Agricultural non-point source pollution intelligent management system based on Internet of Things

Abstract

The invention relates to an agricultural non-point source pollution intelligent management system based on the Internet of Things, and the system comprises an agricultural basic information obtaining module which is used for collecting the agricultural basic data of a target region; the agricultural pollution data acquisition module is used for acquiring agricultural non-point source pollution data of a target area in real time by arranging a monitoring station; the agricultural pollution data analysis module is used for processing and analyzing the agricultural basic data and the agricultural non-point source pollution data to obtain a pollution change trend and a pollution abnormal value; and the pollution early warning module is used for sending early warning information based on the pollution change trend and the pollution abnormal value and providing a treatment decision. The agricultural non-point source pollution abnormal value and the abnormal reason can be rapidly judged, and effective decision support is provided for prevention and treatment of agricultural non-point source pollution.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural non-point source pollution management, and in particular to an intelligent agricultural non-point source pollution management system based on the Internet of Things. Background Art

[0002] Agricultural non-point source pollution, also known as non-point source pollution, refers to the sewage, waste gas, waste, etc. generated by rural production and life activities, which are directly or indirectly discharged into farmland without treatment, causing various pollution to the farmland environment, resulting in excessive pollutant content in the produced crops. These pollutants include various chemicals, heavy metals, nutrients, etc., which have long-term and widespread impacts on the soil, water, atmosphere and other environments, and cause harm to the ecological environment and human health. The uncertainty and difficulty in direct control of agricultural non-point source pollution make environmental management face great challenges.

[0003] The current agricultural non-point source pollution management technology usually focuses on post-event environmental impact assessment, lacks continuous monitoring and immediate assessment of real-time agricultural activities, resulting in the inability to respond in time and take corresponding preventive or mitigation measures when pollution incidents occur; secondly, the traditional method faces problems such as complex data processing, insufficient data utilization, and lack of effective data management mechanism when processing data, and cannot provide effective decision support for the prevention and control of agricultural non-point source pollution. Therefore, the present invention proposes an intelligent management system for agricultural non-point source pollution based on the Internet of Things. Summary of the invention

[0004] The purpose of the present invention is to solve the above technical problems and provide an intelligent management system for agricultural non-point source pollution based on the Internet of Things to monitor agricultural non-point source pollution data in real time and quickly determine pollution abnormalities.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] The smart management system for agricultural non-point source pollution based on the Internet of Things includes: agricultural basic information acquisition module, agricultural pollution data collection module, agricultural pollution data analysis module, and pollution early warning module;

[0007] The agricultural basic information acquisition module is used to collect agricultural basic data of the target area;

[0008] The agricultural pollution data collection module is used to collect agricultural non-point source pollution data of the target area in real time by deploying monitoring stations;

[0009] The agricultural pollution data analysis module is used to process and analyze the agricultural basic data and agricultural non-point source pollution data to obtain pollution change trends and pollution abnormal values;

[0010] The pollution warning module is used to send warning information based on the pollution change trend and pollution abnormal values, and provide governance decisions.

[0011] Optionally, the agricultural basic information acquisition module includes: a governance measure acquisition unit and a governance target determination unit, wherein the governance measure acquisition unit is used to obtain the agricultural governance measures taken in the target area and the real-time agricultural basic data after the implementation of the measures; the governance target determination unit is used to preset the agricultural basic data change trend according to the agricultural governance measures.

[0012] Optionally, the agricultural pollution data collection module includes: a farmland pollution collection unit, a rural pollution collection unit, and a breeding pollution collection unit, wherein the farmland pollution collection unit is used to collect farmland non-point source pollution data and farmland irrigation ditch data in the target area by deploying farmland monitoring stations; the rural pollution collection unit is used to collect rural non-point source pollution data in the target area by deploying rural monitoring stations; and the breeding pollution collection unit is used to collect livestock and poultry breeding pollution data in the target area by deploying breeding monitoring stations.

[0013] Optionally, the farmland non-point source pollution data include farmland underground leaching, micro-environment meteorology and soil temperature, moisture and salinity data; the farmland irrigation ditch data and rural non-point source pollution data both include pH value, dissolved oxygen, temperature, conductivity, turbidity, permanganate index, flow, total nitrogen, total phosphorus, and ammonia nitrogen data; the livestock and poultry breeding pollution data include chemical oxygen demand, total nitrogen, total phosphorus, ammonia nitrogen, and drainage.

