208 results about "Microwave remote sensing" patented technology

The invention relates to the technical field of water and soil conservation monitoring, and discloses a remote sensing image-based water and soil conservation monitoring method, which comprises the following steps of: 1, integrating optical, infrared and microwave remote sensing data, and constructing a soil information atlas; step 2, capturing soil humidity change in each season by using long-time-sequence data according to the soil information, and determining the influence of rainfall, snow melting and evaporation on the reflectivity; step 3, training data of each wave band through a deep neural network according to the influence information of the reflectivity; through an adaptive learning algorithm and a model parameter regular updating mechanism, the problem that in the prior art, characteristic spectrums of wet soil, vegetation and bare soil are overlapped due to seasonal changes is effectively solved, after the seasonal modulation factors are introduced, the system can accurately capture influences of natural factors such as rainfall, snow melting and evaporation on the soil reflectivity, and the soil reflectivity is improved. And model parameters are adaptively adjusted, so that the interference of reflectivity fluctuation on a monitoring result in wet and drought states is eliminated, and the stability of long-term monitoring is ensured.

The invention discloses a method for evaluating the influence of black land ecological barrier pattern evolution on agricultural climate and yield, and relates to the technical field of agricultural ecological environment monitoring and remote sensing model coupling. Comprising the following steps: S1, acquiring a high-resolution satellite image, microwave remote sensing earth surface humidity data, optical remote sensing vegetation coverage data and thermal infrared remote sensing earth surface temperature data of a target area; according to the method for evaluating the influence of the black land ecological barrier pattern evolution on the agricultural climate and the yield, the problem of lack of ecological-climate-agricultural system collaborative modeling in the traditional technology is solved. A high-resolution satellite image is used for analyzing a network topology structure of the protection forest, microwave and thermal infrared remote sensing are fused to invert'water, soil and gas generation 'multi-element parameters, and dynamic quantitative evaluation of ecological barrier spatial heterogeneity evolution on local climate and crop growth is realized in combination with a dynamic weight distribution and two-way nesting technology.

The invention discloses a forest fire risk assessment method combining microwave remote sensing and fire spreading simulation, and the method comprises the following steps: integrating microwave remote sensing data, and selecting a driving factor which affects the occurrence probability of a forest fire; establishing a time series data set based on the selected driving factor, and constructing a forest fire occurrence probability prediction model based on deep learning; simulating a fire spreading process through a cellular automaton-Monte Carlo simulation method, and calculating a potential combustion probability; and comprehensively evaluating the forest fire risk by combining the fire occurrence probability and the potential combustion probability. The forest fire risk comprehensive assessment method provided by the invention has the advantages of high accuracy, strong predictability and the like, the model can capture trends and changes of factors such as meteorology and vegetation within a period of time before a fire occurs, important features in driving factors can be better concerned, and the risk of the forest fire can be comprehensively assessed. The method for comprehensively evaluating the forest fire risk is more accurate in identification of high-risk fire areas, and more scientific and accurate information is provided for forest fire management.

The invention discloses an SAR satellite remote sensing surface water extraction method for an African climate complex region, and the method comprises the steps: carrying out the preprocessing of satellite image data, and making sample point label data; making a shadow mask file, and removing the mountain shadow on the satellite image data; calculating a gray level co-occurrence matrix to generate texture features; establishing a multi-dimensional feature space, and screening the feature space; building a semi-supervised cooperative training model by using two random forest classifiers, and introducing label-free data to assist in model training; and predicting the global surface water distribution of the research area. According to the method, the SAR remote sensing image is combined with the semi-supervised collaborative random forest model, the manpower and time cost of actual sample labeling is greatly reduced, the surface water monitoring efficiency is improved, the problem of visible light remote sensing data missing in regions with complex climates can be solved by using microwave remote sensing data, and the method is suitable for popularization and application. And timely and accurate information is provided for water resource management in the African region.

