60 results about "Land surface temperature" patented technology

The invention relates to the technical field of remote sensing image intelligent processing, in particular to a multi-scale progressive surface temperature fusion downscaling method and device, and the method comprises the steps: preprocessing a surface temperature image in a multi-scale image library; constructing a multi-scale training data set containing the surface temperature and at least one auxiliary parameter; constructing a surface temperature downscaling network based on multi-parameter fusion, and constructing a domain transformation network based on heterogeneous high-frequency information guidance; training a surface temperature downscaling network and a domain transformation network based on a progressive dual-network joint training strategy; finely adjusting the downscaling model meeting a preset low-medium resolution condition; and performing low-medium-high progressive downscaling on the low-resolution surface temperature image to be processed to generate a multi-scale progressive surface temperature meeting a target high-resolution condition. The method fully considers the problem of descending scale difference of different resolutions, achieves the maintenance of the physical characteristics of the surface thermal field, and improves the processing efficiency of large-area remote sensing data.

The invention discloses an active city cooling method based on a three-dimensional city form and a circuit theory, and belongs to the technical field of city environment regulation and heat island effect governance, and the method comprises the steps: S1, recognizing long-term stable cold and heat source patches through obtaining multi-temporal surface temperature (LST) data and combining mathematical form spatial pattern analysis (MSPA) and a landscape connectivity index; s2, adopting a spatial principal component analysis (SPCA) method to construct a comprehensive resistance surface fused with the three-dimensional urban form factors; s3, connecting a cold and heat source to simulate an airflow conduction path based on a circuit theory, extracting a cooling gallery and identifying key nodes; and S4, finally, through a stable surface-connecting line-key point mode active cooling network, space optimization is carried out. According to the method, accurate identification and efficient communication of cold and heat sources can be realized, the heat island effect relieving efficiency is improved, the long-term adaptability of a cooling network is ensured, and a popularized urban thermal environment governance path is provided.

The invention relates to a land surface temperature and emissivity joint inversion method and system and a medium. The inversion method comprises the following steps: acquiring radiation brightness vectors observed by a satellite sensor in a plurality of thermal infrared bands as observation radiation brightness vectors; constructing a standard emissivity spectrum dictionary database as a dictionary matrix; defining a generation rule of the surface emissivity; establishing a forward physical model, and taking an analog value of the observed radiance vector as model output; defining a likelihood function of an observation radiance vector, defining sparsity prior probability distribution for the sparse coefficient vector, and defining uniform prior probability distribution for the surface temperature; joint posterior probability distribution of the surface temperature and the sparse coefficient vector is calculated, and multiple groups of samples are extracted; calculating a posteriori estimation value and an uncertainty interval of the surface temperature; and calculating a posteriori estimation vector of the sparse coefficient vector, and multiplying the posteriori estimation vector with the dictionary matrix to obtain a posteriori estimation value of the surface emissivity. The automation level of remote sensing information extraction and the information output efficiency are improved.

The invention discloses a surface temperature medium and long term forecasting method based on a multi-scale TransFuse pyramid network. The surface temperature medium and long term forecasting method comprises the steps of S1, acquiring original LST time sequence data and performing preprocessing; s2, constructing a three-dimensional time delay embedded feature tensor for the data preprocessed in the S1 by adopting a stepped cross-node tensor feature reconstruction method; s3, on the basis of the three-dimensional time delay embedded feature tensor constructed in the S2, meteorological features of different time scales are extracted in parallel through a dynamic multi-resolution convolution kernel group; s4, performing five-stage cascade operation on the meteorological features of different time scales extracted in the S3 to realize deep fusion of cross-scale features, and performing high-level semantic information integration through a global feature pyramid; and S5, finally outputting a multi-step prediction result through a regression prediction framework based on the fusion features obtained in the S4. According to the invention, an extensible technical normal form is effectively provided for high-precision meteorological prediction in a limited computing power scene, and important application potential is shown in actual business deployment.

