A Method for Controlling the Temporal and Spatial Resolution of LCZ Based on Multi-Source Remote Sensing Information

Abstract

The present invention discloses a method for controlling the spatio-temporal resolution of LCZ based on multi-source remote sensing information, which relates to the technical field of image processing. The method for controlling the spatio-temporal resolution of LCZ based on multi-source remote sensing information includes the following steps: scene weight evaluation, environmental weight evaluation, and spatio-temporal fusion feedback evaluation. The present invention identifies the scene through multi-source remote sensing information to obtain the initial weight, acquires the remote sensing data and the scene characteristic data to obtain the scene weight evaluation coefficient, simultaneously acquires the geographical environment data and combines it with the remote sensing data to obtain the environmental weight evaluation coefficient, then determines whether to perform dynamic weight reallocation according to the scene weight evaluation coefficient and the environmental weight evaluation coefficient, and finally obtains the weight regulation evaluation coefficient according to the obtained spatio-temporal fusion feedback data to determine whether to perform secondary weight allocation, achieving the effect of improving the accuracy of spatio-temporal resolution control and solving the problem of inaccurate spatio-temporal resolution control in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for controlling the spatio-temporal resolution of LCZ based on multi-source remote sensing information. Background Art

[0002] With the acceleration of urbanization and the intensification of climate change, Local Climate Zones (LCZ) as an important method for studying urban microclimate and thermal environment has received extensive attention. However, the accuracy and spatio-temporal resolution of LCZ classification are often limited by the deficiencies of a single remote sensing data source, such as low spatial resolution and discontinuous time coverage.

[0003] The existing research on Local Climate Zones (LCZ) mainly relies on a single remote sensing data source, such as optical images or thermal infrared data. Although these data can provide information on surface cover types, their spatial resolution is limited, or the time observation frequency is insufficient, making it difficult to meet the high-precision requirements in a dynamic and complex environment. Traditional methods mostly adopt fixed-resolution processing, ignoring the complementarity between different data sources, which easily leads to a decrease in classification accuracy. At the same time, the classification models based on machine learning have limited ability to fuse multi-scale and multi-temporal data, lacking technologies for dynamically optimizing spatio-temporal resolution, which restricts the popularization and application of LCZ.

[0004] For example, a twin network and method for change detection of ultra-high spatial resolution remote sensing images disclosed in a patent application with the publication number: CN117494765A includes: deep feature extraction through an asymmetric convolutional residual encoder, then stacking the difference features of different scales along the channel direction, and enhancing the spatio-temporal domain of the multi-scale difference features by using a spatio-temporal attention mechanism; splitting the spatio-temporally enhanced multi-scale difference features according to the number of channels of different scales, and fusing the enhanced difference features and the double-temporal encoder features of the same scale through a feature fusion decoder.

[0005] For example, a high-resolution dynamic vision observation method and device disclosed in an invention patent announcement with the announcement number: CN111695681B includes: Step 1, obtaining low-resolution event stream data, obtaining low-spatial-resolution event stream data from an event camera; Step 2, performing data preprocessing, calculating the multiple of the resolution to be improved according to the spatial resolution size of the input low-resolution event data and the spatial resolution size of the expected high-resolution event data; Step 3, constructing a spiking neural network, using the Spike Response model as the neuron dynamics model to construct a fully connected spiking neural network; Step 4, completing the calculation of high-resolution spatio-temporal pulse signals; Step 5, performing data post-processing to achieve high-resolution dynamic vision observation.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of the present application, it is found that the above technology has at least the following technical problems:

[0007] In the prior art, the requirements for temporal and spatial resolutions vary greatly in different scenarios (such as cities, forests, and farmlands), while the simple weighting method uses fixed weights or lacks the ability to adapt to scenarios, resulting in inaccurate control of temporal and spatial resolutions. Summary of the Invention

[0008] The embodiments of the present application provide a method for controlling the temporal and spatial resolutions of LCZ based on multi-source remote sensing information, which solves the problem of inaccurate control of temporal and spatial resolutions in the prior art and realizes the improvement of the accuracy of temporal and spatial resolution control.

[0009] The embodiments of the present application provide a method for controlling the temporal and spatial resolutions of LCZ based on multi-source remote sensing information, including the following steps: S1, identifying a scene based on multi-source remote sensing information to obtain an initial weight, and obtaining a scene weight evaluation coefficient by acquiring remote sensing data and scene characteristic data within a preset time period, where the scene weight evaluation coefficient is used to quantify the adaptation degree between the initial weight and the scene; S2, acquiring geographical environment data and combining it with remote sensing data to obtain an environmental weight evaluation coefficient, and determining whether to perform dynamic weight reallocation based on the scene weight evaluation coefficient and the environmental weight evaluation coefficient, where the environmental weight evaluation coefficient is used to quantify the adaptation degree between the initial weight and the geographical environment; S3, obtaining a weight regulation evaluation coefficient based on the acquired spatio-temporal fusion feedback data, and determining whether to perform secondary weight allocation based on the weight regulation evaluation coefficient, where the weight regulation evaluation coefficient is used to feedback the rationality degree when the temporal weight and the spatial weight are fused after regulation.

[0010] Further, the specific steps for obtaining the initial weight are as follows: A1, automatically identifying a scene through the image information of multi-source remote sensing information and performing scene classification, where the scene classification means dividing the automatically identified scene according to the specific geographical conditions of the region; A2, constructing a mapping set between the scene category and the initial weight, where the mapping set is constructed by preset staff based on historical data; A3, inputting the automatically identified scene into the mapping set to obtain the corresponding initial weight.

[0011] Further, the remote sensing data includes spatial resolution and temporal resolution; the scene characteristic data includes vegetation index, hydrological index, texture entropy, and texture contrast; the geographical environment data includes surface roughness, air temperature, rainfall, and wind speed; the spatio-temporal fusion feedback data includes mean square error, structural similarity index, spatial residual, temporal residual, and LCZ image clarity; the LCZ image clarity represents the clarity of the LCZ image generated after the end of the preset time period.

