Agricultural ecological environment monitoring method and system based on digital twinborn

Abstract

The invention relates to the technical field of ecological monitoring, in particular to an agricultural ecological environment monitoring method and system based on digital twinning, and the method comprises the following steps: obtaining monitoring data in a farmland, constructing a mapping relation, carrying out time sequence arrangement, merging multi-source data, calling a virtual grid to update a three-dimensional model, generating a mapping result, and analyzing a crop growth image. And tracking environmental changes, comparing ecological stability intervals, extracting risk trends, calling the three-dimensional model, and generating a risk early warning interface layer. According to the method, the continuous data of the agricultural ecological environment is acquired, and the mapping relation is constructed to perform time sequence arrangement on the information, so that the response speed and the processing precision of the change of the agricultural ecological environment are improved, the monitoring and management of the crop growth environment are optimized, and the environment change can be visually displayed through the expression of the real-time updated three-dimensional environment model; by comparing humidity and temperature changes and screening space segments, careful monitoring and accurate early warning of environmental changes are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological monitoring, and in particular to an agricultural ecological environment monitoring method and system based on digital twin. Background Art

[0002] The technical field of ecological monitoring includes the monitoring and management of various elements in the agricultural ecological environment, including the tracking and analysis of factors such as soil quality, climate change, crop growth, and irrigation status. The core content of this field is to comprehensively and real-time monitor and collect data on the agricultural ecological environment through means such as sensors, remote sensing technology, and information and communication technology, to ensure effective control of various environmental impact factors in the agricultural production process. Agricultural ecological environment monitoring technology not only covers the monitoring of natural environmental elements such as soil, air, and water quality, but also includes the potential environmental impacts of waste and pesticide use generated in agricultural production activities. Through the collection, processing, and analysis of monitoring data, it can provide a scientific basis for agricultural production management and help formulate sustainable agricultural development strategies.

[0003] Among them, the agricultural ecological environment monitoring method refers to a technical solution for dynamically monitoring and analyzing various environmental elements in the agricultural ecological environment through specific technical means. The technical matters targeted by this technical theme cover aspects such as agricultural soil quality monitoring, crop growth status, and meteorological condition changes. Environmental data is collected through sensors and transmitted through a wireless network. Combining data storage and processing technology, the collected data is monitored and analyzed in real time. This patent solution mainly obtains various environmental data through automated monitoring devices and transmits the data to a monitoring platform for analysis and processing to achieve real-time supervision and early warning of the agricultural ecological environment.

[0004] The existing technology has deficiencies in the dynamic and refined management of the agricultural ecological environment. Although traditional technologies can collect data through sensors and remote sensing technology, they lack efficiency and accuracy in data integration, real-time update, and in-depth fusion of multi-source information. This limitation results in a lack of timely or accurate response to changes in the agricultural ecological environment, and the inability to make efficient decisions by fully utilizing the collected data, thereby affecting the yield and quality of crops. In the case of failure to update and accurately analyze environmental data in real time, the response measures to sudden climate changes and abnormal environmental conditions are delayed or inadequate, resulting in double losses in agricultural production efficiency and environmental protection measures. Summary of the Invention

[0005] The object of the present invention is to solve the shortcomings existing in the prior art and propose an agricultural ecological environment monitoring method and system based on digital twin.

[0006] To achieve the above object, the present invention adopts the following technical solution, an agricultural ecological environment monitoring method based on digital twin, comprising the following steps: S1: Obtain the continuous data of the soil humidity monitor, temperature sensor and meteorological collection device deployed in the farmland area, construct the corresponding mapping relationship through the sensor number identification, arrange the collected information in time series, and generate an ecological environment synchronous scene image; S2: According to the spatial grid coordinates corresponding to the humidity, temperature and meteorological conditions recorded in the ecological environment synchronous scene image, call the regional virtual grid built in the digital twin, dock the synchronous information of the real scene sensor, and update the performance of the regional three-dimensional environment model according to the real-time environment information to generate a farmland area mapping result; S3: Based on the synchronous state trajectory of the grid entity in the farmland area mapping result, by comparing the change gradients of the humidity and air temperature performance between different differential time points, screen the spatial segments with continuous fluctuation amplitudes, analyze the crop growth images within the spatial segments, and generate an environmental response sensitivity distribution map; S4: Call the block node numbers in the environmental response sensitivity distribution map, track the synchronous evolution process of the humidity drop section and the air temperature rise node, compare the change amplitude curve with the set ecological stability interval section by section, and generate an agricultural ecological environment risk trend identification result.

[0007] As a further solution of the present invention, the ecological environment synchronous scene image includes a spatial feature grid, a time series alignment segment, and a multi-source data fusion area. The farmland area mapping result includes a grid number status set, a real-time environmental parameter group, and a three-dimensional structure performance set. The environmental response sensitivity distribution map includes a parameter change highlight area, a crop status response area, and an environmental factor interference zone. The agricultural ecological environment risk trend identification result includes an offset area number, a trend curve change amount, and an ecological index change section.

[0008] As a further solution of the present invention, the specific steps for obtaining the ecological environment synchronous scene image are as follows: S111: Obtain the continuous data of the soil humidity monitor, temperature sensor and meteorological collection device deployed in the farmland area, evaluate the mapping relationship between the device number and the data record after adding the number identification, and perform a sorting operation on the data record according to the time stamp field to generate a sensor time series number data set; S112: Call the data records corresponding to the device numbers in the sensor time series number data set, screen the soil humidity, temperature and meteorological data entries with overlapping time stamps, perform a pairing operation on the time-overlapping data according to the spatial coordinates of the data record, and perform a combination process on the data record based on the spatial coordinate matching result as a judgment condition to generate an overlapping space-time joint value list; S113: According to the spatial coordinate field and time field in the overlapping spatio-temporal joint value list, use the coordinates as the image pixel numbers, map the time field to the image frame sequence number, and map each type of value to a color channel according to the pixel ratio to generate an ecological environment synchronous scene image.

[0009] As a further solution of the present invention, the steps for obtaining the mapping result of the farmland area are specifically as follows: S211: Use the humidity, temperature, and meteorological condition data in the ecological environment synchronous scene image, call the regional virtual grid coordinates built in the digital twin, evaluate the mapping relationship between the grid coordinates and the sensor data, and generate a grid-based environmental parameter set; S212: Based on the grid-based environmental parameter set, extract the soil hydraulic conductivity, crop coefficient, and evapotranspiration in the multi-region parameter mapping information, and use the formula: ; Calculate the environmental volatility, compare the environmental volatility with the material response threshold of the regional three-dimensional model, and generate a regional dynamic response scalar; Wherein, is the environmental volatility, represents the temperature measurement value, represents the grid weight factor, represents the measured value of the soil hydraulic conductivity, represents the measured average value of evapotranspiration, represents the quantified value of meteorological conditions, represents the crop growth stage coefficient, represents the humidity percentage value; S213: Call the regional dynamic response scalar, and update the texture resolution of the three-dimensional environmental model according to the light intensity and wind speed in the real-time environmental information to generate the mapping result of the farmland area.

