20results about How to "Improve inversion accuracy" patented technology

This invention discloses a method for inverting sea surface wind speed from GNSS reflected signals based on mask perception and image-based Mamba-CNN. The method includes: performing spatiotemporal matching and interpolation processing on multi-source spaceborne GNSS-R observation data and ERA5 reanalysis data; gridding the processed observation parameters according to geographical location to obtain a multi-channel grid image and acquiring a binarized occupancy mask; inputting the multi-channel grid image and the binarized occupancy mask into a mask perception Mamba-CNN model; calibrating the grid features through a mask conditional encoder and a feature linear modulation layer, and performing spatial modeling using feature extraction blocks combining convolutional and Mamba state space paths to obtain the wind speed inversion result; aggregating the extracted features using center-perception pooling, and outputting the final sea surface wind speed inversion image through a regression network. This invention can significantly reduce computational complexity, effectively reconstruct the continuous wind field structure, and improve the inversion accuracy and robustness in high-wind-speed areas.

This invention relates to a multi-temporal radiation signal inversion method based on Conditional Transformer, belonging to the field of satellite remote sensing data processing / spatial information science and technology. The method includes: acquiring meteorological time-series data of the target area to establish a dataset; designing a Conditional Transformer deep learning network; combining the target time-series data and meteorological data encoded by time and meteorological code generators with the output of the Encoder layer, and inputting this combination into the Decoder layer to train the Conditional Transformer deep learning network to obtain a surface radiation signal inversion model; inverting surface radiation brightness temperature data and evaluating the inversion accuracy; efficiently capturing long-distance spatiotemporal dependencies of radiation signals; flexibly inverting radiation changes according to the target time and meteorological conditions; removing nonlinear interference from the atmosphere on radiation; and more accurately inverting the true radiation characteristics of the surface.

This invention relates to the field of remote sensing water quality identification technology, and in particular to a method for identifying black and odorous water bodies based on a temporal convolutional network. By constructing a black and odorous water body identification model comprising a cascaded temporal convolutional network residual module, a channel attention module, a temporal attention module, a global average pooling layer, and a regressor module, and replacing the original output layer of the temporal convolutional network with the regressor module, a mapping from remote sensing image data to continuous water quality parameter predictions is achieved. This solves the technical problem of limited accuracy in identifying black and odorous water bodies by relying solely on general spectral features in existing technologies. Furthermore, by performing addition, subtraction, multiplication, and division operations on the original spectral bands to generate combined bands, and using the Pearson correlation coefficient method to select the original and combined bands with the highest correlation, a sample dataset is constructed by combining this with ground-based measured data. This further expands the sample size based on existing samples, significantly improving the model's learning efficiency.

This invention relates to the field of quantitative remote sensing parameter inversion technology, specifically to a deep learning inversion method for passive microwave cloud-to-surface temperature constrained by physical mechanisms. The method includes the following steps: S1: acquiring model input data and preprocessing it; S2: constructing a deep learning inversion model framework constrained by physical mechanisms; S3: training the deep learning inversion model and performing cloud-to-surface temperature inversion. This invention fully combines the advantages of physical model methods in improving the physical interpretability and universality of surface parameters with the advantages of neural network algorithms in handling complex and nonlinear problems. It can solve the problem of cloud-to-surface microwave surface temperature estimation, which is difficult to achieve with high inversion accuracy, clear physical meaning, and strong generalization ability using traditional methods.

This invention is a method for inverting azimuth difference seismic data in inclined fractured rocks. Previous AVAZ inversion methods for fracture parameters were mostly based on the HTI medium assumption, with insufficient consideration for fracture dip angle. The fixed form of the inversion constraint terms made it difficult to adapt to changes in parameter statistical characteristics, and the regularization parameters were all manually adjusted, affecting inversion accuracy and efficiency. This invention establishes an approximate formula for the reflection coefficient of the TTI medium, characterized by the P-wave and S-wave velocities, density, and fracture elastic parameters of the background medium. It utilizes pre-stack azimuth difference data to perform AVAZ inversion of fracture parameters. Dynamic sparsity constraints are introduced, dynamically adjusting the sparsity of the constraints based on data characteristics, and a covariance matrix is ​​introduced to consider the statistical regularity between parameters. Combining iterative reweighted least squares and adaptive regularization parameter acquisition methods, the dynamic constraint inverse problem is transformed into a weighted... L A 2-norm objective function is used to achieve a stable solution. Data testing shows that this invention can effectively improve the inversion accuracy of crack elastic parameters.