The invention discloses a salinization dynamic monitoring method based on water-salt migration characteristics and a related device, and relates to the technical field of agricultural informationization, the method comprises the following steps: processing microwave remote sensing data into characteristic data, and using a soil salt content inversion model to obtain remote sensing inversion soil salt content, and assimilating microwave remote sensing data by using a water-salt migration model in combination with daily evaporation capacity, soil water content and underground water data to obtain soil salt content changing along with time in a target period. The microwave remote sensing data and the water-salt migration model are combined, the defects of the water-salt migration model in the aspect of soil salinization monitoring can be overcome, the limitation that common optical remote sensing data are greatly restricted by weather factors such as cloud and mist can be overcome, the method can be suitable for soil salinization monitoring in a regional range, and the application prospect is wide. The dynamic change of the salt content of the saline soil can be accurately monitored in a large range for a long time.

The invention belongs to the technical field of microwave remote sensing, and provides an earth surface soil humidity GNSS-R downscaling inversion method based on multi-model fusion. Comprising the following steps: firstly, based on CYGNSS observation data, SMAP SM and auxiliary element data, constructing a training data set of a 36km grid and a test data set of a 3km grid through quality control; a limit gradient enhancement algorithm, a lightweight gradient elevator, a back propagation neural network and a random forest are adopted as base models, the training data set is divided randomly according to the proportion of 7: 3, and all the base models are constructed for training and verification; and finally, deeply learning a test result of each base model through a meta-learner (linear regression model), and automatically adjusting the weight of the test result to obtain a multi-model fused soil humidity downscaling inversion result. According to the method, the advantages of a plurality of base models are fully fused, and the soil humidity downscaling inversion precision can be effectively improved.

The invention relates to the technical field of microwave remote sensing monitoring, in particular relates to microwave remote sensing monitoring applied to the internal temperature of a coal storage yard, and particularly discloses a coal pile multi-frequency-band microwave remote sensing monitoring method and a coal pile multi-frequency-band microwave remote sensing monitoring system. The system comprises a multi-band microwave transmitting and receiving module, a signal data processing module, a data fusion and inversion model, a data storage module, a visual early warning control system and the like. Microwave signals of the surface layer and / or the shallow layer of the coal pile are detected through high-frequency-band microwaves; temperature distribution data in the coal pile are analyzed through inversion calculation of a pre-established data fusion and inversion model, laser spectrum data of the coal pile are obtained through detection of laser equipment, and harmful gas concentration data and corresponding position data are obtained. The method and the system can be used for early warning and monitoring the internal temperature and the spontaneous combustion point of the coal pile of the coal storage yard, and can effectively and accurately monitor.

The invention discloses a straw coverage monitoring method based on multi-source remote sensing data, and the method comprises the steps: carrying out the interpolation processing of SMAP brightness temperature data and ASCAT backscattering data through a Backus-Gilbert method, and generating down-sampling data with the resolution of 10 km; the method comprises the following steps: up-sampling Sentinel-1 synthetic aperture radar data, MODIS NDVI data and LST data to a resolution ratio of 10km; according to the Sentinel-1 data, the MODIS NDVI data and the LST data after up-sampling, a regression model of the 10 km ASCAT data is constructed; linear analysis is carried out according to the vegetation water content and the total primary productivity, VWC-VOD and GPP-VOD fitting equations are obtained, and intercept values of the fitting equations are extracted; defining the intercept value as the inverse evolution of the straw coverage; and constructing a linear hybrid model based on the VOD feature vectors of the end members, and inverting the abundance of the end members through minimum error measurement to obtain the farmland straw coverage. According to the method, SMAP brightness temperature data with low resolution is improved to 1km resolution through a multi-step downscaling and inversion method, and the spatial detail expression capability of microwave remote sensing data is improved.

The invention discloses a method and a system for generating surface soil humidity based on time-space fusion of remote sensing data, and relates to the technical field of soil humidity processing, and the method comprises the following steps: obtaining a vegetation parameter image, an active microwave remote sensing image and a passive microwave remote sensing image of a required date, and superposing the vegetation parameter image and the active microwave remote sensing image to obtain a vegetation parameter image; obtaining a high-resolution parameter image; resampling the parameter image to low resolution, and performing spatial downscaling on the passive microwave remote sensing image through the low-resolution parameter image; the method comprises the following steps: taking a time sequence of each pixel in a passive microwave remote sensing image as a signal, obtaining phase raster data and high-frequency amplitude raster data of different frequencies of the signal, carrying out spatial interpolation, and fitting a spatial interpolation result and a spatial downscaling result in a time dimension to obtain a daily scale surface soil humidity image. According to the method, fitting of the spatial resolution and the temporal resolution is achieved, the soil humidity image with the fine temporal-spatial resolution is obtained, and the method has high application value.

