Intelligent gate remote control method and system based on remote sensing and Internet of Things technology

Abstract

The invention discloses an intelligent gate remote control method and system based on remote sensing and Internet of Things technologies, and belongs to the technical field of gate control. The method comprises the following steps: capturing spectral data of a target area through a remote sensing sensor carried by an unmanned aerial vehicle, and capturing environmental data of the target area through an environmental sensor deployed at a key node in the target area so as to construct a multi-dimensional data set; after data preprocessing is conducted on the multi-dimensional data set, key index abnormal points are screened and marked step by step so as to obtain an abnormal aggregation area, and operation parameters of an abnormal aggregation area gate are fitted; an execution instruction of the gate is generated, the execution condition of the gate is monitored through the state sensor, abnormal early warning is carried out on the gate with abnormal execution, an execution result is transmitted to the data processing module through the Internet of Things equipment, and the execution instruction is updated; and real-time monitoring and analysis of key index abnormal points are realized, so that the use of the gate is optimized, and the effective utilization efficiency of water resources is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gate control, and more particularly to a remote control method and system for an intelligent gate based on remote sensing and Internet of Things technologies. Background Art

[0002] With the growth of global population and the increase of agricultural water demand, the efficient management and utilization of water resources has become an important issue for sustainable agricultural development. Especially in arid and semi-arid areas, the shortage of water resources and unreasonable irrigation methods have seriously affected the water management of farmland, resulting in water waste and soil degradation. Therefore, improving the efficiency of water resource utilization in agricultural irrigation and reducing unnecessary water consumption are urgent needs to promote the green development of agriculture.

[0003] , intelligent agricultural irrigation management system has gradually become a hot topic of research. The integration of remote sensing technology and Internet of Things technology provides efficient and accurate solutions. Remote sensing technology obtains a wide range of farmland moisture and key indicator information through satellites or drones, which can help farmers grasp soil moisture conditions, climate change and other data in real time. The Internet of Things technology transmits this data to the control center in real time through sensors, data acquisition equipment and communication networks to provide support for irrigation decisions.

[0004] The patent application with the authorization announcement number CN203455682U discloses a remote intelligent control system for water conservancy irrigation canal gates, including a communication module, a power supply module, a remote central control center, and a main controller. The main controller is connected with an infrared microwave alarm device, a video monitoring device, a flow measurement device, a gate drive module, and a power control module. This technical solution can realize the superposition display of gate automatic control, anti-theft alarm, anti-theft monitoring video and gate working status related data. It has the characteristics of high power utilization, strong system scalability and versatility, which can reduce the waste of water resources and reduce management and maintenance costs. However, it still fails to solve the accuracy problem of real-time dynamic adjustment of soil moisture changes under variable meteorological conditions, and lacks an effective feedback mechanism to deal with the irrigation needs of abnormal gathering areas. Therefore, in order to overcome these limitations, the present invention proposes a remote control method and system for intelligent gates based on remote sensing and Internet of Things technology. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a remote control method and system for intelligent gates based on remote sensing and Internet of Things technologies, which solves the problems of real-time monitoring and anomaly detection of key indicators in the target area, optimizes the execution instructions of the gates, and improves the efficiency of water resource utilization.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] Intelligent gate remote control system based on remote sensing and Internet of Things technology, including data acquisition module, data processing module and execution feedback module;

[0008] The data acquisition module uses intelligent sampling strategies to capture the spectral data of the target area through remote sensing sensors carried by drones, and captures the environmental data of the target area through environmental sensors deployed at key nodes in the target area. The spectral data and environmental data are transmitted to the central data platform through IoT devices for aggregation to construct a multidimensional data set.

[0009] The data processing module is used to pre-process the multidimensional data set, select key indicators according to the crop type in the target area, gradually screen and mark the abnormal points of key indicators according to the key indicators, identify the abnormal clustering area, and fit the operating parameters of the gate in the abnormal clustering area by establishing a key indicator change model;

[0010] The execution feedback module generates execution instructions for the gates based on the operating parameters of the gates in the abnormal aggregation area, monitors the execution status of the gates through the status sensors installed on the gates, issues abnormal warnings for gates with execution abnormalities, and transmits the execution results to the data processing module through the Internet of Things device to update the execution instructions.

[0011] Specifically, the data acquisition module includes a data acquisition unit and a data transmission unit;

[0012] The intelligent sampling strategy is configured in the data acquisition unit. The intelligent sampling strategy adjusts the sampling frequency and range according to the crop growth cycle and meteorological conditions in the target area. Through the UAV flight planning and sensor automatic control, the spectral data and environmental data are collected, and the timestamps and location coordinates of the spectral data and environmental data collection are recorded;

[0013] The data transmission unit is configured with an optimized transmission strategy, which selects wireless communication methods through IoT devices according to network conditions to transmit spectral data and environmental data to the central data platform.

[0014] Specifically, the steps of the intelligent sampling strategy include:

[0015] Set the initial sampling frequency according to the crop’s growth stage;

[0016] Receive meteorological data, and dynamically adjust the sampling frequency according to the change amount of meteorological data and the change amount of extreme weather conditions, wherein the change amount of meteorological data includes the change amount of temperature, the change amount of precipitation, the change amount of humidity and the change amount of wind speed, and the change amount of extreme weather conditions is obtained according to the extreme degree of meteorological data, and the extreme degree of meteorological data is obtained by the deviation between the received meteorological data and the meteorological standard data;

[0017] The acquisition time of the environmental sensor is adjusted according to the dynamically adjusted acquisition frequency to obtain environmental data, and the flight frequency of the UAV is adjusted to meet the needs of the dynamically adjusted acquisition frequency, and the flight path is recorded to make the path consistent to collect spectral data.

[0018] Specifically, the data processing module includes a preprocessing unit, an anomaly detection unit, and a predictive modeling unit;

[0019] A multi-level recognition strategy is configured in the anomaly detection unit. The multi-level recognition strategy is used to identify abnormal conditions of key indicators in the multidimensional data set that has undergone data preprocessing. The multi-level recognition judgment gradually screens and marks abnormal data points to identify abnormal clustering areas.

[0020] A multidimensional analysis strategy is configured in the predictive modeling unit. The multidimensional analysis strategy obtains gate usage information, combines historical meteorological data to establish a key indicator change model, and fits the model to estimate the impact coefficient, so as to obtain the gate operation parameters according to the key indicator requirements of the abnormal aggregation area.

[0021] Specifically, the steps of the multi-level identification strategy include:

[0022] Configure the time threshold, extract the multidimensional data points within the time threshold from the current timestamp from the multidimensional data set, and form an anomaly recognition data set;

[0023] Select key indicators that affect crop growth based on the crop types in the target area. The crop types include aquatic crops and non-aquatic crops. For aquatic crops, the field liquid level is selected as the key indicator that affects crop growth. For non-aquatic crops, soil moisture is selected as the key indicator that affects crop growth.

