Agricultural resource efficient utilization monitoring system based on artificial intelligence
Through the efficient utilization monitoring system of agricultural resources based on artificial intelligence, the problem of inefficiency of traditional agricultural management methods is solved, precise irrigation and fertilization of soil is achieved, water waste and fertilizer use are reduced, and agricultural production efficiency and quality are improved.
Patent Information
- Application Number
- CN202411441845.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2024-12-10
AI Technical Summary
Traditional agricultural management methods are inefficient and difficult to cope with complex and changeable environmental factors, resulting in waste of water resources and excessive use of fertilizers, affecting agricultural production efficiency and quality.
Design an efficient use monitoring system for agricultural resources based on artificial intelligence, including data acquisition, data analysis, prediction and execution modules, and accurately irrigate and fertilize water resources by collecting, analyzing and predicting soil data and crop image data. and fertilizer use.
Accurate irrigation and fertilization of soil in the monitoring area has been achieved, water resource waste and fertilizer use have been reduced, agricultural production efficiency and quality have been improved, and agricultural resources have been ensured efficient utilization.
Smart Images
Figure CN119107198A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of agricultural irrigation, and in particular to an agricultural resource efficient utilization monitoring system based on artificial intelligence. Background Art
[0002] In today's global population growth and climate change, agriculture is facing unprecedented challenges. In order to ensure food security and sustainable development, efficient use of agricultural resources has become particularly important. Traditional agricultural management methods often rely on experience and manual operations, which are not only inefficient, but also difficult to cope with complex and changing environmental factors. How to use the optimal dose of water and fertilizer to accurately irrigate the soil in the monitoring area, reduce water waste, avoid excessive use of fertilizers, thereby improving agricultural production efficiency and quality and ensuring efficient use of agricultural resources is a problem we need to solve. To this end, this paper provides an agricultural resource efficient utilization monitoring system based on artificial intelligence. Summary of the invention
[0003] In order to solve the above technical problems, the purpose of the present invention is to provide an agricultural resource efficient utilization monitoring system based on artificial intelligence.
[0004] The object of the present invention can be achieved by the following technical solutions: an agricultural resource efficient utilization monitoring system based on artificial intelligence, comprising a monitoring center, wherein the monitoring center is communicatively connected to a data acquisition module, a data analysis module, a prediction module and an execution module; The data acquisition module is used to collect soil data and crop image data in the monitoring area; The data analysis module is used to analyze the collected soil data and crop image data to obtain reference moisture content, soil fertility value in the monitoring area, and reference height of crops in the soil in the monitoring area; The prediction module is used to predict the amount of watering the soil in the monitoring area according to the obtained reference moisture content to obtain the predicted amount of watering, and to predict the amount of fertilizer applied to the soil in the monitoring area according to the obtained fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area to obtain the predicted amount of fertilizer applied; The execution module is used to irrigate the soil in the monitoring area according to the obtained predicted watering amount and predicted fertilization amount.
[0005] Furthermore, the process of the data acquisition module collecting soil data and crop image data in the monitoring area includes: The soil data include pH value, total nitrogen, phosphorus and potassium content, organic matter content and moisture content; The data acquisition module is composed of a pH value acquisition terminal, a nitrogen, phosphorus and potassium acquisition terminal, an organic matter acquisition terminal, a moisture acquisition terminal and an image data acquisition terminal; The monitoring area is divided into several monitoring sub-areas, and the pH value collection terminal, nitrogen, phosphorus and potassium collection terminal, organic matter collection terminal, moisture collection terminal and image data collection terminal are installed at the corresponding positions of the monitoring sub-areas; The pH value of the soil in the monitoring sub-area, the total content of nitrogen, phosphorus and potassium in the soil in the monitoring sub-area, the organic matter content, the moisture content and the crop image data are obtained through the installed pH value collection terminal, nitrogen, phosphorus and potassium collection terminal, organic matter collection terminal, moisture collection terminal and image data collection terminal.