[0014] Optionally, the agricultural pollution data analysis module includes: an environmental impact analysis unit, a chemical impact analysis unit, and an agricultural impact analysis unit, wherein the environmental impact analysis unit is used to perform statistics and calculations on the data affected by the environment in the agricultural non-point source pollution data to obtain environmental impact values; the chemical impact analysis unit is used to perform statistics and calculations on the data affected by the use of chemicals in the agricultural non-point source pollution data to obtain chemical impact values; the agricultural impact analysis unit is used to combine the environmental impact values, chemical impact values, agricultural governance measures and real-time agricultural basic data for analysis to obtain pollution change trends and pollution anomalies.

[0015] Optionally, the environmental impact value and the chemical impact value are calculated as follows:

[0016] The pollutant content change curves affected by the environment and the use of chemicals in farmland non-point source pollution data, farmland irrigation ditch data, rural non-point source pollution data and livestock and poultry breeding pollution data were respectively compiled;

[0017] The environmental impact values ​​and chemical impact values ​​of the farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution and livestock and poultry breeding pollution are calculated respectively based on the pollutant content change curve.

[0018] Optionally, the pollution warning module includes: a pollution warning unit and a governance decision unit, wherein the pollution warning unit is used to compare the pollution change trend with the preset agricultural basic data change trend, and compare the pollution anomaly value with the preset pollution anomaly threshold, and issue warning information based on the comparison result; the governance decision unit is used to provide governance decisions based on the comparison result and in combination with historical governance measures.

[0019] Optionally, the system also includes a visualization module, which is used to construct a regional model of the target area, and integrate the monitoring stations and real-time agricultural non-point source pollution data collected by the monitoring stations, as well as the corresponding real-time pollution increments, early warning information and governance decisions into the regional model for visual display.

[0020] The beneficial effects of the present invention are:

[0021] The present invention establishes an agricultural non-point source pollution monitoring network to realize real-time monitoring of farmland non-point source pollution data, farmland irrigation ditch data, rural non-point source pollution data and livestock and poultry breeding pollution data, and further calculates environmental impact abnormal values ​​and chemical impact abnormal values. It can quickly analyze the abnormal causes based on the abnormal values, and combine the agricultural governance measures being taken and real-time agricultural basic data to further judge the causes of pollution and abnormal causes. At the same time, it can monitor the governance progress of agricultural governance measures and whether the governance effects meet the standards, thereby providing effective decision-making support for the prevention and control of agricultural non-point source pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is a schematic diagram of the structure of an intelligent management system for agricultural non-point source pollution based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] Agricultural non-point source pollution, also known as non-point source pollution, refers to the sewage, waste gas, waste, etc. generated by rural production and life activities, which are directly or indirectly discharged into farmland without treatment, causing various pollution to the farmland environment, resulting in excessive pollutant content in the produced crops. These pollutants include various chemicals, heavy metals, nutrients, etc., which have long-term and widespread impacts on the soil, water, atmosphere and other environments, and cause harm to the ecological environment and human health. The uncertainty and difficulty in direct control of agricultural non-point source pollution make environmental management face great challenges.

[0027] With the advancement of science and technology, especially the rapid development of information technology, sensor technology, data analysis technology and the Internet of Things, the concept of "smart agriculture" has gradually been applied to the governance and management of agricultural non-point source pollution. This technology-based intelligent management method can more accurately and efficiently realize pollution source monitoring, prediction, early warning and decision support, thereby reducing the occurrence and spread of agricultural non-point source pollution. The causes of agricultural non-point source pollution mainly include the following aspects: (1) Excessive use of fertilizers and pesticides: In order to increase production, farmers often apply excessive fertilizers and pesticides, causing these chemicals to flow into water bodies with rainwater runoff and pollute water sources. (2) Improper treatment of livestock and poultry manure: The waste generated by livestock and poultry farming contains a large amount of nutrients such as nitrogen and phosphorus. If it is not properly treated or discharged, it will cause non-point source pollution. (3) Soil erosion: In some areas, due to unreasonable farming methods (such as excessive farming, bare land, etc.), soil erosion occurs, and pollutants are lost into water bodies with soil loss. (4) Improper irrigation of farmland: During irrigation, excessive water brings pollutants in the soil into nearby water bodies, causing eutrophication of water bodies. At present, agricultural non-point source pollution management technology lacks continuous monitoring and immediate evaluation of real-time agricultural activities, resulting in the inability to respond in time and take corresponding prevention or mitigation measures when pollution incidents occur. In addition, when processing data, it faces problems such as complex data processing, insufficient data utilization, and lack of effective data management mechanisms, and is unable to provide effective decision-making support for the prevention and control of agricultural non-point source pollution.

