Dynamic treatment method and system for agricultural non-point source pollution and storage medium

Abstract

The invention relates to a dynamic treatment method for agricultural non-point source pollution. The method comprises the following steps: setting an intelligent monitoring network in an agricultural drainage basin, and monitoring key data in real time through a sensor; the wireless communication module is used for transmitting the data to the central control center for storage and preprocessing; the preprocessed data is deeply analyzed by using big data analysis and an artificial intelligence algorithm, a pollution source is accurately identified, a diffusion trend is predicted, and a personalized treatment scheme including fertilization and pesticide application guidance, sewage treatment process selection, runoff management measures and the like is generated according to the pollution source and the diffusion trend; dynamically adjusting the treatment strategy according to the agricultural production cycle and climate change; technical means such as bioremediation, ecological engineering and efficient chemical fertilizer and pesticide preparations are integrated, a collaborative treatment technical system is constructed, accurate and efficient dynamic treatment of agricultural non-point source pollution is achieved, the quality of agricultural production is improved, and sustainable development of agricultural ecology is promoted.

Description

Technical Field

[0001] This invention relates to the technical field of agricultural production management, and in particular to a dynamic management method, system, and storage medium for agricultural non-point source pollution. Background Technology

[0002] In agricultural production, non-point source pollution has become a key issue restricting environmental quality and sustainable agricultural development. Traditional methods for controlling agricultural non-point source pollution mainly rely on regular water quality testing and soil analysis. These methods are not only time-consuming and labor-intensive, but also fail to reflect pollution dynamics in real time, resulting in a lag in control measures and hindering the achievement of ideal control effects. Furthermore, existing control technologies often focus on single aspects, such as fertilizer reduction or wastewater treatment, neglecting the integrity and complexity of the agricultural ecosystem and failing to form a synergistic control system. These problems make it difficult for existing technologies to meet the demands of modern agriculture for precise, efficient, and dynamic control of non-point source pollution, thereby reducing the quality of agricultural production and necessitating improvement. Summary of the Invention

[0003] In order to improve the quality of agricultural production, this application provides a dynamic treatment method, system and storage medium for agricultural non-point source pollution.

[0004] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution: A dynamic treatment method for agricultural non-point source pollution, the method comprising the following steps: An intelligent monitoring network is set up within the agricultural watershed. The monitoring network includes multiple monitoring sensor nodes, including water quality sensors, weather stations, and soil nutrient sensors, for real-time monitoring of data related to non-point source pollution, such as nitrogen and phosphorus content in water bodies, rainfall, and soil fertility. The data collected by the monitoring sensor nodes is transmitted to the central control center in real time via a wireless communication module. The central control center is used for data storage and preprocessing. Based on big data analytics and artificial intelligence algorithms, the preprocessed data is analyzed to identify pollution sources, predict pollution spread trends, and generate personalized treatment plans based on the analysis results. These treatment plans include guidance on fertilization and pesticide application, selection of wastewater treatment processes, and runoff management measures. Based on agricultural production cycles and climate change, dynamic adjustment and management strategies are generated, including adjusting the operating parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilizer and pesticide application guidelines. By integrating various governance technologies, a collaborative governance technology system is formed, which includes bioremediation technology, ecological engineering technology, and high-efficiency fertilizer and pesticide formulation technology.

[0005] By adopting the above-mentioned technical solutions, an intelligent monitoring network is set up in agricultural watersheds to collect key data such as water quality, meteorology, and soil nutrients in real time. This data is transmitted wirelessly to a central control center for preprocessing. Big data analysis and artificial intelligence algorithms are used to deeply mine the data, accurately identify pollution sources, and predict diffusion trends. Based on this, personalized governance plans are generated, covering fertilization and pesticide application guidance, wastewater treatment process selection, and runoff management measures. The plans dynamically adjust governance measures according to the agricultural production cycle and climate change, such as optimizing farmland drainage system parameters, flexibly configuring runoff collection and purification facilities, and updating fertilization and pesticide application guidance, ensuring the timeliness and accuracy of the governance strategies. At the same time, multiple technologies such as bioremediation, ecological engineering, and high-efficiency fertilizer and pesticide formulations are integrated to form a collaborative governance technology system, comprehensively improving the governance effect. Compared with traditional governance methods, this solution achieves real-time monitoring, accurate early warning, dynamic adjustment, and collaborative governance of agricultural non-point source pollution, effectively reducing the negative impact of agricultural non-point source pollution on the environment, improving the ecological and economic benefits of agricultural production, and promoting sustainable agricultural development.

[0006] In a preferred embodiment, this application can be further configured to include the following steps prior to the step of setting up an intelligent monitoring network within an agricultural watershed: Based on geographic information, land use type and pollution source distribution, the agricultural watershed is divided into multiple monitoring sub-regions, and a unique identifier is assigned to each sub-region. At least one core monitoring station is set up in each sub-region. The core monitoring station is equipped with comprehensive monitoring equipment to collect key pollution data of the sub-region, which serves as the benchmark data source for pollution monitoring in the sub-region.