The invention relates to a multi-source meteorological data fusion technology, and discloses an air temperature reconstruction method fusing data of a micro-meteorological device, which improves the temporal-spatial resolution and precision of ground temperature under a complex terrain. The method comprises the following steps: densely deploying micrometeorological devices in a complex terrain area to obtain high-frequency observation data, carrying out quality control, and carrying out hierarchical processing in two dimensions of space and time by taking pattern forecast grid point data as an initial background field: in the spatial dimension, dynamically updating a fusion weight for grid points with observation stations by using geographical weighted regression, and carrying out data fusion; a residual machine learning model is combined with multi-topographic feature correction for grid points without observation stations, and a high-precision space fusion background field is generated; in the time dimension, errors after space fusion are decoupled into a trend term and a periodic term, an autoregressive integral moving average model is used for predicting a trend, a Fourier algorithm is used for correcting a periodic phase, and then time dimension machine learning correction is carried out on a grid point of an observation-free station. And finally, complete-process automatic, high-temporal-spatial-resolution and low-error complex terrain area air temperature reconstruction is realized.

The embodiment of the invention discloses a surface temperature inversion method and device based on remote sensing satellite data, and a medium, and relates to the technical field of remote sensing, and the method comprises the steps: receiving a heat island effect analysis demand triggered by a user, obtaining satellite remote sensing data of a target region and a corresponding metadata file based on the heat island effect analysis demand, and storing the satellite remote sensing data in the target region; processing the satellite remote sensing data to determine earth surface radiation parameters; the atmospheric features and the earth surface features of the target area are evaluated through the metadata file and a pre-obtained normalized vegetation index, a dynamic adjustment factor corresponding to the target area is determined, a preset single-window algorithm model is optimized through the dynamic adjustment factor, and an optimized single-window algorithm model is determined; and inputting the surface emissivity, the atmospheric transmittance, the brightness temperature value and a pre-acquired atmospheric average action temperature into an optimized single window algorithm model for calculation, and determining a surface temperature distribution diagram of the target area for heat island effect analysis.

The invention relates to a large-scale region natural lake cooling effect core index extraction method and device, and the method comprises the steps: obtaining the lake data of a research region, and screening out natural lakes with the area, shape index, compactness, altitude and gradient in a preset range; for each natural lake, acquiring the remote sensing surface temperature LST of the natural lake, outwards constructing a multi-stage annular buffer area by taking the lake boundary as the standard, and counting the LST average value of each annular buffer area; and performing cubic polynomial fitting by taking the distance X between the outer edge of each annular buffer area and the lake boundary as an independent variable and the corresponding LST average value as a dependent variable to obtain a fitting model, and extracting the cooling effect core index, the cooling distance, the cooling intensity, the cooling range, the cooling gradient and the cooling efficiency based on the fitting model. According to the method, standardization and quantification of the large-scale lake cooling effect can be efficiently achieved, scientific data support is provided for urban thermal environment regulation and control, ecological planning and lake protection, and the method has wide application prospects.

The application discloses a kind of spatiotemporal modeling ground surface temperature downscaling method and system considering energy constraint, comprising: 1) acquisition and preprocessing of multi-source remote sensing and meteorological data;2) feature grouping and spatiotemporal feature tensor construction;3) time feature and spatial feature extraction;4) spatiotemporal feature modeling and high-resolution ground surface temperature estimation;5) loss construction and cross-scale consistency constraint;6) model iterative training and result output.The application breaks through the modeling limitation of time variation law and spatial detail description in the prior art, realizes the collaborative promotion of time continuity and spatial fine expression of ground surface temperature.On this basis, the overall temperature deviation and the problem of insufficient physical rationality commonly existing in the prior art are also effectively avoided, and the application is significantly superior to the prior art in terms of timing stability, spatial accuracy and physical reliability.

