Water area and resource quantity monitoring and predicting method and system based on remote sensing technology

Abstract

The invention discloses a water area and resource quantity monitoring and predicting method and system based on a remote sensing technology, and belongs to the technical field of water resource monitoring. The method comprises the following steps: determining a water area range according to historical data of a research area and an on-site survey condition, and determining a research area range; the method comprises the following steps: respectively acquiring ground data and water depth and water surface elevation data by using an unmanned aerial vehicle and an unmanned ship, respectively processing to obtain a land DEM and a water area DEM, and fusing to form an all-terrain DEM; downloading satellite image data of the research area, and performing geographical registration on the satellite image data; in the geographically registered satellite image data, describing the boundary of the water area through visual interpretation; superposing the water area boundary to an all-terrain DEM, obtaining the elevation of each point on the water area boundary line, calculating the average elevation of the water area boundary, and calculating the water area and the water resource amount to obtain the historical water area and the water resource amount; and on the basis of the obtained historical water area and water resource quantity, utilizing an ARIMA model to predict future water resource quantity and water area.

Description

Technical Field

[0001] The present invention belongs to the technical field of water resource monitoring, and in particular relates to a method and system for monitoring and predicting water area and resource quantity based on remote sensing technology. Background Art

[0002] Accurate monitoring and prediction of water area and water resources are of great significance in areas such as water resource management, ecological and environmental assessment, and disaster prevention and control. Traditional water area monitoring relies primarily on remote sensing technologies, such as multispectral, hyperspectral, and synthetic aperture radar (SAR). These technologies can periodically monitor large areas, but only provide two-dimensional information about the water surface, making it difficult to directly determine water depth and water resources. Although some studies have attempted to develop water depth inversion models based on multispectral data (such as band ratio methods and radiation transfer models), the inversion results are subject to significant uncertainty because the optical properties of water bodies are affected by factors such as suspended matter, chlorophyll concentration, and bottom reflectance. This accuracy, in particular, is difficult to meet practical requirements in complex water environments.

[0003] To determine underwater topography and water resource quantities, existing technologies typically use unmanned vessels equipped with single-beam or multi-beam bathymetry systems for field measurements. However, water area and resource quantity are significantly affected by season, climate, and human activity, and undergo dramatic temporal and spatial dynamics. Relying solely on unmanned vessels for multiple monitoring sessions to capture dynamic features is costly, labor-intensive, and inefficient. Furthermore, the inability to review historical water conditions limits the feasibility of long-term time series analysis and trend prediction.

[0004] Based on historical multi-temporal datasets of water area and resource quantity, combined with time series prediction algorithms (such as ARIMA and LSTM neural networks), models of water area dynamics can be established, enabling quantitative predictions of future trends. These predictions provide a scientific basis for decision-making on water resource scheduling, ecological protection, and flood and drought early warning. However, existing technologies lack a comprehensive technical system integrating real-world terrain modeling, multi-source remote sensing monitoring, and time-series prediction. An efficient, accurate, and operationally applicable solution is urgently needed. To this end, a method and system for monitoring and predicting water area and resource quantity based on remote sensing technology is proposed. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a water area and resource monitoring and prediction method and system based on remote sensing technology, which solves the problems in the existing technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The water area and resource quantity monitoring and prediction method based on remote sensing technology includes the following steps:

[0008] Based on historical data and field surveys of the study area, the water area was determined and the scope of the study area was defined;

[0009] Use drones and unmanned boats to collect ground data and water depth and surface elevation data, and process them to obtain land DEM and water DEM respectively; then fuse the land DEM and water DEM to form a full-terrain DEM;

[0010] Find historical satellite image data, download satellite image data of the study area, and georeference the satellite image data;

[0011] In the georeferenced satellite image data, the water boundary is delineated through visual interpretation. The water boundary is superimposed on the full terrain DEM to obtain the elevation of each point on the water boundary line to calculate the average elevation of the water boundary. The water area and water resources are then calculated to obtain the historical water area and water resources.

[0012] Based on the historical water area and water resources, the ARIMA model is used to predict the future water resources and water area in combination with the changing trends of future meteorological and hydrological conditions.

[0013] Furthermore, when generating land DEM, a drone equipped with LiDAR and a high-resolution camera is used to synchronously collect ground point cloud and orthophoto data; and the point cloud data is processed by software to generate land DEM.

[0014] Furthermore, when generating the water area DEM, an unmanned vessel equipped with a sonar depth sounding system and GPS equipment is used to collect water depth data in real time, and RTK technology is used to collect water surface elevation data as a verification supplement; finally, the water area DEM is obtained after data processing.