[0007] In a preferred embodiment, this application can be further configured to include the following steps after analyzing the preprocessed data based on big data analytics and artificial intelligence algorithms to identify pollution sources, predict pollution spread trends, and generate personalized remediation plans based on the analysis results: Using the aforementioned personalized treatment plan, the pollution status of each sub-region is simulated and the treatment effect is evaluated. Based on the assessment results, key parameters in the governance plan were adjusted, and the implementation details of governance measures in sub-regions were optimized to improve the adaptability and effectiveness of the governance plan.

[0008] In a preferred example, this application can be further configured to include the following steps after generating a dynamically adjusted governance strategy based on agricultural production cycles and climate change: Establish dynamic pollution archives for each sub-region, recording historical pollution data, remediation measures, and environmental change information for each sub-region; Regularly analyze the dynamic pollution archives of sub-regions to identify long-term pollution trends and potential risk points, providing data support for long-term governance planning.

[0009] In a preferred embodiment, this application can be further configured as follows: after the step of integrating multiple governance technologies to form a collaborative governance technology system, the following steps are included: A prediction model for agricultural non-point source pollution is constructed. The model is based on historical monitoring data, meteorological forecast data and agricultural production plans to predict the amount of pollution generated and the extent of its spread in each sub-region over a period of time. Based on the forecast results, the operating parameters of pollution control facilities can be adjusted in advance, and emergency response resources can be deployed to proactively control potential pollution peaks.

[0010] In a preferred embodiment, this application may be further configured to include, after the step of adjusting the operating parameters of the pollution control facilities in advance based on the prediction results, the following step: Obtain actual pollution data and calculate the deviation between the actual pollution data and the predicted data; Based on the deviation value, the parameters and algorithm of the prediction model are optimized to improve the accuracy and reliability of the prediction model and ensure that it can respond more accurately to future pollution changes.

[0011] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions: A dynamic treatment device for agricultural non-point source pollution, the device comprising: a monitoring network setting unit for setting up an intelligent monitoring network within an agricultural watershed; The data preprocessing unit is used to transmit the data collected by the monitoring sensor nodes to the central control center in real time via the wireless communication module. The central control center is used for data storage and preprocessing. The personalized governance solution generation unit is used to analyze preprocessed data based on big data analysis and artificial intelligence algorithms, identify pollution sources, predict pollution diffusion trends, and generate personalized governance solutions based on the analysis results. The governance solutions include guidance on fertilization and pesticide application, selection of sewage treatment processes, and runoff management measures. The dynamic adjustment governance strategy generation unit is used to generate dynamic adjustment governance strategies based on agricultural production cycles and climate change. The dynamic adjustment governance strategies include adjusting the operating parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilizer and pesticide application guidelines. The governance technology integration unit is used to integrate multiple governance technologies to form a collaborative governance technology system.

[0012] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions: An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described dynamic control method for agricultural non-point source pollution.

[0013] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described dynamic treatment method for agricultural non-point source pollution. Attached Figure Description

[0014] Figure 1 This is a flowchart of a dynamic treatment method for agricultural non-point source pollution according to an embodiment of this application; Figure 2 This is a schematic diagram of a dynamic treatment device for agricultural non-point source pollution according to one embodiment of this application; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0015] The present application will be further described in detail below with reference to the accompanying drawings.

[0016] In one embodiment, such as Figure 1 As shown, this application discloses a dynamic treatment method for agricultural non-point source pollution, which specifically includes the following steps: S10: An intelligent monitoring network is set up in the agricultural watershed, the monitoring network including multiple monitoring sensor nodes; The nodes include water quality sensors, weather stations, and soil nutrient sensors, used to monitor in real time data related to non-point source pollution, such as nitrogen and phosphorus content in water bodies, rainfall, and soil fertility. In this embodiment, an intelligent monitoring network is established within the agricultural watershed, encompassing multiple monitoring sensor nodes. For example, in a 100-hectare farmland area, a water quality sensor is deployed every 1 kilometer to monitor the nitrogen and phosphorus content in the water in real time. Weather stations are set up at the center and surrounding areas of the farmland to monitor meteorological data such as rainfall, temperature, humidity, and wind speed. Simultaneously, soil nutrient sensors are installed in different plots to monitor the content of nutrients such as nitrogen, phosphorus, and potassium in the soil. These sensor nodes are powered by solar panels to ensure stable operation in outdoor environments.

[0017] S20: The data collected by the monitoring sensor node is transmitted to the central control center in real time via the wireless communication module. The central control center is used for data storage and preprocessing. Specifically, big data analytics algorithms and artificial intelligence models (such as random forests and neural networks in machine learning) are used to perform in-depth analysis on the preprocessed data. In this embodiment, data collected by monitoring sensor nodes is transmitted in real time to a central control center via a wireless communication module (such as a 4G / 5G network or NB-IoT technology). The central control center is equipped with high-performance servers and data storage devices to clean and preprocess the received data. For example, obviously erroneous data points (such as outliers exceeding the sensor's range) are removed, missing data is interpolated, and data of different formats is uniformly converted into a standard format for subsequent analysis.

