3343 results about "Irrigation" patented technology

The invention relates to the technical field of agricultural information management, and particularly discloses an agricultural information management system and method based on a big data platform, and the method comprises the steps: firstly deploying a multi-source data collection module at an edge calculation node, and obtaining and standardizing the soil moisture content, meteorological environment and equipment operation data in real time; secondly, constructing a local dynamic irrigation strategy model, and realizing multi-objective optimization through a reinforcement learning algorithm; establishing a federated learning framework at the cloud, dynamically distributing node weights by adopting an attention mechanism, and realizing model aggregation of privacy protection in combination with secure multi-party computing; an optimal irrigation instruction is generated through a multi-source data fusion engine, and a three-level response exception handling mechanism is established; and finally, a closed-loop feedback system containing short-term incremental learning and long-term architecture optimization is formed. The corresponding management system comprises six functional modules, namely a data acquisition module, a local modeling module, a federated learning module, a real-time decision-making module, an abnormal monitoring module and a closed-loop optimization module.

The invention relates to the technical field of data twinning, in particular to a saline-alkali soil water-salt motion simulation method based on big data analysis. The method comprises the following steps: collecting saline-alkali soil multi-source monitoring data; based on the saline-alkali soil multi-source monitoring data, salt soil layer correlation feature analysis and water-salt driving factor coupling feature analysis are carried out, and salt soil layer correlation feature data and water-salt driving factor coupling feature data are obtained; simulation relation model design of saline-alkali soil water-salt movement is carried out through the saline-alkali soil level correlation feature data and the water-salt driving factor coupling feature data, and a saline-alkali soil water-salt movement simulation model is generated; based on the saline-alkali soil water-salt motion simulation model, designing saline-alkali soil farmland irrigation simulation parameters; and carrying out water-salt motion simulation prediction and feedback of the saline-alkali soil farmland irrigation on the saline-alkali soil farmland irrigation simulation parameters. According to the saline-alkali soil water-salt motion simulation analysis method, multi-driving-factor fusion and accurate spatial heterogeneity description are achieved.

This application provides a wind-resistant, stable power generation agricultural-solar hybrid system, including pillars, beams, photovoltaic supports, and photovoltaic panels erected in farmland. The photovoltaic panels are equipped with a buffer mechanism and an overload release device. The buffer mechanism effectively absorbs kinetic energy and reduces the swaying amplitude and speed of the photovoltaic panels through its elasticity, and automatically resets the photovoltaic panels after strong winds. The overload release device protects the photovoltaic panels from damage caused by strong winds. This application overcomes the technical defects of existing static wind-resistant systems, reduces system wind resistance, can withstand super typhoons, provide stable power generation and irrigation, and promote agricultural production.

The invention relates to a crop irrigation demand prediction method based on an intelligent integrated prefabricated pump station, and belongs to the technical field of artificial intelligence. The method comprises the following steps: collecting a crop image in a prefabricated pump station irrigation scene, obtaining auxiliary data, calculating a daily accumulated reference evapotranspiration value, and obtaining a time-synchronized multi-modal data set; labeling and dividing the multi-modal data set; constructing an irrigation demand prediction model, wherein the irrigation demand prediction model comprises a spectral reflectivity enhancement module, a double-flow separation convolution module, a cross gating fusion module, a region sensitive pyramid module and a coupling prediction head module; inputting data in the divided training set into the model, and training the model through weighted total loss to obtain a trained model; inputting a to-be-detected image into the trained model to obtain a soil water content and transpiration prediction result; and performing irrigation decision based on the soil water content and transpiration prediction result. The accuracy of irrigation prediction can be improved.