The invention discloses a method for determining a chlorophyll concentration value of phytoplankton based on ocean heat waves. The method comprises the following steps: acquiring ocean green ecological remote sensing image data and ocean heat wave data of a target sea area; and inputting the ocean heat wave data and the ocean green ecological remote sensing image data of the target sea area into a chlorophyll concentration determination model, so that the chlorophyll concentration determination model determines the ocean heat wave grade of the target sea area according to the ocean heat wave data, inputting the ocean green ecological remote sensing image data into a chlorophyll concentration determination sub-model according to the ocean heat wave grade, enabling the chlorophyll concentration determination sub-model to extract corresponding multispectral remote sensing image features and ocean microwave remote sensing image features, and outputting a phytoplankton chlorophyll concentration value of the target sea area; and transmitting the phytoplankton chlorophyll concentration value of the target sea area to a marine ecological monitoring system to assist the marine ecological monitoring system in sea area monitoring. The method can improve the accuracy of determining the chlorophyll concentration value of the phytoplankton and the application reliability.

The invention discloses a satellite-borne synthetic aperture microwave radiometer multi-angle brightness temperature noise suppression method, which belongs to the technical field of microwave remote sensing, and comprises the following steps: acquiring historical marine physical parameters, and calculating to obtain multi-angle brightness temperature according to the historical marine physical parameters; fitting the multi-angle brightness temperature, and establishing a relational expression of the brightness temperature and the observation angle under different physical parameters; and calculating the slope of the fitting curve, calculating the deviation between the brightness temperature of the multiple angles and the brightness temperature of any single angle, and establishing a deviation lookup table of the brightness temperature of the multiple angles and the brightness temperature of the specific angle under different physical parameters. The brightness temperature correction value of the corresponding angle is searched in the lookup table, and the brightness temperature of SMOS multi-angle observation is mapped to a single angle; and averaging the mapped single-angle brightness temperature to obtain the noise-suppressed single-angle brightness temperature.

The invention provides an active and passive combined microwave remote sensing detection method for earth surface air pressure and air pressure profile, which comprises the following steps: by combining a satellite-borne / airborne millimeter wave differential absorption radar and a satellite-borne / airborne microwave radiometer and utilizing oxygen differential absorption measurement, obtaining accurate land / ocean surface air pressure data; and the air pressure profile is further obtained by combining temperature and humidity profile data measured by a satellite-borne / airborne microwave radiometer. Compared with the prior art, the method has the advantages that active and passive microwaves are adopted for combined detection, detection information obtained by a microwave radiometer is complemented, calculation of the surface pressure is enhanced, and the surface pressure inversion precision is improved; according to the method, the surface pressure value can be obtained, and the atmospheric pressure profile can also be obtained. According to the method, accurate surface pressure detection can be realized, and the atmospheric pressure profile can be further deduced by combining the temperature profile and the humidity profile observed by the microwave radiometer.

The invention discloses a soil humidity inversion method and device, a medium and equipment, and relates to the technical field of microwave remote sensing inversion. According to the method, the total backscattering coefficient, the normalized vegetation index, the leaf area index and the average leaf inclination angle of the electromagnetic waves of the target area pixel by pixel are obtained in combination with microwave remote sensing data and atmospheric apparent reflectance data of the target area; according to the normalized vegetation index, the leaf area index and the average leaf inclination angle, spatial clustering is carried out on vegetation, spatial heterogeneity of crop types is captured, and then based on the constraint that the surface roughness parameters and the vegetation parameters of the same vegetation type are the same and the soil humidity in the same surface space window is the same, the spatial heterogeneity of crop types is obtained. Through two-stage iteration inversion of the intra-class scale and the ground surface space window scale, the time dynamic state is adapted, the parameter calibration function of the in-situ soil humidity data is replaced, and the model parameters and the soil humidity can be determined without the in-situ soil humidity data. According to the invention, the accuracy and reliability of the soil humidity inversion method are improved.

