Urban vegetation cooling effect evaluation method and system based on multi-source remote sensing data, terminal and storage medium

Abstract

The invention relates to the technical field of data evaluation, and discloses an urban vegetation cooling effect evaluation method and system based on multi-source remote sensing data, a terminal and a storage medium, and the method comprises the steps: obtaining urban region data of a city, and carrying out the preprocessing and feature extraction to obtain a feature extraction result; inputting the feature extraction result into a vegetation cooling effect evaluation training model, outputting a feature sorting result, a feature analysis result and an ecological threshold recognition result, obtaining a vegetation cooling effect evaluation prediction result, and adjusting the vegetation cooling effect evaluation training model to obtain a vegetation cooling effect evaluation model; and acquiring to-be-evaluated city data of a target city, performing preprocessing and feature extraction to obtain a target feature extraction result, and inputting the target feature extraction result into the vegetation cooling effect evaluation model to obtain a vegetation cooling effect evaluation result. According to the method, through multi-source remote sensing data fusion, the urban vegetation cooling effect is accurately depicted, so that the accuracy of a vegetation cooling effect evaluation result is improved.

Description

Technical Field

[0001] This invention relates to the field of data evaluation technology, and in particular to a method, system, terminal, and computer-readable storage medium for evaluating the cooling effect of urban vegetation based on multi-source remote sensing data. Background Technology

[0002] As an important ecological infrastructure, urban green spaces can effectively alleviate the urban thermal environment and reduce surface temperature through physical processes such as shading and evapotranspiration, playing a key role in regulating the urban microclimate.

[0003] However, existing methods for assessing the cooling effect of urban vegetation mainly rely on a single data source, making it difficult to accurately assess the spatiotemporal dynamics of the cooling effect, especially in the complex environments of rapidly urbanizing areas. The shortcomings of existing technologies include reliance on a single data source, insufficient understanding of spatiotemporal dynamics, lack of awareness of threshold effects, and inadequate analysis of spatial scale effects, resulting in low accuracy and reliability of the assessment results for the urban vegetation cooling effect.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] The main objective of this invention is to provide a method, system, terminal, and storage medium for assessing the urban vegetation cooling effect based on multi-source remote sensing data, aiming to solve the problem of low accuracy and reliability of urban vegetation cooling effect assessment results obtained by existing assessment methods.

[0006] To achieve the above objectives, the present invention provides a method for assessing the cooling effect of urban vegetation based on multi-source remote sensing data. The method includes the following steps: The city area data is obtained, the city area data is preprocessed to obtain target city area data, and feature extraction is performed on the target city area data to obtain feature extraction results. The feature extraction results are input into the vegetation cooling effect evaluation training model. Feature scores are calculated on the first feature information of the feature extraction results to obtain multiple feature importance scores. All feature importance scores are sorted by size to obtain feature ranking results. The feature extraction results are subjected to feature analysis to obtain feature analysis results, and the second feature information of the feature extraction results is subjected to threshold identification to obtain ecological threshold identification results; The vegetation cooling effect assessment prediction result is obtained based on the feature sorting result, the feature analysis result, and the ecological threshold identification result. The vegetation cooling effect assessment training model is then adjusted based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model. The system acquires the target city's data to be evaluated, preprocesses the data to obtain target data, extracts features from the target data to obtain target feature extraction results, and inputs the target feature extraction results into the vegetation cooling effect evaluation model to obtain the vegetation cooling effect evaluation results.

[0007] Optionally, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data includes target optical remote sensing data, target thermal infrared image data, and target lidar data. The process of acquiring urban area data of a city and preprocessing the urban area data to obtain target urban area data specifically includes: Acquire urban area data of the city, wherein the urban area data includes optical remote sensing data, thermal infrared image data and lidar data; Atmospheric correction and cloud masking are performed on the optical remote sensing data to obtain the target optical remote sensing data; Atmospheric correction and cloud masking are performed on the thermal infrared image data to obtain target thermal infrared image data; Data quality control and data resampling are performed on the lidar data to obtain the target lidar data.

[0008] Optionally, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, wherein the step of extracting features from the target urban area data to obtain feature extraction results specifically includes: Vegetation features were extracted from the target optical remote sensing data to obtain vegetation coverage features, green space connectivity features, vegetation shape features, and vegetation moisture features. Surface features are extracted from the target thermal infrared image data to obtain surface temperature characteristics; Vegetation features are extracted from the target lidar data to obtain the vegetation canopy height features; Feature extraction results are obtained based on the vegetation coverage characteristics, green space connectivity characteristics, vegetation shape characteristics, vegetation moisture characteristics, surface temperature characteristics, and vegetation canopy height characteristics.

