Satellite and sensor data integrated acquisition and analysis method and system

Abstract

The invention discloses a satellite and sensor data integrated acquisition and analysis method and system, which are applied to the technical field of data processing, and the method comprises the following steps: obtaining comprehensive data including satellite remote sensing data, sensor data, land utilization data and digital elevation model data; the satellite remote sensing data and the sensor data are preprocessed respectively, and the surface temperature and the daily mean value of the sensor surface temperature are obtained; features of the surface temperature, the land utilization data and the digital elevation model data are extracted respectively and then feature integration is carried out to generate a feature matrix; taking the daily mean value of the surface temperature of the sensor as a true value label, and screening the feature matrix to obtain an effective data set; constructing an integrated learning model according to the effective data set; and obtaining a target feature matrix, inputting the target feature matrix into the integrated learning model for prediction, outputting a surface temperature prediction value of the target area, and completing monitoring of satellite and sensor data of the target area.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a satellite and sensor data integrated collection and analysis method and system. Background Art

[0002] Satellite monitoring is the process of remote sensing and data collection using satellites. Satellites usually carry various sensors such as optical sensors, radars, infrared sensors, etc. These sensors collect data from space and can be used to monitor weather, oceans, geology, environmental changes, vegetation cover, etc. Sensor monitoring is the process of capturing various data in the environment through the use of sensor devices. Sensors can be embedded in various devices and systems to monitor environmental factors such as meteorological conditions, water quality, air quality, traffic flow, etc. Sensor data can be transmitted in real time through Internet-connected devices for real-time monitoring and decision support. Sensor monitoring has a wide range of applications in smart cities, health monitoring, traffic management, and other fields. These monitoring methods play a key role in scientific research, resource management, and decision making.

[0003] While single satellite remote sensing technology or sensor network technology each has its own advantages and limitations, the fusion of large-scale monitoring data and high-resolution data, as well as the fusion of coarse-grained data and fine-grained data, and improving the accuracy and resolution of monitoring data are particularly important for environmental protection and governance, health and safety assurance, environmental policy making, natural disaster warning, resource management and sustainable development.

[0004] In order to overcome these defects, the present application proposes a satellite and sensor data integrated collection and analysis method and system. Summary of the invention

[0005] The purpose of this application is to provide a satellite and sensor data integrated collection and analysis method and system to solve the above-mentioned problems.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for integrated satellite and sensor data collection and analysis, comprising:

[0008] Acquiring comprehensive data, including satellite remote sensing data, sensor data, land use data, and digital elevation model data;

[0009] Preprocessing the satellite remote sensing data and the sensor data respectively to obtain the surface temperature and the daily average value of the sensor surface temperature;

[0010] Extracting the features of the surface temperature, the land use data and the digital elevation model data respectively, and then integrating the features to generate a feature matrix;

[0011] Taking the daily average value of the surface temperature of the sensor as the true value label, the feature matrix is ​​screened to obtain a valid data set;

[0012] Constructing an integrated learning model according to the valid data set; wherein the integrated learning model is composed of a trained random forest model, an XGBoost model, and a LightGBM model;

[0013] The target feature matrix is ​​obtained, the target feature matrix is ​​input into the integrated learning model for prediction, the predicted value of the surface temperature of the target area is output, and the monitoring of the satellite and sensor data of the target area is completed.

[0014] In a second aspect, the present application provides a satellite and sensor data integrated collection and analysis system, comprising:

[0015] Acquisition module: acquiring comprehensive data, including satellite remote sensing data, sensor data, land use data, and digital elevation model data;

[0016] Preprocessing module: preprocessing the satellite remote sensing data and the sensor data respectively to obtain the surface temperature and the daily average value of the sensor surface temperature;

[0017] Feature processing module: extract the features of the surface temperature, the land use data and the digital elevation model data respectively, perform feature integration, and generate a feature matrix; use the daily average value of the sensor surface temperature as the true value label, screen the feature matrix, and obtain a valid data set;

[0018] Model construction module: construct an integrated learning model according to the valid data set; wherein the integrated learning model is composed of a trained random forest model, an XGBoost model, and a LightGBM model;

[0019] Prediction module: obtains the target feature matrix, inputs the target feature matrix into the integrated learning model for prediction, outputs the predicted value of the surface temperature of the target area, and completes the monitoring of the satellite and sensor data of the target area.