[0024] Based on the growth stage of the crops in the target area, the indicator thresholds are configured, including the indicator upper threshold and the indicator lower threshold, and preliminary anomaly detection is performed on the anomaly identification data set. If the key indicator of the multidimensional data point in the anomaly identification data set is greater than the indicator upper threshold or less than the indicator lower threshold, the data point is marked as a potential anomaly point;

[0025] Use time series analysis to fit the long-term trends of key indicators in multidimensional data sets and calculate the trend deviations of key indicators at potential outliers from the fitted trend values;

[0026] Configure the trend deviation threshold to evaluate the cause of abnormal key indicators of potential anomalies. If the trend deviation of the key indicators of potential anomalies is greater than the trend deviation threshold, it is marked as a mutation anomaly; otherwise, it is marked as a trend anomaly.

[0027] Specifically, the steps of the multi-level identification strategy also include:

[0028] Configure the neighborhood threshold to divide the neighborhood area range of mutation anomaly points and trend anomaly points for neighborhood analysis, and calculate the pattern similarity between mutation anomaly points and trend anomaly points and the multi-dimensional data points in their neighborhood areas;

[0029] Configure a similarity threshold, count the number of multidimensional data points in the neighborhood whose pattern similarity is greater than the similarity threshold, and calculate the ratio of the number of multidimensional data points in the neighborhood whose pattern similarity is greater than the similarity threshold to the total number of multidimensional data points in the neighborhood to obtain the similarity frequency in the neighborhood where the mutation anomaly point and the trend anomaly point are located;

[0030] Configure the frequency threshold. If the similar frequency in the neighborhood area where the mutation anomaly point is located is greater than the frequency domain threshold, the neighborhood area is marked as a mutation anomaly aggregation area. Otherwise, a mutation warning is issued for the mutation anomaly point. If the similar frequency in the neighborhood area where the trend anomaly point is located is greater than the frequency domain threshold, the neighborhood area is marked as a trend anomaly aggregation area. Otherwise, a trend warning is issued for the trend anomaly point.

[0031] Output all multidimensional data points in the abnormal clustering area, which includes the mutation abnormal clustering area and the trend abnormal clustering area.

[0032] Specifically, the steps of the multidimensional analysis strategy include:

[0033] Obtain the usage information of the gates in the target area, including location coordinates, opening timestamp, closing timestamp, opening duration, water flow speed, and accumulated water flow;

[0034] Configure the impact area threshold and the impact time threshold, filter out the multidimensional data points within the gate impact area threshold and within the impact time threshold from the gate closing timestamp from the multidimensional data set, so as to construct the impact data set;

[0035] A key indicator change model is constructed based on the impact data set combined with historical meteorological data. The key indicator change model is determined by the key indicators within the threshold of the gate impact area, the gate opening time, the accumulated flow of the gate, the distance between the multidimensional data points in the impact data set and the gate, and meteorological factors.

[0036] The meteorological factor is the comprehensive impact value of meteorological data within the influencing time range, which is jointly determined by the average temperature, average humidity, average wind speed and accumulated precipitation within the influencing time range;

[0037] According to the impact data set, the key indicator change model is fitted to estimate each impact coefficient, and based on the multi-dimensional data points of the abnormal aggregation area and its required key indicators, the abnormal aggregation area includes the mutation abnormal aggregation area and the trend abnormal aggregation area, the gate opening time and cumulative flow volume in the abnormal aggregation area are solved.

[0038] Specifically, the execution feedback module includes an instruction generation unit, a state detection unit and a data update unit;

[0039] The instruction generation unit is configured with an instruction optimization strategy, which generates gate execution instructions based on the gate's operating parameters and transmits instructions for opening, closing or adjusting flow through IoT devices;

[0040] The state detection unit is equipped with a real-time feedback strategy. The real-time feedback strategy collects the key parameters of the gate through the state sensor installed on the gate, detects the execution deviation and makes abnormal judgments, and automatically triggers abnormal warnings.

[0041] A feedback adjustment strategy is configured in the data update unit. The feedback adjustment strategy is used to collect spectral data and environmental data after the execution of the instructions, and transmit them to the data processing module through the Internet of Things device to update the water resource demand in the target area and obtain new execution instructions for the gate.

[0042] Specifically, the specific steps of the instruction optimization strategy include:

[0043] Receive the gate opening time and accumulated water flow in the abnormal concentration area, and obtain the gate location coordinates, and obtain the crop growth stage in the multidimensional data points within the gate influence area threshold according to the gate location coordinates;

[0044] The water flow rate threshold is set according to the crop growth stage, and the average flow rate is calculated based on the gate opening time and the accumulated water flow;

[0045] Calculate the water flow rate based on the default opening of the gate and the average flow rate;

[0046] If the water flow rate at the default gate opening is greater than the water flow rate threshold, the gate opening is adjusted according to the ratio of the average flow rate of the gate to the water flow rate threshold, and the adjusted gate opening and water flow rate threshold are output, otherwise the gate default opening and water flow rate are output;

[0047] An execution instruction is generated based on the gate opening and water flow rate, including the gate opening time, accumulated water flow, opening and water flow rate.

[0048] Specifically, the remote control method of the intelligent gate based on remote sensing and Internet of Things technology includes the following steps:

[0049] Step S1: Using intelligent sampling strategies, the spectral data of the target area is captured by the remote sensing sensor carried by the drone, the environmental data of the target area is captured by the environmental sensors deployed at the key nodes in the target area, and the spectral data and environmental data are transmitted to the central data platform through the Internet of Things devices for aggregation to construct a multidimensional data set;

[0050] Step S2: After preprocessing the multidimensional data set, select key indicators according to the crop type in the target area, gradually screen and mark the abnormal points of key indicators according to the key indicators, identify the abnormal clustering area, and fit the operating parameters of the gate in the abnormal clustering area by establishing a key indicator change model;

[0051] Step S3: Generate execution instructions for the gates based on the operating parameters of the gates in the abnormal concentration area, monitor the execution status of the gates through the status sensors installed on the gates, issue abnormal warnings for gates with execution abnormalities, and transmit the execution results to the data processing module through the Internet of Things device to update the execution instructions.

[0052] Beneficial effects of the present invention:

[0053] 1. Use the remote sensing sensors carried by drones to capture the spectral data of the target area, and combine them with environmental sensors deployed on the ground to collect environmental parameters. These data are transmitted to the central data platform for aggregation through the Internet of Things technology. The comprehensive data collection method provides a comprehensive basis for subsequent data analysis and decision-making. At the same time, according to the growth cycle of crops and immediate meteorological conditions, the sampling frequency and coverage are dynamically adjusted to ensure the timeliness and representativeness of the data. In severe weather or critical growth periods of crops, the system will increase the sampling density to capture soil and environmental changes more finely, thereby improving the accuracy and timeliness of early warnings.