[0009] Optionally, in the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, the first feature information includes vegetation coverage features, green space connectivity features, vegetation shape features, vegetation moisture features, and vegetation canopy height features; the second feature information includes vegetation coverage features and surface temperature features.

[0010] Optionally, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, wherein the step of performing feature analysis on the feature extraction results to obtain feature analysis results specifically includes: Interpretability analysis values ​​were calculated for the vegetation coverage characteristics, green space connectivity characteristics, vegetation shape characteristics, vegetation moisture characteristics, surface temperature characteristics, and vegetation canopy height characteristics, resulting in multiple interpretable analysis values. Obtain a summary map of interpretability analysis values, and analyze the distribution of all interpretability analysis values ​​based on the summary map to obtain feature analysis results.

[0011] Optionally, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, wherein the step of performing threshold identification on the second feature information of the feature extraction result to obtain an ecological threshold identification result specifically includes: Curve fitting is performed on the vegetation coverage characteristics and the surface temperature characteristics to obtain the vegetation cooling relationship curve, and different breakpoint positions are set. The regression coefficients and goodness of fit for all the breakpoint locations are calculated to obtain the target calculation result. The best goodness of fit value in the target calculation result is used as the ecological threshold, and the ecological threshold identification result is obtained based on the ecological threshold.

[0012] Optionally, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, wherein adjusting the vegetation cooling effect assessment training model according to the vegetation cooling effect assessment prediction results to obtain the vegetation cooling effect assessment model specifically includes: The target loss value is obtained by calculating the loss value between the predicted vegetation cooling effect assessment result and the actual result corresponding to the feature extraction result; The parameters of the vegetation cooling effect assessment training model are corrected according to the target loss value until the training status of the vegetation cooling effect assessment training model meets the preset conditions, thus obtaining a well-trained vegetation cooling effect assessment model.

[0013] Optionally, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data includes a system comprising: The data processing module is used to acquire urban area data of the city, preprocess the urban area data to obtain target urban area data, and extract features from the target urban area data to obtain feature extraction results. The feature ranking module is used to input the feature extraction results into the vegetation cooling effect evaluation training model, calculate the feature score of the first feature information of the feature extraction results to obtain multiple feature importance scores, and sort all the feature importance scores by size to obtain the feature ranking result. The feature analysis and recognition module is used to perform feature analysis on the feature extraction results to obtain feature analysis results, and to perform threshold recognition on the second feature information of the feature extraction results to obtain ecological threshold recognition results; The model adjustment module is used to obtain the vegetation cooling effect assessment prediction result based on the feature sorting result, the feature analysis result and the ecological threshold identification result, and to adjust the vegetation cooling effect assessment training model based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model. The data evaluation module is used to acquire the city data to be evaluated in the target city, preprocess the city data to be evaluated to obtain target data, extract features from the target data to obtain target feature extraction results, and input the target feature extraction results into the vegetation cooling effect evaluation model to obtain the vegetation cooling effect evaluation results.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and an urban vegetation cooling effect assessment program based on multi-source remote sensing data stored in the memory and executable on the processor. When the urban vegetation cooling effect assessment program based on multi-source remote sensing data is executed by the processor, it implements the steps of the urban vegetation cooling effect assessment method based on multi-source remote sensing data as described above.

[0015] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an urban vegetation cooling effect assessment program based on multi-source remote sensing data, and when the urban vegetation cooling effect assessment program based on multi-source remote sensing data is executed by a processor, it implements the steps of the urban vegetation cooling effect assessment method based on multi-source remote sensing data as described above.

[0016] In this invention, urban area data of a city is acquired, preprocessed to obtain target urban area data, and features are extracted from the target urban area data to obtain feature extraction results. The feature extraction results are input into a vegetation cooling effect assessment training model, and feature scores are calculated for the first feature information of the feature extraction results to obtain multiple feature importance scores. All feature importance scores are then sorted by size to obtain feature ranking results. Feature analysis is performed on the feature extraction results to obtain feature analysis results, and threshold recognition is performed on the second feature information of the feature extraction results. The invention obtains ecological threshold identification results; based on the feature ranking results, feature analysis results, and ecological threshold identification results, it obtains vegetation cooling effect assessment prediction results, and adjusts the vegetation cooling effect assessment training model according to the vegetation cooling effect assessment prediction results to obtain a vegetation cooling effect assessment model; it acquires the target city's data to be assessed, preprocesses the target city data to obtain target data, extracts features from the target data to obtain target feature extraction results, and inputs the target feature extraction results into the vegetation cooling effect assessment model to obtain the vegetation cooling effect assessment results. This invention achieves accurate characterization of urban vegetation cooling effect through multi-source remote sensing data fusion, and further clarifies the relative contribution ratio of each vegetation factor to the cooling effect through an interpretable machine learning framework, thereby improving the accuracy and reliability of urban vegetation cooling effect assessment results. Attached Figure Description