[0020] In a third aspect, the present application provides a device, comprising a processor and a memory coupled to the processor, wherein the memory stores program instructions for implementing a method for integrated satellite and sensor data collection and analysis; the processor is used to execute the program instructions stored in the memory to implement an integrated satellite and sensor data collection and analysis.

[0021] In a fourth aspect, the present application provides a storage medium storing program instructions executable by a processor, wherein the program instructions are used to execute a method for integrated satellite and sensor data collection and analysis.

[0022] The present application provides a satellite and sensor data integrated collection and analysis method and system, which has the following beneficial effects:

[0023] (1) By integrating multi-source data, including satellite remote sensing data, sensor data, land use data, and digital elevation model data, the monitoring scope has been expanded and the comprehensiveness and accuracy of the data have been improved;

[0024] (2) Through data cleaning, resampling, feature extraction and other steps, the quality and availability of data are effectively improved, providing a solid foundation for subsequent analysis and modeling;

[0025] (3) This application method adopts a stacked integrated machine learning model, which integrates the advantages of different models and improves prediction accuracy and generalization ability. At the same time, the final data set is generated to achieve comprehensive and accurate monitoring of the target area, providing strong data support for smart city construction, ecological environment monitoring and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic diagram of a flow chart of a satellite and sensor data integrated collection and analysis method according to Example 1 of the present application;

[0027] Figure 2 A flowchart of a satellite and sensor data integrated collection and analysis method according to Example 1 of the present application;

[0028] Figure 3 This is a schematic diagram of the structure of a satellite and sensor data integrated collection and analysis system according to Example 2 of the present application;

[0029] Figure 4 This is a schematic diagram of the device structure of Example 3 of the present application;

[0030] Figure 5 This is a schematic diagram of the storage medium structure of Example 4 of the present application. DETAILED DESCRIPTION

[0031] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The following is an analysis of the solutions in the prior art in combination with related technologies.

[0033] Satellite remote sensing monitoring has limited resolution. The resolution of some environmental monitoring satellites is limited and cannot provide high-resolution data, which limits the monitoring of some small-scale environmental changes. At the same time, it is susceptible to weather and clouds, which prevent satellite sensors from obtaining surface data, especially in severe weather conditions. This will lead to data discontinuity; data delay, satellite data transmission and processing may take some time, and data cannot be obtained instantly.

[0034] However, the spatial coverage of sensors is limited, and the coverage of sensor networks is usually limited, so a large number of sensors need to be deployed to cover large areas. Data quality and accuracy, sensors will be disturbed by the environment, resulting in reduced data quality and accuracy. In addition, there may be differences between sensors, which require calibration and correction. In summary, there are some technical limitations and challenges in both satellite environmental monitoring and sensor environmental monitoring. Therefore, the integrated collection and analysis of satellite and sensor data can effectively fuse large-scale monitoring data with high-resolution data, and coarse-grained data with fine-grained data, thereby improving the accuracy and resolution of monitoring data.

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0036] Example 1

[0037] See also Figure 1 , is a flow chart of a satellite and sensor data integrated collection and analysis method according to Example 1 of the present application; the steps include:

[0038] S1: Acquire comprehensive data, wherein the comprehensive data includes satellite remote sensing data, sensor data, land use data, and digital elevation model data.

[0039] In this embodiment, Landsat8 OLI_TIRS satellite remote sensing data is downloaded from the AI ​​Earth platform, surface temperature sensor data is downloaded from the self-developed sensor management platform, 30-meter spatial resolution land use data is downloaded from the China Land Cover Dataset website, and 30-meter resolution digital elevation model data is downloaded from the USGS Earth Explorer platform.