[0028] Therefore, this embodiment provides an intelligent management system for agricultural non-point source pollution based on the Internet of Things, such as Figure 1As shown, it includes: agricultural basic information acquisition module, agricultural pollution data collection module, agricultural pollution data analysis module, and pollution early warning module;

[0029] Agricultural basic information acquisition module, used to collect agricultural basic data of the target area;

[0030] Agricultural pollution data collection module, used to collect agricultural non-point source pollution data in the target area in real time by setting up monitoring stations;

[0031] Agricultural pollution data analysis module, used to process and analyze agricultural basic data and agricultural non-point source pollution data, and obtain pollution change trends and pollution anomalies;

[0032] The pollution warning module is used to send warning information based on pollution change trends and pollution anomalies, and provide governance decisions.

[0033] Specifically, this embodiment establishes an agricultural non-point source pollution monitoring network to achieve real-time monitoring of farmland non-point source pollution data, farmland irrigation ditch data, rural non-point source pollution data and livestock and poultry breeding pollution data, and further calculates environmental impact anomalies and chemical impact anomalies. It can quickly analyze the causes of anomalies based on the anomalies, and combine the agricultural governance measures being taken and real-time agricultural basic data to further determine the causes of pollution and anomalies. At the same time, it can monitor the progress of agricultural governance measures and whether the governance effects meet the standards, thereby providing effective decision-making support for the prevention and control of agricultural non-point source pollution.

[0034] Furthermore, the agricultural basic information acquisition module includes a governance measure acquisition unit and a governance target determination unit, wherein the governance measure acquisition unit is used to obtain the agricultural governance measures taken in the target area and real-time agricultural basic data before and after the implementation of the measures; the governance target determination unit is used to preset the change trend of agricultural basic data according to the agricultural governance measures.

[0035] Specifically, the agricultural control measures and agricultural basic data in this embodiment are obtained through a large amount of basic data accumulated by the Municipal Agriculture and Animal Husbandry Bureau in the comprehensive control of agricultural non-point source pollution, such as long-term positioning monitoring data of farmland film residues, arable land quality monitoring data, and related monitoring data after comprehensive utilization of straw.

[0036] Furthermore, the agricultural pollution data collection module includes a farmland pollution collection unit, a rural pollution collection unit, and a breeding pollution collection unit, wherein the farmland pollution collection unit is used to collect farmland non-point source pollution data and farmland irrigation ditch data in the target area by setting up farmland monitoring stations; the rural pollution collection unit is used to collect rural non-point source pollution data in the target area by setting up rural monitoring stations; and the breeding pollution collection unit is used to collect livestock and poultry breeding pollution data in the target area by setting up breeding monitoring stations.

[0037] Among them, the farmland non-point source pollution data include farmland underground leaching, micro-environment meteorology and soil temperature, moisture and salinity data; the farmland irrigation ditch data and rural non-point source pollution data include pH value, dissolved oxygen, temperature, conductivity, turbidity, permanganate index, flow, total nitrogen, total phosphorus, and ammonia nitrogen data; livestock and poultry breeding pollution data include chemical oxygen demand, total nitrogen, total phosphorus, ammonia nitrogen, and drainage volume.

[0038] Specifically, in this embodiment, data collection mainly involves collection of meteorological data, hydrological data, and water quality data.

[0039] Farmland monitoring stations include farmland non-point source pollution monitoring stations and farmland irrigation ditch monitoring stations. Farmland non-point source pollution monitoring stations need to select representative plots in the target area for deployment, and the selected plots are located in the area where field crops are planted in continuous areas. In addition to the above requirements, the selection of monitoring points should meet the requirements of typicality, representativeness, long-term and anti-interference. Farmland non-point source pollution monitoring includes the simultaneous monitoring of farmland underground leaching, micro-environment meteorology and soil temperature, moisture and salt parameters. The above parameters are crucial to the prevention and control of crop growth and pollutants (mainly nutrients) at the farmland scale.