[0017] Figure 1 This is a flowchart of a preferred embodiment of the method for evaluating the urban vegetation cooling effect based on multi-source remote sensing data according to the present invention; Figure 2 This is a schematic diagram of the overall process of the urban vegetation cooling effect assessment method based on multi-source remote sensing data according to the present invention; Figure 3 This is a structural diagram of a preferred embodiment of the urban vegetation cooling effect assessment system based on multi-source remote sensing data of the present invention; Figure 4 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0020] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0021] Existing methods for assessing the cooling effect of urban vegetation mainly rely on a single data source, making it difficult to accurately assess the spatiotemporal dynamics of the cooling effect of vegetation, and have the following drawbacks: (1) Single data source: Existing methods are mostly based on a single remote sensing data source, such as using only optical remote sensing images or thermal infrared data. It is difficult to obtain information on vegetation cover, structure and physiological status at the same time, resulting in incomplete and inaccurate assessment results. (2) Insufficient understanding of spatiotemporal dynamics: Existing methods lack in-depth analysis of the seasonal variation of vegetation cooling effect and ignore the differences in the contribution of vegetation characteristics to the cooling effect under different seasonal conditions; (3) Difficulty in identifying dominant factors: Existing methods cannot effectively quantify the relative contribution of different vegetation characteristics (e.g., vegetation coverage, canopy height, etc.) to the cooling effect, and lack scientific importance ranking and mechanism explanation; (4) Insufficient analysis of spatial scale effects: Existing methods are difficult to effectively analyze the spatial decay law and influence range of vegetation cooling effect, which limits the understanding of regional scale cooling mechanism.

[0022] Therefore, there is an urgent need in this field for a method to assess the cooling effect of urban vegetation based on multi-source remote sensing data, in order to overcome the shortcomings of existing technologies and improve the accuracy and reliability of the assessment results of the cooling effect of urban vegetation.

[0023] The preferred embodiment of the present invention describes a method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, such as... Figure 1 As shown, the method for assessing the urban vegetation cooling effect based on multi-source remote sensing data includes the following steps: Step S10: Obtain urban area data of the city, preprocess the urban area data to obtain target urban area data, and extract features from the target urban area data to obtain feature extraction results.

[0024] Specifically, before assessing the cooling effect of urban vegetation, data acquisition is required, such as... Figure 2 As shown, urban area data of the city is acquired, including optical remote sensing data, thermal infrared image data, and lidar data. Firstly, relying on the acquisition of multi-source remote sensing data, this invention selects three main data sources to comprehensively and accurately analyze the cooling effect of urban vegetation: Sentinel-2 (high-resolution multispectral imaging satellite) optical imagery (i.e., optical remote sensing data), Landsat-8 (Landsat satellite) thermal infrared data (i.e., thermal infrared image data), and GEDI (Global Ecosystem Dynamics Investigation, spaceborne full-waveform lidar sensor) lidar-derived data (i.e., lidar data). Sentinel-2 optical imagery provides high spatial resolution optical remote sensing data, particularly suitable for analyzing vegetation cover and growth status; Landsat-8 thermal infrared data provides reliable data support for surface temperature retrieval, especially the 100-meter resolution in the thermal infrared band, enabling the acquisition of long-term surface temperature data sequences. Furthermore, GEDI lidar-derived data provides information on vegetation canopy height and three-dimensional structure, crucial for understanding the three-dimensional structure of vegetation and its shading and transpiration effects. The diversity and high quality of these data sources ensure the depth and accuracy of the analysis of urban thermal environment and vegetation effects, and provide the necessary spatial and temporal dimensions for subsequent analysis. Furthermore, by combining different data sources, the limitations of a single data source can be minimized, thereby providing a more comprehensive characterization of the cooling effect of urban vegetation.

[0025] After obtaining urban area data, preprocessing is required to ensure data quality and the reliability of subsequent analysis. For optical remote sensing data, atmospheric correction and cloud masking are performed to obtain target optical remote sensing data. Atmospheric correction is first performed to ensure the accuracy of reflectance values. This is done by combining ground-measured data with an atmospheric model to remove atmospheric influences, ensuring the spectral information of the optical remote sensing data accurately reflects the surface conditions. After atmospheric correction, cloud masking is further performed to remove errors caused by clouds in the optical remote sensing data, as the presence of clouds can lead to deviations in surface temperature estimation. The spatial resolution of Sentinel-2 optical imagery allows for fine differentiation of small and medium-sized green patches in urban areas, effectively avoiding pixel mixing issues. Its rich spectral bands (13 bands) support high-precision land cover classification and can accurately calculate vegetation quality indicators such as NDMI (Normalized Difference Moisture Index) to reflect the physiological vitality of vegetation.