[0015] Furthermore, when generating the water area DEM, the collected data is smoothed, filtered and error-eliminated through software, and the plane coordinates, water depth and water surface elevation values ​​are extracted at 5-meter intervals. The water edge data is used to construct a TIN model to generate the water area DEM.

[0016] Furthermore, the water DEM and land DEM were fused using the mosaic to new raster function in GIS software to obtain the full-terrain DEM.

[0017] Furthermore, the steps of georeferencing satellite image data include:

[0018] S31, by searching for the required historical satellite image data in Google Earth Pro, download the satellite image data of the study area and import it into ArcGIS software;

[0019] S32, opening the reference map, using a georeferencing tool to select corresponding control points in the satellite image data and the reference map, applying a transformation, and saving the georeferenced satellite image data.

[0020] The water area and resource monitoring and prediction system based on remote sensing technology includes:

[0021] Scope determination module: Determine the scope of the water area and the scope of the study area based on historical data and field surveys of the study area;

[0022] DEM generation module: Use drones and unmanned boats to collect ground data and water depth and surface elevation data, and process them to obtain land DEM and water DEM respectively; then fuse the land DEM and water DEM to form a full-terrain DEM;

[0023] Image registration module: search for historical satellite image data, download satellite image data of the study area, and perform georeferencing on the satellite image data;

[0024] Historical data acquisition module: In the geo-referenced satellite image data, the water boundary is depicted through visual interpretation; the water boundary is superimposed on the full terrain DEM, and the elevation of each point on the water boundary line is obtained to calculate the average elevation of the water boundary, and the water area and water resources are calculated to obtain the historical water area and water resources;

[0025] And, the prediction module: based on the historical water area and water resources obtained, the ARIMA model is used, combined with the changing trends of future meteorological and hydrological conditions, to predict the future water resources and water area.

[0026] A computer storage medium stores a readable program, which, when run by a processor, can execute the above-mentioned water area and resource quantity monitoring and prediction method based on remote sensing technology.

[0027] An electronic device comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0028] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned water area and resource quantity monitoring and prediction method based on remote sensing technology.

[0029] A computer program product includes computer instructions, which instruct a computing device to execute operations corresponding to the above-mentioned water area and resource quantity monitoring and prediction method based on remote sensing technology.

[0030] Beneficial effects of the present invention:

[0031] 1. The present invention uses drones equipped with LiDAR (LiDAR is a system that integrates laser, global positioning system, and inertial navigation system technologies to obtain point cloud data and generate accurate digital three-dimensional models) and high-resolution cameras, and unmanned boats equipped with sonar systems to collect elevation data of land and water respectively, thereby obtaining a water-land integrated all-terrain DEM (digital elevation model). Through georeferencing of real-time and historical satellite image data, the past and current water area and water resource quantity can be obtained. Based on historical data, the autoregressive integrated moving average model (ARIMA) is used to predict water resource changes in the future. While improving monitoring accuracy and spatial coverage, it greatly optimizes the dynamic monitoring capabilities of remote sensing technology for water area and resource quantity.

[0032] 2. The monitoring and prediction method of the present invention can save multiple periods of repeated monitoring, improve monitoring efficiency, and provide scientific and reliable decision-making support for water resources management, scheduling, flood prevention and disaster reduction and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0034] Figure 1 This is a flow chart of the water area and resource quantity monitoring and prediction method of the present invention;

[0035] Figure 2 This is a schematic diagram of the full terrain DEM of the study area of ​​the present invention;

[0036] Figure 3 This is the result map of identifying the water area boundary in the study area of ​​the present invention;

[0037] Figure 4 It is the superposition effect diagram of the full terrain DEM and water boundary of the study area of ​​this invention;

[0038] Figure 5 This is the forecast result of water resources using the ARIMA model;

[0039] Figure 6 This is a graph showing the prediction results of water area using the ARIMA model. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0041] Example 1

[0042] like Figure 1 As shown in FIG, the water area and resource quantity monitoring and prediction method based on remote sensing technology includes the following steps:

[0043] S1. Determine the scope of the water area and the scope of the study area based on historical data and field surveys of the study area; the scope of the study area includes the water area and the surrounding land area;

[0044] S2 uses drones equipped with LiDAR and high-resolution cameras to collect ground data and process it to obtain a land DEM. At the same time, an unmanned boat equipped with sonar collects water depth and surface elevation data, which are then smoothed and filtered to generate a water DEM. GIS software is used to fuse the land DEM and water DEM to form a full-terrain DEM.

