each corn supplementary irrigation learning channel generates a corn supplementary irrigation predictor. These predictors predict the corn supplementary irrigation demand based on the input data, and the generated predictors need to meet the corn supplementary irrigation prediction accuracy constraints to ensure the accuracy of the prediction. The output information of W corn supplementary irrigation predictors is collected to obtain corn supplementary irrigation integrated learning data, which contains the prediction results of all predictors for further optimization and integration. Using these learning data as input information and corn supplementary irrigation volume records as output information, a corn supplementary irrigation prediction integrated model is trained to combine the advantages of multiple predictors to improve the accuracy and robustness of the prediction. W independent predictors are integrated together to form a unified prediction processing layer, which can process the outputs of multiple predictors at the same time and comprehensively consider their prediction results. The corn irrigation prediction processing layer is combined with the input layer of the corn irrigation prediction integrated model to form a complete corn irrigation prediction module. The prediction module can generate predicted irrigation amounts based on input data and provide guidance for actual irrigation operations. The corn irrigation prediction module can predict the corn irrigation requirements based on input data and provide a scientific basis for actual irrigation operations. This method can improve irrigation efficiency, save water resources, and promote corn growth and yield.

[0046] Further, as attached Figure 2 As shown, the refill optimization module 15 in the system is also used for:

[0047] The corn irrigation control constraint information of the automatic irrigation module is collected to construct a corn irrigation control constraint matrix; the corn irrigation control constraint matrix is ​​used as the corn supplementary irrigation control variable constraint, and the predicted supplementary irrigation amount is used as the corn supplementary irrigation control target; based on the corn supplementary irrigation control target, the corn supplementary irrigation control parameters are assigned according to the corn supplementary irrigation control variable constraint to obtain a corn supplementary irrigation control decision space that meets the corn supplementary irrigation decision capacity constraint; the supplementary irrigation fitness calculation function is activated; based on the supplementary irrigation fitness calculation function, the corn supplementary irrigation control decision space is optimized to maximize the supplementary irrigation fitness, and the corn supplementary irrigation optimization scheme is generated.

[0048] Specifically, the corn irrigation control constraint information of the automatic irrigation module is collected, including the water supply capacity, water pressure, pipeline capacity, working parameters of the irrigation equipment, etc. of the irrigation system, as well as various restrictions and constraints related to corn irrigation, such as the capacity of the irrigation equipment, the availability of water resources, and the permeability of the soil. By constructing the corn irrigation control constraint matrix, these constraints are converted into a mathematical model to describe the control constraints of corn irrigation. Each element in the matrix may represent a specific constraint, such as the maximum flow rate, minimum flow rate, irrigation time window, etc. of the irrigation equipment. The corn irrigation control constraint matrix is ​​used as the control variable constraint of corn supplementary irrigation, and the predicted supplementary irrigation amount is used as the control target of corn supplementary irrigation. In other words, when making irrigation decisions, it is necessary to consider both the actual feasibility and the expected irrigation demand. The predicted supplementary irrigation amount is calculated based on factors such as corn growth state characteristic data, corn cultivation soil characteristic data, corn irrigation cultivation association scheme, and predicted corn growth environment, reflecting the water demand of corn within a specific time.

[0049] Based on the corn supplementary irrigation control target, the corn supplementary irrigation control parameters are assigned according to the corn supplementary irrigation control variable constraints, and irrigation parameters such as irrigation time, irrigation amount, irrigation frequency, etc. are selected and adjusted to find one or more irrigation schemes to ensure that the irrigation decision meets both the actual constraints and the water demand of corn. These constraints include the capacity of irrigation equipment, the availability of water resources, the permeability of soil, the water demand of crops, etc. The corn supplementary irrigation control decision space is obtained, that is, a set of irrigation schemes that meet the capacity constraints of corn supplementary irrigation decisions. The fitness value is calculated according to the actual effect and expected goal of the irrigation decision. The higher the fitness value, the better the effect of the irrigation decision, and the more it can meet the water demand of corn. Based on the supplementary irrigation fitness calculation function, the corn supplementary irrigation control decision space is optimized to maximize the supplementary irrigation fitness, that is, to find the irrigation scheme that can maximize the supplementary irrigation fitness in the corn supplementary irrigation control decision space, evaluate all schemes, and select the scheme with the highest fitness as the best supplementary irrigation scheme. Finally, the corn supplementary irrigation optimization scheme is generated, which contains the best supplementary irrigation time, frequency, water volume and other parameters to achieve precise irrigation of corn. The corn supplementary irrigation optimization algorithm can optimize the corn supplementary irrigation control decision by combining the predicted supplementary irrigation amount. This method can improve the efficiency and accuracy of irrigation management, reduce the waste of water resources, and ensure the healthy growth of corn and the stability of yield.