[0026] For thermal infrared image data, atmospheric correction and cloud masking are performed to obtain the target thermal infrared image data. Because the thermal infrared band resolution of this satellite image is relatively low, radiometric calibration and atmospheric correction are necessary to ensure the accuracy of temperature estimation. The atmospheric correction process uses the MODTRAN model (MODerate resolution atmospheric TRANsmission) to correct the influence of the atmosphere on the thermal infrared image data. Subsequently, cloud masking is performed on the thermal infrared image data to remove interference from clouds and shadows on surface temperature, ensuring high reliability of the temperature data. Landsat-8 thermal infrared data provides monthly time-series surface temperature data, strongly supporting seasonal dynamic analysis. Temperature inversion is performed using the radiative transfer equation method, combined with atmospheric parameter correction, to ensure the accuracy of temperature estimation. Long-term series data throughout the year ensures the reliability of seasonal pattern analysis.

[0027] For lidar data, data quality control and resampling are performed to obtain target lidar data. First, data affected by terrain (e.g., areas with slopes greater than 10°) and low-quality markers are removed. Next, the lidar data is converted into raster data using inverse range-weighted interpolation to match the spatial scale of the study area (e.g., 30 meters). This process ensures spatial consistency and high spatial resolution of the canopy height data, enabling subsequent data integration and improving the overall accuracy of the analysis. Providing globally covered and standardized canopy height estimates using lidar data guarantees the consistency of regional-scale data.

[0028] After obtaining the target urban area data, feature extraction is required. The purpose of feature extraction is to extract key indicators that reflect vegetation characteristics and surface temperature changes from the processed urban area data (i.e., the target urban area data). These features provide rich information for subsequent model construction. Regarding vegetation cover, vegetation indices (e.g., normalized difference in vegetation index) from the target optical remote sensing data are used to quantitatively extract vegetation cover, i.e., to extract the vegetation cover features of the target optical remote sensing data. Vegetation canopy height is another important feature. Vegetation canopy height features within the study area are extracted using target lidar data. Vegetation canopy height reflects the vertical structure of vegetation, influencing its shading and transpiration effects, and thus playing a significant regulatory role in the urban thermal environment. Through spatial interpolation processing of the target lidar data, the vegetation canopy height features within the study area are obtained. In addition, green space connectivity features, vegetation shape features, and vegetation moisture features were extracted from the target optical remote sensing data. These features, calculated using landscape ecology methods, reflect the shape complexity of green space patches and the spatial connectivity between patches. Green space patches with higher shape complexity typically exhibit stronger boundary effects, which can more effectively promote local heat exchange, thereby enhancing the cooling effect. Green space connectivity influences the spatial expansion of the heat island effect; a more connected green space network contributes to cooling over a wider area. Surface features were also extracted from the target thermal infrared image data to obtain surface temperature characteristics.

[0029] Step S20: Input the feature extraction results into the vegetation cooling effect evaluation training model, calculate the feature score of the first feature information of the feature extraction results to obtain multiple feature importance scores, and sort all the feature importance scores by size to obtain the feature ranking result.

[0030] Specifically, after feature extraction is completed, machine learning methods are used to model the complex nonlinear relationship between vegetation factors and the urban thermal environment. Specifically, firstly, the feature extraction results are integrated to obtain a training dataset, and a vegetation cooling effect assessment training model is created. A set of training samples from the training dataset is then input into the vegetation cooling effect assessment training model (e.g., XGBoost (Extreme Gradient Filtering)). After implementing Boosting (an ensemble learning algorithm based on gradient boosting decision trees) and a regression model, an effect assessment is required. The main purpose is to evaluate the spatiotemporal dynamics of the vegetation cooling effect and the relative contributions of different vegetation factors to the cooling effect. Specifically, the first feature information in the training samples is sorted to obtain a feature ranking result. This first feature information includes vegetation coverage, green space connectivity, vegetation shape, vegetation moisture, and vegetation canopy height. Specifically, feature importance scores are calculated for these features in the training samples, resulting in multiple feature importance scores. These scores reflect the overall contribution of each factor in the model's prediction process; a higher score indicates a greater impact of the factor on the cooling effect. All feature importance scores are then sorted by size to obtain the feature ranking result. By comparing the feature importance rankings for the four seasons, the dominant cooling factors in different seasons are identified.

