Cultivated land intelligent monitoring decision-making model construction method using end-side cloud technology
Through the intelligent monitoring decision model of cultivated land with end-edge cloud technology, combined with drone and satellite remote sensing data, a crop growth model suitable for different environments was established, solving the limitations of existing models, and achieving more accurate farmland quality monitoring and Resource optimization.
Patent Information
- Application Number
- CN202411122115.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-08
AI Technical Summary
The existing arable land monitoring model cannot adapt to the geographical, climatic and soil conditions of different regions, resulting in great limitations of the model and cannot accurately reflect the quality of arable land.
Using end-edge cloud technology, by deploying sensors in the field, using drones and satellite remote sensing for environmental monitoring, edge nodes perform preliminary data processing and pest identification, uploading data to the cloud for big data analysis, and establishing a growth model for crops and soil. And consider the impact of diseases and pests to form a closed-loop decision-making system.
Accurate monitoring and decision-making support for different environments is achieved, decision-making lag is reduced, the speed and accuracy of pest identification and crop growth status analysis is improved, and the use of agricultural resources is optimized.
Smart Images

Figure CN118917752A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of farmland monitoring technology, and in particular to a method for constructing a farmland intelligent monitoring decision model using end-edge cloud technology. Background Art
[0002] The specific situation of cultivated land quality is an important basis for planning. Yunnan has complex landform types, diverse soil types, and large differences in planting systems in different regions. The existing measurement points have limited coverage, and the construction standards and management levels of state (city) and county-level monitoring points are uneven. The monitoring data of different regions and departments lack unified standards and specifications. There are problems such as inaccurate information, incomplete data, insufficient data sharing and service capabilities. The monitoring data is difficult to fully reflect the quality of cultivated land in the province. In order to solve the above problems, based on the second soil census, soil testing and formula fertilization, and high-standard farmland construction, we integrate talents, funds, markets and other resources, introduce advanced technical means, and build a dynamic monitoring and evaluation platform for cultivated land quality in Yunnan Province. The platform adopts big data technology, IoT edge cloud methods, GIS and other technologies, combined with satellite remote sensing, and relies on low-altitude data from drones, soil data, water retreat data and other air-ground multi-source data to carry out research on the atmosphere-soil-crop intelligent perception system in cultivated land quality monitoring. The platform can digitally monitor the climate environment, soil nutrients and moisture, crop growth, pests and diseases, etc. in real time, and build a crop and soil nutrient monitoring technology system. However, the geographical, climatic, and soil conditions in different regions vary greatly. The models in existing technologies cannot adapt to different environments, resulting in particularly large limitations of the models. Therefore, a method for constructing a cultivated land intelligent monitoring decision-making model using end-edge cloud technology is designed. Summary of the invention
[0003] The purpose of the present invention is to provide a method for constructing a farmland intelligent monitoring decision model using edge-cloud technology, so as to solve the problem that the model proposed in the above background technology cannot adapt to different environments, resulting in particularly large model limitations.
[0004] To achieve the above object, the present invention aims to provide a method for constructing a farmland intelligent monitoring decision model using edge-cloud technology, comprising the following steps: S1. Deploy sensors in the field, use drones and satellite remote sensing to comprehensively monitor the farmland environment, and control the operation of integrated equipment through chips to achieve local data preprocessing and transmission; S2, edge nodes receive sensor data, drone and satellite data, and perform preliminary cleaning and anomaly detection. At the same time, they perform preliminary identification and analysis of pests and diseases and crop growth status based on edge computing capabilities; S3, upload the data processed and analyzed by the edge node to the cloud server for unified data management and storage, and use big data analysis to establish the original crop growth model between crops and soil, and at the same time establish the impact model of the environment and pests and diseases, and introduce the probability factors of pests and diseases into the original crop growth model to establish a crop growth model; S4. The cloud server makes decisions on cultivated land environmental resources based on the results of the crop growth model and collects feedback information after the decision is implemented to form a closed-loop system.
[0005] As a further improvement of the technical solution, in S1, the sensor can monitor soil health, meteorological parameters, crop growth status and pests and diseases; the drone is equipped with a camera to regularly take aerial photos of farmland; the satellite remote sensing can obtain Indicators and index.