[0010] As a further solution of the present invention, the steps for obtaining the environmental response sensitivity distribution map are specifically as follows: S311: Based on the synchronous state trajectory of the grid entities in the mapping result of the farmland area, call the humidity and air temperature records of the grid cells in the time dimension, compare the fluctuation degrees of the humidity change rate and the air temperature change rate in a continuous time period, judge whether the continuous fluctuation amplitude exceeds the combined standard of the humidity fluctuation threshold and the air temperature fluctuation threshold, and screen the spatial segments that meet the combined standard conditions to generate a set of continuous fluctuation segments; S312: Call the spatial positions pointed to in the set of continuous fluctuation segments, perform image segmentation on the crop growth image, extract the crop entity boundaries in the image, and calculate the boundary morphological feature values and color distribution values, and judge whether there is a spatial offset phenomenon of structural change or color migration of the crop within the segment to obtain the crop offset feature distribution value; S313: Using the crop offset characteristic distribution value, calling the humidity change rate and temperature change rate corresponding to the continuous fluctuation segment set, performing difference calculation and combination judgment on the crop offset value and the environmental variable change rate, using the formula: ; Calculate the environmental response difference coefficient of the spatial segment, evaluate the correlation between the segment position and the environmental response difference coefficient, and obtain the environmental response sensitivity distribution map; in, Representative The environmental response variance coefficient of the fragments, Representative The crop offset feature distribution value of the fragment, For the The humidity change rate of the segment, For the The temperature change rate of the segment, For the Clip crop image Continuity factor for segment boundaries, is the number of boundary segments in the segment image.

[0011] As a further solution of the present invention, the steps for obtaining the agricultural ecological environment risk trend identification results are specifically as follows: S411: calling the block node number in the environmental response sensitive distribution map, extracting the humidity change data and the temperature change data corresponding to the block, comparing the humidity drop rate and the temperature rise rate node by node, analyzing the synchronous change trend of the humidity change rate and the temperature change rate, and obtaining the synchronous change trend comparison value; S412: According to the synchronous change trend control value, the continuous sections of the humidity drop rate and the temperature rise rate are extracted, the fluctuation range is divided according to the section, and the section difference is compared with the set ecological stability range, using the formula: ; Calculate the regional difference rate, classify and judge the regional difference rate and the interval stability setting boundary, record the consecutive numbered segments beyond the stable interval, and obtain the trend deviation area index sequence; in, represents the regional difference rate, Indicates The humidity change rate of the node, Indicates The temperature change rate of the node, Indicates The humidity fluctuation value of the node, Indicates The temperature fluctuation value of the node, Indicates The humidity range difference of the node, indicating the temperature range difference of the node, indicating the number of nodes in the section; S413: Based on the trend offset area index sequence, track the regional level number indicated, detect the distribution characteristics of the fluctuation trends of humidity and temperature in the area, compare the fluctuation directions and intensities, and obtain the agricultural ecological environment risk trend recognition result.

[0012] As a further solution of the present invention, the method further includes step S5: S5: According to the agricultural ecological environment risk trend recognition result, call the three-dimensional environment model in the digital twin interface, superimpose the meteorological condition animation layer and the soil state, judge whether the boundary change range of the warning block continuously expands, mark the highlighted area and the visible range on the interface, and obtain the agricultural ecological risk warning interface layer; The agricultural ecological risk warning interface layer includes a dynamic boundary layer, a highlighted visible area, and a risk level overlay map.

[0013] As a further solution of the present invention, the obtaining steps of the agricultural ecological risk warning interface layer are specifically: S511: According to the agricultural ecological environment risk trend recognition result, call the three-dimensional environment model in the digital twin interface, load the time series data of wind speed, rainfall, and temperature in the interface, and superimpose the soil humidity value, soil salinity value, and soil organic matter concentration layers to obtain the three-dimensional layer fusion coordinate distribution value; S512: Based on the three-dimensional layer fusion coordinate distribution value, obtain the difference between the meteorological layer parameters and the difference between the soil state layer parameters of the marked area in the real-time and the previous time period continuous frames, and judge the boundary change trend of the block according to the time axis for the difference sequence. Mark the block numbers of the continuous frames with the boundary expanding outward as the expanded area to obtain the continuous boundary expansion recognition result; S513: According to the continuous boundary expansion recognition result, extract the spatial coordinate set of the changed area in the digital twin interface, perform coordinate comparison within the visible range, set the width and color parameters of the highlighted block boundary line, highlight the area that meets the expansion determination condition in the interface, and set the layer name and display order to generate the agricultural ecological risk warning interface layer.

[0014] The digital twin-based agricultural ecological environment monitoring system is used to execute the above digital twin-based agricultural ecological environment monitoring method, and the system includes: The index recognition module obtains the continuous data of soil moisture monitors, temperature sensors, and meteorological collection devices deployed in the farmland area, establishes corresponding index relationships according to the sensor numbers, screens data groups in overlapping time intervals, and generates an ecological environment synchronous scenario image; Based on the calibrated spatial grid coordinates in the ecological environment synchronous scenario image, the virtual mapping module calls the regional virtual grid point numbers in the digital twin environment, compares the humidity values, temperature values, and meteorological parameter values between the grid points, and updates the environmental performance of the corresponding nodes in the 3D model to obtain the farmland area mapping result; The change recognition module calls the humidity change sequence and temperature change sequence of the virtual nodes in the farmland area mapping result, extracts the spatial segments with continuous changes according to the change values between adjacent time points, and generates an environmental response sensitivity distribution map; The trend analysis module extracts the humidity change trajectory and temperature change trajectory of the nodes according to the spatial node numbers marked in the environmental response sensitivity distribution map, identifies the change curves of the two change trajectories in the nodes, judges the change trend direction and amplitude, and generates an agricultural ecological environment risk trend recognition result; The risk warning module calls the spatial hierarchy numbers recorded in the agricultural ecological environment risk trend recognition result, matches the boundary nodes of the farmland area in the 3D model, overlays the meteorological parameter layer and soil moisture layer under the area, judges the boundary change situation of the area corresponding to the warning number, and obtains an agricultural ecological risk warning range layer.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by obtaining the continuous data of the agricultural ecological environment, constructing a mapping relationship to arrange the information in time sequence, and further combining and processing multi-source data in overlapping time intervals, the integration and application of data are made more efficient and accurate. The continuous data collection and composite analysis improve the response speed and processing accuracy to the changes in the agricultural ecological environment, and optimize the monitoring and management of the crop growth environment. Through the real-time updated 3D environmental model performance, the environmental changes can be intuitively displayed, improving the basis and accuracy of decision-making. By comparing the humidity and temperature changes, screening spatial segments, and generating an environmental response sensitivity distribution map, the detailed monitoring and accurate warning of environmental changes are strengthened, providing a dynamic and multi-dimensional monitoring perspective, with significant improvements in both spatial and temporal resolutions, greatly enhancing the effectiveness of risk warning and the adaptability of operations. Brief Description of the Drawings