This invention discloses a method for regulating the thermal environment of urban morphology under the coupling of human and bird's-eye view perspectives. It is based on the radiative transfer equation method and Landsat-8 remote sensing imagery to retrieve land surface temperature; it integrates multimodal data for refined extraction of urban feature information; it constructs a three-dimensional comprehensive representation system of urban morphology under the coupling of bird's-eye and human perspective perspectives; it establishes urban land surface temperature prediction models at different spatial scales, integrating two-dimensional urban morphology, three-dimensional urban morphology from bird's-eye view, and three-dimensional urban morphology from human perspective; and it explores the optimal configuration method for regulating the surface thermal environment of urban morphology at both fine and coarse scales. This invention can provide a scientific basis for the quantitative regulation and spatial planning optimization of the urban thermal environment, achieving refined cooling and thermal environment improvement effects through urban spatial structure optimization and greening configuration adjustment.

The invention discloses a high-temporal-spatial-resolution surface temperature integration method and system based on optimal interpolation, and relates to the field of surface temperature integration, and the method comprises the steps: obtaining a surface temperature image, and carrying out the preprocessing of the image; constructing an auxiliary data set and performing preprocessing; performing spatial interpolation by adopting a thin-plate spline function to obtain a high-temporal-spatial-resolution surface temperature interpolation result; establishing a mapping relation between the low-spatial-temporal-resolution surface temperature and the auxiliary variables, and obtaining a high-spatial-resolution surface temperature spatial downscaling result; performing space-time fusion on the surface temperature by adopting a space-time adaptive reflectivity fusion model to obtain a high-space-time resolution surface temperature space-time fusion result; and carrying out weighted integration on the surface temperature space downscaling result and the space-time fusion result by adopting an optimal interpolation method. According to the method, the problem that an existing method still has certain limitations in surface temperature downscaling and space-time fusion technologies is solved.

The application discloses a kind of based on multilayer neural network ground surface temperature prediction method and system, wherein the method includes: obtaining remote sensing image and its corresponding atmospheric external force data and ground surface temperature data;Remote sensing image is handled to obtain multiple different scale ground surface feature data, and NDVI data and NDBI data of corresponding scale are added to obtain multiple complete ground surface feature data;Ground surface temperature data is handled to obtain ground surface feature data corresponding ground surface temperature data;Ground surface temperature prediction model is constructed, and complete ground surface feature data, ground surface temperature data and atmospheric external force data are used as training set to carry out model training, to obtain trained ground surface temperature prediction model, to carry out ground surface temperature prediction according to trained ground surface temperature prediction model;Therefore, by multilayer perception neural network, since physical information constraint is applied, mapping relationship between input and output is learned from multiple scales, and good prediction effect can be achieved.

The application discloses a frozen soil inversion method based on full-spectrum data of Gaofen-5 satellites, and the method comprises the following steps: acquiring remote sensing image data sets of full-spectrum of Gaofen-5 satellites at different time nodes, and selecting remote sensing image data of specified spectrum corresponding to each time node from the remote sensing image data sets; calculating the land surface temperature grid data corresponding to each time node according to the preset Planck function and the brightness temperature of the remote sensing image data of the specified spectrum, and obtaining the land surface temperature spatial distribution sequence data according to the land surface temperature grid data; calculating the energy sum of each grid in the remote sensing image data in a specified period in the melting state and the frozen state respectively based on the land surface temperature spatial distribution sequence data and the preset frozen top layer calculation model, and determining the distribution information of the frozen soil based on the energy sum of each grid. The application solves the technical problem that the existing frozen soil inversion scheme cannot meet the actual demand.

The present application relates to the technical field of ecological environment quality evaluation, and particularly relates to a method for quantitatively evaluating ecological environment quality by integrating multi-source remote sensing indexes, comprising the following steps: S1: collecting remote sensing data such as Landsat, SRTMDEM, MOD11A2, GlobeLand30 and FLDAS, and performing pretreatment; S2: extracting human pressure index, biological abundance index, vegetation cover index, land surface temperature and ground relative humidity from the multi-source remote sensing data set obtained in step S1; S3: using the regression Kriging method to downscale the ground relative humidity data to match the resolution of other data; and S4: after standardizing all indexes, using principal component analysis to construct MCEEI to reflect the comprehensive quality of the ecological environment; the present application can quickly quantify the surface ecological environment quality condition from multi-source remote sensing data by integrating five indexes, and can solve the problem that the traditional remote sensing evaluation method for ecological environment quality cannot effectively balance the regional difference in large-scale research.