[0031] Step S30: Perform feature analysis on the feature extraction results to obtain feature analysis results, and perform threshold recognition on the second feature information of the feature extraction results to obtain ecological threshold recognition results.

[0032] Specifically, feature analysis is performed on all features in the training samples to obtain feature analysis results. Specifically, interpretability analysis values ​​are calculated for vegetation coverage, green space connectivity, vegetation shape, vegetation moisture, surface temperature, and vegetation canopy height features in the training samples to obtain multiple interpretable analysis values. An interpretable analysis value summary map is obtained, and the distribution of all interpretable analysis values ​​is analyzed based on the interpretable analysis value summary map to obtain feature analysis results. The nonlinear relationship between a single feature and the cooling effect is analyzed through the interpretable analysis value summary map to reveal how changes in feature values ​​affect the prediction results.

[0033] Subsequently, threshold identification is performed on the second feature information in the training samples to obtain the ecological threshold identification result. The second feature information includes vegetation coverage and surface temperature characteristics. Specifically, a piecewise linear regression method is used to fit the vegetation coverage and surface temperature characteristics to obtain a vegetation cooling relationship curve, and different breakpoint positions are set for the vegetation cooling relationship curve. The regression coefficients and goodness of fit at all breakpoint positions are calculated to obtain the target calculation result. When the goodness of fit reaches the optimal value, the marginal diminishing threshold of the cooling effect (i.e., the ecological threshold) is determined. After the vegetation coverage exceeds this ecological threshold, the marginal cooling benefit of further increasing the green area will significantly decrease. Then, the best goodness of fit value in the target calculation result is used as the ecological threshold, and the ecological threshold identification result is obtained based on the ecological threshold.

[0034] Step S40: Obtain the vegetation cooling effect assessment prediction result based on the feature sorting result, the feature analysis result, and the ecological threshold identification result; and adjust the vegetation cooling effect assessment training model based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model.

[0035] Specifically, after obtaining the feature ranking results, feature analysis results, and ecological threshold identification results, a vegetation cooling effect assessment prediction result is obtained based on the feature ranking results, feature analysis results, and ecological threshold identification results. A loss value is calculated between the vegetation cooling effect assessment prediction result and the actual result corresponding to the feature extraction result to obtain a target loss value. The parameters of the vegetation cooling effect assessment training model are then corrected based on the target loss value. The next set of training samples is input into the vegetation cooling effect assessment training model, and the above process is repeated (details omitted here). This continues until the training status of the vegetation cooling effect assessment training model meets preset conditions. These preset conditions include the target loss value meeting preset requirements or the number of training iterations reaching a preset number. The preset requirements can be determined based on the accuracy of the vegetation cooling effect assessment model (details omitted here). The preset number of iterations can be the maximum number of training iterations for the vegetation cooling effect assessment training model. Finally, a well-trained vegetation cooling effect assessment model is obtained.

[0036] Step S50: Obtain the city data to be evaluated for the target city, preprocess the city data to be evaluated to obtain target data, extract features from the target data to obtain target feature extraction results, and input the target feature extraction results into the vegetation cooling effect evaluation model to obtain vegetation cooling effect evaluation results.

[0037] Specifically, after training and obtaining the vegetation cooling effect assessment model, it is necessary to assess the vegetation cooling effect of the target city. This involves acquiring the target city's data to be assessed, preprocessing the data specifically: performing atmospheric correction and cloud masking on the optical remote sensing data, atmospheric correction and cloud masking on the thermal infrared image data, and performing data quality control and resampling on the lidar data. After preprocessing, the target data is obtained. Then, feature extraction is performed on the target data to obtain the target feature extraction results, which are then input into the vegetation cooling effect assessment model to obtain the vegetation cooling effect assessment result.

[0038] This invention, through the fusion of multi-source remote sensing data, can simultaneously acquire high spatial resolution vegetation cover information, accurate temporal data of land surface temperature, and three-dimensional structural parameters of vegetation. This effectively overcomes the problem of insufficient spatiotemporal resolution in existing technologies using single data sources, achieving a comprehensive and accurate characterization of the urban vegetation cooling effect. Furthermore, it employs a corresponding machine learning framework to clarify the relative contribution ratio of each vegetation factor to the cooling effect, providing a scientific basis for urban green space planning decisions. In addition, this invention fills the gap in existing research regarding the insufficient understanding of spatiotemporal dynamics by systematically quantifying the seasonal variation characteristics and spatial decay patterns of the vegetation cooling effect. It also proposes for the first time that a vegetation cover rate of 65-66% is a key ecological threshold for the cooling effect, providing a clear optimization target for urban greening construction.