[0018] S30: Based on big data analysis and artificial intelligence algorithms, the pre-processed data is analyzed to identify pollution sources, predict pollution spread trends, and generate personalized governance solutions based on the analysis results; Specifically, for example, by analyzing historical and real-time data, the main sources of nitrogen and phosphorus loss in farmland are identified as excessive fertilization and runoff pollution caused by rainfall. Based on the analysis results, personalized remediation plans are generated, such as providing precise fertilization and pesticide application guidance for specific farmland areas, recommending appropriate fertilizer types and application rates to reduce nutrient loss; selecting suitable wastewater treatment processes, such as constructing small-scale wetland treatment systems or using biofilter technology to purify farmland runoff; and formulating runoff management measures, such as rationally planning the layout of farmland drainage systems and setting up buffer zones to intercept pollutants in runoff.

[0019] The aforementioned governance plan includes guidance on fertilization and pesticide application, selection of wastewater treatment processes, and runoff management measures. Furthermore, the governance strategy is dynamically adjusted based on the agricultural production cycle and climate change.

[0020] S40: Generate dynamic governance strategies based on agricultural production cycles and climate change; Specifically, the dynamic adjustment and management strategy includes adjusting the operating parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilization and pesticide application guidelines. For example, during the spring planting season, when rainfall is expected to increase, the operating parameters of farmland drainage systems are adjusted in advance to increase drainage capacity and prevent waterlogging and runoff pollution. During the critical growth period of crops, fertilization and pesticide application guidelines are updated based on crop nutrient requirements and soil nutrient monitoring data to increase the precision of fertilizer application. After the autumn harvest, the operating intensity of runoff collection and purification facilities is reduced, while soil improvement measures are strengthened to prepare for the next planting season.

[0021] S50: Integrating multiple governance technologies to form a collaborative governance technology system, including bioremediation technology, ecological engineering technology, and high-efficiency fertilizer and pesticide formulation technology; Specifically, multiple governance technologies are integrated to form a collaborative governance system. For example, bioremediation technology is combined with planting nitrogen and phosphorus-absorbing plants such as reeds and calamus around farmland to utilize their root systems to absorb and purify nutrients in the water; ecological engineering technology is used to construct ecological ditches and artificial wetlands to intercept and purify farmland runoff; and efficient fertilizer and pesticide formulation technology is adopted, and the use of slow-release fertilizers and biological pesticides is promoted to reduce the amount of fertilizers and pesticides applied and lost, thereby achieving comprehensive governance of agricultural non-point source pollution.

[0022] In summary, by establishing an intelligent monitoring network in agricultural watersheds, key data such as water quality, meteorological conditions, and soil nutrients are collected in real time and transmitted wirelessly to a central control center for preprocessing. Big data analytics and artificial intelligence algorithms are used to deeply mine the data, accurately identifying pollution sources and predicting diffusion trends. Based on this, personalized remediation plans are generated, covering fertilization and pesticide application guidance, wastewater treatment process selection, and runoff management measures. The plan dynamically adjusts remediation measures according to the agricultural production cycle and climate change, such as optimizing farmland drainage system parameters, flexibly configuring runoff collection and purification facilities, and updating fertilization and pesticide application guidance, ensuring the timeliness and accuracy of the remediation strategy. Simultaneously, it integrates multiple technologies such as bioremediation, ecological engineering, and high-efficiency fertilizer and pesticide formulations to form a collaborative remediation technology system, comprehensively improving the remediation effect. Compared with traditional remediation methods, this plan achieves real-time monitoring, precise early warning, dynamic adjustment, and collaborative remediation of agricultural non-point source pollution, effectively reducing the negative environmental impact of agricultural non-point source pollution, improving the ecological and economic benefits of agricultural production, and promoting sustainable agricultural development.

[0023] Before step S10, the following steps are also included: S01: Based on geographic information, land use type and pollution source distribution, the agricultural watershed is divided into multiple monitoring sub-regions, and a unique identifier is assigned to each sub-region; In this embodiment of the application, step S01 specifically includes the following steps: Geographic Information Acquisition: Using Geographic Information System (GIS) technology, collect geographic information data such as topography, landforms, and water system distribution of agricultural watersheds. For example, acquire a high-precision digital map of an agricultural watershed with an area of ​​50 square kilometers, which details the location and extent of geographic elements such as rivers, lakes, farmland, and villages.

[0024] Land use classification: Based on the current land use, the agricultural watershed is divided into different functional zones, such as rice cultivation areas, vegetable cultivation areas, orchards, livestock breeding areas, and residential areas. For example, in the aforementioned 50 square kilometer watershed, a 10 square kilometer rice cultivation area, an 8 square kilometer vegetable cultivation area, a 12 square kilometer orchard area, a 5 square kilometer livestock breeding area, and a 15 square kilometer residential area are designated.