[0045] The steps to obtain the full terrain DEM include:

[0046] S21, LiDAR UAV aerial survey and land DEM generation;

[0047] Based on the distribution of water bodies, drone routes were designed to accommodate terrain heights, and high-precision image control points were evenly distributed throughout the study area. Subsequently, during the LiDAR drone survey phase, GPS base stations were used to ensure that the data captured by the drones contained accurate geographic information. Drones equipped with LiDAR and high-resolution cameras were then used to simultaneously collect ground point cloud and orthophoto data. The point cloud data was processed using software such as Hi-Target Business Center, Inertial Explorer, EPiCloud Center, and MicroStation CONNECT Edition to generate a land DEM.

[0048] S22, unmanned vessel water depth measurement and water area DEM generation;

[0049] During the unmanned vessel water survey, a suitable route is first designed based on the distribution of the study area's waters. Before planning, the unmanned vessel is manually controlled to navigate along the water's edge to determine the data range and ensure the route avoids surface structures and obstacles. Subsequently, the unmanned vessel, equipped with a sonar sounding system and GPS equipment, collects real-time depth data. RTK (Real Time Kinematic) technology, a real-time differential GPS (RTDGPS) technique based on carrier phase observations, consists of a base station receiver, a data link, and a rover receiver. Finally, the collected data is smoothed, filtered, and error-corrected using software such as AutoPlanner and HydroSurvey. Plane coordinates, water depth, and water surface elevation values ​​are extracted at 5-meter intervals. The waterfront data is then used to construct a TIN model to generate a water area DEM. A TIN is a form of vector-based digital geographic data constructed by triangulating a series of vertices (points). Each vertex is connected by a series of edges, ultimately forming a triangulated network.

[0050] S23, data fusion and full-terrain DEM generation;

[0051] The land DEM obtained by the drone and the water DEM obtained by the unmanned boat are merged through the mosaic to new raster function in GIS software such as ArcGIS or QGIS to generate a complete all-terrain DEM.

[0052] S3, search for historical satellite image data, download satellite image data of the study area, and georeference the satellite image data;

[0053] The steps for georeferencing satellite imagery data include:

[0054] S31, historical satellite image download;

[0055] Search for the required historical image data in Google Earth Pro, then open SAS.Planet to download high-definition satellite image data of the study area. In this experiment, the historical image data downloaded was from 2021.

[0056] S32, georeferencing;

[0057] Import the downloaded high-definition satellite imagery into ArcMap and open the reference map. Use the georeferencing tool to select corresponding control points (such as road intersections or building corners) in both the satellite imagery data and the reference map. Select an appropriate geometric transformation method (such as affine or polynomial transformation), adjust the control points to reduce residual errors, and finally apply the transformation and save the corrected image data.

[0058] S4, in the georeferenced satellite image data, delineate the water boundary through visual interpretation; superimpose the water boundary onto the full terrain DEM, obtain the elevation of each point on the water boundary line, calculate the average elevation of the water boundary, and calculate the water area and water resources, thereby obtaining the historical water area and water resources;

[0059] In the high-definition satellite data after georeferencing, the boundaries of the water area are accurately depicted through visual interpretation of satellite images (such as Figure 2 Next, with the help of the pre-generated full-terrain DEM, the water boundary is superimposed on the full-terrain DEM (as shown in Figure 3 (as shown), extract the elevation data of each point on the water boundary line, and calculate the average elevation of these points through statistical processing. At the same time, extract the water area DEM. Finally, use the surface volume function in the GIS software, using the elevation information of the water boundary and the water area DEM as the basis, extract the elevation points of the water boundary, calculate the average elevation of the water boundary, and regard the average elevation as the elevation of the water boundary. Then, enter the average elevation in the plane height of the surface volume function, select the water area DEM in the input surface, and select below in the reference plane. Click Calculate to calculate the water resources of the entire water area.

[0060] In this embodiment, through the above steps, the water area and water resources in the four quarters of the study area from 2020 to 2023 are obtained, as shown in Table 1 below.

[0061] Table 1 Water area and water resources in the four quarters from 2020 to 2023

[0062]

[0063] S5, based on the historical water area and water resources, using the ARIMA model and combining the changing trends of future meteorological and hydrological conditions, predict the future water resources and water area;

[0064] In this embodiment, the ARIMA model includes:

[0065] The ARIMA model mainly consists of three parts: autoregressive model (AR), difference process (I) and moving average model (MA).

[0066] The advantage of the AR model, or autoregressive model, is that for data with a long historical trend, the AR model can capture these trends and make predictions based on them.