The invention relates to the technical field of organic fertilizers and planting of watermelons and muskmelons, and provides a special fertilizer for milk irrigated watermelons and muskmelons and a double-stubble planting method for sweetness enhancement of milk irrigated watermelons and muskmelons. The special fertilizer for the milk irrigated watermelons and muskmelons comprises black goat manure, sophora alopecuroide, sesame seed meal, bran, organic fresh milk, brown sugar and zymophyte. The black goat manure is pulverized into powder by a pulverizer, the sophora alopecuroide is pulverizedinto 1 cm to 2 cm, and the ratio of the black goat manure, the sophora alopecuroide, the sesame seed meal, the brans, the organic fresh milk, the brown sugar and the zymophyte is 2700-3200: 80: 50: 150: 5: 1. The double-stubble planting method for sweetness enhancement of the milk irrigated watermelons and muskmelons comprises the following steps: selection of a nursery seedling plate and soil, cleaning and germination accelerating of seeds, soil preparation, transplanting, irrigation, topdressing, shaping and forking of watermelon and muskmelon vines and fruit bearing of the watermelons and the muskmelons. The problems that in an existing watermelon and muskmelon planting process, soil nutrients are damaged due to the fact that chemical fertilizers are used for a long time, and the sweetness of melons is reduced are solved.

The invention discloses a desert region water resource recycling method based on ecological restoration coupling, and the method comprises the steps: building a moisture-vegetation coupled spatial dynamic model through obtaining soil humidity distribution, vegetation coverage and regional microclimate data, and recognizing a suspected water resource retention region; the water resource circulation potential is evaluated in combination with microclimate fluctuation characteristics and earth surface characteristics, and an actual water resource optimal utilization area is screened; according to the water resource circulation potential, the vegetation planting density, variety and irrigation mode are dynamically adjusted, the ecological restoration gain coefficient is calculated, and collaborative optimization of the water resource utilization efficiency and the ecological restoration effect is achieved. Water resource management and ecological restoration are organically coupled, accurate utilization and efficient circulation of water resources are achieved, and the restoration capacity and sustainability of an ecological system in the desert area are remarkably improved.

The invention discloses a gleying rice field intelligent irrigation and drainage regulation and control method based on reinforcement learning. The method comprises the steps that meteorological data, soil data and field surface water level data are collected; calculating crop state information based on the meteorological data and the soil data by using a crop growth model; inputting the meteorological data, the soil data, the field surface water level data and the crop state information into an offline training strategy model, outputting action suggestions, and performing verification and decision making according to preset regulation and control logic in combination with the meteorological data, the soil data, the field surface water level data, an external data source and agronomic rule base data; a control strategy is generated, irrigation, drainage or oxygenation is executed, and irrigation and drainage regulation and control are completed. Compared with the prior art, the method has the advantages that priority regulation and control logic for ORP / pH value real-time feedback is established, a prospective pre-drainage mechanism for rainfall forecast is fused, water layer constraint in the growth period and conditional filtering rules in the fertilization safety period are fused, and a perception-decision-execution closed-loop control system is formed.

The invention discloses a rice field irrigation and drainage decision-making method and system based on human-in-loop reinforcement learning, and the method is realized based on reinforcement learning, and the method comprises the steps: collecting real-time environment parameters of a target rice field in a current decision-making period; constructing an environment state vector based on the real-time environment parameters; constructing an irrigation drainage decision model of a continuous action space based on a soft actor commentator algorithm, wherein the model outputs an action according to the environment state vector; when it is judged that the output action deviates from a reasonable strategy or has a potential risk, a human-in-loop collaborative intervention mechanism in which a human expert participates is introduced, the output action is corrected, and a human-in-loop reward signal is generated through expert intervention; an output action is executed, environment feedback and a multi-target weighted reward signal containing a human-in-loop reward signal are collected, loop iteration is performed based on a closed-loop control system, and the irrigation and drainage decision model is updated; and obtaining irrigation and drainage decision output of the current decision period according to the updated irrigation and drainage decision model.