[0040] S2: Preprocess the satellite remote sensing data and the sensor data respectively to obtain the surface temperature and the daily average value of the sensor surface temperature.

[0041] In this embodiment, the satellite remote sensing data is preprocessed, specifically including:

[0042] Based on the accuracy of the collected satellite remote sensing data, in order to obtain the spatial resolution of the standardized data for subsequent analysis and comparison, the satellite remote sensing data is resampled to adapt it to a unified grid system with a resolution of 1 km. Considering the calibration deviation, inversion accuracy, and universality of the infrared thermal sensor band, the surface temperature is inverted using a single window algorithm, and the calculation formula is:

[0043]

[0044] Among them, T LS is the surface temperature; T a is the average atmospheric temperature; T Sensor is the brightness temperature observed by the remote sensor on the satellite; a and b are the empirical coefficient constants related to the Planck equation; C and D are intermediate variables, and the calculation formula is:

[0045] C=ετ

[0046] D=(1-ε)[1+(1-ε)τ]

[0047] Where ε is the surface emissivity and τ is the atmospheric transmittance from the ground to the sensor.

[0048] Preprocess the sensor data, including:

[0049] Considering the validity of the relevant factor data, the study area is divided into a unified grid system with a resolution of 30 meters. The sensor data is integrated and the daily average value of the sensor data in the grid is taken. When calculating the daily average temperature value monitored by the sensor, it is necessary to determine whether the sensor data of each grid is valid.

[0050] Specifically, the parameter n is introduced to determine the validity of the sensor monitoring data in the grid unit. For example, setting n to 8 means that in a grid unit, the average daily temperature of the grid on that day is considered valid only when the sensor recording period on a certain day is greater than or equal to 8 hours. If a grid records less than n hours, the sensor data of that day is discarded.

[0051] Calculate the daily average value of sensor data within the valid grid, the calculation formula is:

[0052]

[0053] Where i is the grid number; T avg (i) is the daily average temperature of the grid, that is, the daily average value of the sensor surface temperature; N is the number of grid records; t is different time; T i,t is the monitoring data of grid i at time t.

[0054] S3: extracting the features of the surface temperature, the land use data and the digital elevation model data respectively, and integrating the features to generate a feature matrix.

[0055] In this embodiment, various features are extracted and counted in a grid with a resolution of 30 meters to provide input for subsequent models to improve the accuracy of surface temperature inversion.

[0056] Feature extraction of surface temperature: The surface temperature is resampled to a unified grid system with a resolution of 30 meters, and the temperature value T of each 30-meter grid is extracted. rs As basic input features;

[0057] Feature extraction of land use data: Based on the land use data, different land object types are one-hot encoded according to the land use types in a unified grid system with a resolution of 30 meters, and the encoded features L are obtained as the basic input features for controlling different land object conditions;

[0058] Feature extraction of digital elevation model data: resampling the digital elevation model data into a unified grid system with a resolution of 30 meters, as an important feature reflecting terrain changes, extracting the elevation value H of each 30-meter grid as the basic input feature;

[0059] Input the above basis into the feature T rs , L, H are integrated into the feature matrix X = (T rs ,H,L).

[0060] S4: Taking the daily average value of the surface temperature of the sensor as the true value label, the feature matrix is ​​screened to obtain a valid data set.

[0061] In this embodiment, the daily average temperature of the effective grid in the 30-meter resolution grid is extracted from the daily average value of the sensor surface temperature. avg As the true value label. Integrate the feature matrix X with the true value label y; where X includes the temperature value T rs , encoding feature L, elevation value H, true value label y = T avg The measured surface temperature.

[0062] By filtering out grids with non-empty y values, a valid dataset with spatiotemporal consistency (X valid ,y); specifically including:

[0063] (X valid ,y)=(X i,day ,y i,day )|n i,day ≠null,i∈full grid set

[0064] Among them, (Xvalid ,y) is the effective grid feature matrix X valid and the true value label y; i is the grid number; day is the time corresponding to the feature.