[0067] The differencing process (I), also known as differencing, is a mathematical operation used to calculate the difference between adjacent data points in a numerical series. In time series analysis, differencing is often used to transform a non-stationary series into a stationary one, that is, to reduce or eliminate trend and seasonality in the time series.

[0068] The MA model, or moving average model, can better handle time series data with temporary, sudden changes or large noise.

[0069] Based on the historical water area and water resource data obtained, a time series was first constructed through data organization and preprocessing. An ARIMA model was then trained, with the ADF test determining the differencing order d. The autoregressive order p and moving average order q were selected using the PACF and ACF plots. Parameters were fitted and the white noise characteristics of the residuals were verified. ACF (Auto-Correlation Function) and PACF (Partial Auto-Correlation Function) are two important tools in time series analysis; they can be used to test whether a time series is stationary and help determine the parameters of the ARIMA model. Finally, based on the trained model, a forecast of water area and water resource volume for the next two years was made. Initial outliers were removed from the output, providing a scientific basis for decision-making in water resource scheduling and management.

[0070] The results of predicting water resources and water area using the ARIMA model are as follows: Figure 5 and Figure 6 shown.

[0071] Figure 5 In terms of the magnitude of change, the difference between the model prediction value and the measured value in terms of water resources in each period is generally maintained at ±0.4×10 6 m 3 The largest deviation occurred in November 2020 (prediction - measurement ≈ -0.82×10 6 m 3 ), and the errors in other time periods are all less than 0.2×10 6 m 3, indicating good amplitude control. Regarding the change trend, the model accurately captures the overall growth trend and seasonal fluctuations from February 2020 to November 2023, such as the distribution of inflection points such as summer highs and winter lows, which are highly consistent with the measured curve. Regarding the rate of change, the model's predictions of the quarterly growth and deceleration rates are similar to the observed values, with an average growth rate error of only approximately 5%, with only a slight lag during the 2021–2022 winter-spring transition period. Relative error calculations show that the absolute relative error at all time points is less than 8%, with an average relative error of approximately 4.6%, demonstrating high prediction accuracy. In summary, by comparing amplitude, trend, rate, and relative error, the model demonstrates robustness in reproducing the spatiotemporal dynamics of regional water resources and possesses strong fitting and prediction capabilities.

[0072] Figure 6 In terms of the magnitude of change, the difference between the model prediction value and the measured value in each period of water area is within 0.03 km. 2 In terms of the changing trend, whether it is at the turning point of cyclical increase or decrease (such as a sharp rise from November 2020 to February 2021, a slight drop from May 2021 to May 2022 and then a rebound) or in the overall increase from 0.59km 2 Ascend to 0.92km 2 In terms of the long-term growth trajectory, the forecast values ​​can accurately capture the trend direction; in terms of the speed of change, the model increases in each quarter (the maximum is about 0.14km 2 ) is highly consistent with the observed increase, with only minor lags or overshoots occurring in specific intervals (e.g., February–May 2021 and August–November 2022). However, the overall rate error does not exceed 5%. Regarding relative error, the absolute relative error for all observation-forecast pairs is less than 7%, with an average error of only 3.8%, demonstrating high forecast accuracy. In summary, the model not only performs reliably in capturing seasonal fluctuations, identifying overall trends of increase and decrease, and grasping the rate of change, but also maintains acceptable relative errors, validating its excellent fit and reliable forecasting performance for regional water area evolution.

[0073] Based on similar inventive concepts, an embodiment of the present invention also provides a computer storage medium storing a readable program. When the program is run by a processor, it can execute the above-mentioned water area and resource quantity monitoring and prediction method based on remote sensing technology.

[0074] Based on similar inventive concepts, an embodiment of the present invention provides an electronic device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0075] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned water area and resource quantity monitoring and prediction method based on remote sensing technology.

[0076] Based on similar inventive concepts, an embodiment of the present invention also provides a computer program product, including computer instructions, which instruct a computing device to perform operations corresponding to the above-mentioned water area and resource quantity monitoring and prediction method based on remote sensing technology.

[0077] Example 2

[0078] In this embodiment, a water area and resource quantity monitoring and prediction system based on remote sensing technology is proposed, including:

[0079] Scope determination module: Determine the scope of the water area and the scope of the study area based on historical data and field surveys of the study area;

[0080] DEM generation module: Use drones and unmanned boats to collect ground data and water depth and surface elevation data, and process them to obtain land DEM and water DEM respectively; then fuse the land DEM and water DEM to form a full-terrain DEM;

[0081] Image registration module: search for historical satellite image data, download satellite image data of the study area, and perform georeferencing on the satellite image data;

[0082] Historical data acquisition module: In the geo-referenced satellite image data, the water boundary is depicted through visual interpretation; the water boundary is superimposed on the full terrain DEM, and the elevation of each point on the water boundary line is obtained to calculate the average elevation of the water boundary, and the water area and water resources are calculated to obtain the historical water area and water resources;

[0083] Prediction module: Based on the historical water area and water resources, the ARIMA model is used to predict the future water resources and water area in combination with the changing trends of future meteorological and hydrological conditions.

