A method, system, device and storage medium for estimating surface temperature

Abstract

The present invention discloses a surface temperature estimation method, system, device and storage medium, and relates to the technical field of surface temperature estimation. The method comprises the following steps: obtaining a daily surface temperature dataset with low spatial resolution and an underlying surface dataset with high spatial resolution; reprojecting the daily surface temperature dataset with low spatial resolution to obtain a new daily surface temperature dataset; using a sliding window clipping method to process the spatial resolutions of the new daily surface temperature dataset and the underlying surface dataset to be consistent; and inputting the processed new daily surface temperature data and the underlying surface data as feature data into a surface temperature estimation model to obtain daily surface temperature data with high spatial resolution. The model can provide reliable long-time series, high-spatial-resolution surface temperature data when performing resource and environmental monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of surface temperature estimation, and in particular to a surface temperature estimation method, system, device and storage medium. Background Art

[0002] Surface temperature is closely related to the interaction and energy exchange between the Earth's surface and the atmosphere, and is a key parameter in land surface system processes at regional and global scales. As the most important and fundamental physical parameter of the Earth's surface, high-quality surface temperature is widely used in various disciplines, including environmental research, hydrology, ecology, and urban heat island research.

[0003] In agriculture, comparative analysis of long-term surface temperature data can inform crop growth assessments and selection of suitable crops. Furthermore, surface temperature affects soil evaporation and crop transpiration. By analyzing long-term surface temperature data, soil and crop water requirements can be determined, enabling adjustments to irrigation volume and frequency. Furthermore, long-term surface temperature data can be used to predict crop yields under varying surface temperature conditions, providing crucial data support for agricultural production planning, food security management, and crop insurance assessments. In natural disaster monitoring and forecasting (particularly drought and forest fires), high-temporal and high-spatial resolution surface temperature data and water resource data can be used to predict the onset of droughts and facilitate early water resource allocation. Furthermore, changes in surface temperature data prior to a forest fire can be used to analyze the likelihood of a forest fire and the specific areas where it is likely to occur. Therefore, high-temporal and high-spatial resolution surface temperature data provides crucial data support for agriculture, meteorology, and the environment.

[0004] However, the existing surface temperature data has the problem that long time series and high spatial resolution are difficult to coexist, resulting in a lack of reliable long time series and high spatial resolution surface temperature data when conducting resource and environmental monitoring, and therefore cannot meet the needs of application scenarios in agriculture, meteorology, and environment. Summary of the Invention

[0005] In view of the problem that long time series and high spatial resolution are difficult to coexist in the surface temperature data directly obtained by the existing technology, resulting in a lack of reliable long time series and high spatial resolution surface temperature data when conducting resource and environmental monitoring, the present invention proposes a surface temperature estimation method, system, equipment and storage medium. By exploring the nonlinear relationship between long time series and low spatial resolution surface temperature data and high spatial resolution underlying surface information, a long time series and high spatial resolution surface temperature data estimation model is constructed to improve the temporal and spatial resolution of surface temperature data, thereby solving the problems existing in the existing technology.

[0006] A method for estimating land surface temperature comprises the following steps:

[0007] Acquire a low-spatial-resolution daily surface temperature dataset, a high-spatial-resolution underlying surface dataset, and a high-spatial-resolution surface temperature dataset acquired using the Landsat 8 OLI band 10; the low-spatial-resolution dataset ranges from 100 to 1000 meters, and the high-spatial-resolution dataset ranges from 30 meters or less;

[0008] The low spatial resolution daily surface temperature dataset was scaled and reprojected to obtain a new daily surface temperature dataset with the same resolution as the high spatial resolution surface temperature dataset obtained by the Landsat 8 OLI band 10.

[0009] The sliding window clipping method is used to make the spatial resolution of the new daily surface temperature dataset and the underlying surface dataset consistent;

[0010] The high-spatial-resolution surface temperature dataset acquired by the Landsat 8 OLI band 10 was used as the label dataset, and the newly processed daily surface temperature dataset and underlying surface dataset were used as the feature dataset. The random forest model was trained using the label dataset and the feature dataset to obtain the surface temperature estimation model.

[0011] The underlying surface data to be estimated and the new daily surface temperature data with the same spatial resolution are input into the surface temperature estimation model to obtain the daily surface temperature data with high spatial resolution.

[0012] Furthermore, the low spatial resolution daily surface temperature dataset is obtained by selecting MOD11A1 data with cloud cover less than 0.5% from the NASA database.