The invention provides a crop yield estimation method and device, electronic equipment and a storage medium, and relates to the technical field of agricultural information technology, remote sensing monitoring and artificial intelligence crossing, and the method comprises the steps: carrying out VOD space-time fusion processing based on multi-source microwave remote sensing data through a VOD space-time fusion model, and obtaining VOD fusion data; simulating crop growth based on the environment data and the crop planting data through a target crop growth model to obtain crop physiological process data; constructing multi-source feature data based on the VOD fusion data, the crop physiological process data and the environmental data; and through a double-flow space-time deep learning model, carrying out space-time feature extraction and fusion on the multi-source feature data to obtain a biomass estimated value, and further calculating a crop yield estimated value. According to the method, the crop yield is estimated based on fusion of the multi-source microwave remote sensing data, the crop growth model and the deep learning model, the restriction of a single technical normal form is broken through, and the accuracy of an estimation result can be improved.

The invention relates to a satellite-borne microwave radiometer cold air calibration attitude planning method based on multi-objective optimization, and belongs to the field of satellite microwave remote sensing, and the method comprises the steps: building a satellite attitude kinematics model and an attitude dynamics model through a geocentric equator inertial coordinate system, an orbital coordinate system and a satellite body coordinate system; establishing a brightness temperature sum model received by the microwave radiometer in the cold air calibration process; according to the method, a microwave radiometer receiving brightness temperature sum, brightness temperature fluctuation, platform maneuvering capability, energy and a satellite sensor field of view are comprehensively considered, a multi-target optimization model of microwave radiometer cold air calibration consideration constraints is established, solving is performed, constraint conditions are established, and a solution or a solution set is obtained. According to the method, the brightness temperature sum and the brightness temperature fluctuation in the observation area of the microwave radiometer in the cold air calibration process are optimized by adopting multi-objective optimization, and the on-orbit cold air calibration effect and the system reliability of the satellite-borne microwave radiometer are improved.

The invention discloses a typhoon center positioning method, device and equipment based on an SAR (Synthetic Aperture Radar) satellite, relates to the technical field of ocean microwave remote sensing, and is used for solving the problems that a typhoon positioning method in the prior art cannot accurately extract the position of a typhoon center and the positioning accuracy of the typhoon center is low. Comprising the following steps: acquiring basic data of an SAR satellite according to typhoon path information; performing sea surface wind speed and wind direction inversion based on the basic data to obtain inversion data; according to the inversion data, a gradient wind equation, a wind profile equation and the maximum wind speed are adopted to determine a high-wind-speed area of the typhoon; according to a cyclonic vortex structure of the typhoon, based on the vertical vortex field of the high-wind-speed area, the horizontal divergence field of the high-wind-speed area and the composite field of the high-wind-speed area, determining the position range of the center point of the typhoon; and positioning a typhoon center meeting preset precision according to the typhoon center point position range. According to the technical scheme, the positioning precision of the typhoon center can be improved.

The invention relates to the technical field of spaceflight microwave remote sensing, and provides a spaceborne synthetic aperture radar in-orbit autonomous task planning method, device and equipment, and the method comprises the steps: obtaining imaging parameter information; the imaging parameter information is determined by the satellite imaging system based on task annotation information, orbit information and an imaging parameter preset table, and the task annotation information is obtained by the satellite imaging system by analyzing observation requirements of a user; the orbit information is determined based on satellite forecast information. According to the method, imaging parameter information is determined by a satellite imaging system based on task uploading information, orbit information and an imaging parameter preset table, partial parameter calculation and instruction generation processes of traditional satellite-borne SAR task planning are moved to a satellite, manual calculation and ground uploading steps are omitted, and dependence of the task planning process on ground calculation is reduced; the task uploading information is obtained by analyzing the observation demand of the user through the satellite imaging system, the observation demand can be uploaded in advance, satellite resources are fully utilized, and the task execution efficiency is greatly improved.