[0054] 2. Use a multi-level identification strategy to gradually screen out the abnormal points of key indicators. Through time series analysis and neighborhood similarity calculation, effectively distinguish between mutation anomalies and trend anomalies, and provide a scientific basis for formulating targeted water-saving measures. Based on the needs of the abnormal clustering area, combined with historical meteorological data and gate usage records, calculate the optimal gate operation parameters, including opening time and cumulative water flow. This not only improves irrigation efficiency, but also reduces water waste.

[0055] 3. Based on the processed data analysis results, the gate execution instructions are generated, and the execution status is monitored in real time through the status sensors installed on the gate. The closed-loop control mechanism ensures the effective execution of the instructions and can promptly detect and handle execution deviations or equipment failures. The executed data is fed back to the data processing module for updating the key indicator model and adjusting future operation strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a schematic diagram of the structure of the intelligent gate remote control system based on remote sensing and Internet of Things technology of the present invention;

[0057] Figure 2 A flowchart of the specific steps of the intelligent sampling strategy of the present invention;

[0058] Figure 3A flowchart of the specific steps of the multi-level identification strategy of the present invention;

[0059] Figure 4 This is an example diagram of the application of the multi-level recognition strategy of the present invention;

[0060] Figure 5 A flowchart of the specific steps of the multidimensional analysis strategy of the present invention;

[0061] Figure 6 The present invention is a flow chart of the intelligent gate remote control method based on remote sensing and Internet of Things technology. DETAILED DESCRIPTION

[0062] Example 1

[0063] See also Figure 1 ,This embodiment introduces an intelligent gate remote control system based on remote sensing and Internet of Things ,technology, including a data acquisition module, a data processing module and an execution feedback module;

[0064] The data acquisition module uses intelligent sampling strategies to capture the spectral data of the target area through remote sensing sensors carried by drones, and captures the environmental data of the target area through environmental sensors deployed at key nodes in the target area. The spectral data and environmental data are transmitted to the central data platform through IoT devices for aggregation, and a multidimensional data set is constructed to monitor the crop growth status and soil quality in the target area.

[0065] Among them, spectral data include: crop chlorophyll content, crop moisture content, crop growth index;

[0066] Environmental data include: air temperature, soil temperature, air humidity, soil moisture, light intensity, carbon dioxide concentration, and field liquid level;

[0067] In this embodiment, a drone is used as a platform, and a remote sensing sensor is carried out to fly the target area regularly, and the surface spectral data of the target area is collected. The remote sensing sensor includes a multispectral sensor and a thermal infrared sensor. The multispectral sensor is used to capture the spectral reflectance information of the target area in multiple specific bands. When the drone flies according to the route, the multispectral sensor shoots the ground at a certain time interval. Each shot records the original image data of different bands, and the original image data reflects the radiation intensity of the target area in each band. During the acquisition process, the time, position and attitude information of the shooting are recorded to provide necessary auxiliary information for subsequent data processing. The thermal infrared sensor is used to measure the surface temperature distribution of the target area. During the flight of the drone, the thermal infrared sensor continues to work and obtains the thermal radiation information of the ground in real time. Similarly, the time, position and attitude of the shooting should be recorded synchronously to accurately match the multispectral data in time and space. The collected multispectral image data is subjected to radiation calibration processing. Through the pre-determined radiation calibration parameters, which include: sensor response function, atmospheric correction coefficient, etc., the digital quantization values ​​in the original image data are converted into actual surface reflectance data to accurately reflect the spectral characteristics of the target area and provide a reliable basis for subsequent analysis.

[0068] Based on the converted reflectance data, combined with the absorption characteristics of chlorophyll in specific bands, including red light bands and near-infrared bands, the inversion model is used to estimate the chlorophyll content of crops. For example, the absorption peak intensity of the spectral reflectance near 670nm is used to establish an empirical relationship between reflectance and chlorophyll content based on field measurement data, and an empirical formula is established to invert the chlorophyll content in crop leaves. The moisture index is calculated using bands that are sensitive to moisture, such as the short-wave infrared band, such as the normalized moisture index. The value reflecting the moisture content of the crop is obtained by calculating the ratio or difference of the short-wave infrared band reflectance. The extraction of the crop growth index depends on the reflectance of the red light band and the near-infrared band. The crop growth index is calculated by combining the reflectance of the red light band and the near-infrared band in the multispectral data through vegetation index models, such as the normalized vegetation index and the enhanced vegetation index. These indices can intuitively reflect the growth status of crops, such as vegetation coverage, growth vitality, etc. The temperature data collected by the thermal infrared sensor is preprocessed, including noise removal, deviation correction, etc. Then, the thermal infrared data is synchronized with the radiation intensity of each band extracted from the original image data for time and space synchronization. Through timestamp and location information, the thermal infrared data and multispectral data of the same area are ensured to correspond accurately in time and space.

[0069] Environmental sensors are deployed at key nodes in the target area, including the main irrigation points of the agricultural irrigation system, soil moisture monitoring points and meteorological stations. Environmental sensors include temperature and humidity sensors, soil moisture sensors, air pressure sensors, light sensors, field liquid level sensors, etc., which are used to collect environmental data of the target area in real time. In order to ensure the timeliness of the data, environmental sensors collect data at the set sampling frequency and monitor key factors such as soil moisture, meteorological changes and crop demand in real time. All collected spectral data and environmental data are wirelessly transmitted through IoT devices and uploaded to the central data platform for storage and synchronization to ensure the integrity and real-time nature of the data.

[0070] Preferably, the data acquisition module includes a data acquisition unit and a data transmission unit;

[0071] The data collection unit is equipped with an intelligent sampling strategy, which adjusts the sampling frequency and range according to the crop growth cycle and meteorological conditions in the target area. Through the UAV flight planning and sensor automatic control, the spectral data and environmental data are collected at a fixed time, fixed point and quantitatively, and the timestamps and location coordinates of the spectral data and environmental data collection are recorded to ensure that the data coverage is wide and representative.

[0072] The data transmission unit is configured with an optimized transmission strategy, which selects wireless communication methods through IoT devices according to network conditions to transmit spectral data and environmental data to the central data platform;

[0073] See also Figure 2 Preferably, the specific steps of the intelligent sampling strategy include:

[0074] The initial sampling frequency is set according to the growth stage of the crop, which includes the seedling stage, vegetative growth stage, flowering stage, fruit expansion stage, etc., so that different sampling frequencies are configured for different crop growth stages. A higher sampling frequency is used during the vigorous growth period, including the flowering stage and fruit expansion stage;

[0075] Receive meteorological data, including weather temperature, precipitation, wind speed and humidity. Dynamically adjust the sampling frequency according to the change in meteorological data and extreme weather conditions. When the meteorological data changes greatly or there is an extreme change in meteorological data, increase the sampling frequency. The formula for dynamic adjustment of the sampling frequency is as follows:

[0076] ;