[0012] Further, the specific steps for obtaining the scene weight evaluation coefficient are as follows: B1. Number the preset time period and obtain reference scene data from the preset database. The reference scene data includes a preset vegetation index, a preset hydrological index, a reference texture entropy, and a reference texture contrast; B2. Perform data preprocessing on the remote sensing data. The data preprocessing is used to de-unify and normalize the remote sensing data; B3. Obtain a remote sensing base number based on the remote sensing data and the initial weight. The remote sensing base number is used to quantify the current spatio-temporal resolution; B4. Process the remote sensing base number, the scene characteristic data, and the reference scene data to obtain the scene weight evaluation coefficient.

[0013] Further, the specific limiting expression of the scene weight evaluation coefficient is as follows:

[0014] ;

[0015] In the formula, t represents the number of the preset time period, , represents the total number of the preset time periods, represents the remote sensing base number of the t-th preset time period, represents the vegetation index of the t-th preset time period, represents the hydrological index of the t-th preset time period, represents the texture entropy of the t-th preset time period, represents the texture contrast of the t-th preset time period, represents the preset vegetation index, represents the preset hydrological index, represents the reference texture entropy, represents the reference texture contrast, represents the scene weight evaluation coefficient of the t-th preset time period.

[0016] Further, the specific process of the environmental weight evaluation coefficient is as follows: Obtain reference geographical data from the preset database. The reference geographical data includes reference surface roughness, reference air temperature, reference rainfall, and reference wind speed; Obtain the remote sensing base number and process the relative deviation and absolute deviation of the geographical environment data and the corresponding reference geographical data to obtain the environmental weight evaluation coefficient; The relative deviation includes the relative deviation of air temperature, the relative deviation of rainfall, and the relative deviation of wind speed; The relative deviation of air temperature represents the ratio result of the absolute value of the difference between the air temperature and the reference air temperature to the reference air temperature; The relative deviation of rainfall represents the ratio result of the absolute value of the difference between the rainfall and the reference rainfall to the reference rainfall; The relative deviation of wind speed represents the ratio result of the absolute value of the difference between the wind speed and the reference wind speed to the reference wind speed.

[0017] Further, the specific process of determining whether to perform dynamic weight reallocation is as follows: Obtain the scenario threshold and the environment threshold from a preset database, and compare the scenario weight evaluation coefficient and the environment weight evaluation coefficient with the scenario threshold and the environment threshold respectively: If the scenario weight evaluation coefficient is not less than the scenario threshold and the environment weight evaluation coefficient is not less than the environment threshold, then no dynamic weight reallocation is performed; If the scenario weight evaluation coefficient is less than the scenario threshold or the environment weight evaluation coefficient is less than the environment threshold, then dynamic weight reallocation is performed; The dynamic weight reallocation includes weight dynamic adjustment based on spatio-temporal change features and spatio-temporal convolutional network optimization.

[0018] Further, the specific content of the dynamic weight reallocation is as follows: The weight dynamic adjustment based on spatio-temporal change features is achieved through spatio-temporal block dynamic weighting and weight smoothing processing; The spatio-temporal block dynamic weighting means calculating the weights region by region after dividing the LCZ image generated based on multi-source remote sensing information into blocks.

[0019] Further, the specific process of obtaining the weight regulation evaluation coefficient is as follows: Obtain the minimum value of the LCZ image clarity from a preset database, where the minimum value of the LCZ image clarity represents the minimum limit of the clarity of the LCZ image generated based on multi-source remote sensing information; Perform normalization processing on the mean square error, spatial residual, and temporal residual, and the normalization processing is used to unify the dimension of the spatio-temporal fusion data; The weight regulation evaluation coefficient is obtained by processing the sum of deviations, the structural similarity index, the LCZ image clarity, and the corresponding minimum value of the LCZ image clarity respectively, where the sum of deviations represents the result of adding the mean square error, spatial residual, and temporal residual.

[0020] Further, the specific process of determining whether to perform secondary weight allocation is as follows: Obtain the regulation threshold from a preset database, and the regulation threshold is used to determine whether to perform secondary weight allocation; Compare the weight regulation evaluation coefficient with the regulation threshold: If the weight regulation evaluation coefficient is not less than the regulation threshold, then no secondary weight allocation is performed; If the weight regulation evaluation coefficient is less than the regulation threshold, then secondary weight allocation is performed; The secondary weight allocation means using the initial weight after dynamic weight reallocation in the next preset time period as the initial weight, and continuing to obtain the scenario weight evaluation coefficient, the environment weight evaluation coefficient, and the weight regulation evaluation coefficient based on the initial weight until the weight regulation evaluation coefficient is not less than the regulation threshold.

[0021] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0022] 1. Identify the scene through multi-source remote sensing information to obtain the initial weight, and acquire the remote sensing data and scene characteristic data within a preset time period to obtain the scene weight evaluation coefficient. At the same time, obtain the geographical environment data and combine it with the remote sensing data to obtain the environmental weight evaluation coefficient. Then, determine whether to perform dynamic weight reallocation based on the scene weight evaluation coefficient and the environmental weight evaluation coefficient. Finally, obtain the weight regulation evaluation coefficient based on the acquired spatio-temporal fusion feedback data to determine whether to perform secondary weight allocation, thereby improving the effect of spatio-temporal fusion, and further achieving an improvement in the accuracy of spatio-temporal resolution control, effectively solving the problem of inaccurate spatio-temporal resolution control in the prior art.

[0023] 2. Number the preset time period and obtain the reference scene data from the preset database. Then, perform data preprocessing on the remote sensing data. Next, obtain the remote sensing base number based on the remote sensing data and the initial weight. Finally, process the remote sensing base number, the scene characteristic data, and the reference scene data to obtain the scene weight evaluation coefficient, thereby more accurately evaluating the rationality of the initial weight in the corresponding scene, and further achieving dynamic and balanced adjustment of the initial weight to improve the effect of spatio-temporal fusion.