The invention provides a farmland water demand accurate prediction method based on remote sensing data, and the method comprises the steps: firstly, synchronously collecting optical, thermal infrared, microwave remote sensing and ground data, carrying out the time-space alignment based on a dynamic time warping algorithm, and constructing a four-dimensional unified data set; then, an improved asymmetric automatic encoder integrating multi-branch encoding and a space attention mechanism is utilized to generate a deep fusion feature vector; and inputting the feature vector into an STCN-LSTM hybrid model, mining spatial features through multi-scale convolution, capturing a time evolution rule in combination with a bidirectional long short-term memory network, and embedding DSSAT crop physiological parameters to optimize the model weight. And finally, the uncertainty is quantized and predicted through Monte Carlo Dropout, and the error is further reduced by adopting a space-time layering correction strategy. The method breaks through the limitation of a single data source, the prediction error is smaller than 5%, a reliable basis is provided for precise irrigation, and the water resource utilization efficiency is remarkably improved.

The invention belongs to the field of microwave remote sensing, and relates to a Doppler precipitation radar precipitation and three-dimensional wind field synchronous inversion method and system. The Doppler precipitation radar precipitation and three-dimensional wind field synchronous inversion method comprises the following steps: determining a reflectivity factor of an observation area through echo power of a Doppler precipitation radar; according to the reflectivity factor, determining a rainfall area and calculating the size of rainfall particles; calculating the vertical falling speed of the precipitation particles according to the size of the precipitation particles; calculating the radial velocity of precipitation particles according to the echo phase of the Doppler precipitation radar; removing the vertical falling speed of the precipitation particles to obtain the radial movement speed of the precipitation particles caused by the wind field; and according to the rainfall particle radial motion speed caused by the wind field, a radar observation geometry and a three-dimensional wind field inversion algorithm are combined, and a three-dimensional wind field of the rainfall area is obtained through inversion. By adopting the method provided by the invention, the wind field inversion precision is improved.

The invention discloses an SAR-GMTI composite phase modulation interference method based on a phase-adjustable metasurface, and relates to the technical field of microwave remote sensing, and the method comprises the steps: respectively obtaining a cosine phase modulation signal and a multi-phase segmented modulation signal through slow-time cosine phase modulation and slow-time multi-phase segmented modulation; multiplying the two modulation signals to obtain a composite phase modulation signal; due to the fact that the cosine phase modulation signal has good phase continuity and smoothness, the cosine phase modulation signal can show high robustness when facing noise and interference, and the integrity and identifiability of the signal can be kept in a complex environment. Meanwhile, the information of the multi-phase segmented modulation signal is transmitted in a segmented manner, so that the signal in each segment has high anti-noise capability, the anti-interference performance of the whole signal system is improved, the anti-interference capability of the formed composite phase interference signal is greatly enhanced, and the interference precision of the SAR-GMTI system is improved.

The invention relates to the technical field of tree information acquisition, in particular to an urban tree information rapid acquisition method and system, and the method comprises the following steps: obtaining the geographic coordinates of each tree in a city through a GNSS receiver, recording the accuracy and timestamp information of each position, executing data synchronization, and generating urban tree coordinate data. According to the method, the GNSS receiver and the microwave remote sensing equipment are introduced, high-precision and multi-dimensional analysis of tree data is ensured, the GNSS receiver provides accurate coordinates and timestamps, the real-time performance and accuracy of geographic data are enhanced, and the microwave remote sensing technology accurately evaluates the age and health condition of the tree by analyzing the dielectric constant of the tree, so that the reliability of the tree is improved. The image sensor capable of automatically adjusting the focal length and the exposure parameters can capture the color and the shape of the leaves in detail, the detail degree and the accuracy of disease and insect pest diagnosis are improved, tree information mapping is updated in real time, the efficiency of environment monitoring and urban planning is improved, and powerful support is provided for management of an urban ecological system.