[0016] Figure 1 It is a schematic diagram of the working process of the present invention; Figure 2 It is a flowchart for obtaining the ecological environment synchronous scenario image in the present invention; Figure 3It is the flowchart for obtaining the mapping result of the farmland area in the present invention; Figure 4 It is the flowchart for obtaining the environmental response sensitivity distribution map in the present invention; Figure 5 It is the flowchart for obtaining the identification result of the trend of agricultural ecological environment risk in the present invention; Figure 6 It is the flowchart for obtaining the layer of the agricultural ecological risk warning interface in the present invention. Specific embodiments

[0017] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0019] Please refer to Figure 1 , the present invention provides a technical solution, an agricultural ecological environment monitoring method based on digital twin, including the following steps: S1: Obtain the continuous data of the soil moisture monitor, temperature sensor and meteorological collection device deployed in the farmland area, construct the corresponding mapping relationship through the sensor number identification, arrange the collected information in time sequence, and merge the multi-source data with time overlapping intervals according to the spatial coordinates to generate an ecological environment synchronous scene image; S2: According to the spatial grid coordinates corresponding to the humidity, temperature and meteorological conditions recorded in the ecological environment synchronous scene image, call the regional virtual grid built in the digital twin, dock the synchronous information of the real scene sensor, identify the multi-region parameter mapping information, and update the performance of the regional three-dimensional environment model according to the real-time environmental information to generate the mapping result of the farmland area; S3: Based on the synchronous state trajectory of the grid entities in the mapping result of the farmland area, by comparing the change gradients of the humidity and air temperature performance between different differential time points, screen the spatial segments with continuous fluctuation amplitudes, analyze the crop growth images within the spatial segments, and locate the crop and environmental node blocks with synchronous differences to generate an environmental response sensitivity distribution map; S4: Call the block node numbers in the environmental response sensitivity distribution map, track the synchronous evolution process of the humidity drop section and the rising temperature nodes, compare the variation amplitude curve with the set ecological stability interval section by section, extract the regional level numbers with trend offsets, and generate the agricultural ecological environment risk trend identification results; S5: According to the agricultural ecological environment risk trend identification results, call the 3D environmental model in the digital twin interface, overlay the meteorological condition animation layer and the soil state, judge whether the boundary change range of the warning block continuously expands, mark the highlighted area and visible range on the interface, and obtain the agricultural ecological risk warning interface layer; The ecological environment synchronous scene image includes spatial feature grids, time series alignment segments, and multi-source data fusion areas. The farmland area mapping results include grid number status sets, real-time environmental parameter groups, and 3D structure representation sets. The environmental response sensitivity distribution map includes parameter change prominent areas, crop state response areas, and environmental factor interference zones. The agricultural ecological environment risk trend identification results include offset area numbers, trend curve change amounts, and ecological index change sections. The agricultural ecological risk warning interface layer includes dynamic boundary layers, highlighted visible areas, and risk level overlay maps.

[0020] Please refer to Figure 2 , and the specific steps for obtaining the ecological environment synchronous scene image are as follows: S111: Obtain the continuous data of the soil humidity monitor, temperature sensor, and meteorological collection device deployed in the farmland area, evaluate the mapping relationship between the device number and the data record after adding a number identifier, perform a sorting operation on the data record according to the timestamp field, and generate a sensor time series number data set; When obtaining continuous data from soil moisture monitors, temperature sensors, and meteorological collection devices deployed in farmland areas, it is necessary to clarify the deployment coordinates and their numbers of various sensors. Set the designated number of the soil moisture monitor as SM003, the number of the temperature sensor as TP001, and the numbers of the meteorological collection devices as WS001 - WS002. Read the continuous data content reported by each device, add the device number identifier to each data item, and then use the number as the primary key to establish a mapping structure between the number and the data record. During the reading process, first read the data content according to the sensor type, and perform data synchronization processing separately according to the data reporting periods set for each device. Set the humidity monitor to report 1 piece of data every 30 minutes, the temperature sensor every 15 minutes, and the meteorological collection device every 60 minutes. In the synchronized data structure, use the unified timestamp format as the alignment benchmark, standardize the upload time fields of each device to the UTC+8 time zone time format "YYYY-MM-DD HH:mm:ss", and then sort the records in ascending order according to this field to generate a time-series number dataset containing the mapping relationship among the number, data item, and timestamp, so that subsequent association operations can accurately index and match data. For example, for the record with the number SM001 and the collection time of 10:00:00 on April 16, 2025, the data value is 22.5% soil moisture, then the mapping entry is {device number: SM001, timestamp: 2025-04-16 10:00:00, soil moisture: 22.5}. Similarly, for the temperature data of 18.7°C collected by TP002 at the same time point, the corresponding mapping entry is {device number: TP002, timestamp: 2025-04-16 10:00:00, temperature: 18.7}. After the data is processed, it will be sorted in ascending order of time. Set that if multiple devices upload data at 10:00:00, 10:15:00, and 10:30:00 respectively, then arrange all data rows in the above time order to generate a sensor time-series number dataset.

[0021] S112: Call the data records corresponding to the device numbers in the sensor time-series number dataset, filter the soil moisture, temperature, and meteorological data entries with overlapping timestamps, perform a pairing operation on the time-overlapping data according to the spatial coordinates of the data records, and perform a combination process on the data records based on the spatial coordinate matching result as the judgment condition to generate a list of overlapping spatio-temporal combined values; Index all the time series data corresponding to the device number, and then perform an intersection screening on the timestamp fields of different types of sensor data. Set to read the records that coexist in the time series of devices SM002, TP001, and WS001. If data entries exist for all three at 10:00:00, 10:30:00, and 11:00:00 on April 16, 2025, then filter out the data with intersecting timestamps as the candidate set, and compare them based on their spatial coordinate information to determine whether the three sets of data are from sampling points with a geographical distance of no more than 10 meters. If the condition is met, combine the three types of data into a combined record. Set the coordinates of the three to be (35.712, 120.991), (35.713, 120.990), and (35.712, 120.992) respectively. Then calculate the distance by comparing their latitudes and longitudes [(35.712 - 35.713)²+(120.991 - 120.990)²]≈0.0014 degrees≈156 meters. Since it exceeds the threshold, it is determined that their spatial positions are inconsistent, and this set of data does not participate in the combination operation; conversely, if the distance between the three is less than or equal to 10 meters, combine them into a spatio-temporal combined value record. Set at the time point of 10:30:00, SM002 = 21.9%, TP001 = 17.6°C, WS001 = wind speed 3.2 m / s, rainfall 1.5 mm. Then the corresponding combined record is {timestamp: 2025-04-16 10:30:00, coordinates: (35.712, 120.991), humidity: 21.9%, temperature: 17.6°C, wind speed: 3.2 m / s, rainfall: 1.5 mm}. Such combined records are the combined data of timestamps under the same coordinates, where the precision of the spatial coordinates is accurate to six decimal places to ensure that the spatial consistency in the matching determination process can be controlled within a precision range of ≤5 meters. At the same time, the spatial threshold in the determination process needs to be set according to the sensor layout density. For example, in this case, one collection unit is arranged per 30 square meters in the farmland, so it is appropriate to set the spatial matching determination threshold to 6 meters to avoid mixing data from different plots and forming an overlapping spatio-temporal combined value list.