[0013] Furthermore, the high spatial resolution underlying surface dataset includes a normalized vegetation index (NDVI) dataset and a land cover dataset; wherein the NDVI dataset is obtained by selecting a Landsat8-9OLI / TIRS Collection2 Level-2 dataset with a cloud coverage rate of less than 5% from the USGS database, and the SR_B4.TIF and SR_B5.TIF band data in the Level-2 Surface Reflectance Bands are used to calculate the NDVI, and the calculation formula is:

[0014]

[0015] Among them, B4 is the red light band of Landsat8OLI, and B5 is the near-infrared band.

[0016] Furthermore, the high spatial resolution surface temperature dataset obtained by the 10th band of Landsat8 OLI is obtained by selecting the Landsat8-9 OLI / TIRS Collection 2 Level-2 dataset with a cloud coverage rate of less than 5% in the USGS database, and using the Level-2 Surface Temperature Bands to calculate the high spatial resolution surface temperature dataset LST, which is calculated as follows:

[0017] LST=0.00341802×B 10 +149

[0018] Among them, B 10 is the 10th band in the Landsat8-9OLI / TIRS Collection2Level-2 dataset. Further, the surface temperature estimation model is expressed as:

[0019] Y tij =K[NDVI ti , LCD t , MODIS tij ]

[0020] Among them, Y tij is the daily surface temperature data with high spatial resolution on the jth day of the i-th month of the t-th year, K is the trained integrated machine learning algorithm, NDVI ti is the NDVI data of month i in year t, LCD t is the land cover data for year t, MODIS tij The new daily surface temperature data for the jth day of the i-th month of the t-th year after processing is consistent with the spatial resolution of the underlying surface data.

[0021] Furthermore, it also includes the use of mean absolute percentage error MAPE, root mean square error RMSE, mean absolute error MAE, determination coefficient R 2 , Adjusted R 2 The performance of the surface temperature estimation model is evaluated using six indicators: mean square error (MSE); among which:

[0022] The mean absolute percentage error MAPE expression is:

[0023]

[0024] where y i is the actual value of the surface temperature, y′ i is the predicted value of surface temperature, n is the number of samples of surface temperature;

[0025] The root mean square error RMSE expression is:

[0026]

[0027] The mean absolute error MAE expression is:

[0028]

[0029] The coefficient of determination R 2 The expression is:

[0030]

[0031] in is the average surface temperature;

[0032] The adjusted coefficient of determination Adjusted R 2 The expression is:

[0033]

[0034] where R 2 is the coefficient of determination, p is the number of independent variables;

[0035] The mean square error MSE expression is:

[0036]

[0037] The present invention also includes a surface temperature estimation system, comprising:

[0038] An acquisition module is used to acquire a daily surface temperature dataset with low spatial resolution, an underlying surface dataset with high spatial resolution, and a surface temperature dataset with high spatial resolution acquired in the 10th band of the Landsat 8 OLI. The low spatial resolution range is 100 meters to 1000 meters, and the high spatial resolution range is within 30 meters.

[0039] The reprojection module is used to scale the low-spatial-resolution daily surface temperature dataset and reproject the scaled daily surface temperature dataset to obtain a new daily surface temperature dataset with the same resolution as the high-spatial-resolution surface temperature dataset acquired by the Landsat 8 OLI band 10.

[0040] A processing module is used to use a sliding window clipping method to make the spatial resolution of the new daily surface temperature dataset and the underlying surface dataset consistent;

[0041] The model building module is used to use the high-spatial-resolution surface temperature dataset acquired by the Landsat 8 OLI Band 10 as the label dataset, and the new daily surface temperature dataset and underlying surface dataset after processing as the feature dataset. The random forest model is trained with the label dataset and the feature dataset to obtain the surface temperature estimation model.

[0042] The estimation module is used to input the underlying surface data to be estimated and the new daily surface temperature data with the same spatial resolution into the surface temperature estimation model to obtain the daily surface temperature data with high spatial resolution.

[0043] The present invention also includes a computer device for estimating ground surface temperature, comprising: a memory, a processor, and a computer program stored in the memory, wherein the processor implements the steps of the ground surface temperature estimation method when executing the computer program.

[0044] The present invention also includes a readable storage medium, wherein the readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, they are used to execute the steps of the surface temperature estimation method.