This invention discloses a layered inversion method and system for aerosol lidar based on polarization information. The method includes: acquiring parallel and vertical polarization channel echo signals from a polarized Mie scattering lidar; performing layered identification of aerosols based on the total echo signal to determine the altitude range of upper-air and near-surface aerosol layers; for upper-air aerosol layers, calculating the estimated aerosol depolarization ratio based on the polarization channel echo signals and establishing a quantitative inversion relationship between the volume depolarization ratio and the aerosol backscattering coefficient, thereby achieving the inversion of the upper-air aerosol backscattering coefficient; for near-surface aerosols, inverting the backscattering coefficient using the Fernald method; and stitching the inversion results from different altitude regions according to the layered information to form a backscattering coefficient profile across the entire altitude range. Using this invention, the stability and reliability of upper-air aerosol inversion can be effectively improved.

A method based on local multi-source main scattering to whole-vehicle scattering characteristics is proposed. This method divides a complex target into multiple target structural regions, acquires high-resolution scattering data for each local region using a multi-frequency, multi-polarization radar system, and establishes a mapping relationship between local and whole-vehicle scattering behavior by combining imaging processing and main scattering source extraction. Furthermore, a dynamic weighting mechanism is introduced to adaptively adjust the influence weight of each region in the whole-vehicle inversion based on its contribution and measurement confidence, thereby improving the stability and robustness of the inversion results. This invention effectively alleviates the feature loss problem caused by limited viewing angle and structural complexity in traditional measurements and is applicable to multiple application scenarios such as aircraft radar scattering modeling, stealth performance evaluation, and electromagnetic characteristic analysis.

The application discloses a kind of face rainfall distribution reconstruction method and device based on space-time graph neural network, wherein the method first constructs space-time graph structure model, the complex spatial correlation between links is established by the adjacency matrix construction method of multi-factor fusion, and the graph structure data object containing space-time dimension is constructed;Further, hierarchical space-time graph neural network is used for feature extraction and fusion, and the space-time depth feature representation of the fused rainfall field is obtained;In the model optimization process, the microwave rain attenuation physical model is introduced as a constraint condition simultaneously, and the physical consistency loss function is used to ensure that the inversion result conforms to the electromagnetic wave propagation law;Based on the grid rainfall intensity and its uncertainty evaluation output by the network, high-resolution surface rainfall distribution products are generated through spatial interpolation and quality control;Finally, a real-time inference system and feedback mechanism are established to dynamically update and output the rainfall field, providing an intelligent technical solution from "line measurement" to "surface reconstruction" for meteorological and hydrological monitoring.

The application relates to the field of marine environment monitoring and optical sensing technology, and discloses a seawater surface layer temperature and salinity synchronous measurement system and a measurement method. The system comprises a light source module; an optical sensing module arranged at the seawater surface layer and directly contacted with seawater medium, which forms an output light field with statistical characteristics under the interaction of light and seawater; a light field sampling module which samples the intensity distribution of the output light field and obtains light field statistical data; and a data processing module which constructs a probability model of the light field intensity distribution based on the light field statistical data, extracts a statistical entropy characteristic quantity representing the overall statistical state of the output light field, and inversely obtains the seawater surface layer temperature and salinity by using the response relationship of the statistical entropy characteristic quantity with the seawater temperature and salinity. The application takes the overall statistical state of the light field as the sensing core, has the advantages of strong environmental disturbance resistance, universal structure, easy platform integration and the like, and is suitable for long-term in-situ monitoring of marine buoys, floating balls and the like platforms.

The present application relates to the technical field of ocean surveying and mapping, in particular to a seabed terrain inversion method based on terrain relief constraint neural network, comprising: constructing a terrain relief constraint neural network model, selecting a local standard deviation method and selecting a 9*9 moving window to calculate terrain relief information at the center point of the grid, and training the terrain relief constraint neural network model; the RANN method proposed in the present application introduces terrain relief information into the neural network as input, which weakens the influence of terrain relief difference on the model, especially in complex sea areas with terrain relief greater than 400 m, effectively improving the model inversion accuracy in the area with large terrain relief.