[0022] Table 1 Screening results table of multi-sensor at overlapping time points:

[0023] As shown in Table 1, only the data at the moments of 10:00:00 and 11:00:00 meet the spatial intersection matching conditions, so only two combined records are generated for the next image conversion process.

[0024] S113: According to the spatial coordinate field and time field in the overlapping spatio-temporal combined value list, use the coordinates as the image pixel numbers, map the time field to the image frame sequence numbers, and map each type of value to the color channels according to the pixel ratio to generate an ecological environment synchronous scene image; After taking the integer values of latitude and longitude in the spatial coordinates respectively to calculate the pixel positions, set the position (35.712, 120.991) to the 35712th row and 120991st column in the image as the image pixel number. The time field 2025-04-16 10:00:00 is uniformly formatted as "Frame Number 0001", and the frame numbers 0002, 0003, etc. are calculated backward at intervals of 30 minutes. For the humidity, temperature, wind speed, and rainfall values included in the combined record, they need to be mapped and converted to the RGB three channels through pixel values. Set the humidity (0%) to be mapped to the R channel, the temperature (-20°C) to be mapped to the G channel, and the wind speed (20 m / s) or rainfall (100 mm) to be mapped to the B channel. A linear conversion of the values is required. Set the corresponding channel value for the temperature of 17.6°C to be G=(17.6 + 20) / 70×255≈138, the humidity of 21.9% to be R=21.9 / 100×255≈56, and the rainfall of 1.5 mm to be B=1.5 / 100×255≈4. Combine the pixel point RGB(56, 138, 4) and fill it into the pixel position of the 35712th row and 120991st column in the image frame number 0001 to form an image sequence dataset composed of time progression and multi-channel values. In this dataset, each frame represents an ecological image frame constructed from spatial monitoring data at a certain time node, and the changes between frames reflect the fluctuation process of environmental factors. The image generation process is constructed using a two-dimensional pixel matrix structure, and the dimension of each frame image can be set to 2000 rows × 2000 columns, corresponding to a coverage area of approximately 4 square kilometers. Pixel sparse filling is performed according to the sensor deployment range, and the image output format is set to the PNG format. The frame sequence is uniformly named Frame-0001.png, Frame-0002.png, etc., which is convenient for sorting and processing on the time axis to generate ecological environment synchronous scene images.

[0025] Please refer to Figure 3 , and the steps for obtaining the mapping result of the farmland area are specifically as follows: S211: Use the humidity, temperature, and meteorological condition data in the ecological environment synchronous scene image, call the regional virtual grid coordinates built in the digital twin, evaluate the mapping relationship between the grid coordinates and the sensor data, and generate a grid-based environmental parameter set; Collect real-time data through three monitoring points (numbered M1 - M3) deployed in the farmland area. Monitoring point M1 records a humidity of 65%, a temperature of 28°C, and a meteorological condition of cloudy (code C = 2), M2 has a humidity of 72%, a temperature of 25°C, and a sunny meteorological condition (C = 1), and M3 has a humidity of 58%, a temperature of 30°C, and an overcast meteorological condition (C = 3). Convert the monitoring point coordinates to virtual grid coordinates G1 (boundary density 0.8), G2 (boundary density 1.2), G3 (boundary density 0.5). Bind the humidity, temperature, and meteorological code to the corresponding grid coordinates respectively to generate a structured data set containing grid coordinates, environmental parameters, and boundary density, and output it as a gridded environmental parameter set; Table 2: Sensor Data and Grid Mapping Table:

[0026] As shown in Table 2, the boundary density is obtained by calculating the ratio of the grid side length to the number of adjacent grids. Set the side length of G1 to 10 meters and the number of adjacent grids to 8, then the boundary density is 10 / (8 × 1.25) = 0.8.

[0027] S212: Based on the gridded environmental parameter set, extract the soil hydraulic conductivity, crop coefficient, and evapotranspiration in the multi-region parameter mapping information, and use the formula: ; Calculate the environmental volatility, compare the environmental volatility with the material response threshold of the regional three-dimensional model, and generate a regional dynamic response scalar; Among them, is the environmental volatility, represents the temperature measurement value, represents the grid weight factor, represents the measured value of soil hydraulic conductivity, represents the measured average value of evapotranspiration, represents the quantified value of meteorological conditions, represents the crop growth stage coefficient, represents the humidity percentage value; Extract the soil hydraulic conductivity, crop coefficient, and evapotranspiration in the multi-region parameter mapping information. For the G1 grid in Table 1, the soil hydraulic conductivity AK is measured by the cutting ring method to be 0.15 cm / h, the crop coefficient AF is set to 1.2 according to the heading stage of corn, the evapotranspiration AE is calculated by the Penman formula to be 4.2 mm / d, the meteorological condition code AC is quantified to 0.9, 1.1, and 1.3 for sunny (1), cloudy (2), and overcast (3) respectively, and the grid weight factor AW is calculated by the formula AW = boundary density × 0.5 + 0.3. Set the AW of G1 to 0.8 × 0.5 + 0.3 = 0.7 and substitute it into the formula. Substitute the data and calculate the numerator term: AT = 28, AW = 0.7, AK = 0.15 → 28×0.7×0.15 = 2.94; Calculate the denominator term: AE = 4.2, AC = 1.1 → ; Calculate the absolute value term: AF = 1.2, AH = 65 → |1.2 - 65 / 100| = |1.2 - 0.65| = 0.55; Substitute into the formula for calculation: ; Compare the environmental volatility with the material response threshold (preset to 0.8). Since 0.75 < 0.8, it is determined that the environmental dynamics of this grid are not exceeded, and the generated regional dynamic response scalar value is 0.75. The formula enhances the influence of spatial heterogeneity on the dynamic index by introducing the boundary density weight factor and the meteorological quantization value, avoiding the errors caused by homogenization in the traditional method.

[0028] S213: Invoke the regional dynamic response scalar, and update the texture resolution of the three-dimensional environmental model according to the light intensity and wind speed in the real-time environmental information to generate the farmland area mapping result; Taking grid G1 as an example, according to the light intensity and wind speed in the real-time environmental information, the light intensity L is measured as 30,000 lux by the quantum sensor, and the wind speed V is measured as 2.5 m / s by the ultrasonic anemometer. For every 10,000 lux increase in L, the texture resolution is increased by 1 level, and for every 1 m / s increase in V, the particle movement speed is increased by 0.2 units. According to S = 0.75 (lower than the threshold 0.8), a conservative update strategy is adopted: the texture resolution is adjusted to (30,000 / 10,000)×0.75 = 2.25 levels, and the particle movement speed is set to 2.5×0.2×0.75 = 0.375 units, and the farmland area mapping result consistent with the physical environment is output.