[0006] As a further improvement of the technical solution, the specific steps of S2 are as follows: S21, using image processing technology to identify leaf features in images taken by drones; S22. According to the crop Indicators and Indicators, combined with leaf characteristics, assess the current growth status of crops.
[0007] As a further improvement of the present technical solution, the leaf characteristics in S21 include color and texture characteristics and disease and insect pest sign characteristics.
[0008] As a further improvement of the technical solution, in S22, Indicators and The expressions of the indicators are as follows:
[0009] in, is the normalized difference vegetation index; is the reflectivity in the near infrared; is the reflectivity of red light band;
[0010] in, is the enhanced vegetation index; is the scaling factor; is the correction term for red light; is the correction term for blue light; is the reflectivity of the blue light band; is the ambient light intensity compensation item.
[0011] As a further improvement of the technical solution, the specific steps of establishing the crop growth model in S3 are as follows: S31. Predict the impact of soil environment on crop growth and establish an original crop growth model; S32. Predict the probability of pests and diseases occurring at a certain point in time based on environmental factors and historical data; S33. Introduce the impact of pests and diseases into the model of crop growth and establish a crop growth model.
[0012] As a further improvement of the technical solution, the expression of S31 is: The impact of climate and environment on soil:
[0013] in, For in time soil moisture; For in time of precipitation; For in time The amount of irrigation; For in time of soil evaporation; For in time The amount of water absorbed from the soil; in,
[0014] in, is the water requirement ratio of the crop; It is the evapotranspiration of crops; For in time irrigation efficiency; is the measurement time interval;
[0015] in, is the slope of the saturated water vapor pressure curve; For time The net radiation amount; For time of soil heat flux; is a physical constant; For The temperature of time; For in time wind speed; is the saturated water vapor pressure; is the actual water vapor pressure; To consider soil moisture Impact function on evaporation; Impact of soil on crops:
[0016] in, For in time of crop yields; For in time the maximum potential crop yield; is the optimal soil moisture that varies with the crop growth stage; is the critical soil moisture that varies with the crop growth stage; is the water use efficiency of crops over time; The sensitivity of crops to water stress changes over time.
[0017] As a further improvement of the technical solution, the expression of S32 is:
[0018] in, For in time probability of pests and diseases; The influence of temperature and humidity on the occurrence of pests and diseases; The effect of soil moisture on pests and diseases; The impact of seasonal factors on pests and diseases; in,
[0019] in, For in time humidity; represents the interaction term between temperature and humidity; , , and All of them are coefficients determined according to the characteristics of pests and diseases;
[0020] in, For in time Optimal soil moisture range; For The standard deviation of time; For The standard deviation of time; is the attenuation range after exceeding the optimum soil moisture range;
[0021] in, is the amplitude; It is the peak month; is the phase shift; is the baseline level; is the time trend term.
[0022] As a further improvement of the present technical solution, the expression of the crop growth model in S33 is:
[0023] in, is the adjustment factor.
[0024] As a further improvement of the technical solution, in S4, the specific steps of making decisions on cultivated land environmental resources according to the results of the crop growth model are as follows: S41. Set the expected yield target in advance. If the results of the crop growth model are lower than the expected yield target, identify the key factors for yield decline. S42. Make resource optimization decisions based on the identified key factors and combined with data from various sensors deployed in the field, drones and satellite remote sensing monitoring; S43, sending the decision plan to the field intelligent equipment to perform irrigation, fertilization and pest control operations; S44. Regularly review the effectiveness of decision implementation, continuously upload implementation feedback information to the cloud, iterate and optimize the crop growth model, and form a closed-loop system.
[0025] Compared with the prior art, the present invention has the following beneficial effects: 1. In the method of constructing a smart farmland monitoring decision model using edge-cloud technology, the introduction of edge computing makes pest and disease identification and crop growth status analysis faster and closer to the scene, reducing decision-making delays caused by data transmission delays. At the same time, comprehensive big data analysis on the cloud not only establishes a crop growth model, but also comprehensively considers the impact of the environment and pests and diseases, making decision support more accurate.
