Corn cultivation environment monitoring system based on sensor

Abstract

The invention relates to the technical field of agricultural management, in particular to a corn cultivation environment monitoring system based on a sensor, which comprises a data acquisition module, a data processing module, a corn growth model module, an environment dynamic monitoring and early warning module, a decision support module and a visualization module, and a geographic information system and a dynamic monitoring model are combined to capture the dynamic change trend of the cultivation area environment factors. A corn growth model of a deep neural network and a long-short-term memory network is adopted to predict the growth state and resource requirements of corn, a decision support module intelligently generates cultivation management suggestions based on a model prediction result, and a visualization module displays environment data, prediction results and management suggestions through a multi-dimensional graph and an interactive interface. According to the method, the accuracy of corn cultivation management and the resource utilization efficiency are improved, and technical support is provided for intelligent agricultural development.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural management, and in particular to a sensor-based corn cultivation environment monitoring system. Background Art

[0002] Corn is one of the food crops. During the cultivation process of corn, environmental conditions (such as soil moisture, light intensity, temperature, etc.) have a significant impact on its growth rate and health status. Scientific and reasonable monitoring and management of these environmental factors can improve the yield and quality of corn.

[0003] Although the existing corn cultivation and management technology can collect some environmental data, it generally has the following technical problems: First, the collection of environmental data is mostly single-dimensional, lacking comprehensive monitoring of multi-dimensional environmental factors, and it is difficult to fully reflect the dynamic changes in the cultivation area. Secondly, the existing technology mostly uses simple rule algorithms in data processing and analysis, and has insufficient ability to model the complex dynamic relationships of environmental factors, and cannot accurately predict the growth status and resource requirements of corn. In addition, the generated cultivation management recommendations usually rely on manual experience and lack intelligent optimization methods, resulting in low utilization efficiency of water resources and fertilizers. Summary of the invention

[0004] The invention provides a sensor-based corn cultivation environment monitoring system.

[0005] The sensor-based corn cultivation environment monitoring system includes a data acquisition module, a data processing module, a corn growth model module, an environmental dynamic monitoring and early warning module, a decision support module and a visualization module, wherein; The data acquisition module collects environmental data related to corn cultivation in real time through a distributed multi-point sensor network, and the environmental data includes soil data, meteorological data and light intensity; The soil data include soil temperature and humidity, soil salinity, electrical conductivity and water content; The meteorological data include temperature, humidity, wind speed and precipitation; The data processing module is used to clean, denoise, standardize and extract features from the collected environmental data; The corn growth model module constructs a corn growth model based on the extracted features to predict the growth status and potential problems of corn under current environmental conditions; The environmental dynamic monitoring and early warning module combines the geographic information system to dynamically monitor the environmental change trend of the cultivation area, and issues an environmental abnormality early warning based on the threshold judgment rule; The decision support module generates cultivation management suggestions, including irrigation schemes and fertilization strategies, based on the prediction results of the corn growth model and environmental data; The visualization module displays the collected environmental data, the predicted growth status and potential problems of corn under current environmental conditions, and cultivation management suggestions through a visualization interface.

[0006] Optionally, the data acquisition module specifically includes: Sensor network deployment: Multi-point sensor nodes are evenly arranged in the corn cultivation area. The spacing between sensor nodes is determined according to the size of the plot and the complexity of the terrain to ensure that the spatial coverage rate of data collection meets more than 95%; Soil data collection: Each sensor node is equipped with a variety of sensors to collect soil temperature, soil moisture, soil salinity, conductivity and moisture content in real time; Meteorological data collection: Meteorological data were obtained from weather stations in the corn cultivation area, including temperature, humidity, wind speed, and precipitation; Light intensity collection: Light intensity is collected through light sensors, which are deployed in the center of the cultivation area to avoid being blocked by buildings and plants.

[0007] Optionally, the data processing module includes: Data cleaning: Clean the collected environmental data through missing value filling and duplicate data elimination technology; Data denoising: Wavelet transform method is used to remove high-frequency noise in the collected environmental data; Data standardization: Normalize the denoised environmental data to eliminate the dimensional differences between data of different dimensions; Feature extraction: Environmental features are extracted from the standardized environmental data through principal component analysis. The environmental features include light features, climate features, and soil features.