[0029] Please refer to Figure 4 , and the specific steps for obtaining the environmental response sensitivity distribution map are as follows: S311: Based on the synchronous state trajectory of the grid entities in the farmland area mapping result, invoke the humidity and temperature records of the grid cells in the time dimension, compare the fluctuation degrees of the humidity change rate and the temperature change rate in the continuous time period, judge whether the continuous fluctuation amplitude exceeds the combined standard of the humidity fluctuation threshold and the temperature fluctuation threshold, screen the spatial segments that meet the combined standard conditions, and generate a set of continuous fluctuation segments; Based on the synchronization state trajectory of grid entities in the farmland area mapping results, it is necessary to determine the corresponding number and spatial location of each grid cell in the time series. Taking the 10-meter resolution grid in the area as a unit, record the 7-day continuous state trajectory for each grid number, and obtain the soil moisture data and air temperature data at time points from T1 to T7. The humidity values are collected from soil moisture sensors buried at a depth of 20 cm in the surface layer, and the air temperature data are collected from meteorological monitoring units installed at the crop canopy height. The sampling interval is once a day. Set the humidity values from T1 to T7 as 29%, 31%, 28%, 27%, 25%, 26%, 30%, and the air temperatures are 21.8°C, 22.1°C, 21.4°C, 20.9°C, 21.2°C, 21.7°C, 22.3°C respectively. Calculate the humidity change rate and air temperature change rate for this type of data. Use the formula change rate = (the next day - the previous day) / number of interval days to obtain the difference curve between adjacent time points, and count the maximum difference amplitude within three consecutive days. For example, the humidity value from T3 to T5 drops from 28% to 25%, the amplitude is 3%, and the change rate is 1%. If the set humidity fluctuation threshold is 0.8% and the air temperature fluctuation threshold is 0.5°C, then this grid has exceeded the combined fluctuation judgment standard during T3 - T5 and enters the screening range. Count all grid entities in the overall area, calculate the change rate amplitude interval within a continuous time period respectively, record the grid ID and the corresponding time window of the segment where the fluctuation amplitude exceeds the combined standard, delimit the spatial segment area and generate a segment index list according to its coordinate coding. Each segment is identified by (segment number - start and end dates - spatial location), and a unified numbering structure is established. For example, segment P104 - T3T5 - X35Y72 represents the 104th fluctuation segment, the time period is from T3 to T5, and the spatial location is in grid X35Y72. Screen the set of spatial segments that meet the conditions to obtain a set of continuous fluctuation segments.

[0030] S312: Call the spatial location pointed to in the set of continuous fluctuation segments, perform image segmentation on the crop growth image, extract the crop entity boundary in the image, and calculate the boundary morphological feature value and color distribution value to determine whether there is a spatial offset phenomenon of structural change or color migration in the crop within the segment, and obtain the crop offset feature distribution value; Call each fragment index in the continuous fluctuation fragment set, locate its corresponding spatial grid, and call the crop growth image sequence with the same time range. Slice and align the images to ensure that the analysis area corresponds to the spatial fragment. Taking fragment P104 as an example, its coordinates are at X35Y72, and the corresponding time period is from T3 to T5. That is, call the crop images at this spatial position from May 12th to May 14th, 2023. Use the image boundary extraction tool to calculate the edge contour of the crop entity, extract the green vegetation area by the threshold segmentation method, and use the contour tracking algorithm to record its boundary coordinates. Calculate the difference in boundary coordinates between consecutive image frames. For example, the main stem boundaries in image 1 and image 2 are located at pixel coordinates (120, 150) and (125, 152) respectively, and the difference is the Euclidean distance (√((125 - 120)² + (152 - 150)²)) ≈ 5.38 pixels. This boundary offset is the basic index of morphological features. At the same time, obtain the change in the average RGB value of the main color of the crop. For image 1, it is (45, 120, 30), and for image 2, it is (50, 130, 35). The difference is +5 in the red channel, +10 in the green channel, and +5 in the blue channel. After transformation, the color change intensity is about 8.16 units. Combine these two values with the corresponding weights of the crop type to construct a composite index. If the weights are 0.6 and 0.4 respectively, the crop offset value is 0.6×5.38 + 0.4×8.16 ≈ 6.69 units. This process is repeated for the fragment images to form a set of crop offset values corresponding to the spatial fragments. Further analyze the combined change trend of the crop contour morphology and color distribution within different fragments to determine whether there is a spatial offset phenomenon of structural change or color migration. Among them, the structural change is based on the standard that the boundary displacement exceeds 5 pixels, and the color migration is defined by the standard that the RGB change amount exceeds 10 units. Obtain the comprehensive offset value of each fragment through this calculation process to obtain the crop offset feature distribution value.

[0031] S313: Use the crop offset feature distribution value to call the corresponding humidity change rate and temperature change rate in the continuous fluctuation fragment set, perform difference operations and combined judgments on the crop offset value and the environmental variable change rate, using the formula: ; Calculate the environmental response difference coefficient of the spatial fragment, evaluate the correlation degree between the fragment position and the environmental response difference coefficient, and obtain the environmental response sensitivity distribution map; Among them, represents the environmental response difference coefficient of the th fragment, represents the crop offset feature distribution value of the th fragment, is the humidity change rate of the th fragment, is the temperature change rate of the th fragment, is the continuity factor of the segment boundary in the fragment crop image, and is the number of boundary segments existing in the fragment image; Jointly analyze the crop offset feature distribution value, the humidity change rate and the temperature change rate corresponding to the fragment. In this process, a unified data structure needs to be constructed to accommodate each parameter value. Taking fragment P104 as an example, its crop offset value is 6.69, the humidity change rate is 1.0% / day, and the temperature change rate is 0.7℃ / day. The image continuity factor comes from the boundary overlap ratio between image frames. Suppose the boundary overlap rates in three consecutive image frames are 85%, 90%, and 88%, then the sum of the factors is 2.63. Substitute each parameter into the numerical calculation: The substituted values are: ; The environmental response difference coefficient of fragment P104 is obtained as 9.11. Compare this value with the set threshold of 4.0, and it can be judged that it belongs to the abnormal response area. Among them, the threshold 4.0 comes from the boundary value of the 95% confidence interval set in the data statistics. Fragments exceeding this value are regarded as environmentally sensitive areas. The response difference values of the fragments are spatially located, the coordinate positions are recorded, and the one-to-one correspondence mapping between the spatial position information and the response value is evaluated, which is the environmental response sensitivity distribution map.

[0032] Please refer to Figure 5 , and the specific steps for obtaining the identification result of the agricultural ecological environment risk trend are as follows: S411: Call the block node number in the environmental response sensitivity distribution map, extract the humidity change data and temperature change data corresponding to the block, compare the humidity decrease rate and the temperature increase rate node by node, and analyze the synchronous change trend of the humidity change rate and the temperature change rate to obtain the synchronous change trend comparison value; Call the block node number in the environmental response sensitivity distribution map. Extract the numbers by identifying the geographical unit numbers represented by each node in the map. Call the observed data of the corresponding humidity and temperature sensors. Set the node numbers as 101, 102, 103, etc., which correspond to different observation points respectively. Extract the time series data of humidity and temperature under each number. Among them, the humidity change rate can be obtained by the ratio of the humidity difference between adjacent moments to the time interval. The temperature change rate adopts the same calculation method. Suppose the time interval in node 101 is 2 hours and the humidity drops from 60% to 55%, then the humidity change rate is: ; If the temperature rises from 22℃ to 24℃, then the temperature change rate is: ; Repeat the above calculation process to obtain the humidity and air temperature change rate sequences for each node, perform synchronization judgment on each node, mark the nodes where the humidity decrease and air temperature increase trends appear synchronously. If at least 3 consecutive nodes in a certain section have the same synchronous change trend, it is regarded as a synchronous change section. Count the node combinations that meet the synchronization conditions to form a wet-temperature synchronous trend data structure for subsequent comparison. Establish and identify the trend change curves for all synchronous sections to generate the synchronous change trend comparison value.