The invention discloses a method for predicting the irrigation amount of crops in an arid saline-alkali soil area and related equipment. The method comprises the steps that the potential evapotranspiration of a target crop is calculated through a double-source evapotranspiration mechanism model based on key meteorological parameters, obtained through prediction, of a target area, and the leaf area index and the plant height are dynamically updated according to the accumulated temperature process; respectively constructing different stress inhibition functions aiming at the attention salt ions and the pH value in the saline-alkali soil solution, and applying composite inhibition at the stomatal conductance and / or the apparent evapotranspiration resistance site to correct the potential evapotranspiration so as to obtain the ideal crop evapotranspiration corrected by the salinity and the pH value; and based on the corrected ideal crop evapotranspiration, predicting day-by-day irrigation amount and water distribution schedule suggestions in a future preset period. The method can solve the problem that current crop irrigation of saline-alkali soil in an arid inland region depends on experience, influences on different salt types and contents are caused, and quantitative analysis is lacked.

The invention provides a farmland soil multi-parameter real-time monitoring system and method based on the Internet of Things. The system comprises a sensor module, a sensor collaborative scheduling module, a data transmission module, a data processing and storage module, an intelligent decision module, a user interaction module and a power supply module. Soil monitoring data, meteorological satellite information and historical yield records are fused, deep learning, a decision tree and a nutrient balance algorithm are combined, an accurate fertilization and irrigation scheme is generated, maintenance decision optimization is achieved, the water and fertilizer utilization efficiency is improved, and resource waste caused by extensive management is reduced; through dynamic sampling, data cross validation, sensor fault self-diagnosis and multi-source data fusion, the system can make a decision, effectively solves the defects of an existing system in the aspects of monitoring precision, data reliability, equipment endurance and decision refinement, and provides an efficient and reliable monitoring and management scheme for precision agriculture.

The present invention relates to a modular and scalable system for intelligent vertical farming infrastructure, using the latest in water recycling sciences, and artificial-intelligence based automation. This helps to combat the issue of sustainable Agriculture+its minimizing usage of water, energy, and space. It combines a vertical farming structure with multiple levels of cultivation with an irrigation and drainage system to achieve recirculation of water. The water recycling unit consists of rainwater harvesting, wastewater collection and multi-stage treatment subsystems, which can guarantee a continuous supply of high-quality recycled water for irrigation. The invention also combines a network of Internet of Things (IoT)-enabled sensors and AI-based control circuitry to track and manage environmental conditions (e.g. light intensity, humidity, temperature, and nutrient levels).

The invention relates to the technical field of forestry intelligent management and control, and discloses a forestry optimization management and control method and system based on artificial intelligence. The method comprises the following steps: collecting multi-source environment monitoring data such as soil humidity, illumination intensity and vegetation growth indexes in a forestry area, aligning a time sequence through a dynamic time warping algorithm, and separating steady-state and transient components; detecting anomalies through an isolated forest algorithm and generating a thermodynamic diagram, and obtaining a potential disease and pest outbreak area through causal reasoning in combination with historical records; constructing a dynamic growth reference curve, and identifying a disturbance sensitive area by using a generative adversarial network and a convolutional neural network; and integrating and generating a management and control priority partition map, optimizing resource allocation through deep reinforcement learning, outputting a task sequence, and driving equipment to execute irrigation, fertilization or pest control operation. According to the method, multiple artificial intelligence algorithms are fused, accurate control over the whole forestry process is achieved, and the method adapts to the dynamically-changing forestry environment.

An irrigation system includes at least one sensor configured to acquire data regarding a water saturation level of an area of soil, a sprinkler configured to provide water to the area of soil, and a control system. The control system is configured to acquire the data from the at least one sensor and adjust a watering scheme of the sprinkler based on the data to provide a desired water saturation level to the area of soil.