[0045] The present invention provides a surface temperature estimation method, system, device and storage medium, which have the following features:

[0046] Beneficial effects:

[0047] The present invention selects long-term daily surface temperature data as input data for surface temperature estimation, thereby ensuring data continuity and reliability at the source; by reprojecting long-term low-spatial-resolution surface temperature data, the spatial-resolution surface temperature data is sampled into new surface temperature data with the same resolution as the high-spatial-resolution surface temperature data acquired by the 10th band of Landsat 8's OLI, and the spatial resolution of the data is processed to be consistent with the spatial resolution of the underlying surface data through a sliding window clipping method. Based on a random forest model, a surface temperature data estimation model is obtained through specific high-spatial-resolution underlying surface information and long-term low-spatial-resolution surface temperature data, thereby predicting long-term, high-spatial-resolution and high-precision surface temperature data. This method can provide reliable long-term, high-spatial-resolution surface temperature data when conducting resource and environmental monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a schematic diagram of the structure of a method for estimating ground surface temperature in an embodiment of the present invention;

[0049] Figure 2 This is the 30m surface temperature map in the embodiment of the present invention;

[0050] Figure 3 This is the surface temperature map at 990m in the embodiment of the present invention;

[0051] Figure 4 This is a schematic diagram of 30mNDVI in an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of 30m land cover data in an embodiment of the present invention;

[0053] Figure 6 is the R of the RandomForest model in the embodiment of the present invention 2 Schematic diagram of the results;

[0054] Figure 7 is the R of the XG-Boost model in the embodiment of the present invention 2 Schematic diagram of the results;

[0055] Figure 8 is the R of the CatBoost model in the embodiment of the present invention 2 Schematic diagram of the results;

[0056] Figure 9 Schematic diagram of the mean absolute error (MAE) results of the RandomForest model in an embodiment of the present invention; Figure 9 (a) is a schematic diagram of the density distribution results of MAE. Figure 9 (b) is a schematic diagram of the proportion of different MAE intervals;

[0057] Figure 10 This is a schematic diagram of the mean absolute error (MAE) results of the XG-Boost model in an embodiment of the present invention; Figure 10 (a) is a schematic diagram of the density distribution results of MAE. Figure 10 (b) is a schematic diagram of the proportion of different MAE intervals;

[0058] Figure 11 Schematic diagram of the mean absolute error (MAE) results of the CatBoost model in an embodiment of the present invention; Figure 11 (a) is a schematic diagram of the density distribution results of MAE. Figure 11 (b) is a schematic diagram of the proportion of different MAE intervals;

[0059] Figure 12 Schematic diagram of the mean square error (MSE) result of the RandomForest model in an embodiment of the present invention; Figure 12 (a) is a schematic diagram of the density distribution results of MSE. Figure 12 (b) is a schematic diagram of the proportion of different intervals of MSE;

[0060] Figure 13Schematic diagram of the mean square error (MSE) result of the XG-Boost model in an embodiment of the present invention; Figure 13 (a) is a schematic diagram of the density distribution results of MSE. Figure 13 (b) is a schematic diagram of the proportion of different intervals of MSE;

[0061] Figure 14 Schematic diagram of the mean square error (MSE) result of the CatBoost model in an embodiment of the present invention; Figure 14 (a) is a schematic diagram of the density distribution results of MSE. Figure 14 (b) is a schematic diagram of the proportion of different intervals of MSE;

[0062] Figure 15 Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in January 2022 using the RandomForest model in an embodiment of the present invention;

[0063] Figure 16 Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in February 2022 using the RandomForest model in an embodiment of the present invention;

[0064] Figure 17 Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in March 2022 using the RandomForest model in an embodiment of the present invention;

[0065] Figure 18 This is a schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in April 2022 using the RandomForest model in an embodiment of the present invention;

[0066] Figure 19 Schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in May 2022 using the RandomForest model in an embodiment of the present invention;

[0067] Figure 20 Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in June 2022 using the RandomForest model in an embodiment of the present invention;

[0068] Figure 21 Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in July 2022 using the RandomForest model in an embodiment of the present invention;

[0069] Figure 22 Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in August 2022 using the RandomForest model in an embodiment of the present invention;

[0070] Figure 23Schematic diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in September 2022 using the RandomForest model in an embodiment of the present invention;

[0071] Figure 24 This is a schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in October 2022 using the RandomForest model in an embodiment of the present invention;

[0072] Figure 25 This is a schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in November 2022 using the RandomForest model in an embodiment of the present invention;