[0077] in, is the dynamically adjusted sampling frequency, is the initial sampling frequency set according to the growth stage of the crop, is the temperature change, is the change in precipitation, is the humidity change, is the wind speed change, , , and are the weighted coefficients of temperature change, precipitation change, humidity change and wind speed change, which are used to indicate the influence of each meteorological factor on the sampling frequency. The value range is [0.05,0.2], The value range is [0.01,0.1], The value range is [0.02,0.1], The value range is [0.01,0.05], is the weighted coefficient of the impact of extreme weather on the sampling frequency, The value range is [0.1,1], is the ceiling function, It is the change in extreme weather conditions, which is obtained according to the extreme degree of meteorological data. The extreme degree of meteorological data is obtained by the deviation between the received meteorological data and the meteorological standard data, that is:

[0078] ;

[0079] in, , , and Temperature extremes , extreme degree of precipitation , Humidity extremes and wind speed extremes The weight coefficient of The value range is [0.05,0.2], The value range is [0.01,0.1], The value range is [0.02,0.1], The value range is [0.01, 0.05]. The extreme degree of temperature, extreme degree of precipitation, extreme degree of humidity and extreme degree of wind speed are obtained by the deviation between the received meteorological data and the meteorological standard data. is the maximum value function;

[0080] The acquisition time of the environmental sensor is adjusted according to the dynamically adjusted acquisition frequency to obtain environmental data, and the flight frequency of the UAV is adjusted to meet the needs of the dynamically adjusted acquisition frequency, and the flight path is recorded to make the path consistent to collect spectral data.

[0081] Preferably, the specific steps of optimizing the transmission strategy include:

[0082] Regularly monitor network conditions in the target area, including signal strength, network latency, bandwidth, and communication stability, to detect abnormal network conditions, including signal loss and network disconnection, and assess current network quality;

[0083] According to the network quality and the drone flight area in the target area, select the wireless communication method for environmental sensors and remote sensing sensors. For example: LoRa is suitable for long-distance, low-data-rate communications; Wi-Fi is suitable for data transmission within a smaller range and provides higher bandwidth; cellular networks are suitable for scenarios with large ranges and require higher data transmission speeds and low latency;

[0084] Automatically select the communication mode according to the real-time network quality. For example, when the network signal is strong and the bandwidth is sufficient, Wi-Fi or cellular network is preferred; when the network is unstable or the distance is far, switch to LoRa or satellite communication;

[0085] The collected spectral data and environmental data are compressed to reduce the data volume and improve transmission efficiency; the data transmission rate is dynamically adjusted according to the real-time network bandwidth and delay to ensure that transmission interruptions are avoided when the network is congested and to maintain the stability of data transmission.

[0086] The data processing module is used to pre-process the multidimensional data set, select key indicators according to the crop type in the target area, gradually screen and mark the abnormal points of key indicators according to the key indicators, identify the abnormal clustering areas, and fit the operating parameters of the gates in the abnormal clustering areas by establishing a key indicator change model.

[0087] In this embodiment, the collected spectral data and environmental data are first preprocessed, including denoising, filtering and standardization. Subsequently, the preprocessed data is further analyzed by multivariate analysis method, and the potential abnormal conditions, such as low field liquid level or abnormal crop growth, are identified in combination with machine learning algorithms. The machine learning algorithms used include cluster analysis and anomaly detection algorithms. If the data processing module detects an abnormal condition, an alarm mechanism will be triggered to promptly notify relevant personnel for processing. In order to improve the accuracy of the early warning, the detected abnormal conditions are used to establish a key indicator change model using historical meteorological data and key indicator data, and the opening time and cumulative flow of the gate in the abnormal aggregation area are obtained through a comprehensive analysis of meteorological conditions and soil moisture.

[0088] Preferably, the data processing module includes a preprocessing unit, an anomaly detection unit and a predictive modeling unit;

[0089] The preprocessing unit is configured with a data cleaning strategy, which is used to preprocess the collected multidimensional data sets, including data denoising, data interpolation and data standardization, to remove data errors in the multidimensional data sets and improve data quality to ensure the accuracy of subsequent analysis models;

[0090] A multi-level recognition strategy is configured in the anomaly detection unit. The multi-level recognition strategy is used to identify abnormal conditions of key indicators in the multidimensional data set that has undergone data preprocessing. The multi-level recognition judgment gradually screens and marks abnormal data points to identify abnormal clustering areas.

[0091] A multidimensional analysis strategy is configured in the predictive modeling unit. The multidimensional analysis strategy obtains gate usage information, combines historical meteorological data to establish a key indicator change model, and fits the model to estimate the impact coefficient, so as to obtain the gate operation parameters according to the key indicator requirements of the abnormal aggregation area.

[0092] Preferably, the specific steps of the data cleaning strategy include:

[0093] According to the data timestamp and coordinates in the multidimensional data set, the spectral data and environmental data in the multidimensional data set are fused, that is, the spectral data and the environmental data are spatially associated, the buffer radius is set with the key node where the environmental sensor is located as the center, the spectral data is divided into regions, and the original image data is converted into regular grid data using a spatial interpolation algorithm, so as to extract the spectral data of the corresponding area of ​​each key node. Exemplarily, at the same timestamp, the target area is divided into multiple sub-areas according to the coordinates of the environmental data, and for each sub-area, the spectral data in the sub-area is averaged to synthesize the spectral data of each sub-area into a representative spectral data for subsequent analysis, to ensure the regional consistency of the data, and to achieve the coordinate alignment of the environmental data and the spectral data;

[0094] The multidimensional data sets after data integration are cleaned and denoised. Noise filtering technology is used to remove random noise in the multidimensional data sets to ensure the smoothness and availability of the data. For spectral data, bandpass filters and smoothing filters are used to reduce the impact of environmental interference.

[0095] Use statistical methods to check each dimension in the multidimensional dataset, detect and mark missing values. For the environmental data in the multidimensional dataset, use forward filling, backward filling, linear interpolation and other methods to interpolate; for spectral data, use spatial interpolation methods, including IDW interpolation and Kriging interpolation, to estimate missing values ​​based on the spectral data of surrounding adjacent locations to ensure the spatial consistency of spectral data;

[0096] The spectral data and environmental data collected from different sensors are standardized to eliminate the unit differences between different sensors and ensure that all data are in the same dimension to facilitate subsequent analysis and model training.

[0097] See also Figure 3 , Figure 4 , preferably, the specific steps of the multi-level identification strategy include:

[0098] Configure the time threshold to determine the time period obtained from the multidimensional data set, extract the multidimensional data points within the time threshold range from the current timestamp from the multidimensional data set, and form the anomaly recognition data set, that is:

[0099] ;

[0100] in, is an anomaly recognition dataset, It is the first Timestamp Multidimensional data points at coordinate positions, including crop chlorophyll content, crop moisture content, crop growth index, air temperature, soil temperature, air humidity, soil humidity, light intensity, carbon dioxide concentration and field liquid level, It is The timestamp of the time location, is the current timestamp, It is a time threshold. By setting a time threshold, a time period is defined, and multi-dimensional data points between the current timestamp and the time period are extracted to form an anomaly identification data set for anomaly detection. This narrows the scope of the data and ensures that only the data within the most recent time window is focused on, thereby improving the timeliness and pertinence of anomaly detection.