The invention provides a rice irrigation online learning forecasting method and system, the method is realized according to a pre-constructed physical mechanism-neural network hybrid model based on physical mechanism model prediction and neural network error correction fusion, and the method comprises the following steps: S1, obtaining real-time environment data of a current decision period of a target rice field; s2, on the basis of the real-time environment data of the current decision period, forecasting a paddy field water layer depth predicted value of the next decision period through a physical mechanism-neural network hybrid model, and generating an irrigation drainage forecast in combination with a crop irrigation drainage mode; s3, real-time environment data of the target rice field in the next decision period after irrigation drainage forecast is executed are obtained, training samples are constructed and put into an experience playback pool, and the physical mechanism-neural network hybrid model executes online learning based on the experience playback pool; and S4, when the next decision cycle starts, returning to S2 until a preset stop condition is met.

The invention relates to an irrigation decision-making method and system based on a crop model and deep reinforcement learning. The method comprises the following steps: creating a virtual environment for simulating crop growth through a decision support system crop growth model after parameter calibration; then constructing a time sequence state matrix, and encoding the time sequence state matrix into a context vector concentrated with historical dynamic information; outputting irrigation actions of each decision-making day through a strategy network of a deep reinforcement learning agent based on a soft strategy-value algorithm; therefore, a decision support system crop model and a deep reinforcement learning technology are deeply fused, an intelligent irrigation decision system with biological rationality is constructed, and the problems of insufficient training data and environment distortion of an existing deep reinforcement learning model in agricultural application are solved.

The invention discloses a cotton water and fertilizer management method and system based on ground penetrating radar and unmanned aerial vehicle multispectral fusion integration, a terminal and a storage medium, and the method comprises the steps: obtaining the soil actual measurement water content, cotton leaf actual measurement nitrogen content, soil electromagnetic signals and cotton leaf spectral information of a target cotton field sample, and carrying out the preprocessing; obtaining soil water content inversion characteristics and cotton leaf nitrogen spectral characteristics; performing model training according to the actually measured soil water content and the soil water content inversion characteristics to obtain a target soil water content prediction model; performing model training according to the actually measured nitrogen content of the cotton leaves and the nitrogen spectral characteristics of the cotton leaves to obtain a target nitrogen prediction model; outputting the predicted soil water content and the predicted cotton leaf nitrogen content, and determining the irrigation amount and the nitrogen fertilization amount; and irrigating and fertilizing the target cotton field. According to the invention, the prediction efficiency and accuracy of the soil water content and the cotton leaf nitrogen content in the cotton field can be effectively improved, and precise irrigation and fertilization of the cotton field are realized.

The invention discloses a crop irrigation optimization method and device based on digital twinning and three-dimensional reconstruction. The method comprises the following steps: collecting crop growth data and video data of environmental parameters in real time through a multi-mode sensing network; performing frame extraction on the video data to obtain a multi-view image sequence, and generating a crop three-dimensional point cloud model based on a multi-angle reconstruction algorithm; semantic segmentation is carried out on the three-dimensional point cloud of the crop, phenotypic features of the crop are extracted, and environmental data are fused to construct a crop growth digital twinborn body; establishing a soil humidity prediction model, inputting time sequence environment data and crop phenotypic characteristic data, and outputting a soil humidity prediction value in future time; finally, irrigation strategy simulation is executed in the digital twin platform, the optimal irrigation amount is determined through a minimization cost function, an optimal irrigation instruction is issued to a physical irrigation actuator, and closed-loop control is achieved. Through three innovations of three-dimensional phenotype extraction, environment coupling modeling and dynamic strategy simulation, the problems of response lag and extensive decision of a traditional method are solved.

The invention relates to the technical field of greenhouse vegetable planting environment regulation and control, in particular to an internet-based intelligent greenhouse vegetable environment regulation and control system and method, which comprises an acquisition module, a monitoring module, an analysis module, a decision module, an execution control module and a mobile terminal interaction module, in combination with a preset successive cropping obstacle threshold model, analyzing to obtain the soil secondary salinization degree, the nutritional imbalance state, the microflora disorder index and the allelochemical toxicity grade; and the decision module is used for generating a comprehensive regulation and control strategy including crop rotation suggestions, irrigation amount, a fertilization scheme, biological control measures and environmental parameter regulation instructions in combination with facility vegetable types and growth stage requirements. A continuous cropping obstacle analysis result is obtained through the analysis module in combination with big data and a machine learning algorithm, a comprehensive regulation and control strategy is generated, continuous cropping obstacles are effectively dealt with, and the planting efficiency and the vegetable quality are improved.