[0039] Furthermore, such as Figure 3 As shown, based on the above-mentioned method for assessing the urban vegetation cooling effect using multi-source remote sensing data, this invention also provides a system for assessing the urban vegetation cooling effect using multi-source remote sensing data, wherein the system includes: The data processing module 51 is used to acquire urban area data of the city, preprocess the urban area data to obtain target urban area data, and extract features from the target urban area data to obtain feature extraction results. The feature ranking module 52 is used to input the feature extraction results into the vegetation cooling effect evaluation training model, calculate the feature score of the first feature information of the feature extraction results, obtain multiple feature importance scores, and sort all the feature importance scores by size to obtain the feature ranking result. The feature analysis and recognition module 53 is used to perform feature analysis on the feature extraction results to obtain feature analysis results, and to perform threshold recognition on the second feature information of the feature extraction results to obtain ecological threshold recognition results; The model adjustment module 54 is used to obtain the vegetation cooling effect assessment prediction result based on the feature sorting result, the feature analysis result and the ecological threshold identification result, and to adjust the vegetation cooling effect assessment training model based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model. The data evaluation module 55 is used to acquire the city data to be evaluated in the target city, preprocess the city data to be evaluated to obtain target data, extract features from the target data to obtain target feature extraction results, and input the target feature extraction results into the vegetation cooling effect evaluation model to obtain vegetation cooling effect evaluation results.

[0040] Furthermore, such as Figure 4 As shown, based on the above-mentioned method for assessing the urban vegetation cooling effect based on multi-source remote sensing data, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 4 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0041] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores an urban vegetation cooling effect assessment program 40 based on multi-source remote sensing data. This urban vegetation cooling effect assessment program 40 based on multi-source remote sensing data can be executed by the processor 10, thereby implementing the urban vegetation cooling effect assessment method based on multi-source remote sensing data in this application.

[0042] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the urban vegetation cooling effect assessment method based on multi-source remote sensing data.

[0043] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface.

[0044] In one embodiment, when the processor 10 executes the urban vegetation cooling effect assessment program 40 based on multi-source remote sensing data in the memory 20, the following steps are performed: The city area data is obtained, the city area data is preprocessed to obtain target city area data, and feature extraction is performed on the target city area data to obtain feature extraction results. The feature extraction results are input into the vegetation cooling effect evaluation training model. Feature scores are calculated on the first feature information of the feature extraction results to obtain multiple feature importance scores. All feature importance scores are sorted by size to obtain feature ranking results. The feature extraction results are subjected to feature analysis to obtain feature analysis results, and the second feature information of the feature extraction results is subjected to threshold identification to obtain ecological threshold identification results; The vegetation cooling effect assessment prediction result is obtained based on the feature sorting result, the feature analysis result, and the ecological threshold identification result. The vegetation cooling effect assessment training model is then adjusted based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model. The system acquires the target city's data to be evaluated, preprocesses the data to obtain target data, extracts features from the target data to obtain target feature extraction results, and inputs the target feature extraction results into the vegetation cooling effect evaluation model to obtain the vegetation cooling effect evaluation results.

[0045] The target city area data includes target optical remote sensing data, target thermal infrared image data, and target lidar data. The process of acquiring urban area data of a city and preprocessing the urban area data to obtain target urban area data specifically includes: Acquire urban area data of the city, wherein the urban area data includes optical remote sensing data, thermal infrared image data and lidar data; Atmospheric correction and cloud masking are performed on the optical remote sensing data to obtain the target optical remote sensing data; Atmospheric correction and cloud masking are performed on the thermal infrared image data to obtain target thermal infrared image data; Data quality control and data resampling are performed on the lidar data to obtain the target lidar data.

[0046] Specifically, the feature extraction of the target city area data to obtain the feature extraction results includes: Vegetation features were extracted from the target optical remote sensing data to obtain vegetation coverage features, green space connectivity features, vegetation shape features, and vegetation moisture features. Surface features are extracted from the target thermal infrared image data to obtain surface temperature characteristics; Vegetation features are extracted from the target lidar data to obtain the vegetation canopy height features; Feature extraction results are obtained based on the vegetation coverage characteristics, green space connectivity characteristics, vegetation shape characteristics, vegetation moisture characteristics, surface temperature characteristics, and vegetation canopy height characteristics.

[0047] The first feature information includes vegetation coverage features, green space connectivity features, vegetation shape features, vegetation moisture features, and vegetation canopy height features; the second feature information includes vegetation coverage features and surface temperature features.