[0008] Optionally, the corn growth model includes a deep neural network sub-model and a long short-term memory network sub-model, specifically including: Deep neural network sub-model: A deep neural network sub-model is constructed through a deep neural network algorithm to extract high-order nonlinear relationships between environmental features; Long Short-Term Memory Network Sub-Model: A long short-term memory network sub-model is constructed using the long short-term memory network algorithm to capture the dynamic dependencies of environmental features over time; Model joint training: The deep neural network sub-model and the long short-term memory network sub-model are jointly trained and optimized through a unified loss function.

[0009] Optionally, the corn growth model module constructs a corn growth model based on the extracted features to predict the growth status and potential problems of corn under current environmental conditions, specifically including: Real-time data input: The environmental feature data collected in real time and extracted by the data processing module is used as input; Growth status prediction: Based on the output of the corn growth model, predict the growth status of corn under current environmental conditions.

[0010] Optionally, the environmental dynamic monitoring and early warning module uses the geographic information system and environmental characteristic data to construct a dynamic monitoring model for the cultivation area, specifically including: Geographic Information System Construction: Geographic Information System is used to organize and manage the spatial environmental data of the cultivation area and provide spatial support for dynamic monitoring models; Dynamic monitoring model design: The dynamic monitoring model captures the dynamic change trend and spatial distribution characteristics of environmental characteristics through multiple regression and time series algorithms; Visualization of spatial changes: The output of the dynamic monitoring model is displayed in the form of heat maps through a geographic information system.

[0011] Optionally, the environment dynamic monitoring and early warning module issues an abnormal warning based on a threshold judgment rule and a graded early warning mechanism, specifically including: Threshold judgment rule design: Threshold judgment rules can automatically detect abnormal situations by defining the normal range of environmental factors; Grading warning mechanism: Grading warning mechanism ensures that users can respond quickly to environmental abnormalities through abnormal area marking and information push.

[0012] Optionally, the decision support module includes: Decision support generation: The decision support module provides cultivation management suggestions for the cultivation area by analyzing the output results of the corn growth model and environmental characteristic data; Decision suggestion adjustment: The decision support module optimizes and adjusts the generated cultivation suggestions by integrating historical corn growth data and dynamic environmental changes; Decision suggestion output: Decision suggestions are output to users in a variety of ways.

[0013] Optionally, the visualization module includes: Visualization display content: The visualization module displays environmental data, predicted corn growth status and potential problems under current environmental conditions, and cultivation management suggestions in the form of multi-dimensional graphics, charts, and interactive maps; Visualization interaction function: The visualization module provides interactive operation functions, supporting users to query and operate data and suggestions.

[0014] Beneficial effects of the present invention: The present invention realizes the comprehensive collection and dynamic monitoring of the environmental data of the cultivation area through the combination of distributed multi-point sensor network and geographic information system (GIS). The dynamic monitoring model based on time series analysis and spatial distribution modeling can accurately capture the dynamic change trend of soil characteristics (such as humidity, conductivity, etc.), meteorological characteristics (such as temperature, precipitation, etc.) and light intensity, and adopts threshold judgment rules to detect environmental anomalies in real time and generate graded early warning signals, realizing the real-time and refined management of environmental data in the cultivation area, quickly responding to environmental changes, ensuring the stability of corn growth conditions, and significantly reducing the risk of yield loss caused by environmental stress.