[0024] 3. Obtain the reference geographical data from the preset database. Then, obtain the remote sensing base number and process the relative deviation and absolute deviation of the geographical environment data and the corresponding reference geographical data to obtain the environmental weight evaluation coefficient, thereby more accurately evaluating the rationality of the initial weight in the corresponding geographical environment, and further achieving dynamic and balanced adjustment of the initial weight to improve the effect of spatio-temporal fusion. Brief Description of the Drawings

[0025] Figure 1 It is a flowchart of a method for controlling the LCZ spatio-temporal resolution based on multi-source remote sensing information provided by an embodiment of the present application;

[0026] Figure 2 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the mean square error provided by an embodiment of the present application;

[0027] Figure 3 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the structural similarity index provided by an embodiment of the present application;

[0028] Figure 4 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the spatial residual provided by an embodiment of the present application;

[0029] Figure 5 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the time residual provided by an embodiment of the present application;

[0030] Figure 6 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the LCZ image sharpness provided by an embodiment of the present application. Specific Embodiments

[0031] In an embodiment of the present application, by providing a method for controlling the spatio-temporal resolution of LCZ based on multi-source remote sensing information, the problem of inaccurate spatio-temporal resolution control in the prior art is solved. By numbering a preset time period and obtaining reference scene data from a preset database, then performing data preprocessing on the remote sensing data, and obtaining a remote sensing base number according to the remote sensing data and initial weights, then processing the remote sensing base number, scene characteristic data and reference scene data to obtain a scene weight evaluation coefficient. At the same time, by obtaining reference geographical data from a preset database, then obtaining the remote sensing base number and processing the relative deviation and absolute deviation of the geographical environment data and the corresponding reference geographical data to obtain an environmental weight evaluation coefficient. Then, it is judged whether to perform dynamic weight reallocation according to the scene weight evaluation coefficient and the environmental weight evaluation coefficient. Finally, a weight regulation evaluation coefficient is obtained according to the obtained spatio-temporal fusion feedback data to judge whether to perform weight secondary allocation, achieving an improvement in the accuracy of spatio-temporal resolution control.

[0032] The technical solution in the embodiment of the present application is to solve the above problem of inaccurate spatio-temporal resolution control, and the general idea is as follows:

[0033] It is judged whether to perform dynamic weight reallocation according to the obtained scene weight evaluation coefficient and environmental weight evaluation coefficient, and a weight regulation evaluation coefficient is obtained according to the obtained spatio-temporal fusion feedback data to judge whether to perform weight secondary allocation, achieving the effect of improving the accuracy of spatio-temporal resolution control.

[0034] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0035] As Figure 1 shown, it is a flowchart of a method for controlling the spatio-temporal resolution of LCZ based on multi-source remote sensing information provided by an embodiment of the present application. The method includes the following steps: S1, identifying a scene based on multi-source remote sensing information to obtain an initial weight, obtaining a scene weight evaluation coefficient by obtaining remote sensing data and scene characteristic data within a preset time period. The initial weight includes an initial time weight and an initial space weight, and the scene weight evaluation coefficient is used to quantify the degree of adaptation between the initial weight and the scene; S2, obtaining geographical environment data and combining it with the remote sensing data to obtain an environmental weight evaluation coefficient, and judging whether to perform dynamic weight reallocation according to the scene weight evaluation coefficient and the environmental weight evaluation coefficient. The environmental weight evaluation coefficient is used to quantify the degree of adaptation between the initial weight and the geographical environment; S3, obtaining a weight regulation evaluation coefficient according to the obtained spatio-temporal fusion feedback data, and judging whether to perform weight secondary allocation according to the weight regulation evaluation coefficient. The weight regulation evaluation coefficient is used to feedback the rationality degree when the time weight and the space weight are fused after regulation.

[0036] In this embodiment, the remote sensing data, scene characteristic data, and geographical environment data are all relevant data of the same area. LCZ images are generated and compared and analyzed both after the start and end of a preset time period to obtain spatio-temporal fusion feedback data. By integrating multi-source remote sensing information and spatio-temporal fusion feedback, more accurate allocation and dynamic adjustment of spatio-temporal weights are achieved, enhancing the scientificity and rationality of weight allocation. At the same time, this method not only comprehensively considers the impacts of time, space, and environmental factors on the scene, but also ensures the rationality and effectiveness of weights during the fusion process by introducing a weight evaluation coefficient and a feedback mechanism. Through this comprehensive processing strategy, not only the adaptability and flexibility of the method are enhanced, but also the accuracy of spatio-temporal resolution control is improved.

[0037] It should be noted that the remote sensing data includes spatial resolution and temporal resolution. The spatial resolution is directly obtained through satellite sensors, and the temporal resolution is extracted from satellite image data. The scene characteristic data includes vegetation index, hydrological index, texture entropy, and texture contrast. The geographical environment data includes surface roughness, air temperature, rainfall, and wind speed. The spatio-temporal fusion feedback data includes mean square error, structural similarity index, spatial residual, temporal residual, and LCZ image clarity. The LCZ image clarity represents the clarity of the LCZ image generated after the end of the preset time period.

