Agricultural environment intelligent monitoring and automatic management system based on Internet of Things and weather data linkage

Abstract

According to the agricultural environment intelligent monitoring and automatic management system based on linkage of the Internet of Things and weather data, a real-time environment monitoring module is composed of various sensors and multispectral cameras which are distributed in an agricultural production area, the real-time environment monitoring module is connected with a gateway through the Internet of Things, environment data are collected and transmitted to the gateway, and then the environment data are sent to a cloud platform; the multi-source weather data interface is in butt joint with multiple data sources, automatically acquires future weather data according to a preset interval, processes the future weather data and transmits the future weather data to the cloud platform; the cloud prediction model is deployed at the cloud and comprises a storage unit, an analysis unit and a prediction unit, the storage unit stores environment and weather data, the analysis unit performs mining association, and the prediction unit constructs a model by using a machine learning algorithm according to the environment and the weather data and predicts an environment change trend and adverse factors; the automatic execution device communicates with the cloud through the Internet of Things, and when the cloud predicts adverse environment change, the cloud sends an instruction to the device, and the device automatically executes operation.

Description

Technical Field

[0001] This invention relates to the field of agricultural environmental technology, and in particular to an intelligent monitoring and automated management system for agricultural environment based on the Internet of Things and weather data linkage. Background Technology

[0002] Traditional agricultural production relies heavily on farmers' personal experience and intuition to judge the impact of weather changes on crop growth. This approach makes it difficult to accurately quantify the specific correlation between meteorological data and crop growth. Due to the lack of scientific quantitative methods, farmers often cannot accurately predict and respond to the potential risks that weather changes pose to crop growth. While existing automated agricultural management systems can respond to and manage real-time environmental data changes, such as temperature and humidity, to some extent, they generally suffer from a significant deficiency: a lack of proactive decision-making capabilities based on weather forecast information. This limitation prevents the system from making effective adjustments and countermeasures in advance to minimize the impact of adverse weather on crop growth.

[0003] In existing agricultural technology systems, the abundant data collected by weather stations is not effectively integrated with operational equipment in farmland. For example, irrigation systems often cannot automatically adjust based on rainfall forecasts provided by weather stations, still requiring manual intervention. This not only increases labor intensity but may also lead to insufficient or excessive irrigation due to delayed responses. Furthermore, current pest and disease early warning models often neglect the long-term effects of temperature and humidity trends. This short-sighted approach prevents models from accurately predicting the occurrence and development of pests and diseases, thus affecting the timeliness and effectiveness of control measures and potentially adversely impacting crop yield and quality. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention proposes an agricultural management system that integrates network data monitoring, weather forecasting and analysis, and automatic feedback. This system can monitor the crop growth environment in real time, predict agricultural needs based on weather forecasts, and automatically perform irrigation, pest and disease control, and extreme weather protection operations.

[0005] The technical solution adopted by this invention to solve its technical problem is:

[0006] The agricultural environment intelligent monitoring and automated management system based on the Internet of Things and weather data linkage includes a real-time environmental monitoring module, multi-source weather data interface, cloud prediction model and automated execution equipment.

[0007] The real-time environmental monitoring module consists of various sensors and multispectral cameras distributed within the agricultural production area. These sensors and multispectral cameras are connected to a gateway via Internet of Things (IoT) technology, transmitting the collected environmental data to the gateway, which then sends it to the cloud platform.

[0008] The multi-source weather data interface is used to connect to multiple different weather data sources. The multi-source weather data interface can automatically obtain weather data for a future period from each data source according to a preset time interval, and clean, merge and convert the obtained multi-source weather data to a unified format before transmitting it to the cloud platform.

[0009] The cloud-based prediction model is deployed on a cloud platform and includes a data storage unit, a data analysis unit, and a prediction unit. The data storage unit stores agricultural field environmental data transmitted by the real-time environmental monitoring module and weather data transmitted by the multi-source weather data interface. The data analysis unit performs in-depth analysis on the stored data to uncover the correlation between agricultural field environmental parameters and weather data. Based on the analyzed correlations and historical data, the prediction unit uses machine learning algorithms to construct a prediction model to predict the environmental change trend of the agricultural production site in the future, and at the same time predicts possible adverse environmental factors based on weather data.