[0073] Figure 26 This is a schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in December 2022 using the RandomForest model in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0075] The present invention proposes a surface temperature estimation method. First, low spatial resolution data that can provide long time series support are selected as input data to ensure the long time series of the predicted surface temperature. Then, a variety of underlying surface information related to the surface temperature are integrated to ensure the high spatial resolution of the prediction model. Finally, a variety of machine learning models are used to construct a high temporal and spatial resolution surface temperature estimation model to improve the temporal and spatial resolution of existing surface temperature data. Taking a certain city as the research object, long-time series low spatial resolution surface temperature data (MODIS daily surface temperature data) and high spatial resolution underlying surface information (NDVI and land cover data) with strong correlation between the temporal and spatial distribution of surface temperature are used as input variables, and high temporal and high spatial resolution surface temperature data are used as output variables. By constructing different machine learning surface temperature models and comparing their estimation accuracy differences, the temporal and spatial resolution of surface temperature data can be improved. Figure 1 As shown, the specific steps include:

[0076] S1. Data preparation: Obtain long-term, low-spatial-resolution surface temperature data and high-spatial-resolution underlying surface data, as well as high-spatial-resolution surface temperature data obtained in the 10th band of the Landsat 8 OLI.

[0077] S1.1. Obtaining long-term, low-spatial-resolution surface temperature data: The long-term, low-spatial-resolution surface temperature data selected in the present invention is a daily surface temperature dataset with a spatial resolution of 1000 meters (LST990m). The data is downloaded from the MOD11A1 data with a cloud cover of less than 0.5% in the NASA database.

[0078] S1.2. Obtaining high-spatial-resolution underlying surface data: The high-spatial-resolution underlying surface data selected in the present invention include 30-meter spatial-resolution NDVI data (NDVI30m) and 30-meter spatial-resolution land cover data (2022Type30m). The NDVI data is obtained from the Landsat8-9OLI / TIRS Collection2 Level-2 dataset with a cloud coverage rate of less than 5% selected from the USGS database. NDVI is calculated using the SR_B4.TIF and SR_B5.TIF band data in the Level-2 Surface Reflectance Bands (13 files). The land cover data uses the national 30-meter land cover data released by the team of Professors Yang Jie and Huang Xin of Wuhan University.

[0079] S1.3. Surface temperature data with high spatial resolution: The surface temperature data with a spatial resolution of 30 meters obtained in the present invention is used for parameter adjustment and accuracy verification in the process of building the surface temperature model. The data is selected from the Landsat8-9OLI / TIRS Collection2Level-2 dataset with a cloud coverage rate of less than 5% in the USGS database, and the 30-meter spatial resolution surface temperature data (LSTY30m) is calculated using Level-2SurfaceTemperatureBands (14 files).

[0080] S2. Data preprocessing.

[0081] S2.1. Calculate the 30-meter spatial resolution land surface temperature data (LSTY30m) using the Level-2 Surface Temperature Bands (14 files) data in the Landsat 8-9 OLI / TIRS Collection 2 Level-2 dataset. The calculation formula is as follows:

[0082] LST=0.00341802×B 10 +149

[0083] Specific multiplication factor B 10 This can be found in the data manual published by USGS.

[0084] S2.2. Use the Level-2 Surface Reflectance Bands (13 f.les) SR_B4.TIF and SR_B5.TIF bands in the Landsat8-9OLI / TIRS Collection2 Level-2 dataset to calculate the NDVI data with a spatial resolution of 30 meters. The calculation formula is as follows:

[0085]

[0086] Where B4 is the red light band of Landsat8 OLI, and B5 is the near-infrared band.

[0087] S2.3. First, scale the 1000-meter-resolution daily land surface temperature dataset (LST990m) to a uniform unit of Kelvin. Next, reproject the data to match the Landsat 8-9OLI / TIRS projection. Finally, perform sliding window cropping (i.e., define a rectangular region as the study area and crop all data to that region) and resample the data to a 30-meter spatial resolution, ensuring a uniform 30-meter spatial resolution for all input and output data.

[0088] LST 990m =0.02×Data 990m

[0089] Where Data 990m is the extracted original data pixel value.

[0090] For example, MODIS has a lower spatial resolution than Landsat, so the area covered by a single MODIS pixel contains data from multiple Landsat pixels, resulting in incomplete alignment of data with different resolutions. Therefore, a region extraction method is proposed. First, all data projections are unified to avoid pixel mismatching due to different projections. Second, the MODIS data are resampled to an integer multiple of the Landsat data resolution (990m). Each pixel is then split into 33 pixels with the same value, ensuring that the resolution of MODIS pixels is consistent with that of the Landsat data (all 30m), achieving uniform spatial location and resolution. A sliding window approach is then used to unify the data: first, a rectangular region is determined as the study area, and the coordinates of the upper left corner of the rectangle and the pixel index containing this point are obtained. Second, the number of rows and columns of pixels required for the rectangular region is determined (2343, 2112). Finally, the different data are cropped based on the upper left corner pixel index and the number of rows and columns. The above operations unify the projection, spatial position and total number of pixels of all data, reducing the model training error.