This invention belongs to the field of microwave radar image processing technology, and relates to a method for inverting significant wave height based on wave period. First, a significant wave height calculation model is established with the wave period as input. Then, microwave remote sensing images of the sea surface are acquired and preprocessed, such as coordinate transformation (e.g., images from shore-based sea observation radar and shipborne navigation radar) and noise suppression. Next, the wave period is inverted from the preprocessed images using spectral analysis techniques. Finally, the inverted wave period is substituted into the pre-established model to calculate the significant wave height. This invention, by introducing the wave period as a key intermediate variable, closely correlates image features with ocean wave physical parameters, overcoming the shortcomings of insufficient accuracy and stability in existing direct inversion methods. It provides a physically meaningful, highly accurate, and easily operational method for obtaining significant wave height.

The application discloses a kind of geotechnical body physical mechanics parameter coupling inversion survey methods, belong to geotechnical engineering survey technical field, comprising: multi-source survey data cooperation collection and establish five-dimensional data account book;To multi-source data carry out abnormal value elimination, normalization and adaptive weighted space-time fusion;Coupling relationship model of geotechnical body physical mechanics parameter is constructed;Establish the coupling inversion objective function of fusion data fitting error, coupling constraint error and regularization term;Set geological condition, engineering experience, physical meaning and dynamic monitoring multidimensional constraint;Coupling inversion iteration solution is carried out using improved adaptive particle swarm optimization algorithm, and dynamically updates coupling model;Residual error is verified to inversion result, cross validation and engineering verification, and generates survey report.The application significantly improves geotechnical body parameter inversion accuracy and reliability, and is suitable for various geotechnical engineering survey and stability evaluation such as slope, foundation pit, tunnel etc..

This invention relates to the field of biomedical imaging and clinical monitoring technology, and discloses a lower limb wearable photoacoustic tomography hemodynamic monitoring device and imaging method, including an adaptive flexible detection front end, a main unit, and a pneumatic servo coupling subsystem. The front end integrates ultrasonic array elements, optical waveguides, and strain sensors. The pneumatic system controls the pressure of the flexible airbag based on hysteresis dead zone logic to maintain coupling stability and prevent frequent start-stop oscillations of the micro-pump. The optical subsystem uses a reference photodiode to acquire a single-pulse energy reference signal; the signal processing subsystem combines strain data and reflection peak time to correct the three-dimensional coordinates of the array elements; it introduces the energy reference signal for normalization to eliminate laser pulse fluctuation errors; it combines local curvature to generate compensation coefficients to correct acoustic beam divergence and decouple the actual blood flow velocity; and it performs sliding window integration processing on risk factors to suppress false alarms. This invention improves the monitoring accuracy and reliability of deep hemodynamic parameters under non-planar detection conditions.

The application discloses a high spatial resolution mountainous area surface temperature remote sensing inversion hybrid algorithm and belongs to the field of thermal infrared quantitative remote sensing research; the method comprises the following steps: constructing a mountainous area thermal infrared radiation transmission model, deducing a definition formula of a mountainous area small-scale self-heating parameter, defining a mountainous area effective emission rate, and constructing a mountainous area three-dimensional thermal infrared radiation transmission model; using a split window algorithm and simulated on-board brightness temperature data of each thermal infrared band, the optimal combination of the off-ground radiation brightness temperature of each band is estimated through optimal configuration of band combination selection; using a temperature-emission rate separation algorithm, the mountainous area surface temperature and the emission rate are separated from the off-ground radiation brightness temperature of each band at the same time; the application constructs a new mountainous area three-dimensional thermal infrared radiation transmission model and a remote sensing inversion hybrid algorithm capable of accurately inverting the high spatial resolution mountainous area surface temperature, and improves the remote sensing inversion precision of the high spatial resolution mountainous area surface temperature.