[0010] The automated execution equipment communicates with the cloud platform via the Internet of Things. When the cloud prediction model predicts that there will be environmental changes at the agricultural production site that are unfavorable to crop growth, the cloud platform sends control commands to the corresponding automated execution equipment, and the automated execution equipment automatically performs the corresponding operations according to the commands.

[0011] The present invention also has the following additional technical features:

[0012] As a further specific optimization of the technical solution of the present invention, the various sensors include a temperature sensor, a humidity sensor, a light sensor, a soil pH sensor, and a carbon dioxide sensor.

[0013] As a further specific optimization of the technical solution of the present invention: the environmental data includes temperature, humidity, light intensity, soil pH, carbon dioxide concentration, and environmental condition parameters of the agricultural production site.

[0014] As a further specific optimization of the technical solution of the present invention: the weather data source includes official databases of meteorological departments (meteorological bureau API, satellite cloud images and radar data) and / or third-party weather service platforms.

[0015] As a further specific optimization of the technical solution of the present invention: the weather data includes temperature, precipitation, wind force, wind direction and sunshine duration, and the update frequency is ≤15 minutes.

[0016] As a further specific optimization of the technical solution of the present invention: the prediction unit is a lightweight weather prediction model (such as LSTM time series analysis).

[0017] As a further specific optimization of the technical solution of the present invention: the automated execution equipment includes irrigation equipment, ventilation equipment, shading equipment, heating equipment, and fertilization equipment.

[0018] As a further specific optimization of the technical solution of the present invention: the irrigation equipment is equipped with an intelligent irrigation valve, the intelligent irrigation valve is controlled by a cloud platform to implement the irrigation strategy, and the dynamic adjustment of the irrigation strategy is based on a weighted evaluation of real-time soil data and the precipitation forecast for the next 72 hours.

[0019] As a further specific optimization of the technical solution of this invention: activating irrigation equipment for watering, starting ventilation equipment to regulate humidity, and deploying shading equipment to reduce sunlight, etc., to maintain the stability of the agricultural production site environment. The weight calculation formula for the irrigation strategy is: Final irrigation volume = Real-time water shortage demand × (1 - Precipitation probability × 0.8).

[0020] Compared with the prior art, the advantages of this invention are:

[0021] This invention enables real-time and comprehensive collection of agricultural environmental data, accurately capturing various environmental parameters at agricultural production sites through multiple sensors. It can be linked with multi-source weather data to obtain weather change information in advance, combining this information with agricultural environmental data for analysis and prediction, making agricultural environmental management more forward-looking. Employing a cloud-based prediction model, this invention allows for in-depth data analysis and accurate prediction, providing a scientific basis for the control of automated equipment. This achieves intelligent and automated management of the agricultural environment, reducing manual intervention, improving management efficiency, and lowering production costs. Furthermore, this invention can promptly adjust the agricultural environment based on prediction results, effectively preventing damage to crops caused by sudden environmental changes, and contributing to improved crop yield and quality. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the system composition structure of the present invention.

[0023] Figure 2 This is a schematic diagram of the functional execution structure of the present invention. Detailed Implementation

[0024] Exemplary embodiments of the present invention will now be described in more detail with reference to the accompanying drawings.

[0025] Example 1

[0026] The agricultural environment intelligent monitoring and automated management system based on the Internet of Things and weather data linkage includes a real-time environmental monitoring module, multi-source weather data interface, cloud prediction model and automated execution equipment.

[0027] The real-time environmental monitoring module consists of various sensors and multispectral cameras distributed within the agricultural production area, including temperature sensors, humidity sensors, light sensors, soil pH sensors, carbon dioxide sensors, and multispectral cameras. These sensors and multispectral cameras are connected to a gateway via Internet of Things (IoT) technology, enabling them to collect real-time data on temperature, humidity, light intensity, soil pH, carbon dioxide concentration, and other environmental parameters at the agricultural production site. The collected data is then transmitted to the gateway, which in turn sends it to the cloud platform.

[0028] The multi-source weather data interface is used to connect to multiple different weather data sources, including official meteorological databases (meteorological bureau API, satellite cloud images and radar data) and / or third-party weather service platforms. The multi-source weather data interface can automatically obtain weather data for a future period from each data source at preset time intervals, and clean, merge and convert the obtained multi-source weather data to a unified format before transmitting it to the cloud platform. The weather data includes temperature, precipitation, wind force, wind direction and sunshine duration, with an update frequency of ≤15 minutes.