[0091] S3. The surface temperature estimation model is obtained by training the random forest model using the high-spatial-resolution surface temperature data obtained from the 10th band of Landsat 8's OLI as label data and the new surface temperature data and underlying surface data after consistent processing as feature data.

[0092] S3.1. The preprocessed NDVI_30m, Type_30m, and LST_990m data will be used as feature data, and LST_30m will be used as label data. The surface temperature calculation formula with high temporal and spatial resolution can be expressed as:

[0093] Y=AX+B

[0094] In the formula, Y is the high temporal and spatial resolution surface temperature data that needs to be calculated, A is the trained ensemble machine learning model, B is the fitting constant, and X is the combination of the three variables NDVI_30m, Type_30m, and LST_990m, that is:

[0095] X = [x1, x2, x3]

[0096] x1 and x2 are monthly NDVI data (NDVI_30m) and annual land cover data (Type_30m), respectively. x3 is daily MODIS 1km land surface temperature data (LST_990m). In the high-precision land surface temperature data prediction for the jth day of the i-th month of the t-th year, it is expressed as:

[0097] Y tij =K[NDVI ti , LCD t , MODIS tij ]

[0098] Among them, Y tij is the 30m surface temperature data of the jth day of the i-th month of the t-th year, K is the integrated machine learning algorithm obtained by training, NDVI ti is the NDVI data of month i in year t, LCD t is the land cover data for year t, MODIS tij The surface temperature data at 1 km on the jth day of the i-th month of the t-th year.

[0099] S3.2. Construction of surface temperature estimation model.

[0100] S3.2.1. The following three machine learning algorithms are used, including (1) XG-Boost; XG-Boost is the abbreviation of Extreme Gradient Boosting. It is an integrated machine learning algorithm based on decision trees and an improved version of GBDT gradient boosting tree. The two have the same idea, but XG-Boost has made many optimizations, such as using the second-order Taylor formula expansion to optimize the loss function and improve the calculation accuracy, using the regularization term to simplify the model (parameter: reg_lambda) to avoid overfitting, and using the Blocks storage structure to perform parallel calculations (parameter device). (2) CatBoost; CatBoost is similar to XG-Boost and is also an improved version of GBDT. Its characteristics are that the algorithm has fewer parameters, supports categorical variables and has high accuracy. The accuracy of the algorithm can be further improved by modifying the parameters. Compared with the XG-Boost algorithm, which is also a gradient boosting tree, CatBoost has more adjustable parameters, which is convenient for optimization according to one's own needs. (3) Random Forest: Random Forest is an ensemble learning method based on decision trees. It improves the accuracy and stability of the model by constructing multiple decision trees and aggregating the results. Similar to XG-Boost, the Random Forest algorithm also adopts the idea of ​​ensemble learning, but it introduces randomness when constructing decision trees. It uses replacement sampling when selecting data points and introduces random selection when selecting split attributes, thereby increasing the diversity of the model and reducing the risk of overfitting.

[0101] S3.2.2. Based on the feature data and label data, different algorithms use different rules to select feature data and calculate a result. Based on the difference between the label data and the result, the model parameters or scoring rules are adjusted for the next round of calculations, thereby obtaining a result that is closer to the label data. Through continuous iteration, the parameters that best approximate the label data are obtained. The random forest model with the best surface temperature prediction accuracy was used, using different tree splitting rules. The model parameter adjustment results are shown in Table 1.

[0102] Table 1 Results of tuning the main parameters of the random forest model

[0103]

[0104] S4. Model accuracy assessment: When comparing the performance of different surface temperature estimation models, six indicators are introduced: mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), determination coefficient (R) 2 , Adjusted R 2 , mean square error MSE, specifically as follows:

[0105] (1)MAPE (Mean absolute percentage error): MAPE is the mean absolute percentage error, which measures the difference between the predicted value and the actual value. The calculation formula is:

[0106]

[0107] where y i is the actual value of the surface temperature, y i is the predicted value of the surface temperature, and n is the number of samples of the surface temperature.

[0108] (2) RMSE (Root Mean Square Error): RMSE is the root mean square error, which is the square root of MSE (mean square error). RMSE measures the deviation between the predicted value and the actual value. The calculation formula is:

[0109]

[0110] (3) MAE (Mean Absolute Error): MAE is the mean absolute error, which is the average of the absolute differences between the predicted value and the actual value. The calculation formula is as follows:

[0111]

[0112] (4)R 2 (R-squared or Coefficient of Determination):R 2 is the coefficient of determination, which measures the proportion of the variability explained by the model to the total variability, R 2 The value of is between 0 and 1. The value close to 1 means that the model can well explain the variability of the data, that is, the model effect is better. The calculation formula is as follows:

[0113]

[0114] in is the average surface temperature.