[0015] The present invention uses a corn growth model based on a deep neural network and a long short-term memory network to accurately predict the growth status of corn, covering key indicators such as growth rate and health status. The decision support module intelligently generates cultivation management suggestions such as irrigation plans and fertilization strategies based on model prediction results and real-time environmental data, and dynamically adjusts the suggestions to adapt to changes in environmental conditions, thereby improving the utilization efficiency of water resources and fertilizers, reducing unnecessary investment, optimizing cultivation management measures, and ensuring the efficient growth and health of corn through scientific management suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention; Figure 2 The figure is a schematic diagram of the flow chart of the corn growth model module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0019] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0020] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0021] like Figure 1-Figure 2 As shown, the sensor-based corn cultivation environment monitoring system includes a data acquisition module, a data processing module, a corn growth model module, an environmental dynamic monitoring and early warning module, a decision support module and a visualization module, wherein; The data acquisition module collects environmental data related to corn cultivation in real time through a distributed multi-point sensor network. The environmental data includes soil data, meteorological data, and light intensity. Soil data include soil temperature and humidity, soil salinity, electrical conductivity, and water content; Meteorological data include temperature, humidity, wind speed, and precipitation; The data processing module is used to clean, denoise, standardize and extract features from the collected environmental data; The corn growth model module constructs a corn growth model based on the extracted features to predict the growth status and potential problems of corn under the current environmental conditions; The environmental dynamic monitoring and early warning module combines the geographic information system to dynamically monitor the environmental change trend of the cultivation area, and issues environmental abnormality warnings based on threshold judgment rules; The decision support module generates cultivation management recommendations, including irrigation plans and fertilization strategies, based on the prediction results of the corn growth model and environmental data; The visualization module displays the collected environmental data, predicted growth status and potential problems of corn under current environmental conditions, and cultivation management recommendations through a visualization interface.

[0022] The data acquisition module specifically includes: Sensor network deployment: Multi-point sensor nodes are evenly arranged in the corn cultivation area. The spacing between sensor nodes is determined according to the size of the plot and the complexity of the terrain to ensure that the spatial coverage rate of data collection meets more than 95%; Soil data collection: Each sensor node is equipped with a variety of sensors to collect soil temperature, soil moisture, soil salinity, conductivity and moisture content in real time, including; Soil temperature is measured by a thermistor sensor, soil moisture is measured by a soil capacitive moisture sensor, soil salinity is measured by a soil salinity sensor, conductivity is measured by a soil conductivity sensor, and moisture content is measured by a soil tensiometer; Meteorological data collection: Meteorological data were obtained from weather stations in the corn cultivation area, including temperature, humidity, wind speed, and precipitation; Light intensity collection: Light intensity is collected through light sensors, which are deployed in the center of the cultivation area to avoid being blocked by buildings and plants.

[0023] The data processing module includes: Data cleaning: The collected environmental data is cleaned through missing value filling and duplicate data elimination technology, including: Missing value filling: Use interpolation to fill in missing data. The interpolation formula is: ; in, For the filled data, and are adjacent valid data points respectively; Duplicate data elimination: For duplicate records with the same timestamp in the collected data, only the first valid data is retained; Data denoising: Wavelet transform method is used to remove high-frequency noise in the collected environmental data, including: Wavelet decomposition: decompose the collected environmental data signal into multiple frequency sub-bands; Threshold processing: Perform threshold processing on the noise signal of the high-frequency sub-band to filter out irregular interference; Signal reconstruction: Reconstruct the denoised data using the low-frequency signal and the processed high-frequency signal; Data standardization: Normalize the denoised environmental data to eliminate the dimensional differences between data of different dimensions. The standardization formula is expressed as: ; in, is the standardized data, is the original data, , is the minimum and maximum value of the data dimension; Feature extraction: Environmental features are extracted from the standardized environmental data through principal component analysis. Environmental features include light features, climate features, and soil features. The specific steps are as follows: Data covariance matrix calculation: ; in, is the covariance matrix, For the data samples, is the mean vector, is the number of data samples; Eigenvalue and eigenvector calculation: covariance matrix Perform eigendecomposition to obtain eigenvalues ​​and eigenvectors; Select the principal component: Select the first principal components, construct the feature matrix ; Data dimensionality reduction: through feature matrix Extract the key features of the data, the formula is: ; in, is the feature data after dimensionality reduction, To standardize the data, is the principal component matrix.