[0029] The cloud-based prediction model is deployed on a cloud platform and includes a data storage unit, a data analysis unit, and a prediction unit. The data storage unit stores agricultural field environmental data transmitted by the real-time environmental monitoring module and weather data transmitted by the multi-source weather data interface. The data analysis unit performs in-depth analysis on the stored data to uncover the correlation between agricultural field environmental parameters and weather data. The prediction unit is a lightweight weather prediction model (such as LSTM time series analysis). Based on the analyzed correlations and historical data, the prediction unit uses machine learning algorithms to construct a prediction model to predict the environmental change trend of the agricultural production site in the future, and at the same time predicts possible adverse environmental factors based on weather data.

[0030] The automated execution equipment communicates with the cloud platform via the Internet of Things (IoT), including irrigation equipment, ventilation equipment, shading equipment, heating equipment, and fertilization equipment. When the cloud prediction model predicts environmental changes unfavorable to crop growth at the agricultural production site, the cloud platform sends control commands to the corresponding automated execution equipment, which then automatically executes the corresponding operations. For example, the irrigation equipment is equipped with a smart irrigation valve, which is controlled by the cloud platform to implement the irrigation strategy. The irrigation strategy is dynamically adjusted based on a weighted assessment of real-time soil data and the 72-hour precipitation forecast. This includes actions such as turning on the irrigation equipment to water crops, activating ventilation equipment to regulate humidity, and deploying shading equipment to reduce sunlight, all to maintain a stable environment at the agricultural production site. The weighting formula for the irrigation strategy is: Final irrigation volume = Real-time water shortage demand × (1 - Precipitation probability × 0.8).

[0031] Example 2

[0032] The agricultural environment intelligent monitoring and automated management system based on the Internet of Things and weather data linkage includes a real-time environmental monitoring module, multi-source weather data interface, cloud prediction model and automated execution equipment.

[0033] The real-time environmental monitoring module uses high-precision temperature, humidity, light, soil pH, and carbon dioxide sensors. These sensors are evenly distributed throughout the greenhouse, and the data collection frequency is set to once every 5 minutes. The sensors connect to the gateway via ZigBee wireless communication technology, transmitting the collected data such as temperature, humidity, light intensity, soil pH, and carbon dioxide concentration to the gateway. The gateway then sends the data to the cloud platform via a 4G network.

[0034] The multi-source weather data interface connects to the official database of the local meteorological department and two mainstream third-party weather service platforms. Every hour, this interface retrieves weather data for the next 7 days from various data sources, including temperature, precipitation probability, wind speed, wind direction, and sunshine duration. The acquired multi-source weather data undergoes initial cleaning to remove outliers and duplicates. Then, a weighted average method is used to fuse data from different sources for the same parameter. Finally, the fused data is converted to a unified JSON format and transmitted to the cloud platform.

[0035] The cloud-based prediction model's data analysis unit employs big data analytics to perform correlation analysis on stored agricultural field environmental and weather data, such as analyzing the relationships between temperature and light intensity, and precipitation and soil moisture. The prediction unit uses a random forest algorithm to build the prediction model, training and optimizing it with historical data. When new real-time environmental and weather data are input, the prediction model can predict the changing trends of environmental parameters such as temperature, humidity, and light intensity inside the greenhouse within 10 minutes, and determine whether adverse environmental factors such as high temperature, low temperature, high humidity, or insufficient light will occur.

[0036] The automated execution equipment includes electric irrigation valves, axial flow fans, shading net motors, electric heating elements, and intelligent fertilizer applicators. All of these devices communicate with the cloud platform via IoT modules. When the cloud-based predictive model forecasts that the temperature inside the greenhouse will exceed the upper limit of the suitable temperature for crop growth within the next 6 hours, the cloud platform sends a start command to the axial flow fans. Upon receiving the command, the axial flow fans automatically turn on to ventilate and cool the greenhouse. When rainfall is predicted within the next 12 hours and the soil moisture will be below the suitable value, the cloud platform sends an advance irrigation command to the electric irrigation valves, which then perform irrigation operations according to the set water volume and time.

[0037] In actual operation, the system can monitor the environmental conditions inside the greenhouse in real time and make environmental adjustments in advance according to weather changes, ensuring that crops are always in a suitable growing environment. After a planting cycle of trials, the yield of crops in the greenhouse increased by more than 15% compared with traditional management methods, and the quality was also significantly improved.