[0115] (5)Adjusted R 2 : Adjusted R 2 It is R 2 An improvement of the adjusted R, which takes into account the number of independent variables in the model and penalizes the addition of multiple irrelevant variables to the model. 2 Than ordinary R 2 More rigorous and more suitable for comparing models with different numbers of independent variables. The calculation formula is as follows:

[0116]

[0117] where R 2 is the coefficient of determination and p is the number of independent variables.

[0118] (6) MSE (Mean Squared Error): MSE is the mean squared error, which measures the average of the squares of the differences between the predicted value and the actual value. MSE is a commonly used indicator to measure the prediction performance of a model, especially in regression analysis. A high MSE indicates that the model prediction is significantly different from the actual result. The calculation formula is as follows:

[0119]

[0120] The present invention selects input data supported by long time series for surface temperature estimation, ensuring data continuity and reliability at the source; sliding window prediction is performed when cleaning the data, and a rectangle is drawn according to the required coordinates and length and width, which technically provides the possibility and convenience for splicing at a larger spatial scale; through regression analysis of specific high-spatial-resolution underlying surface information and long-time series low-spatial-resolution surface temperature data with machine learning methods, a long-time series, high-spatial-resolution, and high-precision surface temperature data estimation model can be obtained; due to the use of sliding window prediction based on geographic coordinates, this prediction method provides the possibility of large-scale data splicing; the present invention uses long-time series low-spatial-resolution surface temperature data and high-spatial-resolution underlying surface information data as input variables after a specific data cleaning method, and then combines different adjusted machine learning methods to establish a regression model for the long-time series low-spatial-resolution surface temperature data. The model is used to estimate the surface temperature data at a high spatial resolution. According to six commonly used regression analysis accuracy evaluation methods, a long-time series high-spatial-resolution surface temperature estimation method with high accuracy, strong explanatory power, and low overfitting is obtained.

[0121] To demonstrate the practicality of the present invention, part of a city was selected as the study area, and data were downloaded on June 16, 2022 (with low cloud cover). Landsat8OLI data, MODIS11A1 data, and land cover data were downloaded according to the download method in the technical details. After data screening, calculation, and cleaning, four usable data sets were obtained. These four sets of data were unified in terms of geographic coordinates, projection, area, and number of pixels. The surface temperature map of the 30m study area ( Figure 2 Surface temperature map of the middle 30m study area), surface temperature map of the 990m study area ( Figure 3 Surface temperature map of the study area at 990m), 30m NDVI ( Figure 4 30m NDVI), 30m land cover data ( Figure 5 land cover data at 30 m).

[0122] The four variables were used as data to train the machine learning model, and their accuracy was verified using six accuracy verification methods. The density plot was used to print R 2 , MAE, MSE reference model accuracy.

[0123] Goodness of fit of three different machine learning methods: XG-Boost, CatBoost and RandomForest 2 as follows: Figure 6 is the R of the RandomForest model 2 Results diagram, Figure 7 is the R of the XG-Boost model 2 Results diagram, Figure 8 is the R of the CatBoost model 2 Schematic diagram of the results.

[0124] The mean absolute error (MAE) of XG-Boost, CatBoost, and RandomForest is as follows: Figure 9 This is a schematic diagram of the mean absolute error MAE results of the RandomForest model; Figure 9 (a) is a schematic diagram of the density distribution results of MAE. Figure 9 (b) is a schematic diagram of the proportion of different MAE intervals; Figure 10 This is a schematic diagram of the mean absolute error (MAE) results of the XG-Boost model; Figure 10 (a) is a schematic diagram of the density distribution results of MAE. Figure 10 (b) is a schematic diagram of the proportion of different MAE intervals; Figure 11 This is a schematic diagram of the mean absolute error (MAE) results of the CatBoost model; Figure 11 (a) is a schematic diagram of the density distribution results of MAE. Figure 11 (b) is a schematic diagram of the proportion of different MAE intervals.

[0125] The mean square error (MSE) of XG-Boost, CatBoost, and RandomForest is as follows: Figure 12 This is a schematic diagram of the mean square error MSE results of the RandomForest model; Figure 12 (a) is a schematic diagram of the density distribution results of MSE. Figure 12 (b) is a schematic diagram of the proportion of different intervals of MSE; Figure 13 is a schematic diagram of the mean square error (MSE) results of the XG-Boost model; 13 (a) is a schematic diagram of the density distribution results of MSE, Figure 13 (b) is a schematic diagram of the proportion of different intervals of MSE; Figure 14is a schematic diagram of the mean square error (MSE) results of the CatBoost model; 14 (a) is a schematic diagram of the density distribution results of MSE, Figure 14 (b) is a schematic diagram of the proportion of different MSE intervals.