[0025] Pollution source distribution survey: Combining field surveys and historical data, the locations and types of major pollution sources within the watershed were determined, including farmland fertilization and pesticide application sites, livestock and poultry manure discharge points, and rural domestic sewage discharge outlets. For example, several areas with high fertilizer application intensity were found in rice-growing areas, and livestock and poultry manure was found to be randomly piled up and directly discharged without treatment near livestock breeding areas.

[0026] Sub-region division and identification code configuration: Based on comprehensive geographic information, land use types, and pollution source distribution, the entire agricultural watershed is divided into multiple monitoring sub-regions. A unique identification code is generated for each sub-region, containing basic information such as geographical location, main land use type, and main pollution source type. For example, the aforementioned 50 square kilometer watershed is divided into 10 monitoring sub-regions, ZQ1-ZQ10 (ZQ represents a monitoring sub-region). Among them, ZQ1 is located in the northeast of the watershed, mainly a rice-growing area with a few rural domestic sewage discharge outlets nearby; ZQ2 is located in the southeast of the watershed, mainly a vegetable-growing area with many fertilizer application points; and so on. The identification code of each sub-region clearly reflects its location and characteristics in the watershed.

[0027] S02: At least one core monitoring station shall be set up in each sub-region. The core monitoring station shall be equipped with comprehensive monitoring equipment to collect key pollution data of the sub-region as the benchmark data source for pollution monitoring of the sub-region.

[0028] Regarding step S02, the embodiments of this application include: Core monitoring station site selection: Within each monitoring sub-region, a representative location is selected to establish a core monitoring station. Site selection principles include: reflecting the main pollution characteristics of the sub-region, facilitating equipment installation and maintenance, and ensuring good accessibility. For example, in sub-region ZQ1 (rice-growing area), the core monitoring station is located in the center of a typical rice paddy, surrounded by multiple fertilizer application points and close to a main irrigation canal; in sub-region ZQ2 (vegetable-growing area), the core monitoring station is located in the center of a concentrated area of ​​vegetable greenhouses, surrounded by multiple vegetable growers and pesticide application points.

[0029] Monitoring Equipment Configuration: The core monitoring stations will be equipped with comprehensive monitoring equipment to ensure the collection of critical pollution data for this sub-area. Equipment includes, but is not limited to: Water quality sensors: Installed at key water body locations such as irrigation canals and drainage ditches, these sensors monitor water quality indicators in real time, including nitrogen and phosphorus content, chemical oxygen demand (COD), and biochemical oxygen demand (BOD). For example, installing water quality sensors in the irrigation canals of the core monitoring station in the ZQ1 sub-region can acquire real-time data on the concentration of nutrients such as nitrogen and phosphorus in the irrigation water, allowing for timely monitoring of the impact of farmland fertilization on water bodies.

[0030] Weather stations are used to monitor local meteorological conditions, such as rainfall, temperature, humidity, wind speed, and wind direction. A miniature weather station is set up at each core monitoring station, and its data is crucial for analyzing the impact of meteorological factors on agricultural non-point source pollution. For example, at the core monitoring station in the ZQ2 sub-region, the weather station recorded a significant increase in runoff around vegetable greenhouses after a rainstorm, while water quality sensors detected a sharp rise in nitrogen and phosphorus content in drainage ditches, indicating that rainfall is a significant driver of nitrogen and phosphorus loss in this area.

[0031] Soil nutrient sensors: Inserted into farmland soil, these sensors monitor the nutrient content, such as nitrogen, phosphorus, and potassium. Real-time monitoring of soil nutrient changes allows for the assessment of fertilization effectiveness and provides a basis for precision fertilization. For example, at the core monitoring station in the ZQ3 sub-region (orchard), long-term monitoring of nitrogen, phosphorus, and potassium content in the soil revealed elevated phosphorus levels. This suggests that fruit growers may have overused phosphorus-containing fertilizers, thus providing a scientific basis for adjusting fertilization plans.

[0032] Step S30: After analyzing the preprocessed data based on big data analysis and artificial intelligence algorithms to identify pollution sources, predict pollution spread trends, and generate personalized treatment plans based on the analysis results, the following steps are also included: S31: Using the personalized treatment plan, simulate the treatment effect evaluation of the pollution status of each sub-area; For example, in the ZQ1 sub-region (rice-growing area), specialized agricultural non-point source pollution simulation software (such as AGNPS, SWAT, etc.) is used to input the generated personalized remediation plans (including precision fertilization plans, ecological ditch construction plans, etc.) into the simulation software. Simultaneously, in the ZQ2 sub-region (vegetable-growing area), a water quality model (such as WASP, CE-QUAL-ICMLake, etc.) combined with a soil nutrient model is used to simulate the impact of the remediation plans on the water and soil environment.