[0065] S5: Construct an integrated learning model based on the valid data set; wherein the integrated learning model consists of a trained random forest model, an XGBoost model, and a LightGBM model.

[0066] In this embodiment, an integrated learning model is used to realize the integrated analysis of satellite remote sensing data and sensor data, and the output results of different machine learning models are integrated. ensemble , based on the valid data set (X valid ,y), three machine learning models: Random Forest, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting (LightGBM) are used to perform regression modeling on the feature matrix X. The output results of the three models are fused through a linear regression model to finally obtain a high-precision surface temperature prediction value. The specific steps are as follows:

[0067] S51: Establish a training set and a test set according to the valid data set, set the ratio of training set to test set = 7:3, and divide the training set and the test set;

[0068] S52: constructing a random forest model M based on the training set and the test set respectively RF 、XGBoost model M XGB 、LightGBM model M LGBM ;

[0069] S53: Using grid search to select the optimization parameters of the random forest model, the XGBoost model, and the LightGBM model;

[0070] S54: training the random forest model, the XGBoost model, and the LightGBM model respectively according to the optimization parameters;

[0071] S55: Get the output y of the random forest model RF , the output y of the XGBoost model XGB , the output y of the LightGBM model LGBM ;

[0072] S56: Construct a linear regression model, transform y RF ,y XGB ,y LGBM As the input of the linear regression model, the true value label y is used as the label, and the predicted value is obtained The calculation formula is:

[0073]

[0074] Among them, a, b, c, and d are coefficients, which are optimized by the least squares method;

[0075] S57: Get the trained random forest model, XGBoost model, and LightGBM model, i.e., the integrated learning model M ensemble .

[0076] S6: Obtain a target feature matrix, input the target feature matrix into the integrated learning model for prediction, output the predicted value of the surface temperature of the target area, and complete the monitoring of the satellite and sensor data of the target area.

[0077] In this embodiment, the trained integrated learning model is obtained according to step S5, and for the grid system with a resolution of 30 meters in the target area, the target feature matrix of all grids is input into the integrated learning model, and the surface temperature prediction value of each 30-meter grid is output. In this way, the surface temperature data of all grids in the whole period are completed, and an integrated data set of satellite and sensor data is constructed, so as to realize the integrated monitoring of satellite and sensor data of the target area.

[0078] In summary, Example 1 of the present application obtains satellite remote sensing data, sensor data, land use data, and digital elevation model data through multiple platforms, and performs preprocessing to improve data quality; then performs feature extraction, integration, and validity verification on the data to obtain an effective feature data set; uses a stacked integrated machine learning model for modeling, and fuses the output results of different models to improve prediction capabilities; predicts the acquired target feature matrix through an integrated learning model, outputs a surface temperature prediction value, and realizes integrated monitoring of satellite and sensor data in the target area. This application effectively integrates large-scale monitoring data and high-resolution data, improves the accuracy and monitoring range of monitoring data, and provides strong support for smart city construction, ecological environment monitoring, and other fields.

[0079] Example 2

[0080] See also Figure 3 , which is a structural diagram of a satellite and sensor data integrated collection and analysis system according to Embodiment 2 of the present application; the specific contents include:

[0081] Acquisition module: acquiring comprehensive data, including satellite remote sensing data, sensor data, land use data, and digital elevation model data;

[0082] Preprocessing module: preprocessing the satellite remote sensing data and the sensor data respectively to obtain the surface temperature and the daily average value of the sensor surface temperature;

[0083] Feature processing module: extract the features of the surface temperature, the land use data and the digital elevation model data respectively, perform feature integration, and generate a feature matrix; use the daily average value of the sensor surface temperature as the true value label, screen the feature matrix, and obtain a valid data set;

[0084] Model construction module: construct an integrated learning model according to the valid data set; wherein the integrated learning model is composed of a trained random forest model, an XGBoost model, and a LightGBM model;

[0085] Prediction module: obtains the target feature matrix, inputs the target feature matrix into the integrated learning model for prediction, outputs the predicted value of the surface temperature of the target area, and completes the monitoring of the satellite and sensor data of the target area.