[0126] Based on the above machine learning accuracy evaluation indicators, the Random Forest machine learning method with the best performance was selected to predict the ground temperature data with a spatial resolution of 30 meters for each month in 2022. The prediction results are as follows: Figure 15 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in January 2022 using the RandomForest machine learning method. Figure 16 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in February 2022 using the RandomForest machine learning method. Figure 17 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in March 2022 using the RandomForest machine learning method. Figure 18 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in April 2022 using the RandomForest machine learning method. Figure 19 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in May 2022 using the RandomForest machine learning method. Figure 20 This is a schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in June 2022 using the RandomForest machine learning method. Figure 21 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in July 2022 using the RandomForest machine learning method. Figure 22 This is a diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in August 2022 using the RandomForest machine learning method. Figure 23 This is a diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in September 2022 using the RandomForest machine learning method. Figure 24 This is a diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in October 2022 using the RandomForest machine learning method. Figure 25 This is a diagram of the prediction results of ground temperature data with a spatial resolution of 30 meters in November 2022 using the RandomForest machine learning method. Figure 26 This is a schematic diagram of the ground temperature data prediction results with a spatial resolution of 30 meters in December 2022 using the RandomForest machine learning method.

[0127] The present invention can obtain a long-term, high-spatial-resolution, and high-precision surface temperature data estimation model through regression analysis of specific high-spatial-resolution underlying surface information and long-term, low-spatial-resolution surface temperature data with machine learning methods. Due to the use of sliding window prediction based on geographic coordinates, this prediction method makes it possible to achieve large-scale data splicing.

[0128] Based on the same inventive concept, the present invention also proposes a surface temperature estimation system, comprising:

[0129] The acquisition module is used to obtain a low-spatial-resolution daily surface temperature dataset, a high-spatial-resolution underlying surface dataset, and a high-spatial-resolution surface temperature dataset acquired in the 10th band of the Landsat 8 OLI. The low-spatial-resolution range is 100 to 1000 meters, and the high-spatial-resolution range is within 30 meters.

[0130] The reprojection module is used to scale the low-spatial-resolution daily surface temperature dataset and reproject the scaled daily surface temperature dataset to obtain a new daily surface temperature dataset with the same resolution as the high-spatial-resolution surface temperature dataset obtained by the Landsat 8 OLI band 10.

[0131] The processing module is used to use the sliding window clipping method to make the spatial resolution of the new daily surface temperature dataset and the underlying surface dataset consistent.

[0132] The model building module is used to use the high-spatial-resolution surface temperature dataset obtained by the 10th band of Landsat8's OLI as the label dataset, and the new daily surface temperature dataset and underlying surface dataset after consistent processing as the feature dataset. The random forest model is trained using the label dataset and the feature dataset to obtain the surface temperature estimation model.

[0133] The estimation module is used to input the underlying surface data to be estimated and the new daily surface temperature data with the same spatial resolution into the surface temperature estimation model to obtain the daily surface temperature data with high spatial resolution.

[0134] Based on the same inventive concept, the present invention also proposes a computer device for estimating ground surface temperature, comprising: a memory, a processor, and a computer program stored in the memory, wherein the processor implements the steps of the ground surface temperature estimation method when executing the computer program.

[0135] Based on the same inventive concept, the present invention also proposes a readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, they are used to execute the steps of the surface temperature estimation method.

[0136] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A method for estimating surface temperature, characterized in that: The following steps are involved: Acquire a low-spatial-resolution daily surface temperature dataset, a high-spatial-resolution underlying surface dataset, and a high-spatial-resolution surface temperature dataset acquired using the Landsat 8 OLI band 10; the low-spatial-resolution dataset ranges from 100 to 1000 meters, and the high-spatial-resolution dataset ranges from 30 meters or less; The low spatial resolution daily surface temperature dataset was scaled and reprojected to obtain a new daily surface temperature dataset with the same resolution as the high spatial resolution surface temperature dataset obtained by the Landsat 8 OLI band 10. The sliding window clipping method is used to make the spatial resolution of the new daily surface temperature dataset and the underlying surface dataset consistent; The high-spatial-resolution surface temperature dataset acquired by the Landsat 8 OLI band 10 was used as the label dataset, and the newly processed daily surface temperature dataset and underlying surface dataset were used as the feature dataset. The random forest model was trained using the label dataset and the feature dataset to obtain the surface temperature estimation model. The underlying surface data to be estimated and the new daily surface temperature data with the same spatial resolution are input into the surface temperature estimation model to obtain the daily surface temperature data with high spatial resolution.