[0101] Select key indicators that affect crop growth based on the crop types in the target area. The crop types include aquatic crops and non-aquatic crops. For aquatic crops, the field liquid level is selected as the key indicator that affects crop growth. For non-aquatic crops, soil moisture is selected as the key indicator that affects crop growth.

[0102] Based on the growth stage of crops in the target area, indicator thresholds are configured, including the indicator upper threshold and the indicator lower threshold, and preliminary anomaly detection is performed on the anomaly identification data set. If the key indicator of the multidimensional data point in the anomaly identification data set is greater than the indicator upper threshold or less than the indicator lower threshold, the data point is marked as a potential anomaly point to identify the key indicator anomaly in the target area and provide clues for subsequent in-depth analysis.

[0103] Use time series analysis to fit the long-term trends of key indicators in multidimensional data sets to describe the long-term change patterns of key indicators and calculate the trend deviations between the key indicators at potential abnormal points and the fitted trend values, namely:

[0104] ;

[0105] in, It is Trend deviation of key indicators of potential outliers, It is Key indicators of potential anomalies, It is The fitting trend value of the key indicators of potential abnormal points is used to quantify the abnormal degree of the key indicators through trend deviation, which helps to further screen out the real abnormal points;

[0106] Configure the trend deviation threshold to evaluate the cause of the abnormality of the key indicators of potential anomalies. If the trend deviation of the key indicators of the potential anomaly is greater than the trend deviation threshold, it is marked as a mutation anomaly. Otherwise, it is marked as a trend anomaly. The abnormal nature of the potential anomaly is clarified through the trend deviation threshold to provide guidance for subsequent analysis.

[0107] Configure the neighborhood threshold to divide the neighborhood area range of mutation anomaly points and trend anomaly points for neighborhood analysis, and calculate the pattern similarity of the multidimensional data points in the mutation anomaly points and trend anomaly points and their neighborhood areas to determine whether there is an abnormal clustering pattern in space and discover regional or clustered abnormal phenomena. The calculation methods of pattern similarity include Euclidean distance, Manhattan distance, etc.

[0108] Configure the similarity threshold, count the number of multidimensional data points whose pattern similarity is greater than the similarity threshold in the neighborhood area, calculate the ratio of the number of multidimensional data points whose pattern similarity is greater than the similarity threshold in the neighborhood area to the total number of multidimensional data points in the neighborhood area, obtain the similarity frequency in the neighborhood area where the mutation anomaly point and the trend anomaly point are located, configure the frequency threshold, if the similarity frequency in the neighborhood area where the mutation anomaly point is located is greater than the frequency domain threshold, then the neighborhood area is marked as a mutation anomaly aggregation area, otherwise a mutation warning is issued for the mutation anomaly point, if the similarity frequency in the neighborhood area where the trend anomaly point is located is greater than the frequency domain threshold, then the neighborhood area is marked as a trend anomaly aggregation area, otherwise a trend warning is issued for the trend anomaly point, and the spatial agglomeration of abnormal patterns is identified through neighborhood analysis, so as to make more precise abnormality judgments for specific areas.

[0109] Output all multidimensional data points in the abnormal clustering area, which includes the mutation abnormal clustering area and the trend abnormal clustering area.

[0110] See also Figure 5 Preferably, the specific steps of the multidimensional analysis strategy include:

[0111] Obtain the usage information of the gates in the target area, including location coordinates, opening timestamp, closing timestamp, opening duration, water flow speed, and accumulated water flow;

[0112] Configure the impact area threshold and impact time threshold. The impact area threshold is used to measure the impact area of ​​the gate, and the impact time threshold is used to measure the time the gate acts on the impact area after use. Filter out the multidimensional data points within the gate impact area threshold and within the impact time threshold from the gate closing timestamp from the multidimensional data set to construct the impact data set.

[0113] The key indicator change model is constructed based on the impact data set combined with historical meteorological data. The key indicator change model is determined by the key indicators within the threshold of the gate impact area, the gate opening time, the cumulative flow of the gate, the distance between the multidimensional data point in the impact data set and the gate, and meteorological factors, namely:

[0114] ;

[0115] in, It is The closing timestamp of the multidimensional data points at the gate Post-impact time threshold The key indicators of It is Multidimensional data points at the gate opening timestamp The key indicators of is the gate opening time, is the accumulated water flow through the gate, It is The distance between the multidimensional data point and the gate, , , , They are the influence coefficients of opening time, cumulative water flow, location distance and meteorological factors on key indicators. The time range of influence , ]The comprehensive impact value of meteorological data, namely:

[0116] ;

[0117] in, The time range of influence , ], the average temperature within The time range of influence , ], the average humidity in The time range of influence , ], the average wind speed within The time range of influence , ], , , , They are the influence coefficients of average temperature, average humidity, average wind speed, and cumulative precipitation data on the comprehensive impact value;

[0118] The key indicator change model is fitted according to the impact data set, each impact coefficient is estimated, and the opening time and cumulative flow of the gates in the abnormal clustering area are solved based on the multi-dimensional data points in the abnormal clustering area and its required key indicators.

[0119] The execution feedback module generates execution instructions for the gates based on the operating parameters of the gates in the abnormal concentration area, monitors the execution status of the gates through the status sensors installed on the gates, issues abnormal warnings for gates with execution abnormalities, and transmits the execution results to the data processing module through the Internet of Things device to update the execution instructions;

[0120] In this embodiment, the execution feedback module generates the execution instruction of the gate based on the operating parameters of the gate in the abnormal gathering area. Through the Internet of Things device, the execution instruction is sent to the gate in the form of a digital signal to instruct it to open, close or adjust the flow. Through the state sensor installed on the gate, the switch state, flow and other key information of the gate are monitored and fed back in real time. The sensor types include flow sensor, pressure sensor, position sensor, etc. This information is transmitted to the data processing module in real time through the Internet of Things device to ensure that the execution of the control signal is fed back in time. Through continuous monitoring of the state sensor data, it is determined whether the gate has an execution anomaly, such as failure to switch according to the instruction or the flow rate is not up to standard. If an abnormality is found, the system will automatically trigger an early warning and notify relevant personnel to handle it. When an execution deviation is detected, the control system will dynamically adjust the control strategy of the gate according to the feedback information to ensure the normal operation of the irrigation system. In addition, the execution feedback module will update the execution of the control strategy and the new environmental data to the data processing module synchronously as an important basis for adjusting the water resource demand. According to these feedback data and real-time monitoring information, the water resource demand of the target area is adjusted, thereby further optimizing the water-saving strategy.