[0033] Different simulation scenarios are set up in the simulation software, including normal weather conditions, extreme rainfall events, and different fertilizer application rates and times. For example, in the simulation evaluation of sub-region ZQ1, a simulation scenario is set up for the rice growing season after the implementation of precision fertilization and the construction of ecological ditches. The simulation assumes that the rainfall is 1.2 times the region's multi-year average rainfall, simulating the changes in nitrogen and phosphorus content in the water body under these conditions and the effect of ecological ditches on nitrogen and phosphorus interception. In sub-region ZQ2, a simulation scenario is set up for the growing season of vegetable growing areas after the adoption of new fertilization and pesticide application guidelines and wastewater treatment processes, simulating changes in soil nutrient content and pollution load changes in surrounding water bodies.

[0034] Indicators for evaluating the simulated treatment effects were determined, such as the reduction rate of nitrogen and phosphorus content in water bodies, the degree of improvement in soil nutrients, pollutant removal efficiency, and changes in crop yield. For example, in sub-region ZQ1, evaluation indicators included the reduction rate of total nitrogen and total phosphorus content in irrigation drainage, and whether rice yield was affected by the construction of ecological ditches and precision fertilization; in sub-region ZQ2, evaluation indicators included the reduction rate of pollutant concentrations such as chemical oxygen demand (COD) and ammonia nitrogen (NH3-N) in rivers surrounding vegetable growing areas, as well as changes in vegetable quality and yield.

[0035] S32: Based on the assessment results, adjust the key parameters in the governance plan, optimize the implementation details of governance measures in sub-regions, and improve the adaptability and effectiveness of the governance plan; For example, based on the results of the simulated treatment effect evaluation, the advantages and disadvantages of the treatment plan are analyzed. For instance, the simulation results in sub-region ZQ1 show that the precision fertilization plan can effectively reduce the amount of fertilizer applied, but the interception effect of ecological ditches is still not ideal under extreme rainfall events, and the reduction rate of nitrogen and phosphorus content in the water is only 60% of the expected rate. In sub-region ZQ2, the simulation evaluation found that the new wastewater treatment process has a significant effect on the removal of ammonia nitrogen, but the removal rate of COD did not reach the expected target, and the yield of some vegetables decreased slightly.

[0036] Based on the assessment results, key parameters in the treatment plan were adjusted accordingly. In sub-region ZQ1, the density and width of ecological ditches were increased, and the configuration of aquatic plants within the ditches was optimized to improve their interception and absorption capacity for nitrogen and phosphorus. Simultaneously, the precision fertilization plan was further refined, adjusting fertilization time and amount according to the needs of different rice growth stages and real-time weather forecasts. In sub-region ZQ2, wastewater treatment processes were improved, adding COD removal units such as aerated biological filters, and optimizing the types and dosages of microbial agents. Regarding fertilization and pesticide application guidance, the types and dosages of pesticides used were adjusted, selecting pesticides with minimal impact on vegetable yield and quality, and pest and disease monitoring was strengthened to achieve precision pesticide application.

[0037] In addition to adjusting key parameters, the implementation details of the remediation measures in sub-regions were optimized. In sub-region ZQ1, training activities on ecological ditch construction and precision fertilization techniques were conducted in cooperation with local farmers to improve their acceptance and implementation of the remediation measures. Simultaneously, an incentive mechanism was established to provide financial rewards to farmers who actively participated in the remediation efforts and achieved good results. In sub-region ZQ2, the layout of sewage treatment facilities was optimized to be closer to pollution sources, reducing the risk of leakage during sewage transportation. Communication with vegetable growers was strengthened, and fertilization and pesticide application guidelines were adjusted promptly based on their feedback to ensure that the remediation measures met environmental protection requirements while also guaranteeing the normal growth of vegetables and economic benefits.

[0038] Following step S40, step S41 is also included: establishing a sub-regional pollution dynamic archive, recording historical pollution data, treatment measures, and environmental change information for each sub-region; Specifically, in the ZQ1 sub-region (rice-growing area), designated personnel are responsible for collecting and organizing various pollution-related data. Historical water quality monitoring data, including monthly changes in nitrogen and phosphorus content, is obtained from core monitoring stations and sensor nodes; farmers' fertilization records are collected, detailing the type, dosage, and timing of fertilizer application each year; and rainfall and temperature data provided by meteorological stations are compiled and summarized by month. Simultaneously, records of remediation measures implemented in this sub-region are collected, such as the timing, scale, and location of ecological ditch construction, and the promotion of precision fertilization technology. The collected data and records are compiled into tabular form to establish a dynamic pollution archive for the ZQ1 sub-region.