[0040] Underground leaching of farmland refers to the process of leaching water pollutants such as nitrogen and phosphorus from the surface or body of farmland soil into groundwater by means of rainfall, irrigation or melting water from ice and snow, and is one of the important ways of causing non-point source pollution in farmland. In this embodiment, an underground leaching solution collection bucket is set up and a pressure-type water level sensor is installed in the leaching solution collection bucket to convert and calculate the leaching amount, and sampling is performed in the leaching solution collection bucket to detect the pollution data of underground leaching water in farmland.

[0041] Micro-environment meteorological data is obtained by building micro-environment meteorological stations to monitor the conventional meteorological elements on the ground in the target area in real time. The monitoring indicators include rainfall, wind speed, wind direction, temperature, humidity, radiation intensity, etc.

[0042] Soil temperature, moisture and salinity monitoring uses a soil three-parameter sensor, and the monitoring indicators are surface soil temperature, moisture and salinity.

[0043] The layout of farmland irrigation ditch monitoring stations adopts the "cascade monitoring" method, which classifies the irrigation ditches in the target area, selects typical drainage ditch monitoring sections in each level to carry out online water quality monitoring, and reveals the migration and transformation rules of pollutants in drainage ditches of different levels. Farmland irrigation ditch monitoring includes online monitoring of conventional physical and chemical indicators (pH value, dissolved oxygen, temperature, conductivity, turbidity), permanganate index, flow, total nitrogen, total phosphorus, ammonia nitrogen and other indicators. This is achieved by laying water quality monitoring instruments and flow monitoring instruments in irrigation ditches.

[0044] Rural monitoring stations are mainly used to monitor rural domestic sewage, which mainly comes from kitchen and bathing drainage, and has high levels of organic matter, total nitrogen and total phosphorus in pollutants. Villages with large populations, concentrated populations in rows and villages with centralized sewage treatment facilities are preferred for setting up rural monitoring stations, which mainly conduct real-time online monitoring of conventional physical and chemical indicators (pH value, dissolved oxygen, temperature, conductivity, turbidity), flow, permanganate index, total nitrogen, total phosphorus and ammonia nitrogen in rural domestic sewage. The flow is measured by installing a magnetic flowmeter on the main pipeline where the domestic sewage pipe enters the domestic sewage treatment station, and other indicator data are detected in the main pipeline.

[0045] The breeding monitoring station is selected according to the livestock and poultry breeding structure, manure treatment methods and daily excretion of different livestock and poultry manure in the target area. It mainly monitors the chemical oxygen demand, total nitrogen, total phosphorus, ammonia nitrogen and other water quality indicators and water depth and other water quantity indicators in the oxidation ponds of livestock and poultry farms in real time online. A pressure water level sensor is installed in the oxidation pond to dynamically monitor the volume of livestock and poultry wastewater in the oxidation pond, which can be converted into the discharge volume of livestock and poultry wastewater, and sampling is carried out in the oxidation pond to detect other indicator data.

[0046] Furthermore, the agricultural pollution data analysis module includes an environmental impact analysis unit, a chemical impact analysis unit, and an agricultural impact analysis unit, wherein the environmental impact analysis unit is used to perform statistics and calculations on the data affected by the environment in the agricultural non-point source pollution data to obtain environmental impact values; the chemical impact analysis unit is used to perform statistics and calculations on the data affected by the use of chemicals in the agricultural non-point source pollution data to obtain chemical impact values; the agricultural impact analysis unit is used to combine the environmental impact values, chemical impact values, agricultural governance measures, and basic agricultural data for analysis to obtain pollution change trends and pollution anomalies.

[0047] Among them, the calculation method of environmental impact value and chemical impact value is:

[0048] The pollutant content change curves affected by the environment and the use of chemicals in farmland non-point source pollution data, farmland irrigation ditch data, rural non-point source pollution data and livestock and poultry breeding pollution data were respectively compiled;

[0049] Based on the pollutant content change curve, the environmental impact values ​​and chemical impact values ​​of farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution and livestock and poultry breeding pollution were calculated respectively.