[0121] Preferably, the execution feedback module includes an instruction generation unit, a state detection unit and a data update unit;

[0122] The instruction generation unit is configured with an instruction optimization strategy, which generates gate execution instructions based on the gate's operating parameters and transmits instructions for opening, closing or adjusting flow to the gate through the IoT device;

[0123] The state detection unit is equipped with a real-time feedback strategy. The real-time feedback strategy collects the key parameters of the gate, including the switch state, flow rate, and pressure, through the state sensor installed on the gate, detects the execution deviation and makes abnormal judgments, so as to automatically trigger abnormal warnings.

[0124] A feedback adjustment strategy is configured in the data update unit. The feedback adjustment strategy is used to collect spectral data and environmental data after the execution of the instructions, and transmit them to the data processing module through the Internet of Things device to update the water resource demand in the target area and obtain new execution instructions for the gate.

[0125] Preferably, the specific steps of the instruction optimization strategy include:

[0126] Receive the gate opening time and accumulated water flow in the abnormal concentration area, and obtain the gate location coordinates, and obtain the crop growth stage in the multidimensional data points within the gate influence area threshold according to the gate location coordinates;

[0127] The water flow rate threshold is set according to the crop growth stage. Crops at different growth stages have different requirements for water flow rate. For example, a lower water flow rate is required in the seedling stage, while a higher water flow rate is required in the vegetative growth stage.

[0128] According to the gate opening time and the accumulated water flow, the average flow is calculated, that is: ,in, is the average flow rate of the gate, is the cumulative flow of the gate, is the duration of the gate opening;

[0129] According to the default opening of the gate, combined with the average flow, the water flow rate is calculated, that is: ,in, is the water flow rate at the default gate opening, is the default opening of the gate;

[0130] If the water flow rate at the default gate opening is greater than the water flow rate threshold, the gate opening is adjusted, that is: ,in, is the opening of the gate after adjustment, is the water flow rate threshold, and outputs the adjusted gate opening and water flow rate threshold, otherwise outputs the default gate opening and water flow rate;

[0131] An execution instruction is generated based on the gate opening and water flow rate, including the gate opening time, accumulated water flow, opening and water flow rate.

[0132] Preferably, the specific steps of the real-time feedback strategy include:

[0133] Through the flow sensor, pressure sensor and switch status sensor on the gate, key data in the process of executing instructions are collected in real time, including: flow data, switch status data and pressure data;

[0134] Configure the flow rate deviation threshold to detect the actual water flow rate passing through the gate in real time. If the deviation from the water flow rate of the execution instruction is greater than the flow rate deviation threshold, a flow rate warning is issued;

[0135] Configure the flow deviation threshold, count the actual flow through the gate when the opening time is met, calculate the flow deviation between the actual flow and the cumulative flow of the execution instruction, and issue a flow warning if the flow deviation is greater than the flow deviation threshold;

[0136] The warning information is notified to the management personnel or farm operators via SMS or email for manual intervention.

[0137] Preferably, the specific steps of the feedback adjustment strategy include:

[0138] Configuring feedback thresholds , before the execution of the instruction ends After a period of time, the spectral data and environmental data of the abnormal clustering area are collected to detect crop growth and soil changes;

[0139] The collected data will be transmitted to the central data platform through IoT devices for cleaning, standardization and exception processing. Based on changes in key indicators and meteorological conditions, the control instructions of the gates will be regenerated to optimize the irrigation effect.

[0140] Example 2

[0141] See also Figure 6 This embodiment introduces a remote control method for an intelligent gate based on remote sensing and Internet of Things technology, which includes the following steps:

[0142] Step S1: Using intelligent sampling strategies, the spectral data of the target area is captured by the remote sensing sensor carried by the drone, the environmental data of the target area is captured by the environmental sensors deployed at the key nodes in the target area, and the spectral data and environmental data are transmitted to the central data platform through the Internet of Things devices for aggregation to construct a multidimensional data set;

[0143] Step S2: After preprocessing the multidimensional data set, select key indicators according to the crop type in the target area, gradually screen and mark the abnormal points of key indicators according to the key indicators, identify the abnormal clustering area, and fit the operating parameters of the gate in the abnormal clustering area by establishing a key indicator change model;

[0144] Step S3: Generate execution instructions for the gates based on the operating parameters of the gates in the abnormal concentration area, monitor the execution status of the gates through the status sensors installed on the gates, issue abnormal warnings for gates with execution abnormalities, and transmit the execution results to the data processing module through the Internet of Things device to update the execution instructions.

[0145] Specifically, the specific steps for acquiring spectral data and environmental data include:

[0146] Set the initial sampling frequency according to the crop’s growth stage;

[0147] Receive meteorological data, and dynamically adjust the sampling frequency according to the change amount of meteorological data and the change amount of extreme weather conditions, wherein the change amount of meteorological data includes the change amount of temperature, the change amount of precipitation, the change amount of humidity and the change amount of wind speed, and the change amount of extreme weather conditions is obtained according to the extreme degree of meteorological data, and the extreme degree of meteorological data is obtained by the deviation between the received meteorological data and the meteorological standard data;

[0148] The acquisition time of the environmental sensor is adjusted according to the dynamically adjusted acquisition frequency to obtain environmental data, and the flight frequency of the UAV is adjusted to meet the needs of the dynamically adjusted acquisition frequency, and the flight path is recorded to make the path consistent to collect spectral data.

[0149] Specifically, the specific steps for obtaining the abnormal clustering area include:

[0150] Configure the time threshold, extract the multidimensional data points within the time threshold from the current timestamp from the multidimensional data set, and form an anomaly recognition data set;

[0151] Select key indicators that affect crop growth based on the crop types in the target area. The crop types include aquatic crops and non-aquatic crops. For aquatic crops, the field liquid level is selected as the key indicator that affects crop growth. For non-aquatic crops, soil moisture is selected as the key indicator that affects crop growth.

[0152] Based on the growth stage of the crops in the target area, the indicator thresholds are configured, including the indicator upper threshold and the indicator lower threshold, and preliminary anomaly detection is performed on the anomaly identification data set. If the key indicator of the multidimensional data point in the anomaly identification data set is greater than the indicator upper threshold or less than the indicator lower threshold, the data point is marked as a potential anomaly point;

[0153] Use time series analysis to fit the long-term trends of key indicators in multidimensional data sets and calculate the trend deviations of key indicators at potential outliers from the fitted trend values;

[0154] Configure the trend deviation threshold to evaluate the cause of abnormal key indicators of potential anomalies. If the trend deviation of the key indicators of potential anomalies is greater than the trend deviation threshold, it is marked as a mutation anomaly; otherwise, it is marked as a trend anomaly.