[0038] In addition to this embodiment:

[0039] Example of irrigation optimization: The system detects soil moisture at 18% (threshold 20%), but the weather API indicates heavy rainfall (15mm) in 3 hours. The current irrigation task is automatically canceled, and a 5mm difference in water is added after the rain.

[0040] Example of disease prevention: If humidity is predicted to be above 80% for the next 48 hours, the AI ​​model calculates a 65% risk of fungal disease. Preventative pesticides are sprayed in advance, and a notification is sent: "High humidity warning; pruning of leaves to increase ventilation is recommended."

[0041] Example of extreme weather protection: Receive an orange gale warning (wind speed > level 10) from the meteorological bureau. Automatically retract the greenhouse shade netting and control a drone to inspect the stability of surrounding facilities.

[0042] This plan has been tested in the field. The data shows that after integrating weather linkage, the cost of wheat irrigation during the season has been reduced by 38%, and the efficiency of responding to frost disasters has been increased by 76%.

[0043] The above detailed description of embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention.

Claims

1. An intelligent monitoring and automated management system for the agricultural environment based on the Internet of Things and weather data linkage, characterized in that: It includes a real-time environmental monitoring module, a multi-source weather data interface, a cloud-based forecasting model, and automated execution equipment; among which: The real-time environmental monitoring module consists of various sensors and multispectral cameras distributed in the agricultural production area. These sensors and multispectral cameras are connected to a gateway via Internet of Things (IoT) technology, transmitting the collected environmental data to the gateway, which then sends it to the cloud platform. The multi-source weather data interface is used to connect to multiple different weather data sources. The multi-source weather data interface can automatically obtain weather data for a future period from each data source according to a preset time interval, and clean, merge and convert the obtained multi-source weather data to a unified format before transmitting it to the cloud platform. The cloud-based prediction model is deployed on a cloud platform and includes a data storage unit, a data analysis unit, and a prediction unit. The data storage unit stores agricultural field environmental data transmitted by the real-time environmental monitoring module and weather data transmitted by the multi-source weather data interface. The data analysis unit performs in-depth analysis on the stored data to uncover the correlation between agricultural field environmental parameters and weather data. Based on the analyzed correlations and historical data, the prediction unit uses machine learning algorithms to construct a prediction model to predict the environmental change trend of the agricultural production site in the future, and at the same time predicts possible adverse environmental factors based on weather data. The automated execution equipment communicates with the cloud platform via the Internet of Things. When the cloud prediction model predicts that there will be environmental changes at the agricultural production site that are unfavorable to crop growth, the cloud platform sends control commands to the corresponding automated execution equipment, and the automated execution equipment automatically performs the corresponding operations according to the commands.

2. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The various sensors mentioned include temperature sensors, humidity sensors, light sensors, soil pH sensors, and carbon dioxide sensors.

3. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The environmental data includes temperature, humidity, light intensity, soil pH, carbon dioxide concentration, and other environmental parameters at the agricultural production site.

4. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The weather data sources include official meteorological databases (meteorological bureau API, satellite cloud images and radar data) and / or third-party weather service platforms.

5. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The weather data includes temperature, precipitation, wind speed, wind direction, and sunshine duration, and is updated every 15 minutes.

6. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The prediction unit is a lightweight weather prediction model (such as LSTM time series analysis).

7. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The automated execution equipment includes irrigation equipment, ventilation equipment, shading equipment, heating equipment, and fertilization equipment.

8. The agricultural environment intelligent monitoring and automated management system according to claim 1, characterized in that: The irrigation equipment is equipped with an intelligent irrigation valve, which is controlled by a cloud platform to implement the irrigation strategy. The dynamic adjustment of the irrigation strategy is based on a weighted assessment of real-time soil data and the 72-hour precipitation forecast.

9. The intelligent monitoring and automated management system for agricultural environment according to claim 1, characterized in that: Irrigation equipment is turned on to water the crops, ventilation equipment is activated to regulate humidity, and shading equipment is deployed to reduce sunlight, in order to maintain a stable environment at the agricultural production site. The weighting formula for the irrigation strategy is: Final irrigation volume = Real-time water shortage demand × (1 - Precipitation probability × 0.8).

Images