[0050] In this embodiment, the method for calculating the environmental impact value of farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution and livestock and poultry breeding pollution through the pollutant content change curve affected by the environment is specifically as follows:

[0051]

[0052] Among them, A is the environmental impact value, including the environmental impact value A1 of farmland non-point source pollution, the environmental impact value A2 of farmland irrigation ditch, the environmental impact value A3 of rural non-point source pollution, and the environmental impact value A4 of livestock and poultry breeding pollution; α is the abnormal value proportion coefficient, which can be the abnormal value proportion coefficient α1 of farmland non-point source pollution, the abnormal value proportion coefficient α2 of farmland irrigation ditch, the abnormal value proportion coefficient α3 of rural non-point source pollution, and the abnormal value proportion coefficient α4 of livestock and poultry breeding pollution; a n is the proportion coefficient of the nth pollutant in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution, x nt is the specific value of the nth pollutant in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution at time t, x nmax is the maximum value of the safe range of the nth pollutant in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution; N is the type of pollutant in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution; the pollution types in the four types of pollution data are specifically set according to the monitoring situation; T is the monitoring time of the historical monitoring data used in the specific analysis.

[0053] In this embodiment, the method for calculating the chemical impact value of farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution and livestock and poultry breeding pollution through the pollutant content change curve affected by the use of chemicals is specifically as follows:

[0054]

[0055] Among them, B is the chemical impact value, including the chemical impact value B1 in farmland non-point source pollution, the chemical impact value B2 in farmland irrigation ditches, the chemical impact value B3 in rural non-point source pollution, and the chemical impact value B4 in livestock and poultry breeding pollution;; p m is the value of the time interval in days from the mth chemical use process to the statistical moment in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution, U w is the proportion coefficient of the wth harmful component in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution, V mw V is the amount of the wth harmful component used in the mth chemical use process in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution, wmax is the maximum value of the qualified range of the wth harmful component in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution; M is the total number of times chemicals are used in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution during the statistical period; W is the number of types of harmful components in chemicals used in farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution, or livestock and poultry breeding pollution.

[0056] In this embodiment, the environmental impact value, chemical impact value, agricultural control measures and agricultural basic data are combined for analysis to obtain pollution change trends and pollution abnormal values. The specific calculation formula for pollution abnormal values ​​is:

[0057] C=c1A+c2B

[0058] Among them, C is the pollution anomaly value, c1 is the environmental impact value ratio, and c2 is the chemical impact value ratio.

[0059] Furthermore, the pollution warning module includes a pollution warning unit and a governance decision unit, wherein the pollution warning unit is used to compare the pollution change trend with the preset agricultural basic data change trend, and compare the pollution anomaly value with the preset pollution anomaly threshold, and issue warning information based on the comparison results; the governance decision unit is used to provide governance decisions based on the comparison results and combined with historical governance measures.

[0060] Specifically, the governance decisions include controlling fertilizer to increase efficiency, controlling pesticides to reduce harm, controlling water to reduce consumption, controlling film to improve efficiency, comprehensive utilization of straw, and resource utilization of livestock and poultry manure.

[0061] The data obtained from each monitoring station are used for environmental impact calculation and chemical impact calculation respectively. The calculated environmental impact values ​​and chemical impact values ​​are substituted into the agricultural pollution anomaly calculation strategy to output the agricultural pollution anomaly values ​​of the agricultural surface. The calculated agricultural pollution anomaly values ​​are compared with the set agricultural pollution anomaly threshold. If the obtained agricultural pollution anomaly value is greater than or equal to the set agricultural pollution anomaly threshold, an agricultural non-point source pollution warning is issued. If the obtained agricultural pollution anomaly value is less than the set agricultural pollution anomaly threshold, no agricultural non-point source pollution warning is issued. The agricultural non-point source pollution situation is accurately modeled and evaluated to provide effective decision-making support for the prevention and control of agricultural non-point source pollution.

[0062] To further optimize the technical solution, the IoT-based intelligent management system for agricultural non-point source pollution provided in this embodiment also includes a visualization module, which is used to construct a regional model of the target area, and integrate the monitoring stations and real-time agricultural non-point source pollution data collected by the monitoring stations, as well as the corresponding real-time pollution increments, early warning information and governance decisions into the regional model for visual display.