[0006] Furthermore, the process of the data analysis module analyzing the collected soil data and crop image data includes: The pH value of the soil in the monitoring area is obtained according to the pH value of the soil in the monitoring sub-area obtained, the total content of nitrogen, phosphorus and potassium in the soil in the monitoring area is obtained according to the total content of nitrogen, phosphorus and potassium in the soil in the monitoring sub-area obtained, the organic matter content in the soil in the monitoring area is obtained according to the organic matter content in the soil in the monitoring sub-area obtained, the moisture content in the soil in the monitoring area is obtained according to the moisture content in the soil in the monitoring sub-area obtained, and the moisture content in the soil in the monitoring area obtained is recorded as the reference moisture content; The fertility value of the soil in the monitoring area is obtained based on the pH value, total nitrogen, phosphorus and potassium content, organic matter content and water content of the soil in the monitoring area; The reference height of the crops in the soil in the monitoring area is obtained according to the acquired image data of the crops in the soil in the monitoring sub-area.
[0007] Furthermore, the process of obtaining the reference height of the crops in the soil in the monitoring area according to the acquired image data of the crops in the soil in the monitoring sub-area includes: Record the acquired crop image data in the soil in the monitoring sub-area as crop image sub-data, and obtain the number and height of the crops in the crop image sub-data; The total height of the crops in the acquired crop image sub-data is divided by the total number of the crops in the acquired crop image sub-data to obtain a reference height of the crops in the soil in the monitoring area.
[0008] Furthermore, the process of the prediction module predicting the watering amount of the soil in the monitoring area according to the obtained reference moisture content includes: Construct a watering amount prediction model, obtain historical watering amounts corresponding to different historical reference moisture contents according to historical data, construct a watering amount prediction model according to the corresponding relationship between the historical reference moisture contents and the historical watering amounts, use the historical reference moisture contents as the input of the watering amount prediction model, use the historical watering amounts corresponding to the historical reference moisture contents as the output of the watering amount prediction model, and train the watering amount prediction model through different historical reference moisture contents and the historical watering amounts corresponding to different historical reference moisture contents; The obtained reference moisture content is input into a watering amount prediction model, and the watering amount prediction model outputs to obtain a predicted watering amount.
[0009] Furthermore, the process of predicting the amount of fertilizer to be applied to the soil in the monitoring area according to the obtained fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area includes: According to historical data, historical fertilizer application amounts corresponding to different historical fertility values and corresponding historical reference heights are obtained, and a fertilizer application amount prediction model is constructed according to the corresponding relationship between historical fertility values, corresponding historical reference heights and historical fertilizer application amounts; The fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area are input into the fertilizer application prediction model, and the fertilizer application prediction model outputs to obtain the predicted fertilizer application amount.
[0010] Furthermore, the process of constructing a fertilizer application amount prediction model according to the correspondence between the historical fertility value and the corresponding historical reference height and the historical fertilizer application amount includes: A fertility value-reference height relationship chain is provided in the fertilizer application amount prediction model, and the fertility value-reference height relationship chain is composed of a fertility value node and a reference height node, and the fertility value node is connected to the reference height node; The historical fertility values and the corresponding historical reference heights are used as the input of the fertilizer application model, the historical fertility values are input into the fertility value node, the corresponding historical reference height is input into the reference height node, and the historical fertilizer application amounts corresponding to the historical fertility values and the corresponding historical reference heights are used as the output of the fertilizer application model. The fertilizer application prediction model is trained through different historical fertility values and corresponding historical reference heights, and different historical fertility values and corresponding historical reference heights.
[0011] Furthermore, the process of the execution module irrigating the soil in the monitoring area according to the obtained predicted watering amount and predicted fertilization amount includes: Irrigation instructions are issued based on the predicted watering amount and predicted fertilization amount. Water with the same dosage as the predicted watering amount and fertilizer with the same dosage as the predicted fertilization amount are obtained according to the irrigation instructions. The water with the same dosage as the predicted watering amount and fertilizer with the same dosage as the predicted fertilization amount are loaded into irrigation equipment, and the irrigation equipment irrigates the soil in the monitoring area.