[0155] Configure the neighborhood threshold to divide the neighborhood area range of mutation anomaly points and trend anomaly points for neighborhood analysis, and calculate the pattern similarity between mutation anomaly points and trend anomaly points and the multi-dimensional data points in their neighborhood areas;

[0156] Configure a similarity threshold, count the number of multidimensional data points in the neighborhood whose pattern similarity is greater than the similarity threshold, and calculate the ratio of the number of multidimensional data points in the neighborhood whose pattern similarity is greater than the similarity threshold to the total number of multidimensional data points in the neighborhood to obtain the similarity frequency in the neighborhood where the mutation anomaly point and the trend anomaly point are located;

[0157] Configure the frequency threshold. If the similar frequency in the neighborhood area where the mutation anomaly point is located is greater than the frequency domain threshold, the neighborhood area is marked as a mutation anomaly aggregation area. Otherwise, a mutation warning is issued for the mutation anomaly point. If the similar frequency in the neighborhood area where the trend anomaly point is located is greater than the frequency domain threshold, the neighborhood area is marked as a trend anomaly aggregation area. Otherwise, a trend warning is issued for the trend anomaly point.

[0158] Output all multidimensional data points in the abnormal clustering area, which includes the mutation abnormal clustering area and the trend abnormal clustering area.

[0159] Specifically, the specific steps for constructing the key indicator change model include:

[0160] Obtain the usage information of the gates in the target area, including location coordinates, opening timestamp, closing timestamp, opening duration, water flow speed, and accumulated water flow;

[0161] Configure the impact area threshold and the impact time threshold, filter out the multidimensional data points within the gate impact area threshold and within the impact time threshold from the gate closing timestamp from the multidimensional data set, so as to construct the impact data set;

[0162] A key indicator change model is constructed based on the impact data set combined with historical meteorological data. The key indicator change model is determined by the key indicators within the threshold of the gate impact area, the gate opening time, the accumulated flow of the gate, the distance between the multidimensional data points in the impact data set and the gate, and meteorological factors.

[0163] The meteorological factor is the comprehensive impact value of meteorological data within the influencing time range, which is jointly determined by the average temperature, average humidity, average wind speed and accumulated precipitation within the influencing time range;

[0164] According to the impact data set, the key indicator change model is fitted to estimate each impact coefficient, and based on the multi-dimensional data points of the abnormal aggregation area and its required key indicators, the abnormal aggregation area includes the mutation abnormal aggregation area and the trend abnormal aggregation area, the gate opening time and cumulative flow volume in the abnormal aggregation area are solved.

[0165] Working principle and its effect:

[0166] The intelligent gate remote control method and system based on remote sensing and Internet of Things technology realizes efficient water resource management through three main modules, ensures reasonable irrigation, and thus achieves the purpose of water saving.

[0167] The data acquisition module uses the remote sensing sensors carried by drones to obtain spectral data, and combines with environmental sensors deployed at key nodes to collect meteorological and environmental data. According to the crop growth status and weather conditions, the intelligent sampling strategy dynamically adjusts the sampling frequency and range to optimize data collection. Through the IoT devices, the collected data is quickly transmitted to the central data platform to ensure the real-time and accuracy of the data. The data processing module cleans and formats the collected multidimensional data for subsequent analysis. A multi-level recognition strategy is used to identify abnormal conditions of key indicators, potential abnormal points are marked by set upper and lower humidity thresholds, and trend analysis is performed to identify abnormal clustering areas. Combining the key indicator change model with historical meteorological data, the operating parameters of the gate, such as the calculation of opening time and flow, are generated based on the needs of the abnormal clustering area. The execution feedback module formulates corresponding execution instructions based on the operating parameters generated by the data processing module and transmits them through the IoT devices. The execution of the gate is monitored in real time, execution deviations are detected in time, and early warnings are triggered. Feedback the execution results, update the water resource demand of the target area, and continuously optimize the execution instructions.

[0168] By accurately monitoring key indicators and environmental changes, it is possible to effectively determine when irrigation is needed and reduce water waste. The combination of drones and sensors automates data collection, and real-time data feedback helps to quickly respond to complex environmental changes. Through intelligent irrigation for specific growth stages and conditions, the use of water resources is optimized, thereby improving crop growth and output. Reasonable management of irrigation water volume, avoiding unnecessary water flow, reducing the risk of salinization of soil and water bodies, and protecting the ecological environment. By integrating advanced sensing technology, big data analysis, and intelligent control algorithms, intelligent water resource management is achieved, which not only promotes sustainable agricultural development, but also helps to meet the challenges brought by climate change.

[0169] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. Intelligent gate remote control system based on remote sensing and Internet of Things technology, characterized by: It includes a data acquisition module, a data processing module and an execution feedback module; The data acquisition module uses an intelligent sampling strategy to capture the spectral data of the target area through the remote sensing sensor carried by the drone, captures the environmental data of the target area through the environmental sensors deployed at the key nodes in the target area, and transmits the spectral data and environmental data to the central data platform through the Internet of Things device for aggregation to construct a multidimensional data set; The data processing module is used to select key indicators according to the crop type of the target area after preprocessing the multidimensional data set, gradually screen and mark the abnormal points of the key indicators according to the key indicators, identify the abnormal aggregation area, and fit the operating parameters of the gate in the abnormal aggregation area by establishing a key indicator change model; The execution feedback module generates execution instructions for the gates based on the operating parameters of the gates in the abnormal aggregation area, monitors the execution status of the gates through status sensors installed on the gates, issues abnormal warnings for gates with execution abnormalities, and transmits the execution results to the data processing module through the Internet of Things device to update the execution instructions.

2. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 1 is characterized in that: The data acquisition module includes a data acquisition unit and a data transmission unit; The intelligent sampling strategy is configured in the data acquisition unit, and the intelligent sampling strategy adjusts the sampling frequency and range according to the crop growth cycle and meteorological conditions of the target area, collects spectral data and environmental data through UAV flight planning and sensor automatic control, and records the timestamps and location coordinates of the spectral data and environmental data acquisition; The data transmission unit is configured with an optimized transmission strategy, which selects a wireless communication method through an IoT device according to network conditions to transmit spectral data and environmental data to a central data platform.

3. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 2 is characterized in that: The steps of the intelligent sampling strategy include: Set the initial sampling frequency according to the growth stage of the crop; Receive meteorological data, and dynamically adjust the sampling frequency according to the change amount of meteorological data and the change amount of extreme weather conditions, wherein the change amount of meteorological data includes the change amount of temperature, the change amount of precipitation, the change amount of humidity and the change amount of wind speed, and the change amount of extreme weather conditions is obtained according to the extreme degree of meteorological data, and the extreme degree of meteorological data is obtained by the deviation between the received meteorological data and the meteorological standard data; The acquisition time of the environmental sensor is adjusted according to the dynamically adjusted acquisition frequency to obtain environmental data, and the flight frequency of the UAV is adjusted to meet the needs of the dynamically adjusted acquisition frequency, and the flight path is recorded to collect spectral data.

4. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 1 is characterized in that: The data processing module includes a preprocessing unit, an anomaly detection unit and a prediction modeling unit; The anomaly detection unit is configured with a multi-level recognition strategy, which is used to identify abnormal conditions of key indicators in the multi-dimensional data set that has undergone data preprocessing, and to gradually screen and mark abnormal data points through multi-level recognition judgment to identify abnormal clustering areas; A multidimensional analysis strategy is configured in the predictive modeling unit. The multidimensional analysis strategy obtains gate usage information, establishes a key indicator change model in combination with historical meteorological data, and fits the model to estimate the impact coefficient, so as to obtain the gate operating parameters according to the key indicator requirements of the abnormal aggregation area.

5. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 4 is characterized in that: The steps of the multi-level identification strategy include: Configure the time threshold, extract the multidimensional data points within the time threshold from the current timestamp from the multidimensional data set, and form an anomaly recognition data set; Select key indicators that affect crop growth based on the crop types in the target area. The crop types include aquatic crops and non-aquatic crops. For aquatic crops, the field liquid level is selected as the key indicator that affects crop growth. For non-aquatic crops, soil moisture is selected as the key indicator that affects crop growth. Based on the growth stage of the crops in the target area, the indicator thresholds are configured, including the indicator upper threshold and the indicator lower threshold, and preliminary anomaly detection is performed on the anomaly identification data set. If the key indicator of the multidimensional data point in the anomaly identification data set is greater than the indicator upper threshold or less than the indicator lower threshold, the data point is marked as a potential anomaly point; Use time series analysis to fit the long-term trends of key indicators in multidimensional data sets and calculate the trend deviations of key indicators at potential outliers from the fitted trend values; Configure the trend deviation threshold to evaluate the cause of abnormal key indicators of potential anomalies. If the trend deviation of the key indicators of potential anomalies is greater than the trend deviation threshold, it is marked as a mutation anomaly; otherwise, it is marked as a trend anomaly.

6. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 5, characterized in that: The steps of the multi-level identification strategy also include: Configure the neighborhood threshold to divide the neighborhood area range of mutation anomaly points and trend anomaly points for neighborhood analysis, and calculate the pattern similarity between mutation anomaly points and trend anomaly points and the multi-dimensional data points in their neighborhood areas; Configure a similarity threshold, count the number of multidimensional data points in the neighborhood whose pattern similarity is greater than the similarity threshold, and calculate the ratio of the number of multidimensional data points in the neighborhood whose pattern similarity is greater than the similarity threshold to the total number of multidimensional data points in the neighborhood to obtain the similarity frequency in the neighborhood where the mutation anomaly point and the trend anomaly point are located; Configure the frequency threshold. If the similar frequency in the neighborhood area where the mutation anomaly point is located is greater than the frequency domain threshold, the neighborhood area is marked as a mutation anomaly aggregation area. Otherwise, a mutation warning is issued for the mutation anomaly point. If the similar frequency in the neighborhood area where the trend anomaly point is located is greater than the frequency domain threshold, the neighborhood area is marked as a trend anomaly aggregation area. Otherwise, a trend warning is issued for the trend anomaly point. Output all multidimensional data points in the abnormal clustering area, which includes the mutation abnormal clustering area and the trend abnormal clustering area.

7. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 4, characterized in that: The steps of the multidimensional analysis strategy include: Obtain the usage information of the gates in the target area, including location coordinates, opening timestamp, closing timestamp, opening duration, water flow speed, and accumulated water flow; Configure the impact area threshold and the impact time threshold, filter out the multidimensional data points within the gate impact area threshold and within the impact time threshold from the gate closing timestamp from the multidimensional data set, so as to construct the impact data set; A key indicator change model is constructed based on the impact data set combined with historical meteorological data. The key indicator change model is determined by the key indicators within the threshold of the gate impact area, the gate opening time, the accumulated flow of the gate, the distance between the multidimensional data points in the impact data set and the gate, and meteorological factors. The meteorological factor is the comprehensive impact value of meteorological data within the influencing time range, which is jointly determined by the average temperature, average humidity, average wind speed and accumulated precipitation within the influencing time range; According to the impact data set, the key indicator change model is fitted to estimate each impact coefficient, and based on the multi-dimensional data points of the abnormal aggregation area and its required key indicators, the abnormal aggregation area includes the mutation abnormal aggregation area and the trend abnormal aggregation area, the gate opening time and cumulative flow volume in the abnormal aggregation area are solved.

8. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 7, characterized in that: The execution feedback module includes an instruction generation unit, a state detection unit and a data update unit; The instruction generation unit is configured with an instruction optimization strategy, which generates gate execution instructions based on the operating parameters of the gate, and transmits instructions for opening, closing or adjusting the flow through the Internet of Things device; The state detection unit is configured with a real-time feedback strategy, which collects key parameters of the gate through the state sensor installed on the gate, detects execution deviations and makes abnormal judgments, so as to automatically trigger abnormal warnings; The data update unit is configured with a feedback adjustment strategy, which is used to collect spectral data and environmental data after the execution of the instruction, and transmit them to the data processing module through the Internet of Things device to update the water resource demand of the target area and obtain new gate execution instructions.

9. The intelligent gate remote control system based on remote sensing and Internet of Things technology as claimed in claim 8, characterized in that: The specific steps of the instruction optimization strategy include: Receive the gate opening time and accumulated water flow in the abnormal concentration area, and obtain the gate location coordinates, and obtain the crop growth stage in the multidimensional data points within the gate influence area threshold according to the gate location coordinates; The water flow rate threshold is set according to the crop growth stage, and the average flow rate is calculated based on the gate opening time and the accumulated water flow; Calculate the water flow rate based on the default opening of the gate and the average flow rate; If the water flow rate at the default gate opening is greater than the water flow rate threshold, the gate opening is adjusted according to the ratio of the average flow rate of the gate to the water flow rate threshold, and the adjusted gate opening and water flow rate threshold are output, otherwise the gate default opening and water flow rate are output; An execution instruction is generated based on the gate opening and water flow rate, including the gate opening time, accumulated water flow, opening and water flow rate.

10. A remote control method for an intelligent gate based on remote sensing and Internet of Things technology, which is implemented based on the remote control system for an intelligent gate based on remote sensing and Internet of Things technology described in any one of claims 1 to 9, characterized in that: The following steps are involved: Step S1: Using intelligent sampling strategies, the spectral data of the target area is captured by the remote sensing sensor carried by the drone, the environmental data of the target area is captured by the environmental sensors deployed at the key nodes in the target area, and the spectral data and environmental data are transmitted to the central data platform through the Internet of Things devices for aggregation to construct a multidimensional data set; Step S2: After preprocessing the multidimensional data set, select key indicators according to the crop type in the target area, gradually screen and mark the abnormal points of key indicators according to the key indicators, identify the abnormal clustering area, and fit the operating parameters of the gate in the abnormal clustering area by establishing a key indicator change model; Step S3: Generate execution instructions for the gates based on the operating parameters of the gates in the abnormal concentration area, monitor the execution status of the gates through the status sensors installed on the gates, issue abnormal warnings for gates with execution abnormalities, and transmit the execution results to the data processing module through the Internet of Things device to update the execution instructions.

Images