[0039] Step S42: Regularly analyze the pollution dynamic files of sub-regions to identify long-term pollution change trends and potential risk points, and provide data support for long-term governance planning; For example, the pollution dynamics data for sub-region ZQ1 are analyzed quarterly. Statistical analysis methods are used to calculate the average and standard deviation of nitrogen and phosphorus content in the water, and to analyze their trends. Correlation analysis is employed to explore the relationship between rainfall and nitrogen and phosphorus content in the water, as well as the correlation between fertilization time and peak nitrogen and phosphorus content. For instance, the analysis revealed that nitrogen and phosphorus content in sub-region ZQ1 increases significantly during the concentrated rainfall period in June and July each year, and shows a strong correlation with fertilization time (end of May). Comparing the pollution dynamics data for three consecutive years, the analysis shows that the total nitrogen content in the water of sub-region ZQ1 has shown a decreasing trend year by year, indicating that the treatment measures such as precision fertilization and ecological ditch construction have achieved positive results. However, in some areas, due to some farmers' failure to strictly follow the precision fertilization guidelines, there is still a risk of occasional exceedances of nitrogen and phosphorus content. Simultaneously, the analysis found that with the expansion of rice planting area and the increase in total fertilizer application, residual nutrients in the soil tend to accumulate gradually, potentially becoming a future pollution risk.

[0040] For steps S41-S42, the following effects are achieved. After step S50, step S51 is also included: constructing an agricultural non-point source pollution prediction model, which is based on historical monitoring data, meteorological forecast data and agricultural production plans to predict the amount of pollution generated and the diffusion range of each sub-region in the future. In the embodiments of this application, the following example is given: In the ZQ1 sub-region (rice-growing area), water quality monitoring data (including nitrogen and phosphorus content in the water), meteorological data (rainfall, temperature, humidity, etc.), and agricultural production data (fertilization time, fertilizer amount, changes in rice planting area, etc.) from the past three years were collected. Simultaneously, meteorological forecast data for the next month (such as rainfall forecasts from professional meteorological departments) and agricultural production plans (such as the number of farmers expected to fertilize this month and the fertilized area) were obtained.

[0041] Using machine learning algorithms (such as ARIMA time series analysis algorithm and LSTM network in this embodiment), a model for predicting agricultural non-point source pollution is constructed by using collected historical data as the training set. Taking the ZQ1 sub-region as an example, the model input variables include historical water nitrogen and phosphorus content, rainfall, temperature, fertilization time, and fertilization amount, while the output variables are the predicted values ​​of water nitrogen and phosphorus content and the pollution diffusion range (such as the predicted downstream river areas that may be affected by the pollution) for a future period (such as the next week).

[0042] S52: Based on the forecast results, adjust the operating parameters of pollution prevention and control facilities in advance, deploy emergency response resources, and achieve proactive prevention and control of potential pollution peaks; For example, according to the constructed prediction model, the total nitrogen content in the ZQ1 sub-region may reach 3.2 mg / L and the total phosphorus content may reach 0.45 mg / L in the next week. Furthermore, due to an expected rainfall event, the pollution spread may extend to the river area within 2 kilometers downstream.

[0043] Adjustments to pollution control facilities and deployment of emergency resources: Based on forecast results, the operational intensity of ecological ditches in the ZQ1 sub-region will be increased in advance, such as activating backup sewage pumping stations and temporarily storing some sewage in regulating ponds to reduce instantaneous runoff during rainfall. Simultaneously, emergency treatment resources will be deployed at key locations in downstream rivers, such as administering water purification agents and adding temporary biological treatment facilities, to cope with potential pollution peaks.

[0044] S53: Obtain actual pollution data and calculate the deviation between actual pollution data and predicted data; After the predicted period ends (e.g., one week later), the actual nitrogen and phosphorus content data of the water body is obtained through the water quality sensor in the ZQ1 sub-region. At the same time, the actual operating parameters of the ecological ditches and sewage treatment facilities (such as the actual amount of sewage treated and the actual amount of pollutants intercepted) are recorded.

[0045] Deviation calculation: The actual nitrogen and phosphorus content of the water body is compared with the predicted value output by the prediction model to calculate the deviation value.

[0046] S54: Based on the deviation value, optimize the parameters and algorithm of the prediction model to improve the accuracy and reliability of the prediction model and ensure that it can respond more accurately to future pollution changes; For example, the calculated deviation values ​​are analyzed to explore the possible causes of the deviations. For instance, in the ZQ1 sub-region, the deviation in total nitrogen content may be due to some farmers not applying fertilizer as planned, resulting in less actual fertilizer application than predicted; the deviation in total phosphorus content may be due to rainfall intensity being slightly lower than expected, leading to a reduction in phosphorus loss in runoff.

[0047] Model parameter and algorithm optimization: Based on the bias analysis results, adjust the parameters of the prediction model (such as seasonal factors in time series models, weight coefficients in machine learning models, etc.) and the algorithm. For example, in the LSTM model, add feature dimensions related to fertilization behavior and optimize the model's handling mechanism for fertilization time delays; adjust the differencing order in the ARIMA model to better adapt to the randomness of rainfall variations.