[0026] 2. In the method of constructing an intelligent farmland monitoring decision-making model using edge-cloud technology, a more accurate original crop growth model can be constructed by predicting the impact of environmental factors on soil and the specific effect of soil environment on crop growth. The crop growth model can more accurately guide fertilizer application, irrigation plans and the timing of pest and disease control, thereby optimizing the use of agricultural resources. The crop growth model can be applied to farmland in different environments and has strong applicability. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 The figure is a flow chart of the overall method of the present invention. DETAILED DESCRIPTION
[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0029] Example See also Figure 1 As shown in the figure, a method for constructing a farmland intelligent monitoring decision model using edge-cloud technology is provided, including the following steps: S1. Deploy sensors in the field, monitor the farmland environment through drones and satellite remote sensing, and control the operation of integrated equipment through chips to realize the preprocessing and transmission of local data; the sensors can monitor soil health, meteorological parameters, crop growth status and pests and diseases; the drones are equipped with camera equipment to regularly take aerial photos of farmland to obtain macroscopic image information of crop growth for monitoring crop growth, pests and diseases and irrigation needs; the satellite remote sensing can obtain Indicators and Indicators, assess crop growth and land use, and supplement the spatiotemporal coverage of drone monitoring. Microcontrollers or embedded systems are integrated on sensor nodes and drones, and built-in algorithms perform preliminary processing on raw data, such as filtering, calibration, and compression, to reduce the burden of data transmission.
[0030] S2. The edge node receives sensor data, drone and satellite data, performs preliminary cleaning and anomaly detection, and performs preliminary identification and analysis of pests and diseases and crop growth status based on edge computing capabilities. The specific steps are as follows: S21. Use image processing technology to identify leaf features in images taken by drones; leaf features include color, texture, and signs of pests and diseases. Observe changes in leaf color. Dark green usually means healthy leaves and higher chlorophyll content, while yellow or brown may indicate malnutrition or pests and diseases. Features such as smoothness, spots, curling, or wilting on the leaf surface can reflect the water status, disease, or nutritional status of the plant. Healthy leaves usually have even textures, while diseased or dehydrated leaves may appear spotted, wrinkled, or have burnt edges. S22. According to the crop Indicators and Indicators, combined with leaf characteristics, assess the current growth status of crops.
[0031] Indicators and The expressions of the indicators are as follows:
[0032] in, is the normalized difference vegetation index; is the reflectivity in the near infrared; is the reflectivity of red light band; It can reflect the greenness and coverage density of vegetation, and the value range is generally arrive The higher the value, the denser the vegetation and the better the growth condition;
[0033] in, is the enhanced vegetation index; is the scaling factor; is the correction term for red light; is the correction term for blue light; is the reflectivity of the blue light band; is the ambient light intensity compensation item. , The atmospheric scattering effect is corrected by additionally considering the blue light band, and the sensitivity and accuracy to high chlorophyll vegetation are improved by introducing other correction terms.
[0034] Comparison of crop growth cycles and A rapid rise at the beginning indicates that the crop is emerging and growing faster; a stable or declining trend after reaching a peak may mean that it has entered the maturity stage or is affected by environmental factors.
[0035] pass and Indicators can indirectly reflect changes in leaf greenness and thus infer crop nutritional status. and A value of usually means that the vegetation is lush and growing well; if and Higher values but with abnormal leaf color or texture may indicate the presence of pests or diseases or abiotic stress; low values may also mean malnutrition or damage by pests and diseases; conversely, high values may indicate and A low reading and normal leaf color and texture usually means that the crop is growing vigorously; otherwise, there may be growth problems.