[0050] Furthermore, the refill optimization module 15 in the system is also used for:

[0051] The calculation function of the irrigation fitness is: I(q, j, μ) = log γ(W1*q+W2*j+W3*μ); where I(q, j, μ) represents the fitness of supplementary irrigation, γ represents the fitness calculation factor of supplementary irrigation, γ is greater than 1, q represents the predicted quality coefficient of supplementary irrigation, j represents the predicted efficiency coefficient of supplementary irrigation, μ represents the predicted water source utilization coefficient of supplementary irrigation, W1, W2, and W3 represent the weight constraints for the calculation of supplementary irrigation fitness, and W1, W2, and W3 are all positive numbers, and the sum of W1, W2, and W3 is 1.

[0052] Specifically, the calculation function of the irrigation fitness is I(q, j, μ) = log γ (W1*q+W2*j+W3*μ); where I(q, j, μ) represents the fitness of supplementary irrigation, γ represents the calculation factor of the fitness of supplementary irrigation, and γ is greater than 1, which is used to adjust the calculation of fitness so that the fitness can better reflect the pros and cons of the irrigation scheme; q represents the predicted quality coefficient of supplementary irrigation, which reflects the quality of nutrients and other beneficial substances contained in the irrigation water, and the effects of these substances on corn growth; j represents the predicted efficiency coefficient of supplementary irrigation, which reflects the efficiency of irrigation water absorption and utilization by corn roots; μ represents the predicted water source utilization coefficient of supplementary irrigation, which reflects the utilization of irrigation water resources Efficiency, including loss and efficiency in the process of water collection, treatment and distribution; W1, W2, and W3 represent the weight constraints for calculating the fitness of irrigation, and W1, W2, and W3 are all positive numbers, and the sum of W1, W2, and W3 is 1, which is used to measure the importance of the predicted irrigation quality coefficient q, the predicted irrigation efficiency coefficient j, and the predicted irrigation water source utilization coefficient μ in the overall irrigation fitness calculation. Different weight distributions will affect the calculation results of the final fitness. The system can flexibly adjust the importance of different irrigation indicators according to actual needs and changes in conditions to adapt to different agricultural management strategies. Through the irrigation fitness calculation function, the system can comprehensively consider multiple factors such as the predicted irrigation amount, quality, efficiency, and water source utilization to evaluate the fitness of the irrigation scheme. The higher the irrigation fitness, the more suitable the irrigation scheme is for the growth needs of corn under current conditions, so it can be selected as the optimal irrigation scheme. By adjusting these coefficients and weights, it can better adapt to different corn growth stages and soil conditions, thereby optimizing irrigation decisions. According to the predicted data and actual conditions, the irrigation strategy is automatically adjusted to achieve precise irrigation and improve the efficiency of water resource utilization.