[0048] In summary, by constructing a predictive model for agricultural non-point source pollution, we can anticipate the amount and extent of pollution generation and diffusion over a future period, providing a valuable window of opportunity for pollution prevention and control. Adjusting pollution control facilities and deploying emergency resources in advance can effectively address potential pollution peaks and reduce the impact of pollution events on the surrounding environment and residents' lives. For example, in the ZQ1 sub-region, by increasing the operational intensity of ecological ditches and deploying emergency treatment resources in advance, events causing excessive nitrogen and phosphorus levels in water bodies due to rainfall were successfully avoided, ensuring the water quality safety of downstream rivers.

[0049] Regularly acquiring actual pollution data and calculating deviation values ​​provides direct feedback for optimizing the prediction model. Adjusting model parameters and algorithms based on these deviation values ​​enables the prediction model to continuously adapt to the dynamic changes in agricultural production and the uncertainties of environmental conditions, improving the accuracy and reliability of prediction results and providing strong support for more precise pollution control measures.

[0050] Adjusting pollution control facilities and deploying emergency resources in advance can avoid over-operation of these facilities during unnecessary periods, reducing energy consumption and equipment wear and tear, thereby saving operating costs. At the same time, optimizing forecasting models reduces resource waste caused by inaccurate predictions (such as over-dosing of water purification agents), improves resource utilization efficiency, and lowers the overall cost of agricultural non-point source pollution control while achieving effective pollution control.

[0051] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0052] In one embodiment, a dynamic treatment device for agricultural non-point source pollution is provided, which corresponds one-to-one with the dynamic treatment method for agricultural non-point source pollution described in the above embodiments. For example... Figure 2 As shown, the dynamic treatment device for agricultural non-point source pollution includes a monitoring network setting unit, which is used to set up an intelligent monitoring network within the agricultural watershed. The data preprocessing unit is used to transmit the data collected by the monitoring sensor nodes to the central control center in real time via the wireless communication module. The central control center is used for data storage and preprocessing. The personalized governance solution generation unit is used to analyze preprocessed data based on big data analysis and artificial intelligence algorithms, identify pollution sources, predict pollution diffusion trends, and generate personalized governance solutions based on the analysis results. The governance solutions include guidance on fertilization and pesticide application, selection of sewage treatment processes, and runoff management measures. The dynamic adjustment governance strategy generation unit is used to generate dynamic adjustment governance strategies based on agricultural production cycles and climate change. The dynamic adjustment governance strategies include adjusting the operating parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilizer and pesticide application guidelines. The governance technology integration unit is used to integrate multiple governance technologies to form a collaborative governance technology system.

[0053] Specific limitations regarding the dynamic control device for agricultural non-point source pollution can be found in the limitations of the dynamic control method for agricultural non-point source pollution described above, and will not be repeated here. Each module in the aforementioned dynamic control device for agricultural non-point source pollution can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the corresponding operations of each module.

[0054] In one embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, this electronic device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores the database. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a dynamic management method for agricultural non-point source pollution.

[0055] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: S10: Set up an intelligent monitoring network in the agricultural watershed. The monitoring network includes multiple monitoring sensor nodes, including water quality sensors, weather stations and soil nutrient sensors, for real-time monitoring of data related to non-point source pollution, such as nitrogen and phosphorus content in water, rainfall and soil fertility. S20: The data collected by the monitoring sensor node is transmitted to the central control center in real time via the wireless communication module. The central control center is used for data storage and preprocessing. S30: Based on big data analysis and artificial intelligence algorithms, the preprocessed data is analyzed to identify pollution sources, predict pollution spread trends, and generate personalized treatment plans based on the analysis results. The treatment plans include guidance on fertilization and pesticide application, selection of wastewater treatment processes, and runoff management measures. S40: Generate dynamic adjustment and management strategies based on agricultural production cycles and climate change. The dynamic adjustment and management strategies include adjusting the operating parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilization and pesticide application guidelines. S50: Integrate multiple governance technologies to form a collaborative governance technology system, including bioremediation technology, ecological engineering technology, and high-efficiency fertilizer and pesticide formulation technology.

[0056] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: S10: Set up an intelligent monitoring network in the agricultural watershed. The monitoring network includes multiple monitoring sensor nodes, including water quality sensors, weather stations and soil nutrient sensors, for real-time monitoring of data related to non-point source pollution, such as nitrogen and phosphorus content in water, rainfall and soil fertility. S20: The data collected by the monitoring sensor node is transmitted to the central control center in real time via the wireless communication module. The central control center is used for data storage and preprocessing. S30: Based on big data analysis and artificial intelligence algorithms, the preprocessed data is analyzed to identify pollution sources, predict pollution spread trends, and generate personalized treatment plans based on the analysis results. The treatment plans include guidance on fertilization and pesticide application, selection of wastewater treatment processes, and runoff management measures. S40: Generate dynamic adjustment and management strategies based on agricultural production cycles and climate change. The dynamic adjustment and management strategies include adjusting the operating parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilization and pesticide application guidelines. S50: Integrate multiple governance technologies to form a collaborative governance technology system, including bioremediation technology, ecological engineering technology, and high-efficiency fertilizer and pesticide formulation technology.