[0024] The corn growth model includes a deep neural network sub-model and a long short-term memory network sub-model, specifically: Deep neural network sub-model: A deep neural network sub-model is constructed using a deep neural network algorithm to extract high-order nonlinear relationships between environmental features, including: Input layer: receives environmental feature data extracted from the data processing module. The data dimension is ,in, The characteristic dimension includes soil characteristics, meteorological characteristics and light characteristics; Hidden layer: It consists of multiple layers of fully connected neural network. The output of each layer is: ; in, For the The output of the layer, For the The weight matrix of the layer, For the The bias vector of the layer, is the activation function (such as ReLU), is the index of the hidden layer; Output layer: maps the output of the hidden layer to a low-dimensional vector as a high-order nonlinear representation of environmental features. The output is used as the input of the long short-term memory network sub-model; LSTM sub-model: The LSTM sub-model is constructed by using the LSTM algorithm to capture the dynamic dependencies of environmental features over time, including: (1) Input layer: receives the feature representation output by the deep neural network sub-model and forms a time series input matrix ,in, is the number of time steps, is the feature dimension; (2) Long short-term memory network layer: The long short-term memory network unit is used to process time series data and calculate the hidden state of each time step. and memory cell status , the specific formula is: The input gate is calculated as: ; The forget gate is calculated as: ; The output gate is calculated as: ; The memory cell update calculation is: ; The hidden state update is calculated as: ; in, is the input of the current time step, , are the hidden state and memory unit state of the current time step, is the weight matrix, is the bias term, is the Sigmoid activation function, and tanh is the hyperbolic tangent activation function; (3) Output layer: the final output of the long short-term memory network layer After the fully connected layer, it is mapped to the growth state prediction results, including: Growth rate (such as plant height growth rate, leaf area growth rate); Health status (such as photosynthesis efficiency, leaf color index); Model joint training: The deep neural network sub-model and the long short-term memory network sub-model are jointly trained and optimized through a unified loss function. The loss function is expressed as: ; in, is the loss function value, For the actual growth state, To predict growth status, is the total number of samples; Data division: The historical corn cultivation data were divided into training set, validation set and test set in a ratio of 7:2:1; Historical corn cultivation data include environmental characteristics, management data, and growth status data; Environmental characteristics include soil characteristics, meteorological characteristics, and light characteristics; Management data include irrigation records, fertilization records, and pest and disease control records; Growth status data Growth stage, growth indicators and yield related indicators; The growth stages include sowing period, emergence period, jointing period, tasseling period, grain filling period and maturity period; Growth indicators include plant height and number of leaves; Yield-related indicators include the number of ears per plant and the number of grains per plant.

[0025] The corn growth model module constructs a corn growth model based on the extracted features to predict the growth status and potential problems of corn under the current environmental conditions, including: Real-time data input: The environmental feature data collected in real time and extracted by the data processing module is used as input. The data includes: Soil characteristics: including soil temperature and humidity, soil salinity, electrical conductivity and water content; Meteorological characteristics: including air temperature and humidity, wind speed and precipitation Light characteristics: light intensity; The input data is processed by the deep neural network sub-model and the long short-term memory network sub-model to form a multi-dimensional time series representation ,in, is the number of time steps, is the feature dimension; Growth status prediction: Based on the output of the corn growth model, the growth status of corn under the current environmental conditions is predicted. The growth status includes growth rate and health status: Growth rate: plant height growth rate, leaf area growth rate. The corn growth model combines multi-dimensional environmental characteristics such as soil, weather, and light with historical data to output the growth rate change trend. Health status: The corn growth model calculates photosynthesis efficiency through light intensity, soil moisture, and soil temperature and humidity, and evaluates the overall growth status of corn based on environmental conditions and soil health status.