[0012] Compared with the prior art, the beneficial effects of the present invention are: collecting soil data and crop image data in the monitoring area, analyzing the collected soil data and crop image data, obtaining reference moisture content, soil fertility value of the monitoring area and reference height of crops in the soil in the monitoring area, predicting the amount of watering and fertilizing of the soil in the monitoring area, obtaining predicted watering and predicted fertilization, irrigating the soil in the monitoring area according to the obtained predicted watering and predicted fertilization, and accurately irrigating the soil in the monitoring area with water of the same dosage as the predicted watering and fertilizer of the same dosage as the predicted fertilization, reducing the waste of water resources, avoiding excessive use of fertilizers, and ensuring that crops get enough water and nutrition, thereby ensuring efficient use of agricultural resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION
[0014] like Figure 1 As shown, an agricultural resource efficient utilization monitoring system based on artificial intelligence includes a monitoring center, and the monitoring center is communicatively connected to a data acquisition module, a data analysis module, a prediction module and an execution module; The data acquisition module is used to collect soil data and crop image data in the monitoring area; It should be further explained that, in the specific implementation process, the process of the data acquisition module collecting soil data and crop image data in the monitoring area includes: The soil data include pH value, total nitrogen, phosphorus and potassium content, organic matter content and moisture content; The organic matter includes humus, cellulose, hemicellulose, lignin, etc.; The data acquisition module is composed of a pH value acquisition terminal, a nitrogen, phosphorus and potassium acquisition terminal, an organic matter acquisition terminal, a moisture acquisition terminal and an image data acquisition terminal; The pH value acquisition terminal is used to collect the pH value of the soil, the nitrogen, phosphorus and potassium acquisition terminal is used to collect the total content of nitrogen, phosphorus and potassium in the soil, the organic matter acquisition terminal is used to collect the organic matter content in the soil, the moisture acquisition terminal is used to collect the moisture content in the soil, and the image data acquisition terminal is used to collect image data of crops in the soil; The monitoring area is divided into a number of monitoring sub-areas, and the divided monitoring sub-areas are labeled as i, i=1, 2, 3, ..., n, where n is a positive integer; The pH value collection terminal, nitrogen, phosphorus and potassium collection terminal, organic matter collection terminal, moisture collection terminal and image data collection terminal are installed at the corresponding positions of the monitoring sub-area, the pH value of the soil in the monitoring sub-area is obtained through the installed pH value collection terminal, the total content of nitrogen, phosphorus and potassium in the soil in the monitoring sub-area is obtained through the installed nitrogen, phosphorus and potassium collection terminal, the organic matter content in the soil in the monitoring sub-area is obtained through the installed organic matter collection terminal, the moisture content in the soil in the monitoring sub-area is obtained through the installed moisture collection terminal, and the crop image data in the soil in the monitoring sub-area is obtained through the installed image data collection terminal.