The invention provides a remote sensing method for improving the thickness estimation precision of accumulated snow on the surface of north pole sea ice. According to the method, firstly, the monthly-scale actually-measured accumulated snow thickness (ASD) is obtained through the active microwave technology; then, by analyzing AMSR-2 brightness temperature data provided by the American snow and ice data center, the polarization ratio (PR) and the spectral gradient ratio (GR) of different channels are calculated; meanwhile, daily snow density data (sden) of the American snow and ice center is converted into monthly snow density data. Thirdly, performing space matching on the processed data and measured data of one-year ice and multi-year ice provided by OSI SAF, and extracting key variables based on importance features; by selecting appropriate variables and machine learning and deep learning models for training, a model combination with the best correlation, the minimum deviation and the lowest root mean square error (RMSE) is screened out to estimate the surface accumulated snow thickness of one-year ice and multi-year ice. Besides, different sea ice types are distinguished by using the sea ice type data of the OSI SAF, and a specific model is applied to each type, so that long-time sequence data of the thickness of the accumulated snow on the surface of the north pole sea ice is obtained. According to the method, by integrating active and passive microwave remote sensing observation data and an advanced deep learning method, the remote sensing estimation precision of the sea ice surface accumulated snow thickness is remarkably improved.

The invention relates to the technical field of microwave remote sensing, in particular to a Ku, Ka and W three-frequency-band meteorological radar multi-source joint detection system and method and a storage medium, and the system comprises an antenna feeder subsystem, a main control computer, an integrated digital processor, a Ku / Ka integrated radio frequency machine, a Ku-frequency-band power amplifier, a Ka-frequency-band power amplifier, a W-frequency-band transmitter, a W-frequency-band power amplifier, a W-frequency-band receiver and a servo mechanism. The system is designed according to a working mode and working parameters of a main control computer, realizes multiple functions such as Ku / Ka / W single-frequency-band independent working or multi-frequency-band simultaneous working and the like, and has co-polarization and cross-polarization echo signal receiving capability; by controlling the servo mechanism, two modes of fixed-point detection and conical scanning detection are realized, and detection requirements of different meteorological elements are met; the detection capabilities of three frequency bands of Ku, Ka and W are integrated in the system, the detection mode is flexibly configured according to weather conditions and detection requirements, the system has the multi-frequency-band, multi-polarization and multi-element integrated detection capability, and the detection efficiency of the meteorological radar is improved.

The invention provides a method and a system for measuring soil moisture under crop coverage, a medium and electronic equipment. The soil moisture measurement method comprises the following steps: acquiring a microwave remote sensing image and field actual measurement data of a farmland to be monitored; preprocessing the microwave remote sensing image to obtain a farmland backscattering coefficient image; building a crop microwave scattering model based on the field measured data, and obtaining a farmland backscattering coefficient; and based on the farmland backscattering coefficient image, optimizing the farmland backscattering coefficient by using a Bayesian algorithm to obtain a farmland soil moisture estimation result. According to the method provided by the invention, the accuracy of soil moisture measurement under crop coverage can be improved.

The invention provides a super-resolution reconstruction method based on a CNN (convolutional neural network)-Transform hybrid architecture. According to the method, aiming at the defects of generalization and performance of a traditional super-resolution reconstruction algorithm of satellite-borne passive microwave remote sensing data, accurate matching and dynamic fusion of orbit ascending and orbit descending data are realized through an interactive feature alignment module, and a double-branch network is constructed by means of a multi-scale space-time attention mechanism module; extracting and integrating spatio-temporal characteristics under different receptive fields; meanwhile, a long-distance dependency relationship is established by using a hybrid adaptive attention module, the global feature modeling capability is enhanced, and finally the spatial resolution of passive microwave remote sensing data is remarkably improved through an efficient up-sampling module. According to the invention, passive microwave remote sensing data with higher spatial resolution can be obtained, and passive microwave remote sensing data with higher quality can be provided for global scale earth surface parameter inversion and monitoring research.