[0033] S412: According to the synchronous change trend comparison value, extract the continuous sections where the humidity decrease rate and air temperature increase rate change. Divide the fluctuation amplitude intervals according to the sections and compare the section differences with the set ecological stability interval. Use the formula: ; Calculate the regional difference rate, classify and judge the regional difference rate and the interval stability setting boundary, record the continuous numbered sections that exceed the stability interval, and obtain the trend deviation region index sequence; Among them, represents the regional difference rate, represents the humidity change rate of the th node, represents the humidity fluctuation value of the th node, represents the humidity range of the th node, represents the number of nodes in the section; Parameter meaning and formula calculation derivation process: Suppose the total number of monitoring points is five, that is , and the numbers are respectively ; All parameters are from the hourly meteorological monitoring records of the monitoring points for 3 consecutive days. The humidity and air temperature are recorded by the digital temperature and humidity acquisition terminal at 10-minute intervals, and the change rate is calculated by taking the data of adjacent time periods. The fluctuation value is measured by the standard deviation, and the range is calculated by the difference between the maximum value and the minimum value; The 1st monitoring point: humidity change rate % / h, which comes from the humidity decreasing from 64% to 61% at the 2nd time period of the monitoring record day, with a time interval of 2 hours. The change rate is: ; The unit conversion is unified to 0.015, corresponding to 0.15 in percentage system, and the normalized value is 0.14. The air temperature change rate ℃ / h, the collection time is the same 2-hour period, the air temperature rises from 23.4℃ to 27.8℃, and the change rate is: ; The normalized value after unit conversion is 0.22 humidity fluctuation value , which comes from the standard deviation of 5 consecutive groups of humidity data and the air temperature fluctuation value , the humidity range with the same processing method , take the difference between the maximum value of 68% and the minimum value of 48% and then normalize the air temperature range , take the difference between the maximum value of 33.1℃ and the minimum value of 25.6℃ and then normalize; Set the parameters of the following points in this way as follows: The second monitoring point: , , , , , ; The third monitoring point: , , , , , ; The fourth monitoring point: , , , , , ; The fifth monitoring point: , , , , , ; Calculate the numerator part: ; ; ; ; ; Total of numerator: ; Calculate the denominator part: ; ; Calculate the denominator: ; Substitute into the formula for calculation: ; The results show that the regional difference rate between the humidity and the temperature change in the current continuous section is 0.00864, and the value is less than the upper limit setting value of 0.0100 for the ecological stability boundary. Therefore, it can be determined that there is no trend deviation fluctuation in this section during the current observation period, and it is not included in the trend deviation area index sequence. This value reflects the intensity measure of the deviation of the humidity-temperature change in this section and is used as an important numerical criterion for judging whether to include deviation recognition.

[0034] S413: Based on the trend deviation area index sequence, track the regional level numbers indicated, detect the distribution characteristics of the fluctuation trends of humidity and temperature in the area, compare the fluctuation directions and intensities, and obtain the agricultural ecological environment risk trend recognition results; Identify and track the regional level numbers of all nodes marked as trend deviations, map the numbers to the hierarchical structure in the spatial area, set the nodes 103 and 104 to belong to area A2, and the nodes 107 and 108 to belong to area B1. Collect the humidity change rates and temperature change rates of the nodes in the area group by group, establish a climate change data set within the regional level, and perform a direction consistency judgment on each group of data. The humidity shows a downward trend and the temperature shows an upward trend, and the change amplitude needs to exceed the average change rate within the section of this area. The judgment basis can set the humidity change critical value to 1.5% / h and the temperature rise critical value to 0.8°C / h. If the proportion of nodes greater than this threshold in the area exceeds 60%, then determine that this area is a trend deviation area, and then mark the nodes that meet the conditions in this area as deviation trend points, and count the spatial aggregation degree of all trend deviation points. The aggregation degree can be defined as the average distance between adjacent deviation points is less than 100 meters, or more than 3 continuous deviation point combinations are formed in space, then mark it as a risk area, record the deviation point combination and its location area together, and generate the agricultural ecological environment risk trend recognition results.

[0035] Please refer to Figure 6 , and the specific steps for obtaining the agricultural ecological risk warning interface layer are as follows: S511: According to the agricultural ecological environment risk trend recognition results, call the three-dimensional environment model in the digital twin interface, load the time series data of wind speed, rainfall, and temperature in the interface, and overlay the soil humidity value, soil salinity value, and soil organic matter concentration layers to obtain the three-dimensional layer fusion coordinate distribution value; It is necessary to extract the key parameters in the risk identification layer, including the spatial coordinate point positions, the time series arrangement structure, and their corresponding risk level information. This extraction process is carried out based on the preset partition coding rules. Combining the grid data of soil humidity, salinity value, and organic matter concentration in each region, the attribute identification of each risk point is performed. Suppose a certain region is identified as a mild risk during the period from 9:00 to 21:00 on May 5, 2024. Its corresponding coordinate points, time numbers, and risk marks will be synchronously extracted and organized into a unified data set. The constructed three-dimensional environment model in the digital twin platform is called, and a layer mapping table is established in the model coordinate system to correspond to the mapping relationship between each coordinate point in the above data set and the spatial points in the three-dimensional model, completing the coordinate correction and structure access operations. On this basis, the meteorological data layer is introduced, and the hourly temperature, wind speed, and rainfall values in the region are loaded and mapped to the corresponding position points in chronological order to form a meteorological layer structure with spatial and time attributes. The soil state layer is superimposed on the model interface, and the soil humidity value, salinity value, and organic matter content value are extracted. The soil information and meteorological information of each position point are associated and combined one by one, and they are marked as different time series attribute combinations under the same spatial node to obtain a unified fusion data set mapped to the three-dimensional interface. This data set serves as the basis for subsequent layer comparison, boundary judgment, and visual highlighting, and the three-dimensional layer fusion coordinate distribution value is obtained.