[0063] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. The intelligent management system of agricultural non-point source pollution based on the Internet of Things is characterized by: include: Agricultural basic information acquisition module, agricultural pollution data collection module, agricultural pollution data analysis module, pollution early warning module; The agricultural basic information acquisition module is used to collect agricultural basic data of the target area; The agricultural pollution data collection module is used to collect agricultural non-point source pollution data of the target area in real time by deploying monitoring stations; The agricultural pollution data analysis module is used to process and analyze the agricultural basic data and agricultural non-point source pollution data to obtain pollution change trends and pollution abnormal values; The pollution warning module is used to send warning information based on the pollution change trend and pollution abnormal values, and provide governance decisions.

2. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to claim 1 is characterized in that: The agricultural basic information acquisition module includes: a governance measure acquisition unit and a governance target determination unit, wherein the governance measure acquisition unit is used to obtain the agricultural governance measures taken in the target area and the real-time agricultural basic data after the implementation of the measures; the governance target determination unit is used to preset the agricultural basic data change trend according to the agricultural governance measures.

3. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to claim 1 is characterized in that: The agricultural pollution data collection module includes: a farmland pollution collection unit, a rural pollution collection unit, and a breeding pollution collection unit, wherein the farmland pollution collection unit is used to collect farmland non-point source pollution data and farmland irrigation ditch data in the target area by deploying farmland monitoring stations; the rural pollution collection unit is used to collect rural non-point source pollution data in the target area by deploying rural monitoring stations; and the breeding pollution collection unit is used to collect livestock and poultry breeding pollution data in the target area by deploying breeding monitoring stations.

4. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to claim 3 is characterized in that: The farmland non-point source pollution data include farmland underground leaching, micro-environment meteorology and soil temperature, moisture and salt data; the farmland irrigation ditch data and rural non-point source pollution data include pH value, dissolved oxygen, temperature, conductivity, turbidity, permanganate index, flow, total nitrogen, total phosphorus, and ammonia nitrogen data; the livestock and poultry breeding pollution data include chemical oxygen demand, total nitrogen, total phosphorus, ammonia nitrogen, and drainage.

5. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to claim 1 is characterized in that: The agricultural pollution data analysis module includes: an environmental impact analysis unit, a chemical impact analysis unit, and an agricultural impact analysis unit, wherein the environmental impact analysis unit is used to count and calculate the data affected by the environment in the agricultural non-point source pollution data to obtain the environmental impact value; the chemical impact analysis unit is used to count and calculate the data affected by the use of chemicals in the agricultural non-point source pollution data to obtain the chemical impact value; the agricultural impact analysis unit is used to combine the environmental impact value, chemical impact value, agricultural governance measures and real-time agricultural basic data for analysis to obtain pollution change trends and pollution anomalies.

6. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to claim 5 is characterized in that: The calculation method of the environmental impact value and chemical impact value is: The pollutant content change curves affected by the environment and the use of chemicals in farmland non-point source pollution data, farmland irrigation ditch data, rural non-point source pollution data and livestock and poultry breeding pollution data were respectively compiled; The environmental impact values ​​and chemical impact values ​​of the farmland non-point source pollution, farmland irrigation ditch pollution, rural non-point source pollution and livestock and poultry breeding pollution are calculated respectively based on the pollutant content change curve.

7. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to claim 1 is characterized in that: The pollution warning module includes: a pollution warning unit and a governance decision unit, wherein the pollution warning unit is used to compare the pollution change trend with the preset agricultural basic data change trend, and compare the pollution anomaly value with the preset pollution anomaly threshold, and issue warning information based on the comparison result; the governance decision unit is used to provide governance decisions based on the comparison result and in combination with historical governance measures.

8. The intelligent management system for agricultural non-point source pollution based on the Internet of Things according to any one of claims 1 to 7, characterized in that: The system also includes a visualization module, which is used to construct a regional model of the target area, and integrate the monitoring stations and real-time agricultural non-point source pollution data collected by the monitoring stations, as well as the corresponding real-time pollution increments, early warning information and governance decisions into the regional model for visual display.

Images