The invention discloses a method and a device for correcting nonlinear deviation of a backscattering coefficient, relates to the technical field of active microwave remote sensing, and aims to solve the problem of poor measurement precision of the backscattering coefficient of a microwave scatterometer in the prior art. The method comprises the following steps: acquiring measurement data and truth value data of the satellite microwave scatterometer; performing data preprocessing on the measurement data and the truth value data to obtain an initial sample data set; constructing an azimuth angle uniform distribution calibration model data set by using a dynamic uniform distribution construction method and a random error elimination method based on the initial sample data set; correcting the back scattering coefficient nonlinear deviation of the satellite microwave scatterometer based on the azimuth angle uniform distribution calibration model data set; based on this, accurate correction of the non-linear deviation of the backscattering coefficient of the satellite microwave scatterometer is realized, and the measurement accuracy of the backscattering coefficient of the satellite microwave scatterometer is improved.

The invention belongs to the technical field of atmospheric microwave remote sensing and monitoring, and relates to a rapid temperature and humidity profile inversion method for a multi-frequency atmospheric microwave radiometer. Acquiring a brightness temperature data set of the multi-frequency atmospheric microwave radiometer, performing space-time matching on the brightness temperature data set and corresponding ERA5 reanalysis or sounding balloon temperature and humidity profile data, constructing a matched data set, and dividing the matched data set into a test set, a training set and a verification set; establishing an atmosphere temperature and humidity profile inversion model based on a CNN-LSTM combined neural network; and training the model by using the training set, guiding the model optimization process by using the verification set, finally inputting multi-frequency brightness temperature data measured by the multi-frequency microwave radiometer into the trained model, and carrying out inversion to obtain an atmosphere temperature and humidity profile. According to observation data of the multi-frequency atmosphere microwave radiometer, regional atmosphere temperature and humidity profile data are rapidly and accurately obtained, and efficient inversion of the temperature and humidity profile is achieved; the vertical detection advantage of the multi-frequency microwave radiometer is exerted, the inversion efficiency is improved, and the method has a wide application prospect.

The invention belongs to the technical field of microwave radar image processing, and relates to a wind wave significant wave height inversion method based on a wind wave period, which comprises the following steps: firstly, establishing a significant wave height calculation model taking the wind wave period as input; then, acquiring a sea surface microwave remote sensing image, and performing coordinate transformation, such as preprocessing of a shore-based sea observation radar image, a shipborne navigation radar image, noise suppression and the like; thirdly, inverting a wind wave period from the preprocessed image through a spectrum analysis technology; and finally, substituting the wind wave period obtained by inversion into a pre-established model, and calculating to obtain the significant wave height. According to the method, the wind wave period is introduced to serve as a key intermediate variable, the image features and the sea wave physical parameters are closely associated, the defect that an existing direct inversion method is insufficient in precision and stability is overcome, and an effective wave height obtaining means which is clear in physical significance, high in inversion precision and easy to popularize in a business mode is provided.

The invention discloses a forest fire risk dynamic assessment and early warning system based on multi-source data fusion and artificial intelligence, and belongs to the technical field of forest fire prevention and disaster early warning. The system aims at solving the technical problems that in an existing forest fire monitoring technology, evaluation lags behind, data is single, and risk prospective prediction cannot be achieved. According to the technical scheme, satellite microwave remote sensing, optical remote sensing and near real-time meteorological and topographic data are integrated through a multi-source data acquisition module, and are fused and processed through a feature extraction module to generate a fire danger influence factor feature set containing the water content, the load capacity, the meteorological conditions and the topographic features of combustible materials; a dynamic risk distribution diagram in a future preset time period is output through a machine learning model of the dynamic risk assessment module, and finally automatic early warning is achieved through the early warning and decision making module. The system is mainly used for realizing scientific and accurate assessment and early warning of forest fire risks, and provides technical support for forest fire prevention decision making.

The invention discloses a method and device for determining a deployment strategy of a soil moisture sensor network, and the method comprises the steps: obtaining the feature data of each pixel point based on the collected digital elevation data of a to-be-deployed region through employing the soil moisture data obtained through the inversion of microwave remote sensing data as reference data; clustering is carried out according to the feature data of all the pixel points, the positions of representative sample points are obtained, then modeling is carried out by using a Gaussian process regression model, evaluation and screening are carried out by combining the obtained positions of the representative sample points and the inverted soil moisture data, and therefore the optimal deployment positions and number of sensors are determined; the number and the positions of the sensors selected through the method are high in accuracy.