[0038] Among them, the vegetation index (i.e., the normalized difference vegetation index) is generated through an online platform (such as Google Earth Engine) and is used to measure the surface vegetation coverage and growth status. The hydrological index (i.e., the normalized difference water index) is extracted using Google Earth Engine to measure the water body coverage area and analyze the seasonal changes of hydrology. The texture entropy is obtained by calculating the gray-level co-occurrence matrix through the texture analysis tool in ENVI software and is the entropy of the gray-level co-occurrence matrix of the LCZ image, describing the complexity of the gray value distribution in the image. The texture contrast is obtained by calculating the contrast in the gray-level co-occurrence matrix. The surface roughness is measured by ground radar and is the contrast of the gray-level co-occurrence matrix of the LCZ image, used to measure the significance of pixel gray value differences in the LCZ image. The air temperature, rainfall, and wind speed are all provided by satellite data. The mean square error is calculated using the built-in functions of Python or MATLAB. The structural similarity index is calculated using the built-in functions of Python (scikit-image library) or MATLAB. The spatial residual is calculated by analyzing the deviation of the spatial texture features of the image. The temporal residual is calculated by comparing the differences in the time series trends. The LCZ image clarity is obtained through remote sensing image processing software. Through the above data, not only support for spatio-temporal fusion is provided, but also a data basis for subsequent analysis is provided.

[0039] Further, the specific steps to obtain the initial weights are as follows: A1. Automatically identify the scene through the image information of multi-source remote sensing information and perform scene classification, where scene classification means dividing the automatically identified scene according to the specific geographical conditions of the region; A2. Construct a mapping set between the scene categories and the initial weights, and the mapping set is constructed by the preset staff based on historical data; A3. Input the automatically identified scene into the mapping set to obtain the corresponding initial weights.

[0040] In this embodiment, the automatic classification technology of remote sensing images is used, that is, the computer is used to identify and classify the attributes of the information on the remote sensing images of the earth's surface and its environment; and by constructing a mapping set between the scene categories and the initial weights, fast and accurate initial weight allocation is realized. This process not only improves the automation and intelligence levels, reduces manual intervention, but also ensures the rationality and reliability of weight allocation.

[0041] Further, the specific steps to obtain the scene weight evaluation coefficient are as follows: B1. Number the preset time period and obtain the reference scene data from the preset database. The reference scene data includes the preset vegetation index, the preset hydrological index, the reference texture entropy, and the reference texture contrast; B2. Perform data preprocessing on the remote sensing data, and the data preprocessing is used to de-unitize and normalize the remote sensing data; B3. Obtain the remote sensing base number according to the remote sensing data and the initial weights, and the remote sensing base number is used to quantify the current spatio-temporal resolution; B4. Process the remote sensing base number, the scene characteristic data, and the reference scene data to obtain the scene weight evaluation coefficient.

[0042] In this embodiment, by comprehensively considering multi-source remote sensing data, accurate evaluation of the initial weights in the corresponding scenes is realized, which not only improves the accuracy and reliability of weight evaluation, but also provides strong support for subsequent analysis and decision-making; at the same time, the flexibility and scalability of this method also enable it to adapt to the changes of different scenes and requirements, providing space for the in-depth application of remote sensing data.

[0043] Specifically, the specific limit expression of the scene weight evaluation coefficient is as follows:

[0044] ;

[0045] ;

[0046] In the formula, t represents the number of the preset time period, , represents the total number of the preset time periods, represents the spatial resolution of the t-th preset time period, represents the temporal resolution of the t-th preset time period, represents the initial time weight of the t-th preset time period, Represents the initial spatial weight of the t-th preset time period. Represents the remote sensing base number of the t-th preset time period. Represents the vegetation index of the t-th preset time period. Represents the hydrological index of the t-th preset time period. Represents the texture entropy of the t-th preset time period. Represents the texture contrast of the t-th preset time period. Represents the preset vegetation index. Represents the preset hydrological index. Represents the reference texture entropy. Represents the reference texture contrast. Represents the scene weight evaluation coefficient of the t-th preset time period.

[0047] In this embodiment, the algorithm comprehensively analyzes the remote sensing base number, scene characteristic data, and reference scene data to obtain the scene weight evaluation coefficient. In the formula, the remote sensing base number is obtained by comprehensively processing the initial weight and the corresponding spatio-temporal resolution. When the remote sensing base number is determined, as the scene characteristic data is closer to the corresponding reference scene data, the scene weight evaluation coefficient is larger. For example, when the vegetation index is closer to the preset vegetation index, the absolute deviation between the vegetation index and the preset vegetation index is small, and then the corresponding scene weight evaluation coefficient is larger. The same applies to the hydrological index. Another example is that when the texture entropy is closer to the reference texture entropy, the relative deviation between the texture entropy and the reference texture entropy is smaller, and then the corresponding scene weight evaluation coefficient is larger. The same applies to the texture contrast. The larger the scene weight evaluation coefficient, the more balanced the fusion of the spatio-temporal resolution, and then the more applicable the corresponding initial weight is to the current area.

[0048] In this algorithm, the parameters involved in the processing of the scene weight evaluation coefficient are interrelated and do not exist independently. Among them, the growth of vegetation is closely related to the hydrological conditions. Vegetation affects the water cycle through transpiration, and the hydrological conditions in turn affect the growth and distribution of vegetation. Therefore, the vegetation index and the hydrological index usually show a positive correlation because the growth of vegetation depends on water resources, especially in wetlands or seasonal water areas. In the analysis of remote sensing images, the vegetation index and texture features are often used jointly to improve the accuracy of classification and recognition. The vegetation index can reflect information such as the growth status and coverage of vegetation. Areas with uniform vegetation coverage (such as dense forests) have low texture contrast, and areas with complex hydrological conditions (such as interlaced water bodies and vegetation) usually have a higher texture entropy. Texture features can provide additional information about the type of surface cover, soil moisture, etc. Texture entropy and texture contrast are two important parameters for describing image texture features. Areas with high texture contrast usually have a higher corresponding texture entropy, especially in terrains or ecological boundaries with strong diversity. Through the above analysis, the rationality of the initial weight in the corresponding scene is evaluated more accurately, and then the initial weight is dynamically and evenly adjusted to improve the effect of spatio-temporal fusion.

[0049] Specifically, the reference scene data is obtained from a preset database. In a specific embodiment, the preset vegetation index and the preset hydrological index are the means of the vegetation index and the hydrological index in the corresponding season in historical data. The reference texture entropy and the reference texture contrast are set according to the requirements for generating LCZ images, and the requirements for generating LCZ images are specifically set by preset staff according to industry standards.