[0053] In summary, the irrigation system provided by the present application that automatically adjusts the amount of rainwater collected for corn irrigation has the following technical effects:

[0054] The invention adopts a corn monitoring module for obtaining corn growth state characteristic data and corn cultivation soil characteristic data; an irrigation cultivation association module for receiving a corn irrigation cultivation association scheme of a predetermined future time zone window; a growth environment prediction module for predicting the corn growth environment based on the predetermined future time zone window to obtain a predicted corn growth environment; a corn supplementary irrigation prediction module predicts the supplementary irrigation amount based on the corn growth state characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association scheme and the predicted corn growth environment to obtain a predicted supplementary irrigation amount; a supplementary irrigation optimization module performs corn supplementary irrigation optimization based on the embedded supplementary irrigation optimization algorithm and the predicted supplementary irrigation amount to obtain a corn supplementary irrigation optimization scheme; a rainwater collection supplementary irrigation module performs corn irrigation according to the corn supplementary irrigation optimization scheme, wherein the rainwater collection supplementary irrigation module includes a rainwater collection module and an automatic irrigation module. That is to say, by integrating multiple sensors and algorithms, the growth state and soil conditions of corn are monitored in real time, and accurate irrigation management is performed according to the predicted future environment, thereby achieving the technical effect of improving irrigation quality.

[0055] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0056] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An irrigation system that automatically adjusts the amount of rainwater collected for corn irrigation, characterized in that: The system comprises: A corn monitoring module, wherein the corn monitoring module is used to obtain corn growth status characteristic data and corn cultivation soil characteristic data; An irrigation and cultivation association module, the irrigation and cultivation association module is used to receive a corn irrigation and cultivation association plan for a predetermined future time zone window; A growth environment prediction module, the growth environment prediction module is used to predict the corn growth environment based on the predetermined future time zone window to obtain a predicted corn growth environment; A corn supplementary irrigation prediction module, the corn supplementary irrigation prediction module is used to predict the supplementary irrigation amount based on the corn growth state characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association scheme and the predicted corn growth environment to obtain the predicted supplementary irrigation amount; A supplementary irrigation optimization module, wherein the supplementary irrigation optimization module is used to optimize corn supplementary irrigation based on an embedded supplementary irrigation optimization algorithm and the predicted supplementary irrigation amount to obtain a corn supplementary irrigation optimization plan; A rainwater collection and irrigation module, the rainwater collection and irrigation module is used to irrigate corn according to the corn irrigation optimization scheme, wherein the rainwater collection and irrigation module includes a rainwater collection module and an automatic irrigation module; The supplementary irrigation optimization module performs corn supplementary irrigation optimization based on the embedded supplementary irrigation optimization algorithm and the predicted supplementary irrigation amount to obtain a corn supplementary irrigation optimization solution, including: Collecting corn irrigation control constraint information of the automatic irrigation module and constructing a corn irrigation control constraint matrix; The corn irrigation control constraint matrix is ​​used as the corn supplementary irrigation control variable constraint, and the predicted supplementary irrigation amount is used as the corn supplementary irrigation control target; Based on the corn supplementary irrigation control target, assign corn supplementary irrigation control parameters according to the corn supplementary irrigation control variable constraints to obtain a corn supplementary irrigation control decision space that meets the corn supplementary irrigation decision capacity constraints; Activate the recharging fitness calculation function; Based on the supplementary irrigation fitness calculation function, the supplementary irrigation fitness maximization optimization is performed on the corn supplementary irrigation control decision space to generate the corn supplementary irrigation optimization plan; Among them, the calculation function of the recharging fitness is: I(q,j,μ)=log γ (W1*q+W2*j+W3*μ); Among them, I(q, j, μ) represents the fitness of supplementary irrigation, γ represents the calculation factor of the fitness of supplementary irrigation, γ is greater than 1, q represents the predicted quality coefficient of supplementary irrigation, j represents the predicted efficiency coefficient of supplementary irrigation, μ represents the predicted utilization coefficient of supplementary irrigation water source, W1, W2, and W3 represent the weight constraints of the calculation of supplementary irrigation fitness, and W1, W2, and W3 are all positive numbers, and the sum of W1, W2, and W3 is 1.