[0036] S3. Upload the data processed and analyzed by the edge node to the cloud server for unified data management and storage, and use big data analysis to establish the original crop growth model between crops and soil, and at the same time establish the impact model of environment and pests and diseases, and introduce the probability factors of pests and diseases into the original crop growth model to establish a crop growth model. The specific steps are as follows: S31. Predict the impact of soil environment on crop growth and establish an original crop growth model; the expression is: The impact of climate and environment on soil:
[0037] That is, soil moisture content equals precipitation plus irrigation minus evaporation minus absorption; in, For in time soil moisture; For in time of precipitation, which is estimated through satellite remote sensing; For in time The irrigation amount is determined based on the crop water requirement and natural precipitation. The crop water requirement is determined by the crop water requirement ratio. and crop evapotranspiration Multiply them together to get; For in time of soil evaporation; For in time The amount of water absorbed from the soil; in,
[0038] in, is the crop water requirement ratio, which reflects the water requirement ratio of a specific crop relative to a reference crop (usually grassland); is the crop evapotranspiration, which represents the total loss of water evaporation and plant transpiration from a standard grass surface under conditions without water limitation; For in time The irrigation efficiency reflects the proportion of water effectively used by crops in the actual irrigation system, taking into account the loss during the irrigation process; is the measurement time interval, i.e. the length of time for calculating the water absorption;
[0039] This formula is based on the Penman-Monteith equation and reflects the effect of temperature changes on the evaporation rate; in, is the slope of the saturated water vapor pressure curve; For time The net radiation amount; For time of soil heat flux; It is a physical constant used to quantify the effect of temperature change on evaporative heat release; For The temperature of time; For in time wind speed; is the saturated water vapor pressure; is the actual water vapor pressure; both the saturated water vapor pressure and the actual water vapor pressure are affected by temperature; To consider soil moisture The effect function on evaporation; because when the soil becomes dry, the evaporation rate will decrease; Impact of soil on crops:
[0040] in, For in time of crop yields; For in time the maximum potential crop yield; is the optimal soil moisture that varies with the crop growth stage; is the critical soil moisture that varies with the crop growth stage; is the water use efficiency of crops over time; The sensitivity of crops to water stress changes over time. , , , and The values of are obtained through experimental data, and each crop type and growth environment is different.
[0041] S32. Based on environmental factors and historical data, predict the probability of pests and diseases occurring at a certain point in time; the expression is:
[0042] in, For in time probability of pests and diseases; The effect of temperature and humidity on the occurrence of pests and diseases is that the growth and reproduction of many pathogens and pests are closely related to specific temperature and humidity conditions. For example, a warm and humid environment is conducive to the reproduction of certain fungal diseases and insects. The influence of soil moisture on pests and diseases. The pH value, fertility and moisture status of the soil affect the health of crops and also indirectly affect the breeding of pests and diseases. A suitable soil environment can enhance crop resistance and reduce pests and diseases. The seasonal factors affect pests and diseases. Seasonal changes affect the life cycle of pests and diseases and determine their active and dormant periods. in,
[0043] in, For in time humidity; represents the interaction term of temperature and humidity, that is, the combined effect of temperature and humidity on pests and diseases or crop growth; , , and All of them are coefficients determined according to the characteristics of pests and diseases;
[0044] in, For in time Optimal soil moisture range; For The standard deviation of time; For The standard deviation of time; is the attenuation range after exceeding the optimum soil moisture range; This function describes the soil moisture The nonlinear relationship between soil moisture and crop growth or pests and diseases. When the humidity is within the range of , the Gaussian function is used to represent the favorable effect under the optimum humidity conditions, where Controls the width of the curve, adding a decay range when the soil moisture exceeds the optimal range When another standard deviation Used to reflect the degree of mitigation of adverse impacts; It can not only help determine the best irrigation time to avoid the adverse effects of too much or too little water on crop growth, but also be used in pest and disease management strategies, because soil moisture has an important impact on the reproduction and activities of pests and diseases;
[0045] in, is the amplitude; For example, if pests and diseases are most active in the summer, Probably towards the middle months of summer; is the phase shift, which is used to adjust the specific time point when the peak occurs; is the baseline level, representing a constant effect beyond seasonal variation; It is a time trend item, reflecting the long-term climate change trend or other factors that change slowly over time.