The invention discloses a remote sensing moisture index construction method combining surface temperature and short wave infrared information. The method comprises the following steps: step 1, collecting satellite remote sensing data in a research area; step 2, meteorological radiation data collection and spatial interpolation of a research area; 3, performing remote sensing inversion on the surface biophysical parameters; step 4, calculating surface net radiation and soil heat flux; step 5, constructing a remote sensing moisture index combined with the surface temperature and the short wave infrared information; and step 6, performing space-time reconstruction on the remote sensing moisture index. The remote sensing moisture index combining the surface temperature and the short-wave infrared information is constructed, the key defect that a traditional moisture index based on the surface temperature information is greatly influenced by albedo is overcome, and the supersaturation effect of the moisture index based on the short-wave infrared information in a high vegetation coverage area is optimized; satellite thermal infrared and short wave infrared observation information can be fully utilized, and large-range, data-area-free, complex and non-uniform underlying surface moisture index calculation is achieved.

The application discloses a kind of generation near real-time hourly all-weather ground temperature method, belong to ground temperature acquisition technical field.The application will near real-time hourly all-weather ground estimation be divided into time fusion and spatial fusion two parts, realize the space-time fusion of two kinds of ground temperature.For the target moment of remote sensing ground temperature serious missing, in time scale, the more accurate remote sensing ground temperature of certain clear sky reference time before target time is initial quantity, using reanalysis data provides the ground temperature variation between target time and clear sky reference time to estimate the near real-time all-weather ground temperature of target time;Since it needs to meet many conditions to execute time fusion algorithm, part of pixel is difficult to meet, when using machine learning model to map the correlation between time fusion all-weather ground temperature and influence factor in space, and the relationship is used for missing pixel, obtains the near real-time hourly all-weather ground temperature of final spatial continuity.

The application provides a kind of urban green land cooling benefit evaluation and optimization method, system, equipment and medium based on interpretable space machine learning, method includes: based on the city boundary data of target area, land use data and land surface temperature data, constructs urban green land data set and corresponding city land surface temperature data set;For each spatial unit in the city green land data set, calculate its corresponding several urban green land characteristic indexes;Geographic weighted random forest model is constructed, for fitting the longitude and latitude of all spatial units and several urban green land characteristic indexes and the nonlinear relationship of the land surface temperature data of the corresponding spatial unit in the city land surface temperature data set;The target area is divided into zones, and based on the geographic weighted random forest model, the interpretable modeling of the cooling benefit of each urban green land characteristic index in the target area and in each zone of the target area is constructed;According to local conditions, obtain the green land cooling benefit optimization decision of target area.

The application provides a window method for analyzing land surface temperature, comprising: A1 determining the interval of high spatial resolution vegetation coverage in a window area centered on a target pixel; A2 constructing a low spatial resolution vegetation coverage pixel set belonging to the interval of A1, and establishing a window with a data pair of remote sensing land surface temperature and low spatial resolution vegetation coverage of the pixel set; A3 dividing the window of A2 into several sub-windows according to the horizontal axis, and constructing a normal distribution model of land surface temperature and its variation interval in each sub-window; A4 determining the derivative of land surface temperature with respect to vegetation coverage at the target pixel according to the variation interval of land surface temperature in each sub-window of A3; A5 resolving the remote sensing land surface temperature of the target pixel according to the derivative of A4; and A6 spatially downscaling the remote sensing land surface temperature of the target pixel according to the derivative of A4. The application avoids the error caused by using all pixels to calculate the derivative of land surface temperature with respect to vegetation coverage in the feature space method, and realizes the integration of remote sensing land surface temperature decomposition and enhancement.