2. A method for estimating ground surface temperature according to claim 1, characterized in that: The low spatial resolution daily surface temperature dataset is obtained by selecting MOD11A1 data with cloud cover less than 0.5% from the NASA database.

3. A method for estimating ground surface temperature according to claim 1, characterized in that: The high spatial resolution underlying surface dataset includes a normalized vegetation index (NDVI) dataset and a land cover dataset; the NDVI dataset is obtained by selecting the Landsat8-9OLI / TIRS Collection2 Level-2 dataset with a cloud coverage rate of less than 5% from the USGS database, and the SR_B4.TIF and SR_B5.TIF band data in the Level-2 Surface Reflectance Bands are used to calculate the NDVI, and the calculation formula is: Among them, B4 is the red light band of Landsat8OLI, and B5 is the near-infrared band.

4. A method for estimating ground surface temperature according to claim 1, characterized in that: The high spatial resolution surface temperature dataset obtained by the Landsat8 OLI band 10 is obtained by selecting the Landsat8-9 OLI / TIRS Collection2 Level-2 dataset with a cloud coverage rate of less than 5% in the USGS database, and using Level-2 Surface Temperature Bands to calculate the high spatial resolution surface temperature dataset LST. The calculation formula is: LST=0.00341802×B 10 +149 Among them, B 10 It is the 10th band in the Landsat8-9OLI / TIRS Collection2Level-2 dataset.

5. A method for estimating ground surface temperature according to claim 3, characterized in that: The surface temperature estimation model is expressed as: Y tij =K[NDVI ti ,LCD t ,MODIS tij ] Among them, Y tij is the daily surface temperature data with high spatial resolution on the jth day of the i-th month of the t-th year, K is the trained integrated machine learning algorithm, NDVI ti is the NDVI data of month i in year t, LCD t is the land cover data for year t, MODIS tij The new daily surface temperature data for the jth day of the i-th month of the t-th year after processing to be consistent with the spatial resolution of the underlying surface data.

6. A method for estimating ground surface temperature according to claim 1, characterized in that: It also includes the mean absolute percentage error MAPE, root mean square error RMSE, mean absolute error MAE, determination coefficient R 2 , Adjusted R 2 The performance of the surface temperature estimation model is evaluated using six indicators: The mean absolute percentage error MAPE expression is: where y i is the actual value of the surface temperature, y i is the predicted value of surface temperature, n is the number of samples of surface temperature; The root mean square error RMSE expression is: The mean absolute error MAE expression is: The coefficient of determination R 2 The expression is: in is the average surface temperature; The adjusted coefficient of determination Adjusted R 2 The expression is: where R 2 is the coefficient of determination, p is the number of independent variables; The mean square error MSE expression is:

7. A surface temperature estimation system, characterized in that: include: An acquisition module is used to acquire a daily surface temperature dataset with low spatial resolution, an underlying surface dataset with high spatial resolution, and a surface temperature dataset with high spatial resolution acquired in the 10th band of the Landsat 8 OLI. The low spatial resolution range is 100 meters to 1000 meters, and the high spatial resolution range is within 30 meters. The reprojection module is used to scale the low-spatial-resolution daily surface temperature dataset and reproject the scaled daily surface temperature dataset to obtain a new daily surface temperature dataset with the same resolution as the high-spatial-resolution surface temperature dataset acquired by the Landsat 8 OLI band 10. A processing module is used to use a sliding window clipping method to make the spatial resolution of the new daily surface temperature dataset and the underlying surface dataset consistent; The model building module is used to use the high-spatial-resolution surface temperature dataset acquired by the Landsat 8 OLI Band 10 as the label dataset, and the new daily surface temperature dataset and underlying surface dataset after processing as the feature dataset. The random forest model is trained with the label dataset and the feature dataset to obtain the surface temperature estimation model. The estimation module is used to input the underlying surface data to be estimated and the new daily surface temperature data with the same spatial resolution into the surface temperature estimation model to obtain the daily surface temperature data with high spatial resolution.

8. A computer device for estimating surface temperature, characterized in that: include: A memory, a processor, and a computer program stored in the memory, wherein when the processor executes the computer program, the steps of the surface temperature estimation method according to any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, they are used to execute the steps of the surface temperature estimation method according to any one of claims 1 to 6.

Images