[0026] The environmental dynamic monitoring and early warning module uses geographic information systems and environmental characteristic data to build a dynamic monitoring model for the cultivation area, including: Geographic Information System Construction: Geographic Information System is used to organize and manage the spatial environmental data of the cultivation area and provide spatial support for the dynamic monitoring model, including: Regional information collection: Obtain the geographical boundaries, plot distribution, soil type and terrain information of the corn cultivation area, and store it in GIS data formats (such as Shapefile, GeoJSON); Associate the collected environmental characteristic data (such as soil characteristics, meteorological characteristics, and light characteristics) with the geographic location coordinates to form a spatial distribution data set; Spatial hierarchical management: The monitoring units of the cultivation area are divided according to the geographical area. Each monitoring unit corresponds to a specific sensor node. The time series data of the dynamic changes of environmental factors are stored for each monitoring unit for subsequent dynamic monitoring. Dynamic monitoring model design: The dynamic monitoring model captures the dynamic change trend and spatial distribution characteristics of environmental characteristics through multiple regression and time series algorithms, including: Input data: Environmental characteristic data obtained from the data acquisition module, including soil characteristics, meteorological characteristics and light characteristics. The input data is associated with the location of the GIS monitoring unit to form a time series input matrix ,in, is the number of time steps, is the feature dimension, Index for monitoring unit; Trend modeling: The sliding window method is used to calculate the dynamic change trend of environmental characteristics, which is expressed as: ; in, is the average trend value of the sliding window, is the time step The environmental characteristic value of is the sliding window size; Multiple regression analysis: Use multiple linear regression to analyze the relationship between different environmental characteristics, expressed as: ; in, For monitoring unit target factors (such as soil moisture change rate), For monitoring unit No. environmental characteristics, is the regression coefficient, is the error term; Visualization of spatial changes: The output results of the dynamic monitoring model are displayed in the form of heat maps through the geographic information system, visualizing the real-time change trend and spatial distribution of environmental factors, providing a basis for anomaly detection The dynamic monitoring model uses time series modeling and multivariate regression analysis, combined with the GIS system, to achieve comprehensive monitoring of the dynamic changes of environmental factors in the cultivation area, capture environmental change trends in real time, and provide support for subsequent early warnings.

[0027] The environmental dynamic monitoring and early warning module issues abnormal warnings based on threshold judgment rules and graded early warning mechanisms, including: Threshold judgment rule design: Threshold judgment rules realize automatic detection of abnormal situations by defining the normal range of environmental factors, including: Threshold definition: Based on agricultural standards and historical environmental data, set threshold ranges for environmental factors, such as: Soil moisture threshold: ; Temperature threshold: ; Light intensity threshold: ; Wind speed threshold: ; Single-factor anomaly detection: Comparing data collected in real time And set the threshold: ; Multi-factor comprehensive detection: If multiple factors in a single monitoring unit exceed the threshold range at the same time, it will be marked as a "high-risk area" and a risk level (such as low, medium, or high) will be generated based on the number and severity of abnormal factors; Grading warning mechanism: Grading warning mechanism ensures that users can quickly respond to environmental abnormalities through abnormal area marking and information push, including: Early warning signal generation: Mark abnormal areas on GIS maps and distinguish risk levels by color (such as green, yellow, and red), generate abnormal reports, and record the type, duration, and spatial distribution of abnormal environmental factors; Warning signal transmission: Warning signals are sent in real time through a visual interface, mobile application or email.

[0028] The decision support modules include: Decision support generation: The decision support module provides cultivation management suggestions for the cultivation area by analyzing the output results of the corn growth model and environmental characteristic data, including: Irrigation plan generation: Calculate irrigation amount based on soil moisture requirements predicted by corn growth model, current soil moisture and weather forecast information (precipitation); Calculate irrigation volume: Calculate single irrigation volume based on irrigation demand , expressed as: ; in, is the crop coefficient, which is determined according to the growth stage of corn. is the potential evapotranspiration, calculated by combining environmental data and meteorological models. is the effective rainfall, estimated through historical rainfall data, like , it is recommended to suspend irrigation if ,generate irrigation time and flow recommendations; Fertilization strategy generation: Based on the nutrient requirements predicted by the corn growth model and the soil nutrient content, the application amount of each fertilizer is calculated, such as the nitrogen nutrient content, which is calculated as: ; in, is the amount of fertilizer applied, The nitrogen requirement predicted by the maize growth model, is the current soil nitrogen content; Recommended fertilization time: Generate a reasonable fertilization schedule based on the corn growth stage and soil fertilizer effectiveness duration; Decision support module optimizes and adjusts the generated cultivation suggestions by integrating historical corn growth data and dynamic environmental changes to ensure the efficiency of management measures, including: Incorporate environmental dynamics: Consider the real-time impact of environmental data (such as current precipitation and future weather forecasts) on irrigation plans. If high precipitation is predicted in the next 48 hours, adjust the irrigation plan to avoid over-irrigation.