[0086] Example 3

[0087] See also Figure 4 , is a schematic diagram of the device structure of Embodiment 3 of the present application. The device 50 includes a processor 51 and a memory 52 coupled to the processor 51 .

[0088] The memory 52 stores program instructions for implementing the above-mentioned satellite and sensor data integrated collection and analysis method.

[0089] The processor 51 is used to execute program instructions stored in the memory 52 to realize an integrated collection and analysis of satellite and sensor data.

[0090] The processor 51 may also be referred to as a CPU (Central Processing Unit).

[0091] The processor 51 may be an integrated circuit chip with signal processing capabilities. The processor 51 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0092] Example 4

[0093] See also Figure 5, which is a schematic diagram of the structure of the storage medium of Example 4 of the present application. The storage medium of the embodiment of the present application stores a program file 61 that can implement all the above methods, wherein the program file 61 can be stored in the above storage medium in the form of a software product, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a computer, a server, a mobile phone, a tablet, and other devices.

[0094] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0095] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0096] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the appended claims and their equivalents.

[0097] Of course, the present invention may have many other implementations. Based on this implementation, other implementations obtained by ordinary technicians in this field without any creative work are all within the scope of protection of the present invention.

Claims

1. A satellite and sensor data integrated collection and analysis method, characterized in that: include: Acquiring comprehensive data, including satellite remote sensing data, sensor data, land use data, and digital elevation model data; Preprocessing the satellite remote sensing data and the sensor data respectively to obtain the surface temperature and the daily average value of the sensor surface temperature; Extracting the features of the surface temperature, the land use data and the digital elevation model data respectively, and then integrating the features to generate a feature matrix; Taking the daily average value of the surface temperature of the sensor as the true value label, the feature matrix is ​​screened to obtain a valid data set; Constructing an integrated learning model according to the valid data set; wherein the integrated learning model is composed of a trained random forest model, an XGBoost model, and a LightGBM model; The target feature matrix is ​​obtained, the target feature matrix is ​​input into the integrated learning model for prediction, the predicted value of the surface temperature of the target area is output, and the monitoring of the satellite and sensor data of the target area is completed.

2. The satellite and sensor data integrated collection and analysis method according to claim 1, characterized in that: The steps of preprocessing the satellite remote sensing data and the sensor data to obtain the daily average value of the surface temperature and the sensor surface temperature include the following steps: The single window algorithm is used to invert the surface temperature, and the calculation formula is: Among them, T LS is the surface temperature; T a is the average atmospheric temperature; T Sensor is the brightness temperature observed by the remote sensor on the satellite; a and b are the empirical coefficient constants related to the Planck equation; C and D are intermediate variables, and the calculation formula is: C=ετ D=(1-ε)[1+(1-ε)τ] Where ε is the surface emissivity; τ is the atmospheric transmittance from the ground to the sensor; Divide the area where sensor data is obtained into grids, determine the validity of sensor data in the grid cells, and calculate the daily average value of sensor data in the valid grids. The calculation formula is: Where i is the grid number; T avg (i) is the average daily temperature of the grid; N is the number of grid records; t is different time; T i,t is the monitoring data of grid i at time t.

3. The integrated satellite and sensor data collection and analysis method according to claim 2, characterized in that: The determination of the validity of the sensor data in the grid unit includes: introducing a parameter n, if the sensor recording period is greater than or equal to n hours, the sensor data of the grid is determined to be valid, that is, it is a valid grid; if the sensor recording period is less than n hours, the recorded sensor data.

4. The satellite and sensor data integrated collection and analysis method according to claim 1, characterized in that: After extracting the features of the surface temperature, the land use data and the digital elevation model data respectively, integrating the features and generating a feature matrix specifically includes the following steps: Resample the surface temperature to a grid and extract the temperature value T of the grid rs ; Based on the land use data, one-hot encoding is performed on different land feature types according to the land use types in the grid to obtain a coding feature L; Resampling the digital elevation model data into a grid, and extracting the elevation value H of the grid; Set the temperature value T rs , encoding features L, elevation values ​​H are integrated into the feature matrix X = (T rs ,H,L).