[0048] Specifically, the step of performing feature analysis on the feature extraction results to obtain feature analysis results includes: Interpretability analysis values ​​were calculated for the vegetation coverage characteristics, green space connectivity characteristics, vegetation shape characteristics, vegetation moisture characteristics, surface temperature characteristics, and vegetation canopy height characteristics, resulting in multiple interpretable analysis values. Obtain a summary map of interpretability analysis values, and analyze the distribution of all interpretability analysis values ​​based on the summary map to obtain feature analysis results.

[0049] Specifically, the step of performing threshold recognition on the second feature information of the feature extraction result to obtain the ecological threshold recognition result includes: Curve fitting is performed on the vegetation coverage characteristics and the surface temperature characteristics to obtain the vegetation cooling relationship curve, and different breakpoint positions are set. The regression coefficients and goodness of fit for all the breakpoint locations are calculated to obtain the target calculation result. The best goodness of fit value in the target calculation result is used as the ecological threshold, and the ecological threshold identification result is obtained based on the ecological threshold.

[0050] Specifically, adjusting the vegetation cooling effect assessment training model based on the vegetation cooling effect assessment prediction results to obtain the vegetation cooling effect assessment model includes: The target loss value is obtained by calculating the loss value between the predicted vegetation cooling effect assessment result and the actual result corresponding to the feature extraction result; The parameters of the vegetation cooling effect assessment training model are corrected according to the target loss value until the training status of the vegetation cooling effect assessment training model meets the preset conditions, thus obtaining a well-trained vegetation cooling effect assessment model.

[0051] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an urban vegetation cooling effect assessment program based on multi-source remote sensing data, and when the urban vegetation cooling effect assessment program based on multi-source remote sensing data is executed by a processor, it implements the steps of the urban vegetation cooling effect assessment method based on multi-source remote sensing data as described above.

[0052] In summary, this invention provides a method, system, terminal, and storage medium for assessing the urban vegetation cooling effect based on multi-source remote sensing data. The method includes: acquiring urban area data of a city; preprocessing the urban area data to obtain target urban area data; extracting features from the target urban area data to obtain feature extraction results; inputting the feature extraction results into a vegetation cooling effect assessment training model; calculating feature scores for the first feature information of the feature extraction results to obtain multiple feature importance scores; sorting all the feature importance scores by size to obtain feature ranking results; and performing feature analysis on the feature extraction results to obtain feature analysis results. The second feature information of the extracted feature results is threshold-identified to obtain an ecological threshold identification result. Based on the feature ranking result, the feature analysis result, and the ecological threshold identification result, a vegetation cooling effect assessment prediction result is obtained. The vegetation cooling effect assessment training model is adjusted based on the vegetation cooling effect assessment prediction result to obtain a vegetation cooling effect assessment model. The target city's data to be assessed is acquired, preprocessed to obtain target data, and features are extracted from the target data to obtain target feature extraction results. These target feature extraction results are then input into the vegetation cooling effect assessment model to obtain the vegetation cooling effect assessment result. This invention achieves accurate characterization of the urban vegetation cooling effect through multi-source remote sensing data fusion. Furthermore, through an interpretable machine learning framework, the relative contribution ratio of each vegetation factor to the cooling effect is clarified, thereby improving the accuracy and reliability of the urban vegetation cooling effect assessment results.

[0053] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0054] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0055] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for assessing the cooling effect of urban vegetation based on multi-source remote sensing data, characterized in that, The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data includes: The city area data is obtained, the city area data is preprocessed to obtain target city area data, and feature extraction is performed on the target city area data to obtain feature extraction results. The feature extraction results are input into the vegetation cooling effect evaluation training model. Feature scores are calculated on the first feature information of the feature extraction results to obtain multiple feature importance scores. All feature importance scores are sorted by size to obtain feature ranking results. The feature extraction results are subjected to feature analysis to obtain feature analysis results, and the second feature information of the feature extraction results is subjected to threshold identification to obtain ecological threshold identification results; The vegetation cooling effect assessment prediction result is obtained based on the feature sorting result, the feature analysis result, and the ecological threshold identification result. The vegetation cooling effect assessment training model is then adjusted based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model. The system acquires the target city's data to be evaluated, preprocesses the data to obtain target data, extracts features from the target data to obtain target feature extraction results, and inputs the target feature extraction results into the vegetation cooling effect evaluation model to obtain the vegetation cooling effect evaluation results.

2. The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data according to claim 1, characterized in that, The target city area data includes target optical remote sensing data, target thermal infrared image data, and target lidar data; The process of acquiring urban area data of a city and preprocessing the urban area data to obtain target urban area data specifically includes: Acquire urban area data of the city, wherein the urban area data includes optical remote sensing data, thermal infrared image data and lidar data; Atmospheric correction and cloud masking are performed on the optical remote sensing data to obtain the target optical remote sensing data; Atmospheric correction and cloud masking are performed on the thermal infrared image data to obtain the target thermal infrared image data; Data quality control and data resampling are performed on the lidar data to obtain the target lidar data.