[0057] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0058] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0059] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A dynamic management method of agricultural non-point source pollution, characterized in that, The method comprises the steps of: setting up an intelligent monitoring network in an agricultural watershed, the monitoring network comprising a plurality of monitoring sensor nodes, the nodes comprising water quality sensors, weather stations and soil nutrient sensors for real-time monitoring of data related to non-point source pollution such as water body nitrogen and phosphorus content, rainfall and soil fertility; transmitting the data collected by the monitoring sensor nodes to a central control center in real time through a wireless communication module, the central control center being used for storage and preprocessing of the data; analyzing the preprocessed data based on big data analysis and artificial intelligence algorithms, identifying pollution sources, predicting pollution diffusion trends, and generating personalized management solutions based on the analysis results, the management solutions including fertilization and pesticide guidance, sewage treatment process selection and runoff management measures; generating dynamic adjustment management strategies according to the agricultural production cycle and climate change, the dynamic adjustment management strategies including adjusting the operation parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilization and pesticide guidance; integrating various management technical means to form a synergistic management technical system, the technical means including biological remediation technology, ecological engineering technology, and efficient fertilizer and pesticide formulation technology.

2. The method of claim 1, wherein the method is a dynamic management method of agricultural non-point source pollution. Before the step of setting up an intelligent monitoring network in an agricultural watershed, the following steps are further included: dividing the agricultural watershed into a plurality of monitoring sub-regions according to geographic information, land use types and pollution source distribution, and configuring a unique identification code for each sub-region; setting up at least one core monitoring station in each sub-region, the core monitoring station being equipped with comprehensive monitoring equipment for collecting key pollution data of the sub-region as a benchmark data source for sub-regional pollution monitoring.

3. The dynamic management method of agricultural non-point source pollution according to claim 2, characterized in that, After the step of analyzing the preprocessed data based on big data analysis and artificial intelligence algorithms, identifying pollution sources, predicting pollution diffusion trends, and generating personalized management solutions based on the analysis results, the following steps are further included: using the personalized management solutions to simulate the management effect evaluation of the pollution status of each sub-region; adjusting the key parameters in the management solutions according to the evaluation results, optimizing the implementation details of the management measures in the sub-regions, and improving the adaptability and effectiveness of the management solutions.

4. The dynamic management method of agricultural non-point source pollution according to claim 3, characterized in that, After the step of generating dynamic adjustment management strategies according to the agricultural production cycle and climate change, the following steps are further included: establishing a sub-regional pollution dynamic archive to record historical pollution data, management measures and environmental change information of each sub-region; periodically analyzing the sub-regional pollution dynamic archive to identify long-term pollution trends and potential risk points, and providing data support for long-term management planning.

5. The dynamic management method of agricultural non-point source pollution according to claim 4, characterized in that, After the step of integrating various management technical means to form a synergistic management technical system, the following steps are included: building an agricultural non-point source pollution prediction model based on historical monitoring data, weather forecast data and agricultural production plans to predict the pollution generation amount and diffusion range of each sub-region in the future; according to the prediction results, adjusting the operation parameters of pollution prevention and control facilities in advance, deploying emergency treatment resources, and achieving proactive prevention and control of potential pollution peaks.

6. The dynamic management method of agricultural non-point source pollution according to claim 5, characterized in that, After the step of adjusting the operation parameters of pollution control facilities in advance according to the prediction results, the method further comprises steps of: acquiring actual pollution data and calculating deviation values between the actual pollution data and the predicted data; based on the deviation values, optimizing parameters and algorithms of the prediction model to improve the accuracy and reliability of the prediction model, so as to ensure that the future pollution changes can be more accurately responded to.

7. A dynamic management device for agricultural non-point source pollution, applied to the dynamic management method for agricultural non-point source pollution in any of claims 1-6, characterized in that, The device comprises a monitoring network setting unit for setting an intelligent monitoring network in an agricultural watershed; a data preprocessing unit for transmitting data collected by the monitoring sensor nodes to a central control center in real time through a wireless communication module, the central control center being used for storing and preprocessing the data; a personalized management scheme generation unit for analyzing the preprocessed data based on big data analysis and artificial intelligence algorithms, identifying pollution sources, predicting pollution diffusion trends, and generating personalized management schemes according to the analysis results, the management schemes including fertilization and pesticide guidance, sewage treatment process selection, and runoff management measures; a dynamic adjustment management strategy generation unit for generating dynamic adjustment management strategies according to the agricultural production cycle and climate change, the dynamic adjustment management strategies including adjusting the operation parameters of farmland drainage systems, changing runoff collection and purification facilities, and updating fertilization and pesticide guidance; a management technology means integration unit for integrating various management technology means to form a collaborative management technology system.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the dynamic management method of agricultural non-point source pollution according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to realize the steps of the dynamic management method of agricultural non-point source pollution according to any one of claims 1 to 6.

Images