[0036] S512: Based on the three-dimensional layer fusion coordinate distribution value, obtain the differences in meteorological layer parameters and soil state layer parameters in the marked areas in the real-time and previous time period consecutive frames, and judge the change trend of the block boundary of the difference sequence along the time axis. Mark the consecutive frame block numbers with the boundary expanding outward as the expanded areas to obtain the continuous boundary expansion recognition result; Perform a differential comparison operation on the layer content in any two consecutive time periods. This comparison focuses on the changes in soil and meteorological conditions at each spatial position over time. Set a numerical comparison of rainfall values, air temperature, and wind speed at a certain position between 9:00 and 10:00 on May 5th, and at the same time judge the numerical changes in its soil moisture, salinity value, and organic matter concentration during the corresponding period. For numerical changes, a static time window can be set for centralized comparison. Classify the change values by region and screen whether they exceed the preset change threshold. Set that when more than 70% of the nodes in a certain grid area exceed the standard change range in terms of meteorological or soil numerical changes, mark this area as a potential boundary change block. Then number and track record such blocks. Continuously track the status of the numbered blocks in multiple time periods. If the expansion conditions are met in three consecutive time periods, it is regarded as the actual expansion of the boundary. Extract and store the set of boundary coordinates in the spatial dimension, and merge adjacent areas that meet the conditions to form a new boundary recognition range. On this basis, construct the boundary change judgment structure at the current stage, and further count parameters such as the area, directionality, and duration of its boundary expansion to obtain the continuous boundary expansion recognition result.

[0037] S513: According to the continuous boundary expansion recognition result, extract the set of spatial coordinates of the changed area in the digital twin interface, and perform coordinate comparison within the visible range. Set the width and color parameters of the boundary line of the highlighted block, highlight the area that meets the expansion judgment condition in the interface, and set the layer name and display order to generate the layer of the agricultural ecological risk warning interface; Extract and map the set of spatial coordinates in the rendering interface of the digital twin. This set comes from all the area nodes marked as boundary expansion in the previous stage. Their spatial positions will be uniformly called through the provided three-dimensional coordinate interface and combined into a set of boundary line segments. Set the rendering parameters for the boundary line segments, including attributes such as line color, width, and layer transparency. Set the boundary of the expanded area to be red, 2 pixels wide, and the transparency to 0.7, and bind the layer name such as "Risk-Border-Layer" and the display priority parameter to 1 so that it is presented preferentially during the interface loading process. At the same time, add a layer legend and control buttons to the layer control panel on the right side so that users can control the layer to be turned on or off. On this basis, extract the visible window range of the current interface and only render the area boundaries within the view range to improve the layer loading efficiency. Display the numbers of each expanded area on the boundary line in the interface, and attach the time information of the real-time expansion status, such as "Area A expanded at 12:00 on May 5th", to help users identify the timeliness and location of the changes. The boundary line information will be bound to the current three-dimensional scene layer and embedded in the environmental model structure to generate the layer of the agricultural ecological risk warning interface.

[0038] The agricultural ecological environment monitoring system based on digital twin is used to execute the above-mentioned agricultural ecological environment monitoring method based on digital twin. The system includes: The index recognition module acquires the continuous data of the soil humidity monitor, temperature sensor and meteorological collection device deployed in the farmland area, establishes the corresponding index relationship according to the sensor number, screens the data groups in the overlapping time intervals, and generates the ecological environment synchronous scene image; The virtual mapping module, based on the calibrated spatial grid coordinates in the ecological environment synchronous scene image, calls the regional virtual grid point numbers in the digital twin environment, compares the humidity values, temperature values and meteorological parameter values between the grid points, and updates the environmental performance of the corresponding nodes in the three-dimensional model to obtain the mapping result of the farmland area; The change recognition module calls the humidity change sequence and temperature change sequence of the virtual nodes in the mapping result of the farmland area, extracts the spatial segments with continuous changes according to the change values between adjacent time points, and generates the environmental response sensitive distribution map; The trend analysis module extracts the humidity change trajectory and temperature change trajectory of the nodes according to the spatial node numbers marked in the environmental response sensitive distribution map, identifies the change curves of the two change trajectories in the nodes, judges the change trend direction and amplitude, and generates the agricultural ecological environment risk trend recognition result; The risk warning module calls the spatial hierarchy numbers recorded in the agricultural ecological environment risk trend recognition result, matches the boundary nodes of the farmland area in the three-dimensional model, overlays the meteorological parameter layer and soil humidity layer under the area, judges the boundary change situation of the area corresponding to the warning number, and obtains the agricultural ecological risk warning range layer.

[0039] The above is only the preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for monitoring the agricultural ecological environment based on digital twins, characterized in that, It includes the following steps: S1: Obtain the continuous data of the soil humidity monitor, temperature sensor, and meteorological collection device deployed in the farmland area. Construct the corresponding mapping relationship through the sensor number identification, arrange the collected information in time series, and generate an ecological environment synchronous scene image; S2: According to the spatial grid coordinates corresponding to the humidity, temperature, and meteorological conditions recorded in the ecological environment synchronous scene image, call the regional virtual grid built in the digital twin, dock the synchronous information of the real scene sensor, and update the performance of the regional three-dimensional environment model according to the real-time environmental information to generate the farmland area mapping result; S3: Based on the synchronous state trajectory of the grid entities in the farmland area mapping result, by comparing the change gradients of the humidity and air temperature performance between different differential time points, screen the spatial segments with continuous fluctuation amplitudes, analyze the crop growth images within the spatial segments, and generate an environmental response sensitivity distribution map; S4: Call the block node numbers in the environmental response sensitivity distribution map, track the synchronous evolution process of the humidity drop section and the air temperature rise node, compare the change amplitude curve with the set ecological stability interval by section difference, and generate the identification result of the agricultural ecological environment risk trend.

2. The method for monitoring the agricultural ecological environment based on digital twin according to claim 1, characterized in that, The ecological environment synchronous scene image includes a spatial feature grid, a time series alignment segment, and a multi-source data fusion area. The farmland area mapping result includes a grid number status set, a real-time environmental parameter group, and a three-dimensional structure performance set. The environmental response sensitivity distribution map includes a parameter change prominent area, a crop status response area, and an environmental factor interference zone. The identification result of the agricultural ecological environment risk trend includes an offset area number, a trend curve change amount, and an ecological index change section.

3. The method for monitoring the agricultural ecological environment based on digital twin according to claim 1, characterized in that The specific steps for obtaining the ecological environment synchronous scene image are as follows: S111: Obtain the continuous data of the soil humidity monitor, temperature sensor, and meteorological collection device deployed in the farmland area. After adding the number identification, evaluate the mapping relationship between the device number and the data record, and perform a sorting operation on the data record according to the time stamp field to generate a sensor time series number data set; S112: Call the data records corresponding to the device numbers in the sensor time series number data set, screen the soil humidity, temperature, and meteorological data entries with overlapping time stamps, perform a pairing operation on the time-overlapping data according to the spatial coordinates of the data record, and perform a combination process on the data record based on the spatial coordinate matching result as a judgment condition to generate an overlapping space-time joint value list; S113: According to the spatial coordinate field and time field in the overlapping space-time joint value list, use the coordinates as the image pixel numbers, map the time field to the image frame sequence number, and map each type of value to the color channel according to the pixel ratio to generate an ecological environment synchronous scene image.