2. The irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation as claimed in claim 1, characterized in that: The corn monitoring module is used to obtain corn growth status characteristic data and corn cultivation soil characteristic data, including: According to the corn monitoring module, a corn monitoring image set is obtained; Performing enhancement processing on the corn monitoring image set according to the enhancement processing algorithm embedded in the corn monitoring module to obtain a corn monitoring enhanced image set; Activate a corn growth state integrated detection channel in the corn monitoring module, wherein the corn growth state integrated detection channel includes P corn growth state feature identification channels corresponding to P corn growth state feature indicators, where P is a positive integer greater than 1; Inputting the corn monitoring enhanced image set into the P corn growth state feature recognition channels to obtain P corn growth state feature recognition results; The P corn growth status feature recognition results are integrated to generate the corn growth status feature data.

3. The irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation as claimed in claim 2, characterized in that: The corn monitoring image set is enhanced according to the enhanced processing algorithm embedded in the corn monitoring module to obtain the corn monitoring enhanced image set, including: Preprocessing is performed according to the corn monitoring image set to obtain a first corn monitoring image processing result, wherein the preprocessing includes image color conversion and image size adjustment; Perform multi-scale decomposition according to the first corn monitoring image processing result to obtain a second corn monitoring image processing result; Performing inverse normalization according to the second corn monitoring image processing result to obtain a third corn monitoring image processing result; Performing contrast enhancement according to the third corn monitoring image processing result to generate a fourth corn monitoring image processing result; Scale reconstruction is performed according to the processing result of the fourth corn monitoring image to generate the corn monitoring enhanced image set.

4. The irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation as claimed in claim 1, characterized in that: The corn supplementary irrigation prediction module predicts the supplementary irrigation amount based on the corn growth state characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association scheme and the predicted corn growth environment to obtain the predicted supplementary irrigation amount, including: Load corn growth status characteristic data records, corn cultivation soil characteristic data records, corn irrigation cultivation association plan records, corn growth environment records and corn supplementary irrigation volume records; Activate W corn supplementary irrigation learning channels, where W is a positive integer greater than 1; Based on the corn growth state characteristic data record, the corn cultivation soil characteristic data record, the corn irrigation cultivation associated program record, the corn growth environment record and the corn supplementary irrigation amount record, and according to the W corn supplementary irrigation learning channels, the corn supplementary irrigation prediction module is built; The corn growth status characteristic data, the corn cultivation soil characteristic data, the corn irrigation cultivation association plan and the predicted corn growth environment are input into the corn supplementary irrigation prediction module to generate the predicted supplementary irrigation amount.

5. The irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation as claimed in claim 4, characterized in that: Based on the corn growth state characteristic data record, the corn cultivation soil characteristic data record, the corn irrigation cultivation associated program record, the corn growth environment record and the corn supplementary irrigation amount record, and according to the W corn supplementary irrigation learning channels, the corn supplementary irrigation prediction module is constructed, including: Taking the corn growth state characteristic data record, the corn cultivation soil characteristic data record, the corn irrigation cultivation associated scheme record and the corn growth environment record as input data, and taking the corn supplementary irrigation amount record as output data, supervised learning is performed on the W corn supplementary irrigation learning channels to generate W corn supplementary irrigation predictors that meet the corn supplementary irrigation prediction accuracy constraint; Collecting the output information of the W corn supplementary irrigation predictors to obtain corn supplementary irrigation integrated learning data; Using the corn supplementary irrigation integrated learning data as input information and the corn supplementary irrigation amount record as output information, training a corn supplementary irrigation prediction integrated model that meets the corn supplementary irrigation prediction accuracy constraint; The W corn irrigation prediction devices are combined as parallel independent nodes to generate a corn irrigation prediction processing layer; The corn supplementary irrigation prediction processing layer is merged with the input layer of the corn supplementary irrigation prediction integrated model to generate the corn supplementary irrigation prediction module.

6. The irrigation system for automatically adjusting the amount of rainwater collected for corn irrigation as claimed in claim 1, characterized in that: The corn monitoring module is used to obtain corn growth status characteristic data and corn cultivation soil characteristic data, including: According to the corn monitoring module, corn cultivation soil monitoring data is obtained; Data cleaning is performed based on the corn-growing soil monitoring data to generate the corn-growing soil characteristic data.

Images