[0046] S33. Introduce the impact of pests and diseases into the model of crop growth impact to establish a crop growth model; pests and diseases directly consume the nutrients of crops, affecting their normal growth, resulting in slow growth and reduced yields, and pests gnawing or pathogen infection can directly damage crop tissues, reduce photosynthesis efficiency, and affect crop growth and development; The expression of crop growth model is:
[0047] in, A correction factor to reflect the impact of pests and diseases. This factor decreases as the probability of pests and diseases increases, indicating the potential yield-reducing effect of pests and diseases on crop yields. is the adjustment coefficient used to quantify the probability of pests and diseases The magnitude of the impact on crop yields, specifically, It describes the proportion of crop yield reduction caused by a unit increase in the probability of pests and diseases. Its value is usually positive, reflecting the more serious the pests and diseases (i.e. The larger the value, the more crop yields will decrease; when When , it means that pests and diseases have no impact on crop yield; when When it is small, it indicates that the impact of pests and diseases on yield is relatively light; when When it is larger, it means that the impact of pests and diseases on crop yield is very significant, and even if the probability of pests and diseases is small, it may lead to a large yield loss; Therefore, adjust The model can reflect the different severity of the impact of pests and diseases on crop yields in different crop types or under different environments. The value of needs to be determined based on historical data, experimental research or expert knowledge to ensure the accuracy and practicality of the model prediction.
[0048] S4. The cloud server makes decisions on cultivated land environmental resources based on the results of the crop growth model and collects feedback information after the decision is implemented to form a closed-loop system.
[0049] In S4, the specific steps for making decisions on cultivated land environmental resources based on the results of the crop growth model are as follows: S41. Set expected yield targets in advance. If the results of the crop growth model are lower than the expected yield targets, identify the key factors that lead to yield decline, including soil moisture status, nutritional status, climatic conditions, and crop layout and planting density. Identify key periods and factors for yield growth or decline based on yield trends predicted by crop growth models; assess the probability of pests and diseases and their potential yield-reducing effects on crop yields, and determine the urgency and priority of pest and disease management; analyze soil moisture and nutrient conditions to identify the need to adjust irrigation and fertilization plans; S42. Make resource optimization decisions based on the identified key factors and in combination with the data from various sensors, drones and satellite remote sensing monitoring deployed in the field; decisions include irrigation decisions, formulating refined irrigation plans based on soil moisture monitoring data to ensure that crops have enough water during the critical growth period while avoiding water waste; fertilization decisions, customizing fertilization plans based on crop nutrient demand models and soil nutrient conditions to improve fertilizer utilization and reduce environmental pollution; pest and disease control decisions, deploying biological, chemical or physical control measures in advance based on pest and disease forecasts, and taking priority action in high-risk areas and periods; crop management, adjusting crop layout and planting density, and optimizing crop rotation or intercropping patterns to reduce the occurrence of pests and diseases and improve land utilization.
[0050] S43. Send the decision plan to the field intelligent equipment to perform irrigation, fertilization and pest control operations; continuously monitor the implementation effect through sensors deployed in the field, and collect data such as crop growth response, soil conditions, and the occurrence of pests and diseases; S44. Regularly review the effectiveness of decision-making implementation, continuously upload the feedback information of implementation to the cloud, iterate and optimize the crop growth model, and form a closed-loop system. Not only can it timely discover and solve problems in agricultural production, but also can gradually optimize management strategies through continuous feedback and learning, and ultimately achieve the comprehensive benefits of increasing crop yields, reducing costs, and protecting the ecological environment.
[0051] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A method for constructing a farmland intelligent monitoring decision model using edge-cloud technology, characterized in that: The steps include: S1. Deploy sensors in the field, monitor the farmland environment through drones and satellite remote sensing, and control the operation of integrated equipment through chips to realize local data preprocessing and transmission; S2, edge nodes receive sensor data, drone and satellite data, and perform preliminary cleaning and anomaly detection. At the same time, they perform preliminary identification and analysis of pests and diseases and crop growth status based on edge computing capabilities; S3, upload the data processed and analyzed by the edge node to the cloud server for unified data management and storage, and use big data analysis to establish the original crop growth model between crops and soil, and at the same time establish the impact model of the environment and pests and diseases, and introduce the probability factors of pests and diseases into the original crop growth model to establish a crop growth model; S4. The cloud server makes decisions on cultivated land environmental resources based on the results of the crop growth model and collects feedback information after the decision is implemented to form a closed-loop system.
2. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 1 is characterized in that: In S1, the sensor can monitor soil health, meteorological parameters, crop growth status, and pests and diseases; the drone is equipped with a camera to regularly take aerial photos of farmland; the satellite remote sensing can obtain Indicators and index.
3. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 2 is characterized in that: The specific steps of S2 are as follows: S21, using image processing technology to identify leaf features in images taken by drones; S22. According to the crop Indicators and Indicators, combined with leaf characteristics, assess the current growth status of crops.
4. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 3 is characterized in that: The leaf features in S21 include color and texture features and pest and disease sign features.
5. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 4 is characterized in that: In the S22, Indicators and The expressions of the indicators are as follows: in, is the normalized difference vegetation index; is the reflectivity in the near infrared; is the reflectivity of red light band; in, is the enhanced vegetation index; is the scaling factor; is the correction term for red light; is the correction term for blue light; is the reflectivity of the blue light band; is the ambient light intensity compensation item.
6. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 5 is characterized in that: The specific steps of establishing the crop growth model in S3 are as follows: S31. Predict the impact of soil environment on crop growth and establish an original crop growth model; S32. Predict the probability of pests and diseases occurring at a certain point in time based on environmental factors and historical data; S33. Introduce the impact of pests and diseases into the model of crop growth and establish a crop growth model.
7. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 6 is characterized in that: The expression of S31 is: The impact of climate and environment on soil: in, For in time soil moisture; For in time of precipitation; For in time The amount of irrigation; For in time of soil evaporation; For in time The amount of water absorbed from the soil; in, in, is the water requirement ratio of the crop; It is the evapotranspiration of crops; For in time irrigation efficiency; is the measurement time interval; in, is the slope of the saturated water vapor pressure curve; For time The net radiation amount; For time of soil heat flux; is a physical constant; For The temperature of time; For in time wind speed; is the saturated water vapor pressure; is the actual water vapor pressure; To consider soil moisture Impact function on evaporation; Impact of soil on crops: in, For in time of crop yields; For in time the maximum potential crop yield; is the optimal soil moisture that varies with the crop growth stage; is the critical soil moisture that varies with the crop growth stage; is the water use efficiency of crops over time; The sensitivity of crops to water stress changes over time.
8. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 7 is characterized in that: The expression of S32 is: in, For in time probability of pests and diseases; The influence of temperature and humidity on the occurrence of pests and diseases; The effect of soil moisture on pests and diseases; The impact of seasonal factors on pests and diseases; in, in, For in time humidity; represents the interaction term between temperature and humidity; , , and All of them are coefficients determined according to the characteristics of pests and diseases; in, For in time Optimal soil moisture range; For The standard deviation of time; For The standard deviation of time; is the attenuation range after exceeding the optimum soil moisture range; in, is the amplitude; It is the peak month; is the phase shift; is the baseline level; is the time trend term.
9. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 8, characterized in that: The expression of the crop growth model in S33 is: in, is the adjustment factor.
10. The method for constructing a farmland intelligent monitoring decision model using edge-to-edge cloud technology according to claim 9, characterized in that: In S4, the specific steps of making decisions on cultivated land environmental resources according to the crop growth model results are as follows: S41. Set the expected yield target in advance. If the results of the crop growth model are lower than the expected yield target, identify the key factors for yield decline. S42. Make resource optimization decisions based on the identified key factors and combined with data from various sensors deployed in the field, drones and satellite remote sensing monitoring; S43, sending the decision plan to the field intelligent equipment to perform irrigation, fertilization and pest control operations; S44. Regularly review the effectiveness of decision implementation, continuously upload implementation feedback information to the cloud, iterate and optimize the crop growth model, and form a closed-loop system.
Citation Information
Patent Citations
Crop planting management system and method based on cloud services
CN110347127A
Three-dimensional reconstruction method for farmland site edge cloud cooperation
CN111080794A
Water-fertilizer-pesticide integrated intelligent irrigation system based on machine learning algorithm
CN112450056A
Intelligent water and fertilizer decision-making method and system for greenhouse substrate cultivation
CN112715119A
Crop disease and pest monitoring method and system based on Internet of Things, and storage medium
CN113095555A
Cited By
Rice planting equipment with high enzyme activity and planting method thereof
CN119422585A
Straw returning-to-field deep scarification cultivation regulation and control method based on soil temperature and humidity
CN119866711A
Fertilization and topdressing intelligent decision-making system and method based on rice open space sensing data
CN120355524A
Intelligent dynamic monitoring method for ecological products
CN120409926A
An ecological product intelligent dynamic monitoring method
CN120409926B