[0050] Furthermore, the specific process of the environmental weight evaluation coefficient is as follows: Obtain reference geographical data from a preset database. The reference geographical data includes reference surface roughness, reference temperature, reference rainfall, and reference wind speed; Obtain remote sensing data and process the relative and absolute deviations between the geographical environment data and the corresponding reference geographical data to obtain the environmental weight evaluation coefficient; The absolute deviation represents the absolute value of the difference between the surface roughness and the reference surface roughness; The relative deviations include relative temperature deviation, relative rainfall deviation, and relative wind speed deviation; The relative temperature deviation represents the ratio of the absolute value of the difference between the temperature and the reference temperature to the reference temperature; The relative rainfall deviation represents the ratio of the absolute value of the difference between the rainfall and the reference rainfall to the reference rainfall; The relative wind speed deviation represents the ratio of the absolute value of the difference between the wind speed and the reference wind speed to the reference wind speed.

[0051] The specific limiting expression of the environmental weight evaluation coefficient is as follows:

[0052] ;

[0053] ;

[0054] where \(t\) represents the number of the preset time period, , represents the total number of the preset time periods, represents the spatial resolution of the \(t\)-th preset time period, represents the temporal resolution of the \(t\)-th preset time period, represents the initial time weight of the \(t\)-th preset time period, represents the initial spatial weight of the \(t\)-th preset time period, represents the remote sensing base number of the \(t\)-th preset time period, represents the surface roughness of the \(t\)-th preset time period, represents the air temperature of the \(t\)-th preset time period, represents the rainfall of the \(t\)-th preset time period, represents the wind speed of the \(t\)-th preset time period, represents the reference surface roughness, represents the reference air temperature, represents the reference rainfall, represents the reference wind speed, represents the environmental weight evaluation coefficient of the \(t\)-th preset time period.

[0055] In this embodiment, the environmental weight evaluation coefficient is obtained through comprehensive analysis of the remote sensing base number, geographical environment data and the corresponding reference geographical data. In the formula, the remote sensing base number is obtained through comprehensive processing according to the initial weights and the corresponding spatio-temporal resolutions. When the remote sensing base number is determined, the closer the geographical environment data is to the corresponding reference geographical data, the larger the environmental weight evaluation coefficient is. For example, the closer the surface roughness is to the reference surface roughness, the smaller the absolute deviation between the surface roughness and the reference surface roughness is, and then the larger the corresponding environmental weight evaluation coefficient is. Another example is that when the air temperature is closer to the reference air temperature, the smaller the relative deviation between the air temperature and the reference air temperature is, and then the larger the corresponding environmental weight evaluation coefficient is. The same applies to rainfall and wind speed. The larger the environmental weight evaluation coefficient is, the more balanced the fusion of spatio-temporal resolutions is, and then the more applicable the corresponding initial weight is to the geographical environment of the current region.

[0056] In this algorithm, the parameters involved in the processing of the environmental weight evaluation coefficient are interrelated and do not exist independently. Among them, the air is affected by ground obstacles during the flow process. The greater the surface roughness, the greater the frictional force acting on the air, and the more the corresponding wind speed decreases. At the same time, the surface roughness may affect the heat exchange process of the surface, thereby affecting the air temperature. In addition, the wind speed may affect the distribution and change of the air temperature. For example, on a sunny day, the greater the wind speed, the faster the air temperature may drop because the wind will accelerate the heat dissipation of the surface. At the same time, the higher the wind speed, the more dispersed the rainfall distribution, which may lead to a decrease in precipitation in some areas. The long-term action of rainfall may increase the surface roughness (promote vegetation growth or landform change), and high-roughness areas are usually more conducive to the formation of local rainfall; through the above analysis, the rationality of the initial weight in the corresponding geographical environment is more accurately evaluated, and then the initial weight is dynamically and evenly adjusted to improve the effect of spatio-temporal fusion.

[0057] Specifically, the reference geographical data is obtained from a preset database. In a specific embodiment, the reference surface roughness is the mean value of the surface roughness of the corresponding season in the historical data, and the reference air temperature, reference rainfall, and reference wind speed are the mean values of the air temperature, rainfall, and wind speed provided by the meteorological bureau.

[0058] Furthermore, the specific process of determining whether to perform dynamic weight reallocation is as follows: Obtain the scenario threshold and environmental threshold from the preset database, and compare the scenario weight evaluation coefficient and the environmental weight evaluation coefficient with the scenario threshold and the environmental threshold respectively: If the scenario weight evaluation coefficient is not less than the scenario threshold and the environmental weight evaluation coefficient is not less than the environmental threshold, then no dynamic weight reallocation is performed; If the scenario weight evaluation coefficient is less than the scenario threshold or the environmental weight evaluation coefficient is less than the environmental threshold, then dynamic weight reallocation is performed; The dynamic weight reallocation includes dynamic weight adjustment based on spatio-temporal change characteristics and spatio-temporal convolutional network optimization.

[0059] In this embodiment, the process of dynamic weight reallocation can flexibly and accurately handle the weight allocation problems under different scenarios and environmental conditions, and through the scenario threshold and environmental threshold, it can intelligently determine whether the current scenario weight evaluation coefficient and environmental weight evaluation coefficient meet the established standards, realizing flexible response and optimization of weight allocation under different scenarios and environmental conditions, thereby improving the adaptability and stability of the system.

[0060] Specifically, the scenario threshold is obtained from the preset database. In a specific embodiment, the remote sensing data and scenario characteristic data corresponding to the situation where the spatio-temporal fusion does not meet the industry standards in the historical data are substituted into the specific limit expression of the scenario weight evaluation coefficient to obtain the corresponding data set, and the mean value operation is performed on the data set to obtain the scenario threshold.