[0015] The data analysis module is used to analyze the collected soil data and crop image data to obtain reference moisture content, soil fertility value in the monitoring area, and reference height of crops in the soil in the monitoring area; It should be further explained that, in the specific implementation process, the process of the data analysis module analyzing the collected soil data and crop image data includes: The pH value of the soil in the monitoring sub-area obtained is recorded as Si, the total content of nitrogen, phosphorus and potassium in the soil in the monitoring sub-area obtained is recorded as Di, the organic matter content in the soil in the monitoring sub-area obtained is recorded as Yi, and the moisture content in the soil in the monitoring sub-area obtained is recorded as Fi; The pH value of the soil in the monitoring area is obtained according to the pH value of the soil in the monitoring sub-area, and the pH value of the soil in the monitoring area is recorded as S 总 ; in, ; The total nitrogen, phosphorus and potassium content in the soil in the monitoring area is obtained according to the total nitrogen, phosphorus and potassium content in the soil in the monitoring sub-area, and the total nitrogen, phosphorus and potassium content in the soil in the monitoring area is recorded as D 总 ; in, ; The organic matter content of the soil in the monitoring area is obtained according to the organic matter content of the soil in the monitoring sub-area, and the organic matter content of the soil in the monitoring area is recorded as Y 总 ; in, ; The soil moisture content in the monitoring area is obtained according to the obtained soil moisture content in the monitoring sub-area, and the soil moisture content in the monitoring area is recorded as the reference moisture content, and the reference moisture content is recorded as F 总 ; in, ; The fertility value of the soil in the monitoring area is obtained based on the pH value, total nitrogen, phosphorus and potassium content, organic matter content and water content of the soil in the monitoring area; The fertility value of the soil obtained was recorded as FL; in, ; qz_s is the weight of the pH value of the soil in the monitoring area, qz_d is the weight of the total content of nitrogen, phosphorus and potassium in the soil in the monitoring area, qz_y is the weight of the organic matter content in the soil in the monitoring area, and qz_f is the weight of the moisture content in the soil in the monitoring area; The obtained crop image data in the soil of the monitoring sub-area is recorded as the crop image sub-data, the number and height of the crops in the crop image sub-data are obtained, the number of crops in the obtained crop image sub-data is recorded as Qi, and the height of the crops in the obtained crop image sub-data is recorded as G j ; Where j = 1, 2, 3, ..., m, ; The reference height of the crops in the soil in the monitoring area is obtained according to the number and height of the crops in the obtained crop image sub-data, and the obtained reference height of the crops in the soil in the monitoring area is recorded as G 参 ; in, .
[0016] The prediction module is used to predict the amount of watering the soil in the monitoring area according to the obtained reference moisture content to obtain the predicted amount of watering, and to predict the amount of fertilizer applied to the soil in the monitoring area according to the obtained fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area to obtain the predicted amount of fertilizer applied; It should be further explained that, in the specific implementation process, the process in which the prediction module predicts the watering amount of the soil in the monitoring area according to the obtained reference moisture content includes: Construct a watering amount prediction model, obtain historical watering amounts corresponding to different historical reference moisture contents according to historical data, construct a watering amount prediction model according to the corresponding relationship between historical reference moisture contents and historical watering amounts, use historical reference moisture contents as input of the watering amount prediction model, use historical watering amounts corresponding to historical reference moisture contents as output of the watering amount prediction model, train the watering amount prediction model through different historical reference moisture contents and historical watering amounts corresponding to different historical reference moisture contents, so as to realize continuous optimization of the watering amount prediction model; The reference moisture content is input into a watering amount prediction model, and the watering amount prediction model outputs a predicted watering amount; It should be further explained that, in the specific implementation process, the process of predicting the amount of fertilizer to be applied to the soil in the monitoring area according to the obtained fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area includes: Constructing a fertilizer application amount prediction model, wherein a fertility value-reference height relationship chain is provided in the fertilizer application amount prediction model, wherein the fertility value-reference height relationship chain is composed of a fertility value node and a reference height node, and the fertility value node is connected to the reference height node; According to historical data, historical fertilizer amounts corresponding to different historical fertility values and corresponding historical reference heights are obtained, and a fertilizer amount prediction model is constructed according to the corresponding relationship between the historical fertility values, the corresponding historical reference heights and the historical fertilizer amounts. The historical fertility values and the corresponding historical reference heights are used as inputs of the fertilizer amount model, the historical fertility values are input into the fertility value nodes, the corresponding historical reference heights are input into the reference height nodes, and the historical fertilizer amounts corresponding to the historical fertility values and the corresponding historical reference heights are used as outputs of the fertilizer amount model. The fertilizer amount prediction model is trained through different historical fertility values and corresponding historical reference heights, and different historical fertility values and corresponding historical reference heights. Historical fertilizer amounts corresponding to the corresponding historical reference heights are used to continuously optimize the fertilizer amount prediction model. The fertility value of the soil in the monitoring area is input into the fertility value node in the fertilization amount prediction model, and the reference height of the crops in the soil in the monitoring area is input into the reference height node in the fertilization amount prediction model. The fertilization amount prediction model outputs and obtains the predicted fertilization amount.