The invention provides an hour-by-hour all-weather surface temperature reconstruction method based on a stationary satellite. The method comprises the following steps: S1, collecting surface temperature data and multi-source characteristic variable auxiliary data, and constructing a sample data set; s2, constructing a nuclear drive model dynamically constrained by a temperature intraday circulation model, and synchronously realizing spatial downscaling and ideal surface temperature reconstruction; s3, weather interference and sensor system errors are estimated through regression and prediction of a space-time fusion method driven by a hybrid neural network; and S4, the weather interference and the sensor system error are superposed on the ideal surface temperature, and the all-weather surface temperature is reconstructed. According to the method, nuclear driving and space-time fusion methods are organically combined, and all-weather surface temperature with high space-time resolution is reconstructed based on a stationary satellite FY-4A surface temperature product. The method has good stability and interpretability, and the precision of a reconstruction result is high.

The present application relates to the technical field of remote sensing image intelligent processing, and particularly relates to a multi-scale progressive land surface temperature fusion downscaling method and device, wherein the method comprises: preprocessing land surface temperature images in a multi-scale image library; constructing a multi-scale training data set containing land surface temperature and at least one auxiliary parameter; constructing a land surface temperature downscaling network based on multi-parameter fusion, and constructing a domain transformation network based on heterogeneous high-frequency information guidance; training the land surface temperature downscaling network and the domain transformation network based on a progressive double-network joint training strategy; fine-tuning a downscaling model meeting a preset low-to-medium resolution condition; and performing low-to-medium-to-high progressive downscaling on a low-resolution land surface temperature image to be processed, so as to generate a multi-scale progressive land surface temperature meeting a target high-resolution condition. The present application fully considers the downscaling difference problem under different resolutions, realizes the physical property retention of a land surface thermal field, and improves the processing efficiency of large-area remote sensing data.

The invention provides a comprehensive analysis method and system for a long-term coupling relationship between urban development and an urban thermal environment. The method comprises the following steps: S1, acquiring and preprocessing surface temperature data and night light intensity data; s2, based on the preprocessed data, interaction relation analysis of the surface temperature and the night light intensity is carried out, wherein the interaction relation analysis comprises the steps that the long-term change trend of the surface temperature and the night light intensity is calculated; evaluating the correlation between the surface temperature and the dynamic change trend of the noctilucent intensity; calculating the double-variant spatial autocorrelation of the surface temperature and the luminous intensity; an LST-NTL change trend coupling coordination degree model is constructed, and the coordination degree of the thermal environment and the urbanization level is measured; and S3, comprehensively analyzing a result, and revealing a spatial law and an internal mechanism of co-evolution of the surface temperature and the luminous intensity in the urban development process. Theoretical support and scientific basis are provided for urban thermal environment optimization and toughness improvement, and policy making of low-carbon urban construction and climate adaptation type space governance is assisted.

The application belongs to the field of land surface temperature reconstruction, and relates to a high spatiotemporal resolution land surface temperature reconstruction method in a cloud and fog environment, comprising the following steps: calculating a first reference land surface temperature and a first land surface temperature residual of a clear sky pixel under low spatial resolution according to a first land surface temperature annual variation model; obtaining seamless land surface reflectivity data under high spatial resolution; defining a relative solar radiation index based on high spatial resolution digital elevation model data; screening clear sky pixels participating in XGBoost model modeling; adopting an XGBoost model to respectively construct a land surface temperature annual variation model coefficient under low spatial resolution and a plurality of model relationships between daily land surface temperature residuals and land surface attributes; obtaining a high spatial resolution land surface temperature annual variation model coefficient and daily land surface temperature residual based on the plurality of model relationships constructed, and obtaining a high spatial resolution daily land surface temperature; and improving the accuracy and stability of the land surface temperature reconstruction result.