[0084] The method of the present invention can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CDROM, RAM, floppy disk, hard disk or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded over a network and will be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It will be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method shown here.

[0085] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention, and such changes and modifications fall within the scope of the invention as claimed.

Claims

1. A method for monitoring and predicting water area and resource quantity based on remote sensing technology, characterized in that: The following steps are involved: Based on historical data and field surveys of the study area, the water area was determined and the scope of the study area was defined; Use drones and unmanned boats to collect ground data and water depth and surface elevation data, and process them to obtain land DEM and water DEM respectively; Merge the land DEM and water DEM to form a full-terrain DEM; Find historical satellite image data, download satellite image data of the study area, and georeference the satellite image data; In the georeferenced satellite image data, the water boundary is delineated through visual interpretation. The water boundary is superimposed on the full terrain DEM to obtain the elevation of each point on the water boundary line to calculate the average elevation of the water boundary. The water area and water resources are then calculated to obtain the historical water area and water resources. Based on the historical water area and water resources, the ARIMA model is used to predict the future water resources and water area in combination with the changing trends of future meteorological and hydrological conditions.

2. The method for monitoring and predicting water area and resource quantity based on remote sensing technology according to claim 1, characterized in that: When generating land DEM, a drone equipped with LiDAR and a high-resolution camera is used to synchronously collect ground point cloud and orthophoto data; the point cloud data is then processed using software to generate the land DEM.

3. The method for monitoring and predicting water area and resource quantity based on remote sensing technology according to claim 1, characterized in that: When generating the water area DEM, an unmanned vessel equipped with a sonar depth sounding system and GPS equipment is used to collect water depth data in real time, and RTK technology is used to collect water surface elevation data as a verification supplement; finally, the water area DEM is obtained after data processing.

4. The method for monitoring and predicting water area and resource quantity based on remote sensing technology according to claim 3 is characterized in that: When generating the water area DEM, the collected data is smoothed, filtered and error-eliminated through software, and the plane coordinates, water depth and water surface elevation values ​​are extracted at 5-meter intervals. The water edge data is used to construct a TIN model to generate the water area DEM.

5. The method for monitoring and predicting water area and resource quantity based on remote sensing technology according to claim 1 is characterized in that: The water DEM and land DEM were fused using the mosaic to new raster function in GIS software to obtain the full terrain DEM.

6. The method for monitoring and predicting water area and resource quantity based on remote sensing technology according to claim 1, characterized in that: The steps for georeferencing satellite imagery data include: S31, by searching for the required historical satellite image data in Google Earth Pro, download the satellite image data of the study area and import it into ArcGIS software; S32, opening the reference map, using a georeferencing tool to select corresponding control points in the satellite image data and the reference map, applying a transformation, and saving the georeferenced satellite image data.

7. The water area and resource monitoring and prediction system based on remote sensing technology is characterized by: include: Scope determination module: Determine the scope of the water area and the scope of the study area based on historical data and field surveys of the study area; DEM generation module: Use drones and unmanned boats to collect ground data and water depth and surface elevation data, and process them to obtain land DEM and water DEM respectively; Merge the land DEM and water DEM to form a full-terrain DEM; Image registration module: search for historical satellite image data, download satellite image data of the study area, and perform georeferencing on the satellite image data; Historical data acquisition module: In the geo-referenced satellite image data, the water boundary is depicted through visual interpretation; the water boundary is superimposed on the full terrain DEM, and the elevation of each point on the water boundary line is obtained to calculate the average elevation of the water boundary, and the water area and water resources are calculated to obtain the historical water area and water resources; And, the prediction module: based on the historical water area and water resources obtained, the ARIMA model is used, combined with the changing trends of future meteorological and hydrological conditions, to predict the future water resources and water area.

8. A computer storage medium storing a readable program, characterized in that: When the program is executed by a processor, it can execute the water area and resource quantity monitoring and prediction method based on remote sensing technology as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the water area and resource quantity monitoring and prediction method based on remote sensing technology as described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that The computer instructions instruct the computing device to execute operations corresponding to the water area and resource quantity monitoring and prediction method based on remote sensing technology as described in any one of claims 1-6.

Images