[0061] Specifically, the environmental threshold is obtained from a preset database. In a specific embodiment, remote sensing data and geographical environment data corresponding to the situation where spatio-temporal fusion does not meet industry standards in historical data are substituted into the specific limit expression of the environmental weight evaluation coefficient to obtain a corresponding data set, and the mean operation is performed on the data set to obtain the environmental threshold.

[0062] Furthermore, the specific content of dynamic weight reallocation is as follows: The weight dynamic adjustment based on spatio-temporal change characteristics is achieved through spatio-temporal block dynamic weighting and weight smoothing processing; Spatio-temporal block dynamic weighting means calculating weights for each region after dividing the LCZ image generated based on multi-source remote sensing information into blocks; The specific content of spatio-temporal convolutional network optimization is as follows: Input the spatio-temporal weight map, NDVI (Normalized Difference Vegetation Index) change rate map, and edge complexity map of the previous preset time period into the spatio-temporal convolutional network, then the initial weight of the next preset time period is output. The spatio-temporal weight map is used to describe the weight distribution of spatial resolution and temporal resolution in the fusion process, the NDVI change rate map is used to reflect the change amplitude of the vegetation index within the preset time period, and the edge complexity map describes the density and complexity of the edges in the LCZ image generated based on multi-source remote sensing information.

[0063] In this embodiment, through spatio-temporal block dynamic weighting, weight smoothing processing, and spatio-temporal convolutional network optimization, the reallocation of dynamic weights is achieved. This method can comprehensively consider factors such as spatial resolution, temporal resolution, change amplitude of vegetation index, and edge complexity based on the LCZ image generated from multi-source remote sensing information, thereby improving the accuracy and rationality of weight allocation.

[0064] Furthermore, the specific process for obtaining the weight regulation evaluation coefficient is as follows: Obtain the minimum value of LCZ image clarity from the preset database, and the minimum value of LCZ image clarity represents the minimum limit of the clarity of the LCZ image generated based on multi-source remote sensing information; Perform normalization processing on the mean square error, spatial residual, and temporal residual, and the normalization processing is used to unify the dimension of spatio-temporal fusion data; The weight regulation evaluation coefficient is obtained by respectively processing the sum of deviations, structural similarity index, LCZ image clarity, and the corresponding minimum value of LCZ image clarity. The sum of deviations represents the result of adding the mean square error, spatial residual, and temporal residual.

[0065] The specific limit expression of the weight regulation evaluation coefficient is as follows:

[0066] ;

[0067] In the formula, t represents the number of the preset time period, , represents the total number of preset time periods, denotes the mean squared error of the t-th preset time period, denotes the structural similarity index of the t-th preset time period, denotes the spatial residual of the t-th preset time period, denotes the temporal residual of the t-th preset time period, denotes the LCZ image sharpness of the t-th preset time period, denotes the minimum value of LCZ image sharpness, denotes the weight regulation evaluation coefficient of the t-th preset time period.

[0068] In this embodiment, the algorithm comprehensively analyzes the spatio-temporal fusion feedback data and the minimum value of LCZ image sharpness to obtain the weight regulation evaluation coefficient. In the formula, as the mean squared error, temporal residual, and spatial residual decrease, the weight regulation evaluation coefficient increases. As the structural similarity index increases, the weight regulation evaluation coefficient also increases. Similarly, as the LCZ image sharpness increases, the weight regulation evaluation coefficient also increases. Among them, the mean squared error, structural similarity index, spatial residual, temporal residual, and LCZ image sharpness are concepts and indicators in their respective fields. There is no direct connection between the data, but they affect each other. For example, a higher mean squared error usually corresponds to a lower structural similarity index because a larger pixel value error will lead to a decrease in image perception quality. And a higher mean squared error also results in a lower LCZ image sharpness because excessive errors usually manifest as image blurring or detail loss. When the structural similarity index is lower, it usually indicates that the spatial structure or temporal consistency of the fused image is poor, and the corresponding spatial residual or temporal residual is larger. At the same time, the higher the structural similarity index, the higher the LCZ image sharpness because good structural similarity means more image details and textures are retained. When the spatial residual and temporal residual are larger, the LCZ image sharpness will be lower because the residuals in space and time will destroy the sharpness and consistency of the image.

[0069] Such as Figure 2 shown, it is a schematic diagram of the change of the weight regulation evaluation coefficient with the mean squared error provided by the embodiment of the present application. After de-normalizing the spatio-temporal fusion feedback data, assuming the minimum value of LCZ image sharpness is 0.1, when the structural similarity index is 0.8, the spatial residual is 0.5, the temporal residual is 0.5, and the LCZ image sharpness is 1, as the mean squared error increases, the image shows a downward trend, indicating that there is a negative correlation between the mean squared error and the weight regulation evaluation coefficient; as Figure 3 shown, Figure 3It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the structural similarity index provided by the embodiment of the present application. When the mean square error is 0.5, the spatial residual is 0.5, the temporal residual is 0.5, and the LCZ image clarity is 1, as the structural similarity index increases, the image shows an upward trend, indicating a positive correlation between the structural similarity index and the weight regulation evaluation coefficient; as Figure 4 shown, Figure 4 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the spatial residual provided by the embodiment of the present application. When the mean square error is 0.5, the structural similarity index is 0.8, the temporal residual is 0.5, and the LCZ image clarity is 1, as the spatial residual increases, the image shows a downward trend, indicating a negative correlation between the spatial residual and the weight regulation evaluation coefficient; as Figure 5 shown, Figure 5 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the temporal residual provided by the embodiment of the present application. When the mean square error is 0.5, the structural similarity index is 0.8, the spatial residual is 0.5, and the LCZ image clarity is 1, as the temporal residual increases, the image shows a downward trend, indicating a negative correlation between the temporal residual and the weight regulation evaluation coefficient; as Figure 6 shown, Figure 6 It is a schematic diagram showing the change of the weight regulation evaluation coefficient with the LCZ image clarity provided by the embodiment of the present application. When the mean square error is 0.5, the structural similarity index is 0.8, the spatial residual is 0.5, and the temporal residual is 0.5, as the LCZ image clarity increases, the image shows an upward trend, indicating a positive correlation between the LCZ image clarity and the weight regulation evaluation coefficient; the larger the weight regulation evaluation coefficient, the more suitable the adjusted initial weight is for the current scene and geographical environment. By analyzing the weight regulation evaluation coefficient, the effect of dynamic weight reallocation is evaluated more accurately, which helps to further improve the weight allocation.