The invention discloses a soil moisture and surface temperature inversion method and system based on AI-Agent and electronic equipment. According to the method, AI-Agent intelligent management is innovatively integrated, and high-precision inversion of passive microwave remote sensing data is realized. The method specifically comprises the steps of collecting multi-source data of a research area; performing multi-level space-time classification on the research area by adopting a tree structure; constructing a multi-source training database containing remote sensing image data, bare soil and vegetation radiation transmission physical simulation data, assimilation data and ground station observation data for each level of sub-region; a soil moisture and surface temperature joint iterative inversion model is constructed based on a full-connection neural network, and collaborative optimization of mutual priori of the soil moisture and the surface temperature is realized; the AI-Agent is responsible for data intelligent integration, spatio-temporal feature automatic extraction, multi-level classification, TPE hyper-parameter optimization and nested coordination training of a large model (overall area) and a small model (subarea fine adjustment). The defects that a traditional algorithm is insufficient in precision, high in morbidity and weak in generalization ability are effectively overcome.

This invention discloses a method, system, device, and medium for downscaling surface temperature remote sensing products. The method includes the following steps: obtaining T at the target time T. 前 T 后 Raw low spatial resolution land surface temperature data and raw high spatial resolution land surface temperature data; obtain T 前 T 后 The invention obtains low spatial resolution land surface temperature data after sampling and the ID value of each sampled pixel corresponding to the original pixel; it then obtains the pixel-by-pixel rate of change of the low spatial resolution land surface temperature data; uses a pre-trained dynamic multilayer sensing network DyNet to predict the category-by-category rate of change of the high spatial resolution land surface temperature data; and uses a pre-trained weighted sensing network WNet to predict the land surface temperature at the target time T. The technical solution provided by this invention can solve the technical problems that existing linear unmixing models cannot effectively estimate land surface temperature and that existing weighting functions fail near the rate of change of -1.

The invention provides a ground surface temperature attribution method coupling a land surface process mode and ground surface energy balance, and relates to the technical field of data processing, and the method comprises the steps: optimizing an earth system mode according to an irrigation water taking process, and obtaining a land surface process mode considering a human irrigation water taking process; based on actual irrigation water statistical data, performing weighted calculation through a soil moisture deficit coefficient and an irrigation area to obtain grid scale irrigation water consumption space-time distribution, and inputting the grid scale irrigation water consumption space-time distribution into a land surface process mode to obtain a land surface temperature value under the influence of irrigation; based on the Taylor expansion form of the earth surface energy balance equation, attributing the change of the earth surface temperature value, and constructing an attribution framework based on the earth surface energy balance equation; and calculating the ground surface temperature attribution by using the actual irrigation water statistical data, the land surface process mode and the attribution framework to obtain a ground surface temperature attribution result. According to the method, the problem that the influence of underlying surface water activities on local climate is difficult to accurately predict and cause is solved.

The invention provides an earth surface temperature satellite remote sensing estimation method and system based on passive microwave single-channel brightness temperature, and relates to the technical field of satellite remote sensing, and the method comprises the steps: based on a global monthly scale microwave emissivity climate state data set, aiming at the selected Ku frequency vertical polarization channel brightness temperature, calculating the Ku frequency vertical polarization channel brightness temperature; acquiring Ku frequency vertical polarization climate state emissivity with global spatial heterogeneity characteristics; performing quality control on the brightness temperature of the Ku frequency vertical polarization channel and the Ku frequency vertical polarization climate state emissivity with the global spatial heterogeneity characteristic, and re-projecting and sampling the emissivity data to the same spatial projection and resolution as the brightness temperature data so as to obtain preprocessed brightness temperature and emissivity data; and constructing a land surface temperature estimation model with global universality based on the Ku frequency vertical polarization brightness temperature according to a passive microwave radiation transfer equation with approximate derivation and the preprocessed brightness temperature and emissivity. The fabric can effectively penetrate through cloud layer shielding.

The invention relates to a novel drought index construction method based on multi-factor coupling, and belongs to the technical field of agricultural drought monitoring. The method comprises the following steps: calculating vegetation coverage FVC, land surface temperature LST, soil water content SMC and enhanced vegetation index EVI by using multi-source remote sensing image data, calculating chaos characteristic parameters of each factor, determining sensitivity weight of each factor to drought according to the chaos characteristic parameters, adopting an improved random forest algorithm as a multi-factor coupling model, inputting a weighted characteristic matrix for training, and determining drought sensitivity of each factor. And optimizing key parameters of the random forest by adopting a particle swarm optimization algorithm, determining nonlinear mapping from a weighted feature to a chaos coupling multi-factor drought index CCMDI, and judging a drought level according to an index value. According to the method, the comprehensive process of drought formation and development is represented more truly, and high-precision inversion of the drought grade is realized.