The invention relates to the technical field of agricultural data analysis, in particular to a land reclamation suitability evaluation and cultivated land quality improvement method based on big data, which comprises the following steps of: acquiring and superposing land utilization, soil and elevation data to construct a multi-source land attribute evaluation data set, calculating the distance from a pattern spot to a water source, reconstructing a weight through Gaussian attenuation, and calculating the land utilization, soil and elevation data; the method comprises the following steps: forming a spatial distance weighted feature matrix, extracting a gradient and an irrigation guarantee rate, performing weight reduction on an overrun part of a conflict threshold value, performing linear weighting calculation on a comprehensive score after normalization, dividing a regulation priority area, matching quality improvement measures, and forming a cultivated land quality improvement project layout map. A pattern spot level evaluation basis is formed through multi-source attribute space superposition, water source distance attenuation calculation is introduced to enable weight to change along with reachability, irrigation difference response is enhanced, conflict constraint correction is carried out on gradient and irrigation guarantee, adverse combination influence is inhibited, stable sorting is formed through uniform scale weighting, and the method is applied to the field of irrigation. And improvement priority area identification and quality improvement measure directional configuration are supported.

The invention discloses a regulation and control method for preventing nitrogen and phosphorus loss of saline-alkali farmland drainage, and particularly relates to the technical field of agricultural environment protection and water and fertilizer management. Establishing a three-dimensional drainage path initial model, and calculating a drainage easy flow intensity coefficient according to the gradient and sodium saturation joint index of each micro-unit; further monitoring the change rate of nitrogen and phosphorus concentration in different areas through experimental nitrogen and phosphorus tracking irrigation to obtain a nitrogen and phosphorus migration sensitivity parameter; and performing weighted combination on the drainage easy flow intensity coefficient and the nitrogen and phosphorus migration sensitivity parameter, constructing a nitrogen and phosphorus loss risk index, forming a saline-alkali farmland nitrogen and phosphorus loss risk hot area distribution map, taking an area with the identified risk index exceeding a preset threshold value as a target area needing regulation and control, and implementing differential regulation and control measures in the target area to obtain a saline-alkali farmland nitrogen and phosphorus loss risk hot area distribution map. The method can realize accurate identification and dynamic regulation and control of the nitrogen and phosphorus loss of the saline-alkali farmland, improves the utilization efficiency of the fertilizer, reduces the risk of agricultural non-point source pollution, and has relatively strong popularization significance.

The invention relates to the technical field of agricultural cultivation management, in particular to a precise honeysuckle fertilization method based on soil nutrient monitoring, which comprises the following steps: S1, measuring soil nutrient parameters of a honeysuckle planting field; s2, the nitrogen supply level, the phosphorus supply level and the potassium supply level of the soil are judged; s3, determining the dilution ratio of the humic acid macroelement water-soluble fertilizer; s4, diluting the humic acid macroelement water-soluble fertilizer into a solution according to the dilution ratio; s5, applying the solution diluted in the step S4 in a root irrigation mode; s6, measuring the growth and quality indexes of the honeysuckle after fertilization to verify the fertilization effect. According to the method, on-demand application of the humic acid water-soluble fertilizer and traceable quantitative management of the fertilization effect are realized through closed-loop verification of the fertilization decision and the growth quality index based on the soil nutrient supply level.