[0070] Specifically, assuming that the minimum value of the LCZ image clarity is 0.4, and after de - normalizing the spatio - temporal fusion feedback data, a data change table of the weight regulation evaluation coefficient can be obtained, as shown in Table 1 specifically:

[0071] Table 1 Data change table of the weight regulation evaluation coefficient

[0072]

[0073] As can be seen from Table 1, with the decrease of the mean square error, spatial residual and temporal residual, and the increase of the structural similarity index and the clarity of the LCZ image, the weight regulation evaluation coefficient gradually increases. For example, when the mean square error decreases from 0.6 in the first row to 0.3 in the fifth row, the structural similarity index increases from 0.4 in the first row to 0.8 in the fifth row, the spatial residual decreases from 0.8 in the first row to 0.2 in the fifth row, the temporal residual decreases from 0.9 in the first row to 0.2 in the fifth row, and the clarity of the LCZ image increases from 0.5 in the first row to 0.9 in the fifth row, the corresponding weight regulation evaluation coefficient also increases from 1.01 in the first row to 1.61 in the fifth row. Through the specific analysis of the weight regulation evaluation coefficient, the effect of dynamic weight reallocation is more accurately quantified, providing a basis for subsequent weight allocation.

[0074] Specifically, the minimum value of the LCZ image clarity is obtained from a preset database. In a specific embodiment, the minimum value of the LCZ image clarity is specifically set by a preset staff according to industry standards. For example, if the scene category is a city and it is required that the clarity of the LCZ image of the city reaches at least 0.6, then 0.6 is recorded as the minimum value of the LCZ image clarity.

[0075] Further, the specific process of determining whether to perform weight secondary allocation is as follows: Obtain a regulation threshold from a preset database, and the regulation threshold is used to determine whether to perform weight secondary allocation; compare the weight regulation evaluation coefficient with the regulation threshold: if the weight regulation evaluation coefficient is not less than the regulation threshold, then no weight secondary allocation is performed; if the weight regulation evaluation coefficient is less than the regulation threshold, then weight secondary allocation is performed; weight secondary allocation means that in the next preset time period, the initial weight after dynamic weight reallocation is used as the initial weight, and based on the initial weight, the scene weight evaluation coefficient, environmental weight evaluation coefficient, and weight regulation evaluation coefficient are continuously obtained until the weight regulation evaluation coefficient is not less than the regulation threshold.

[0076] In this embodiment, starting from the initial weight after dynamic weight reallocation, through continuous iteration and optimization, the scene weight evaluation coefficient, environmental weight evaluation coefficient, and weight regulation evaluation coefficient are gradually adjusted until they reach or exceed the corresponding thresholds. This process not only improves the accuracy and rationality of weight allocation but also ensures the stability and adaptability of this method in different scenarios and environments.

[0077] Specifically, the regulation threshold is obtained from a preset database. In a specific embodiment, the spatio-temporal fusion feedback data corresponding to the situation where the spatio-temporal fusion does not meet industry standards in historical data is substituted into the specific limit expression of the weight regulation evaluation coefficient to obtain a corresponding data set, and the mean value operation is performed on the data set to obtain the regulation threshold.

[0078] In summary, in the embodiments of the present application, the initial weights are obtained by identifying scenarios through multi-source remote sensing information, and the remote sensing data and scenario characteristic data within a preset time period are obtained to obtain the scenario weight evaluation coefficient. At the same time, the geographical environment data is obtained and combined with the remote sensing data to obtain the environmental weight evaluation coefficient. Then, it is determined whether to perform dynamic weight reallocation according to the scenario weight evaluation coefficient and the environmental weight evaluation coefficient. Finally, the weight regulation evaluation coefficient is obtained based on the obtained spatio-temporal fusion feedback data to determine whether to perform secondary weight allocation, thereby improving the effect of spatio-temporal fusion, and further achieving the improvement of the accuracy of spatio-temporal resolution control, effectively solving the problem of inaccurate spatio-temporal resolution control in the prior art.

[0079] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0081] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide means for implementing the specified functions in Figure 1One process or multiple processes and / or blocks Figure 1 Steps of the functions specified in one block or multiple blocks.