[0029] Historical data comparison: Use historical corn growth data to verify the impact of fertilization and irrigation strategies on corn yields, further optimize current recommendations, and compare current forecasts with historical optimal strategies to ensure that the generated recommendations have a scientific basis; Decision suggestion output: Decision suggestions are output to users in a variety of ways to ensure the readability and operability of information, including: Output form: Display the recommendations in the form of charts on the system visualization interface, such as soil moisture change charts and fertilization schedules, and generate downloadable management reports that detail the basis and expected results of irrigation and fertilization recommendations.

[0030] Operation Tips: Provide concise operation steps, such as recommending the operating time of irrigation equipment and the selection of fertilization tools, and provide users with key action suggestions, such as "It is recommended to complete irrigation within 3 hours" or "Apply 25kg / ha of nitrogen fertilizer this weekend."

[0031] The visualization modules include: Visualization content: The visualization module displays environmental data, predicted corn growth status and potential problems under current environmental conditions, and cultivation management suggestions in the form of multi-dimensional graphics, charts, and interactive maps, including: Environmental data visualization: Display trend changes of real-time environmental data, including: Time variation curves of soil characteristics (such as soil moisture, electrical conductivity, etc.); Dynamic trend charts of meteorological characteristics (such as temperature, precipitation, wind speed, etc.); Diagram of daily variation of light intensity; Display the spatial distribution of environmental factors within the cultivation area in the form of heat maps on geographic information maps; Visualization of growth model prediction results: Displays the prediction results of corn growth status, including: Time series diagram of plant height growth rate and leaf area change; Scoring charts for health status (such as photosynthetic efficiency and growth vitality index); Simulate growth trends and display growth change predictions under different environmental conditions.

[0032] Visualization of cultivation management suggestions: The execution plan of irrigation scheme and fertilization strategy is displayed through task charts, including: charts of recommended irrigation amounts and schedules; Fertilization schedule and fertilizer amount bar chart; Visualization interaction function: The visualization module provides interactive operation functions to support users to query and operate data and suggestions, including: Data filtering and query: Users can filter the data they need to view by region, time range or environmental factors; Export function: Users can export visualization content as images or reports for subsequent reference or printing.

[0033] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0034] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A sensor-based corn cultivation environment monitoring system, characterized in that: It includes data acquisition module, data processing module, corn growth model module, environmental dynamic monitoring and early warning module, decision support module and visualization module, among which; The data acquisition module collects environmental data related to corn cultivation in real time through a distributed multi-point sensor network, and the environmental data includes soil data, meteorological data and light intensity; The soil data include soil temperature and humidity, soil salinity, electrical conductivity and water content; The meteorological data include temperature, humidity, wind speed and precipitation; The data processing module is used to clean, denoise, standardize and extract features from the collected environmental data; The corn growth model module constructs a corn growth model based on the extracted features to predict the growth status and potential problems of corn under current environmental conditions; The environmental dynamic monitoring and early warning module combines the geographic information system to dynamically monitor the environmental change trend of the cultivation area, and issues an environmental abnormality early warning based on the threshold judgment rule; The decision support module generates cultivation management suggestions, including irrigation schemes and fertilization strategies, based on the prediction results of the corn growth model and environmental data; The visualization module displays the collected environmental data, the predicted growth status and potential problems of corn under current environmental conditions, and cultivation management suggestions through a visualization interface.