3. The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data according to claim 2, characterized in that, The step of extracting features from the target city area data to obtain feature extraction results specifically includes: Vegetation features were extracted from the target optical remote sensing data to obtain vegetation coverage features, green space connectivity features, vegetation shape features, and vegetation moisture features. Surface features are extracted from the target thermal infrared image data to obtain surface temperature features; Vegetation features are extracted from the target lidar data to obtain the vegetation canopy height features; Feature extraction results are obtained based on the vegetation coverage characteristics, green space connectivity characteristics, vegetation shape characteristics, vegetation moisture characteristics, surface temperature characteristics, and vegetation canopy height characteristics.

4. The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data according to claim 1, characterized in that, The first feature information includes vegetation coverage features, green space connectivity features, vegetation shape features, vegetation moisture features, and vegetation canopy height features; the second feature information includes vegetation coverage features and surface temperature features.

5. The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data according to claim 3, characterized in that, The step of performing feature analysis on the feature extraction results to obtain feature analysis results specifically includes: Interpretability analysis values ​​were calculated for the vegetation coverage characteristics, green space connectivity characteristics, vegetation shape characteristics, vegetation moisture characteristics, surface temperature characteristics, and vegetation canopy height characteristics, resulting in multiple interpretable analysis values. Obtain a summary map of interpretability analysis values, and analyze the distribution of all interpretability analysis values ​​based on the summary map to obtain feature analysis results.

6. The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data according to claim 4, characterized in that, The step of performing threshold identification on the second feature information of the feature extraction result to obtain the ecological threshold identification result specifically includes: Curve fitting is performed on the vegetation coverage characteristics and the surface temperature characteristics to obtain the vegetation cooling relationship curve, and different breakpoint positions are set. The regression coefficients and goodness of fit for all the breakpoint locations are calculated to obtain the target calculation result. The best goodness of fit value in the target calculation result is used as the ecological threshold, and the ecological threshold identification result is obtained based on the ecological threshold.

7. The method for assessing the urban vegetation cooling effect based on multi-source remote sensing data according to claim 1, characterized in that, The step of adjusting the vegetation cooling effect assessment training model based on the vegetation cooling effect assessment prediction results to obtain the vegetation cooling effect assessment model specifically includes: The target loss value is obtained by calculating the loss value between the predicted vegetation cooling effect assessment result and the actual result corresponding to the feature extraction result; The parameters of the vegetation cooling effect assessment training model are corrected according to the target loss value until the training status of the vegetation cooling effect assessment training model meets the preset conditions, thus obtaining a well-trained vegetation cooling effect assessment model.

8. A system for assessing the cooling effect of urban vegetation based on multi-source remote sensing data, characterized in that, The urban vegetation cooling effect assessment system based on multi-source remote sensing data includes: The data processing module is used to acquire urban area data of the city, preprocess the urban area data to obtain target urban area data, and extract features from the target urban area data to obtain feature extraction results. The feature ranking module is used to input the feature extraction results into the vegetation cooling effect evaluation training model, calculate the feature score of the first feature information of the feature extraction results to obtain multiple feature importance scores, and sort all the feature importance scores by size to obtain the feature ranking result. The feature analysis and recognition module is used to perform feature analysis on the feature extraction results to obtain feature analysis results, and to perform threshold recognition on the second feature information of the feature extraction results to obtain ecological threshold recognition results; The model adjustment module is used to obtain the vegetation cooling effect assessment prediction result based on the feature sorting result, the feature analysis result and the ecological threshold identification result, and to adjust the vegetation cooling effect assessment training model based on the vegetation cooling effect assessment prediction result to obtain the vegetation cooling effect assessment model. The data evaluation module is used to acquire the city data to be evaluated in the target city, preprocess the city data to be evaluated to obtain target data, extract features from the target data to obtain target feature extraction results, and input the target feature extraction results into the vegetation cooling effect evaluation model to obtain the vegetation cooling effect evaluation results.

9. A terminal, characterized in that, The terminal includes a memory, a processor, and a program stored in the memory and executable on the processor. When the program is executed by the processor, it implements the steps of the method for evaluating the urban vegetation cooling effect based on multi-source remote sensing data as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which stores an urban vegetation cooling effect assessment program based on multi-source remote sensing data. When the urban vegetation cooling effect assessment program based on multi-source remote sensing data is executed by a processor, it implements the steps of the urban vegetation cooling effect assessment method based on multi-source remote sensing data as described in any one of claims 1-7.

Images