[0083] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A method for controlling the spatiotemporal resolution of LCZ based on multi-source remote sensing information, characterized in that: The following steps are involved: S1, identifying the scene based on multi-source remote sensing information to obtain an initial weight, and obtaining a scene weight evaluation coefficient by acquiring remote sensing data and scene characteristic data within a preset time period, wherein the scene weight evaluation coefficient is used to quantify the degree of adaptation between the initial weight and the scene; S2, obtaining geographic environment data and combining it with remote sensing data to obtain an environmental weight assessment coefficient, and judging whether to perform dynamic weight redistribution according to the scene weight assessment coefficient and the environmental weight assessment coefficient, wherein the environmental weight assessment coefficient is used to quantify the degree of adaptation of the initial weight to the geographic environment; S3, obtaining a weight control evaluation coefficient according to the acquired spatiotemporal fusion feedback data, and judging whether to perform a secondary weight distribution according to the weight control evaluation coefficient, wherein the weight control evaluation coefficient is used to feedback the rationality of the fusion after the time weight and the space weight are regulated; The specific steps for obtaining the scene weight evaluation coefficient are as follows: B1, numbering the preset time periods and acquiring reference scene data from a preset database, wherein the reference scene data includes a preset vegetation index, a preset hydrological index, a reference texture entropy, and a reference texture contrast; B2, performing data preprocessing on the remote sensing data, wherein the data preprocessing is used to de-unitize and normalize the remote sensing data; B3, obtaining a remote sensing base number according to the remote sensing data and the initial weight, wherein the remote sensing base number is used to quantify the current spatiotemporal resolution; B4, processing the remote sensing base, scene characteristic data and reference scene data to obtain the scene weight evaluation coefficient; The specific limiting expression of the scene weight evaluation coefficient is as follows: ； Where t represents the number of the preset time period, , Indicates the total number of preset time periods. Represents the remote sensing base number of the t-th preset time period, represents the vegetation index of the t-th preset time period, represents the hydrological index of the t-th preset time period, represents the texture entropy of the t-th preset time period, represents the texture contrast of the t-th preset time period, Indicates the preset vegetation index. Indicates the preset hydrological index, represents the reference texture entropy, represents the reference texture contrast, represents the scene weight evaluation coefficient of the t-th preset time period; The specific process of obtaining the environmental weight assessment coefficient is as follows: Acquire reference geographic data from a preset database, wherein the reference geographic data includes reference surface roughness, reference temperature, reference rainfall, and reference wind speed; Obtain remote sensing base data and process the relative deviation and absolute deviation of geographic environment data and corresponding reference geographic data to obtain environmental weight assessment coefficients; The relative deviation includes relative deviation of temperature, relative deviation of rainfall and relative deviation of wind speed; The relative temperature deviation represents the ratio of the absolute value of the difference between the temperature and the reference temperature to the reference temperature; The relative deviation of rainfall represents the ratio of the absolute value of the difference between rainfall and reference rainfall to the reference rainfall; The relative wind speed deviation represents the ratio of the absolute value of the difference between the wind speed and the reference wind speed to the reference wind speed.

2. The LCZ spatiotemporal resolution control method based on multi-source remote sensing information as claimed in claim 1, characterized in that: The specific steps of obtaining the initial weights are as follows: A1, automatically identifying scenes and classifying scenes through image information of multi-source remote sensing information, wherein the scene classification means dividing the automatically identified scenes according to specific geographical conditions of the region; A2, constructing a mapping set of scene categories and initial weights, wherein the mapping set is constructed by a preset staff member based on historical data; A3, the automatically identified scene input mapping is concentrated to obtain the corresponding initial weights.

3. The LCZ spatiotemporal resolution control method based on multi-source remote sensing information as claimed in claim 1, characterized in that: The remote sensing data includes spatial resolution and temporal resolution; The scene characteristic data include vegetation index, hydrological index, texture entropy and texture contrast; The geographical environment data include surface roughness, temperature, rainfall and wind speed; The spatiotemporal fusion feedback data includes mean square error, structural similarity index, spatial residual, temporal residual and LCZ image clarity; The LCZ image clarity indicates the clarity of the LCZ image generated after a preset time period ends.

4. The LCZ spatiotemporal resolution control method based on multi-source remote sensing information as claimed in claim 1, characterized in that: The specific process of determining whether to perform dynamic weight redistribution is as follows: Obtain the scene threshold and environment threshold from the preset database, and compare the scene weight evaluation coefficient and environment weight evaluation coefficient with the scene threshold and environment threshold respectively: If the scenario weight evaluation coefficient is not less than the scenario threshold and the environment weight evaluation coefficient is not less than the environment threshold, no dynamic weight redistribution is performed; If the scenario weight evaluation coefficient is less than the scenario threshold or the environment weight evaluation coefficient is less than the environment threshold, dynamic weight redistribution is performed; The dynamic weight redistribution includes dynamic weight adjustment based on spatiotemporal variation characteristics and spatiotemporal convolutional network optimization.

5. The LCZ spatiotemporal resolution control method based on multi-source remote sensing information as claimed in claim 4, characterized in that: The specific contents of the dynamic weight redistribution are as follows: The dynamic adjustment of weights based on spatiotemporal variation characteristics is achieved through spatiotemporal block dynamic weighting and weight smoothing processing; The spatiotemporal block dynamic weighting means that the weight is calculated region by region after the LCZ image generated based on multi-source remote sensing information is divided into blocks.

6. The LCZ spatiotemporal resolution control method based on multi-source remote sensing information as claimed in claim 1, characterized in that: The specific process of obtaining the weight control evaluation coefficient is as follows: Acquire a minimum value of LCZ image clarity from a preset database, wherein the minimum value of LCZ image clarity represents a minimum limit value of clarity of an LCZ image generated based on multi-source remote sensing information; Normalizing the mean square error, the spatial residual, and the temporal residual, wherein the normalization is used to unify the dimensions of the spatiotemporal fusion data; The weight control evaluation coefficient is obtained by processing the sum of deviations, the structural similarity index, the LCZ image clarity and the corresponding minimum LCZ image clarity respectively, wherein the sum of deviations represents the result of adding the mean square error, the spatial residual and the temporal residual.

7. The LCZ spatiotemporal resolution control method based on multi-source remote sensing information as claimed in claim 6, characterized in that: The specific process of determining whether to perform secondary weight distribution is as follows: Obtaining a control threshold from a preset database, where the control threshold is used to determine whether to perform secondary weight distribution; Compare the weight control evaluation coefficient with the control threshold: If the weight control evaluation coefficient is not less than the control threshold, no secondary weight distribution will be performed; If the weight control evaluation coefficient is less than the control threshold, the weight is redistributed; The secondary weight distribution means that the initial weight after dynamic weight redistribution in the next preset time period is used as the initial weight, and the scene weight evaluation coefficient, environment weight evaluation coefficient and weight control evaluation coefficient are continuously obtained based on the initial weight until the weight control evaluation coefficient is not less than the control threshold.

Images