4. The method for monitoring the agricultural ecological environment based on digital twin according to claim 3, characterized in that, The specific steps for obtaining the farmland area mapping result are as follows: S211: Use the humidity, temperature, and meteorological condition data in the ecological environment synchronous scene image, call the regional virtual grid coordinates built in the digital twin, evaluate the mapping relationship between the grid coordinates and the sensor data, and generate a grid-based environmental parameter set; S212: Based on the grid environmental parameter set, extract the soil hydraulic conductivity, crop coefficient, and evapotranspiration in the multi-region parameter mapping information, and use the formula: ； Calculate the environmental volatility, compare the environmental volatility with the material response threshold of the regional three-dimensional model, and generate a regional dynamic response scalar; Among them, is the environmental volatility, represents the temperature measurement value, represents the grid weight factor, represents the measured value of soil hydraulic conductivity, represents the measured average value of evapotranspiration, represents the quantified value of meteorological conditions, represents the crop growth stage coefficient, represents the humidity percentage value; S213: Invoke the regional dynamic response scalar, and update the texture resolution of the three-dimensional environmental model according to the light intensity and wind speed in the real-time environmental information to generate a farmland area mapping result.

5. The method for monitoring the agricultural ecological environment based on digital twin according to claim 4, characterized in that The specific steps for obtaining the environmental response sensitivity distribution map are as follows: S311: Based on the synchronous state trajectory of the grid entities in the farmland area mapping result, invoke the humidity and temperature records of the grid cells in the time dimension, compare the fluctuation degrees of the humidity change rate and the temperature change rate in a continuous time period, determine whether the continuous fluctuation amplitude exceeds the combined standard of the humidity fluctuation threshold and the temperature fluctuation threshold, filter the spatial segments that meet the combined standard conditions, and generate a set of continuous fluctuation segments; S312: Invoke the spatial positions pointed to in the set of continuous fluctuation segments, perform image segmentation on the crop growth images, extract the crop entity boundaries in the images, and calculate the boundary morphological feature values and color distribution values to determine whether there is a spatial offset phenomenon of structural change or color migration in the crop within the segment, and obtain the crop offset feature distribution value; S313: Use the crop offset feature distribution value, invoke the corresponding humidity change rate and temperature change rate in the set of continuous fluctuation segments, perform a difference operation and combined judgment on the crop offset value and the environmental variable change rate, and use the formula: ； Calculate the environmental response difference coefficient of the spatial segment, evaluate the correlation degree between the segment position and the environmental response difference coefficient, and obtain the environmental response sensitivity distribution map; Among them, represents the environmental response difference coefficient of the th segment, represents the crop offset characteristic distribution value of the th segment, is the humidity change rate of the th segment, is the air temperature change rate of the th segment, is the continuity factor of the segment boundary in the crop image of the th segment, is the number of boundary segments existing in the image of this segment.

6. The method for monitoring the agricultural ecological environment based on digital twin according to claim 5, wherein, The specific steps for obtaining the agricultural ecological environment risk trend recognition result are as follows: S411: Invoke the block node numbers in the environmental response sensitivity distribution map, extract the corresponding humidity change data and temperature change data of the blocks, compare the humidity decline rate and the temperature rise rate node by node, and analyze the synchronous change trend of the humidity change rate and the temperature change rate to obtain a synchronous change trend comparison value; S412: According to the synchronous change trend comparison value, extract the continuous sections of the changes in the humidity decline rate and the temperature rise rate, divide the fluctuation amplitude intervals according to the sections, and compare the section differences with the set ecological stability interval, and use the formula: ； Calculate the regional difference rate, classify and judge the regional difference rate and the interval stability setting boundary, and record the continuous numbered sections that exceed the stable interval to obtain a trend offset area index sequence; Among them, represents the regional difference rate, represents the humidity change rate of the th node, represents the air temperature change rate of the th node, represents the humidity fluctuation value of the th node, represents the air temperature fluctuation value of the th node, represents the humidity range of the th node, represents the air temperature range of the th node, represents the number of nodes in the section; S413: Based on the trend offset area index sequence, track the indicated regional level numbers, detect the fluctuation trend distribution characteristics of humidity and temperature in the area, and compare the fluctuation directions and intensities to obtain the agricultural ecological environment risk trend recognition result.

7. The method for monitoring the agricultural ecological environment based on digital twins according to claim 1, characterized in that, The method further includes step S5: S5: According to the agricultural ecological environment risk trend recognition result, invoke the three-dimensional environmental model in the digital twin interface, overlay the meteorological condition animation layer and the soil state, judge whether the boundary change range of the warning block continuously expands, mark the highlighted area and the visible range of the interface, and obtain the agricultural ecological risk warning interface layer; The agricultural ecological risk warning interface layer includes a dynamic boundary layer, a highlighted visible area, and a risk level overlay map.

8. The method for monitoring the agricultural ecological environment based on digital twin according to claim 7, wherein The steps for obtaining the agricultural ecological risk warning interface layer are specifically as follows: S511: According to the agricultural ecological environment risk trend recognition result, call the three-dimensional environment model in the digital twin interface, load the time series data of wind speed, rainfall, and temperature in the interface, and overlay the soil humidity value, soil salinity value, and soil organic matter concentration layers to obtain the three-dimensional layer fusion coordinate distribution value; S512: Based on the three-dimensional layer fusion coordinate distribution value, obtain the difference between the meteorological layer parameters and the difference between the soil state layer parameters in the marked area of the real-time and the previous time period continuous frames, and judge the change trend of the block boundary according to the time axis for the difference sequence. Mark the block numbers of the continuous frames with the boundary expanding outward as the expanded area to obtain the continuous boundary expansion recognition result; S513: According to the continuous boundary expansion recognition result, extract the spatial coordinate set of the changed area in the digital twin interface, perform coordinate comparison within the visible range, set the width and color parameters of the highlighted block boundary line, highlight the area that meets the expansion determination condition in the interface, and set the layer name and display order to generate the agricultural ecological risk warning interface layer.

9. The agricultural ecological environment monitoring system based on digital twin is characterized in that The system is used to implement the digital twin-based agricultural ecological environment monitoring method described in any one of claims 1-8. The system includes: The index recognition module obtains the continuous data of the soil humidity monitor, temperature sensor, and meteorological collection device deployed in the farmland area, establishes the corresponding index relationship according to the sensor number, screens the data groups in the overlapping time interval, and generates the ecological environment synchronous scene image; The virtual mapping module, based on the calibrated spatial grid coordinates in the ecological environment synchronous scene image, calls the regional virtual grid point numbers in the digital twin environment, compares the humidity values, temperature values, and meteorological parameter values between the grid points, and updates the environmental performance of the corresponding nodes in the three-dimensional model to obtain the farmland area mapping result; The change recognition module calls the humidity change sequence and temperature change sequence of the virtual nodes in the farmland area mapping result, extracts the continuous spatial segments with changes according to the change values between adjacent time points, and generates the environmental response sensitive distribution map; The trend analysis module extracts the humidity change trajectory and temperature change trajectory of the nodes according to the spatial node numbers marked in the environmental response sensitive distribution map, identifies the change curves of the two change trajectories in the nodes, judges the change trend direction and amplitude, and generates the agricultural ecological environment risk trend recognition result; The risk warning module calls the spatial hierarchy numbers recorded in the agricultural ecological environment risk trend recognition result, matches the farmland area boundary nodes in the three-dimensional model, overlays the meteorological parameter layer and soil humidity layer in the area, and judges the boundary change situation of the area corresponding to the warning number to obtain the agricultural ecological risk warning range layer.

Images