2. The sensor-based corn cultivation environment monitoring system according to claim 1, characterized in that: The data acquisition module specifically includes: Sensor network deployment: Multi-point sensor nodes are evenly arranged in the corn cultivation area, and the spacing between sensor nodes is determined according to the size of the plot and the complexity of the terrain; Soil data collection: Each sensor node is equipped with a variety of sensors to collect soil temperature, soil moisture, soil salinity, conductivity and moisture content in real time; Meteorological data collection: Meteorological data were obtained from weather stations in the corn cultivation area, including temperature, humidity, wind speed, and precipitation; Light intensity collection: Light intensity is collected through light sensors.

3. The sensor-based corn cultivation environment monitoring system according to claim 2, characterized in that: The data processing module comprises: Data cleaning: Clean the collected environmental data through missing value filling and duplicate data elimination technology; Data denoising: Wavelet transform method is used to remove high-frequency noise in the collected environmental data; Data standardization: Normalize the denoised environmental data to eliminate the dimensional differences between data of different dimensions; Feature extraction: Environmental features are extracted from the standardized environmental data through principal component analysis. The environmental features include light features, climate features, and soil features.

4. The sensor-based corn cultivation environment monitoring system according to claim 3 is characterized in that: The corn growth model includes a deep neural network sub-model and a long short-term memory network sub-model, specifically including: Deep neural network sub-model: A deep neural network sub-model is constructed through a deep neural network algorithm to extract high-order nonlinear relationships between environmental features; Long Short-Term Memory Network Sub-Model: A long short-term memory network sub-model is constructed using the long short-term memory network algorithm to capture the dynamic dependencies of environmental features over time; Model joint training: The deep neural network sub-model and the long short-term memory network sub-model are jointly trained and optimized through a unified loss function.

5. The sensor-based corn cultivation environment monitoring system according to claim 4, characterized in that: The corn growth model module constructs a corn growth model based on the extracted features to predict the growth status and potential problems of corn under current environmental conditions, specifically including: Real-time data input: The environmental feature data collected in real time and extracted by the data processing module is used as input; Growth status prediction: Based on the output of the corn growth model, predict the growth status of corn under current environmental conditions.

6. The sensor-based corn cultivation environment monitoring system according to claim 5, characterized in that: The environmental dynamic monitoring and early warning module uses the geographic information system and environmental characteristic data to build a dynamic monitoring model for the cultivation area, specifically including: Geographic Information System Construction: Geographic Information System is used to organize and manage the spatial environmental data of the cultivation area and provide spatial support for dynamic monitoring models; Dynamic monitoring model design: The dynamic monitoring model captures the dynamic change trend and spatial distribution characteristics of environmental characteristics through multiple regression and time series algorithms; Visualization of spatial changes: The output of the dynamic monitoring model is displayed in the form of heat maps through a geographic information system.

7. The sensor-based corn cultivation environment monitoring system according to claim 6, characterized in that: The environmental dynamic monitoring and early warning module issues abnormal early warnings based on threshold judgment rules and hierarchical early warning mechanisms, specifically including: Threshold judgment rule design: Threshold judgment rules can automatically detect abnormal situations by defining the normal range of environmental factors; Grading warning mechanism: Grading warning mechanism ensures that users respond to environmental abnormalities by marking abnormal areas and pushing information.

8. The sensor-based corn cultivation environment monitoring system according to claim 7, characterized in that: The decision support module includes: Decision support generation: The decision support module provides cultivation management suggestions for the cultivation area by analyzing the output results of the corn growth model and environmental characteristic data; Decision suggestion adjustment: The decision support module optimizes and adjusts the generated cultivation suggestions by integrating historical corn growth data and dynamic environmental changes; Decision suggestion output: Decision suggestions are output to users in a variety of ways.

9. The sensor-based corn cultivation environment monitoring system according to claim 8, characterized in that: The visualization module comprises: Visualization display content: The visualization module displays environmental data, predicted corn growth status and potential problems under current environmental conditions, and cultivation management suggestions in the form of multi-dimensional graphics, charts, and interactive maps; Visualization interaction function: The visualization module provides interactive operation functions, supporting users to query and operate data and suggestions.

Images