5. The satellite and sensor data integrated collection and analysis method according to claim 1, characterized in that: In the step of taking the daily average value of the surface temperature of the sensor as the true value label and screening the feature matrix to obtain a valid data set, the following steps are specifically included: Integrate the feature matrix X with the true value label y; where X includes the temperature value T rs , encoding feature L, elevation value H, true value label y = T avg is the measured surface temperature; By filtering out grids with non-empty y values, a valid dataset (X valid ,y); specific include: (X valid ,y)=(X i,day ,y i,day )|y i,day ≠null,i∈full grid set Among them, (X valid ,y) is the effective grid feature matrix X valid and the true value label y; i is the grid number; day is the time corresponding to the feature.

6. The satellite and sensor data integrated collection and analysis method according to claim 1, characterized in that: In the step of constructing an integrated learning model according to the valid data set, wherein the integrated learning model is composed of a trained random forest model, an XGBoost model, and a LightGBM model, the following steps are specifically included: Establishing a training set and a test set according to the valid data set; Based on the training set and the test set, a random forest model, an XGBoost model, and a LightGBM model are constructed respectively, and the optimization parameters of the random forest model, the XGBoost model, and the LightGBM model are selected by grid search; The random forest model, XGBoost model, and LightGBM model are trained respectively according to the optimization parameters to obtain the output y of the random forest model. RF , the output y of the XGBoost model XGB , the output y of the LightGBM model LGBM ; y RF ,y XGB ,y LGBM As input to the pre-built linear regression model, the true value label y is used as the label, and the predicted value is obtained The calculation formula is: Among them, a, b, c, and d are coefficients, which are optimized by the least squares method; then the trained random forest model, XGBoost model, and LightGBM model are obtained, that is, the integrated learning model M ensemble .

7. The satellite and sensor data integrated collection and analysis method according to claim 1, characterized in that: The steps of obtaining a target feature matrix, inputting the target feature matrix into the integrated learning model for prediction, outputting a predicted value of the surface temperature of the target area, and completing the monitoring of the satellite and sensor data of the target area specifically include the following steps: Inputting the target feature matrix into the integrated learning model to obtain a predicted value of surface temperature; Based on the predicted surface temperature values, the surface temperature data of the entire grid for the entire period is supplemented, a data set of satellite and sensor data is constructed, and the monitoring of satellite and sensor data in the target area is completed.

8. A system for the integrated satellite and sensor data collection and analysis method according to claim 1, characterized in that: include: Acquisition module: acquiring comprehensive data, including satellite remote sensing data, sensor data, land use data, and digital elevation model data; Preprocessing module: preprocessing the satellite remote sensing data and the sensor data respectively to obtain the surface temperature and the daily average value of the sensor surface temperature; Feature processing module: extracting the features of the surface temperature, the land use data and the digital elevation model data respectively, and then integrating the features to generate a feature matrix; Taking the daily average value of the surface temperature of the sensor as the true value label, the feature matrix is ​​screened to obtain a valid data set; Model construction module: construct an integrated learning model according to the valid data set; wherein the integrated learning model is composed of a trained random forest model, an XGBoost model, and a LightGBM model; Prediction module: obtains the target feature matrix, inputs the target feature matrix into the integrated learning model for prediction, outputs the predicted value of the surface temperature of the target area, and completes the monitoring of the satellite and sensor data of the target area.

9. A device, characterized in that: The device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions for implementing a method for integrated satellite and sensor data collection and analysis as described in any one of claims 1-7; and the processor is used to execute the program instructions stored in the memory to implement an integrated satellite and sensor data collection and analysis.

10. A storage medium, characterized in that: The method stores program instructions executable by a processor, wherein the program instructions are used to execute the satellite and sensor data integrated collection and analysis method as described in any one of claims 1 to 7.

Images