The invention relates to the technical field of soil drainage and salt improvement, in particular to a coastal saline-alkali soil drainage and salt improvement intelligent regulation and control method and system based on artificial intelligence, and the method specifically comprises the following steps: dividing treatment units, arranging sensing equipment, and collecting multi-source heterogeneous data to form a data set; after data cleaning and time-space synchronization are conducted, standardized feature vectors are obtained through sectional physical perception standardization processing; constructing a graph neural network micro-area irrigation volume demand prediction model, and predicting recommended irrigation volume and soil salinity variation; calculating a loss function of the model and performing iterative training on the model; and performing periodic decision regulation and control circulation on the trained model, converting the output of the multi-source heterogeneous data collected at each decision moment through the model into an instruction, issuing the instruction, and synchronously performing drainage regulation and control. According to the invention, water-salt environment optimization regulation and control can be realized, and an intelligent treatment closed loop is formed.

The invention relates to the technical field of agricultural engineering, in particular to a water and fertilizer regulation and control method and system for saline-alkali soil grain-fed crops, and the method comprises the following steps: S1, synchronously obtaining soil salinity concentration, soil moisture content and available nitrogen concentration; s2, calculating a salinity stress index, and dividing stress levels; s3, if the soil moisture content is lower than the preset crop suitable lower limit, the irrigation compensation amount is increased; if the soil moisture content is normal, the pulse irrigation mode is adjusted according to the stress level; s4, the nitrogen fertilizer notch amount is calculated according to comparison between the available nitrogen concentration in the S1 and the nitrogen demand threshold value in the crop growth stage; and S5, dynamically adjusting the fertilizer injection concentration and the irrigation duration in the water and fertilizer integrated application. By monitoring soil parameters in real time and dynamically adjusting water and fertilizer supply, accurate regulation and control of water and fertilizer of saline-alkali soil crops are achieved, the utilization efficiency of the fertilizer is improved, the growth environment of the crops is optimized, and resource waste and environmental pollution are reduced.

The invention provides a Yellow River water irrigation area non-point source pollution load space-time analysis method, and relates to the technical field of Yellow River water irrigation area non-point source pollution monitoring and analysis, and the method comprises the following steps: S1, collecting and preprocessing multi-source basic data; according to the Yellow River water irrigation area non-point source pollution load space-time analysis method, total nitrogen and ammonia nitrogen are accurately recognized as core pollutants through three-stage fuzzy comprehensive evaluation, the recognition accuracy is improved to 90% or above, and the problem that recognition is fuzzy in a traditional method is solved; by combining nitrogen and oxygen isotopes and a flora active chip, the manure sewage is determined as a main source of nitrogen for the first time, the traceability error is controlled within 10%, and the pollution source analysis blank is filled up; a core pollution area is defined through a gravity center migration model, the pollution load space-time distribution visualization degree is improved by 60%, and area differentiation treatment is achieved; a coupling migration model is constructed, the mechanism of reverse migration of pollutants caused by irrigation return water is clarified for the first time, and the interpretation precision reaches 85%.

The method may comprise receiving historical data (e.g., mineralogy data, irrigation data, raffinate data, heat data, lift height data, geographic data on ore placement and / or blower data); training a predictive model using the historical data to create a trained predictive model; adding future assumption data to the trained predictive model; running the forecast engine for a plurality of parameters to obtain forecast data for a mining production target; comparing the forecast data for the mining production target to the actual data for the mining production target; determining deviations between the forecast data and the actual data, based on the comparing; and changing each of the plurality of parameters from the forecast data to the actual data to determine a contribution to the deviations for each of the plurality of parameters.