[0017] The execution module is used to irrigate the soil in the monitoring area according to the obtained predicted watering amount and predicted fertilization amount; It should be further explained that, in the specific implementation process, the process of the execution module irrigating the soil in the monitoring area according to the obtained predicted watering amount and predicted fertilization amount includes: issuing an irrigation instruction according to the obtained predicted watering amount and predicted fertilization amount, obtaining water with the same dosage as the predicted watering amount and fertilizer with the same dosage as the predicted fertilization amount according to the irrigation instruction, loading the obtained water with the same dosage as the predicted watering amount and fertilizer with the same dosage as the predicted fertilization amount into irrigation equipment, and irrigating the soil in the monitoring area with the irrigation equipment; In an embodiment of the present invention, soil data and crop image data in a monitoring area are collected and monitored, the amount of fertilizer applied to the soil in the monitoring area is predicted based on the soil fertility value and the reference height of the crops to obtain a predicted amount of fertilizer applied, the amount of watering the soil in the monitoring area is predicted based on the reference moisture content to obtain a predicted amount of watering, and the soil in the monitoring area is precisely irrigated with the same dose of water as the predicted amount of watering and the same dose of fertilizer as the predicted amount of fertilizer applied, thereby improving irrigation efficiency, reducing waste of water resources, ensuring that crops receive sufficient water and nutrition, improving agricultural production efficiency and quality, avoiding excessive use of fertilizers, reducing waste and environmental pollution, and thus ensuring efficient use of agricultural resources.
[0018] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims
1. An agricultural resource efficient utilization monitoring system based on artificial intelligence, comprising a monitoring center, characterized in that: The monitoring center is communicatively connected to a data acquisition module, a data analysis module, a prediction module and an execution module; The data acquisition module is used to collect soil data and crop image data in the monitoring area; The data analysis module is used to analyze the collected soil data and crop image data to obtain reference moisture content, soil fertility value in the monitoring area, and reference height of crops in the soil in the monitoring area; The prediction module is used to predict the amount of watering the soil in the monitoring area according to the obtained reference moisture content to obtain the predicted amount of watering, and to predict the amount of fertilizer applied to the soil in the monitoring area according to the obtained fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area to obtain the predicted amount of fertilizer applied; The execution module is used to irrigate the soil in the monitoring area according to the obtained predicted watering amount and predicted fertilization amount.
2. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 1, characterized in that: The process of the data acquisition module collecting soil data and crop image data in the monitoring area includes: The soil data include pH value, total nitrogen, phosphorus and potassium content, organic matter content and moisture content; The data acquisition module is composed of a pH value acquisition terminal, a nitrogen, phosphorus and potassium acquisition terminal, an organic matter acquisition terminal, a moisture acquisition terminal and an image data acquisition terminal; The monitoring area is divided into several monitoring sub-areas, and the pH value collection terminal, nitrogen, phosphorus and potassium collection terminal, organic matter collection terminal, moisture collection terminal and image data collection terminal are installed at the corresponding positions of the monitoring sub-areas; The pH value of the soil in the monitoring sub-area, the total content of nitrogen, phosphorus and potassium in the soil in the monitoring sub-area, the organic matter content, the moisture content and the crop image data are obtained through the installed pH value collection terminal, nitrogen, phosphorus and potassium collection terminal, organic matter collection terminal, moisture collection terminal and image data collection terminal.
3. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 2 is characterized in that: The process of the data analysis module analyzing the collected soil data and crop image data includes: The pH value of the soil in the monitoring area is obtained according to the pH value of the soil in the monitoring sub-area obtained, the total content of nitrogen, phosphorus and potassium in the soil in the monitoring area is obtained according to the total content of nitrogen, phosphorus and potassium in the soil in the monitoring sub-area obtained, the organic matter content in the soil in the monitoring area is obtained according to the organic matter content in the soil in the monitoring sub-area obtained, the moisture content in the soil in the monitoring area is obtained according to the moisture content in the soil in the monitoring sub-area obtained, and the moisture content in the soil in the monitoring area obtained is recorded as the reference moisture content; The fertility value of the soil in the monitoring area is obtained based on the pH value, total nitrogen, phosphorus and potassium content, organic matter content and water content of the soil in the monitoring area; The reference height of the crops in the soil in the monitoring area is obtained according to the acquired image data of the crops in the soil in the monitoring sub-area.
4. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 3 is characterized in that: The process of obtaining the reference height of crops in the soil in the monitoring area according to the acquired crop image data in the soil in the monitoring sub-area includes: Record the acquired crop image data in the soil in the monitoring sub-area as crop image sub-data, and obtain the number and height of the crops in the crop image sub-data; The total height of the crops in the acquired crop image sub-data is divided by the total number of the crops in the acquired crop image sub-data to obtain a reference height of the crops in the soil in the monitoring area.
5. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 4 is characterized in that: The process of the prediction module predicting the watering amount of the soil in the monitoring area according to the obtained reference moisture content includes: Construct a watering amount prediction model, obtain historical watering amounts corresponding to different historical reference moisture contents according to historical data, construct a watering amount prediction model according to the corresponding relationship between the historical reference moisture contents and the historical watering amounts, use the historical reference moisture contents as the input of the watering amount prediction model, use the historical watering amounts corresponding to the historical reference moisture contents as the output of the watering amount prediction model, and train the watering amount prediction model through different historical reference moisture contents and the historical watering amounts corresponding to different historical reference moisture contents; The obtained reference moisture content is input into a watering amount prediction model, and the watering amount prediction model outputs to obtain a predicted watering amount.
6. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 5, characterized in that: The process of predicting the amount of fertilizer to be applied to the soil in the monitoring area based on the obtained soil fertility value in the monitoring area and the reference height of crops in the soil in the monitoring area includes: According to historical data, historical fertilizer application amounts corresponding to different historical fertility values and corresponding historical reference heights are obtained, and a fertilizer application amount prediction model is constructed according to the corresponding relationship between historical fertility values, corresponding historical reference heights and historical fertilizer application amounts; The fertility value of the soil in the monitoring area and the reference height of the crops in the soil in the monitoring area are input into the fertilizer application prediction model, and the fertilizer application prediction model outputs to obtain the predicted fertilizer application amount.
7. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 6, characterized in that: The process of constructing a fertilizer application prediction model based on the correspondence between historical fertility values and corresponding historical reference heights and historical fertilizer application amounts includes: A fertility value-reference height relationship chain is provided in the fertilizer application amount prediction model, and the fertility value-reference height relationship chain is composed of a fertility value node and a reference height node, and the fertility value node is connected to the reference height node; The historical fertility values and the corresponding historical reference heights are used as the input of the fertilizer application model, the historical fertility values are input into the fertility value node, the corresponding historical reference height is input into the reference height node, and the historical fertilizer application amounts corresponding to the historical fertility values and the corresponding historical reference heights are used as the output of the fertilizer application model. The fertilizer application prediction model is trained through different historical fertility values and corresponding historical reference heights, and different historical fertility values and corresponding historical reference heights.
8. The artificial intelligence-based agricultural resource efficient utilization monitoring system according to claim 7, characterized in that: The process of the execution module irrigating the soil in the monitoring area according to the obtained predicted watering amount and predicted fertilization amount includes: Irrigation instructions are issued based on the predicted watering amount and predicted fertilization amount. Water with the same dosage as the predicted watering amount and fertilizer with the same dosage as the predicted fertilization amount are obtained according to the irrigation instructions. The water with the same dosage as the predicted watering amount and fertilizer with the same dosage as the predicted fertilization amount are loaded into irrigation equipment, and the irrigation equipment irrigates the soil in the monitoring area.