This invention relates to the field of meteorological forecasting technology and discloses a method for predicting surface temperature and evaporation. The invention first performs multi-scale mode decomposition on the raw meteorological data, separating high-frequency noise components from mid- and low-frequency effective information components. This eliminates interference from high-frequency random disturbances at the data preprocessing level, effectively solving the inherent non-stationarity and strong volatility problems of meteorological data. Subsequently, a CNN-BiLSTM-Attention hybrid model is constructed to perform parallel predictions on the selected mode components. The core of this invention lies in introducing a barrel theory optimization algorithm to adaptively and jointly optimize the mode decomposition parameters and deep learning hyperparameters, overcoming the limitations of manual parameter tuning. Finally, the prediction results of each component are reconstructed, and long-term predicted values ​​are output. This effectively solves the problems of insufficient accuracy, difficulty in parameter tuning, and weak cross-site generalization ability of traditional methods and existing combined models when dealing with non-stationary, multi-scale meteorological sequences, significantly improving the accuracy, stability, and automation level of prediction.

The invention discloses a land surface temperature determination method and a related device, and the method comprises the steps: obtaining a land surface temperature prediction model based on pre-training according to a first land surface temperature image at a first moment, a second land surface temperature image at a second moment, and a third land surface temperature image at the second moment; and determining a target surface temperature image at the first moment. Spatial features and time features are respectively extracted through a double-branch network (namely a spatial feature extraction branch and a time feature extraction branch) of a pre-trained surface temperature prediction model, so that surface spatial texture information and time dynamic change features can be obtained; the spatial features and the time features can be subjected to interaction and joint modeling in a feature layer through cross fusion branches, complex nonlinear land surface temperature dynamic changes can be captured, and high-frequency spatial details of a target land surface temperature image can be recovered while global consistency is maintained through a feature reconstruction sub-network. And the accuracy and reliability of surface temperature data are improved.

This invention discloses a machine learning method for reconstructing cloudless land surface temperature by combining spatial information. First, raw land surface temperature data is acquired using satellite remote sensing. This data is then combined with auxiliary data such as topography, land use, population density, reflectance, and vegetation index to initially fill in missing values. Next, spatial information of the land surface temperature is calculated based on this data. Then, combined with the aforementioned auxiliary data, a random forest regression is used to obtain the reconstructed land surface temperature. Following this, residuals are obtained from the original data, and Kriging regression is used to predict the missing residuals. Finally, these residuals are used to correct the reconstructed land surface temperature, yielding cloudless land surface temperature data. This invention can accurately reconstruct land surface temperature data, providing an algorithmic foundation for obtaining high spatiotemporal resolution data and solving the key problem of obtaining continuous imagery for studying urban thermal environment changes.

The invention belongs to the technical field of surface temperature remote sensing monitoring, and particularly discloses a pixel scale surface temperature uncertainty full-process evaluation method, which specifically comprises the following steps: measuring data information of atmospheric uplink radiation, atmospheric downlink radiation and surface emissivity, and obtaining point source surface temperature; estimating the uncertainty and the component of the surface temperature of the point source according to an error propagation theory; constructing a random forest downscaling model, and performing surface temperature downscaling processing on the image by using the model to obtain downscaling surface temperature; the uncertainty of surface temperature downscaling is quantified through a Monte Carlo simulation method; constructing a two-point method scale conversion model based on the point source surface temperature and the downscaling surface temperature; predicting the downscaling surface temperature by adopting a two-point method scale conversion model to obtain predicted surface temperature, and aggregating the predicted surface temperature to obtain pixel scale surface temperature; constructing a DTC model based on the MODIS data; the uncertainty of the pixel scale surface temperature is quantified through Monte Carlo simulation, an error propagation theory and a DTC model.