The invention discloses a crop irrigation strategy real-time optimization method considering weather forecast. The method comprises the following steps: S1, acquiring historical meteorological data; s2, a localized AquaCrop crop growth model is constructed; s3, coupling the AquaCrop crop growth model and the NSGA-III multi-objective optimization algorithm model to obtain a coupling model, and solving to obtain a fixed irrigation strategy; s4, formulating optimization time periods, and dynamically integrating new all-season meteorological data in each optimization time period by adopting a DTW (Dynamic Time Warning) algorithm; and S5, correspondingly taking the fixed irrigation strategy obtained in the S3 as an irrigation strategy of the first optimization time period of the growing season according to time, taking various data of the optimization time period as input of the coupling model again to obtain a new irrigation strategy, applying the new irrigation strategy to the next optimization time period, and continuously optimizing. According to the method, the irrigation scheme can be adjusted in time in the growing season, and the method has important significance on guaranteeing grain safety and promoting rainfall flood resource utilization.

The invention relates to the technical field of agricultural intelligent prediction, and discloses a fertilization decision-making system fusing soil and rice growth vigor information data acquisition and analysis, which is characterized in that a microcontroller controls an irrigation valve to apply an irrigation pulse with a preset duration, and a soil humidity sensor is used to monitor a time interval when moisture falls back from a peak value to a baseline; according to the method, irrigation behaviors are reconstructed into an active diagnostic tool, traditional chemical index detection is replaced by physical process dynamic monitoring, lag adjustment is converted into a pre-prediction mode, meanwhile, acoustic verification and a differential correction mechanism are combined, and the crop transpiration rate is predicted. And an anti-environmental interference accurate decision-making system is constructed on the basis of low-cost hardware.

The method may comprise receiving historical data (e.g., mineralogy data, irrigation data, raffinate data, heat data, lift height data, geographic data on ore placement and / or blower data); training a predictive model using the historical data to create a trained predictive model; adding future assumption data to the trained predictive model; running the forecast engine for a plurality of parameters to obtain forecast data for a mining production target; comparing the forecast data for the mining production target to the actual data for the mining production target; determining deviations between the forecast data and the actual data, based on the comparing; and changing each of the plurality of parameters from the forecast data to the actual data to determine a contribution to the deviations for each of the plurality of parameters.

The invention discloses a saline-alkali soil multi-water-source accurate salt control irrigation and drainage integrated system and equipment, and relates to the technical field of saline-alkali soil irrigation and drainage, and the system comprises a multi-water-source intelligent evaluation and dynamic allocation module, an accurate salt control-irrigation and drainage cooperative regulation and control module and an integrated anti-blocking salt discharge and tail water reuse module; by monitoring water source salinity, soil data and a crop salt demand model in real time, dynamically calculating an optimal water source combination, for example, low-salt rainwater is preferentially used for sensitive crops, and a valve is automatically regulated and controlled to switch water sources, the scheme has the advantages that high-salt brackish water is prevented from aggravating salinization, the water resource utilization rate is increased by 30% or above, and blindness of traditional artificial experience allocation is solved; meanwhile, decision making is driven through multi-module data linkage, for example, the irrigation and drainage proportion is regulated and controlled through water source data, and the control unit responds to salinity exceeding within 10 seconds; the scheme has the advantages that manual intervention is reduced by 90%, the engineering advantages of anti-corrosion flow guide design, water flow driving energy conservation, modularization, easy maintenance and the like are implied, and the method is suitable for various saline-alkali land terrains.

The invention relates to the technical field of intelligent irrigation, in particular to an intelligent watering control method and system for agricultural production, and the method comprises the steps: data collection, global data reconstruction, soil moisture content prediction, watering strategy optimization, sensor layout optimization, control execution and model updating. In the prior art, a pure mathematical method is generally adopted to calculate global humidity from sparse point data, and multi-dimensional environment information cannot be effectively fused, so that the reconstruction precision is limited and the physical credibility is insufficient; a physical information enhanced confrontation generation network is adopted to carry out global perception, sparse measurement values, geographic coordinates and real-time environment data are fused into conditional tensors to be input into a generator, and training is guided by forcing sensor data consistency in a loss function and introducing moisture diffusion physical constraints; the method can generate a high-resolution and physically reasonable global soil humidity distribution diagram, and significantly improves the reconstruction precision and reliability from sparse points to planar information in a complex farmland environment.