This invention discloses a method and apparatus for crack morphology inversion combining full-time step and physical model, comprising: inputting crack height and crack offset in the crack height direction into a physical model; first, processing the crack height through a crack propagation sub-model to output crack geometric parameters for the full-time step; then, processing the crack geometric parameters and crack offset in the crack height direction through a fiber strain response sub-model to output axial strain rate at simulated measurement points for the full-time step; adjusting the axial strain rate at simulated measurement points based on positive and negative strain rate scaling factors; calculating the loss value between the adjusted simulated axial strain rate and the measured axial strain rate; if the loss value is greater than a preset loss threshold, adjusting the corresponding optimization control parameters until the loss value is less than or equal to the preset loss threshold, or a preset iteration stop condition is reached; and outputting the target crack geometric parameters for the full-time step based on the finally adjusted optimization control parameters. This invention can improve the accuracy and efficiency of crack morphology inversion.

The application discloses a double-layer iterative laser radar visibility inversion method and system based on near-field constraint and K value dynamic inversion, and relates to the technical field of atmospheric remote sensing. Through designing an inner-outer double-layer iteration structure, the application decouples and links the optimization processes of two strongly coupled variables, i.e. the far-field boundary value and the K value, realizes the collaborative inversion of the two variables, finds a globally optimal parameter combination, and greatly improves the inversion accuracy of the extinction coefficient and the visibility. In addition, the application proposes a "near-field physical constraint" principle, utilizes the reliable characteristics of the near-field signal, converts the difficult-to-determine far-field boundary value optimization problem into a judgment problem of the physical form of the near-field profile, and enables the algorithm to have strong self-adaptive capability and to realize self-calibration without relying on external observation data.

This invention provides a method and system for jointly inverting precipitation microphysical parameter profiles based on active radar and passive microwave. The method uses multi-source observation data from active radar and passive microwave to constrain particle microphysical parameters and establish a dual-optimization inversion model. The observation operators of the inversion model include the changes in microphysical properties of different types of particles and the electromagnetic wave attenuation effect, which can reduce the uncertainty of inversion caused by particle microphysical assumptions and attenuation effects. Thus, the optimal state variables of different types of precipitation particles on the profile can be obtained by inversion, improving the accuracy of precipitation microphysical parameter profile inversion.

This invention relates to the field of parameter field cascade reconstruction technology, and discloses a method for cascade reconstruction of three-dimensional water vapor parameter fields based on sparse GNSS station network data. The method includes: 1. Collecting observation data from m GNSS stations sparsely distributed within a target area; 2. Obtaining the slant path water vapor content of all GNSS signals corresponding to each GNSS station; 3. Establishing a water vapor tomography equation set for each GNSS station, using a single GNSS station as the basic unit; 4. Obtaining the local three-dimensional water vapor parameter field of each GNSS station; 5. Dividing the entire target area into spatial units with the same spatial resolution as the local three-dimensional water vapor parameter field of each station, and calculating the spatial correlation coefficient between each spatial unit and the local three-dimensional water vapor parameter field of each station at each height level; 6. Constructing a recursive model to obtain the three-dimensional water vapor parameter field of the target area. This invention achieves high-precision reconstruction of the three-dimensional water vapor parameter field of the target area under sparse GNSS station network conditions, improving the inversion accuracy of three-dimensional water vapor parameter fields based on sparse GNSS station networks.

The invention discloses a mine roof risk identification and evaluation method based on surrounding rock structural plane spatial evolution. The method comprises the following steps: acquiring basic geometric and spatial data of a surrounding rock structural plane of a slope adjacent to a roof; structural plane space modeling is carried out, plane domain labels are marked, and structural plane candidate pairing preprocessing is completed under a unified space coordinate system; analyzing the incidence relation between the roof structural plane and the side structural plane in the spatial position and the extension direction, and determining a structural plane combination with spatial continuity; the roof surrounding rock internal structural plane distribution state and a confidence degree set are inversely output; constructing a roof turquoise body space model containing a hypothetical structural plane and a candidate set; extracting parameters to form a characteristic parameter set for instability analysis; analyzing the spatial relationship between the turquoise body and the free surface of the top plate, and determining the spatial range and the exposure index of the turquoise body; and calculating the instability probability of the turquoise body, and carrying out grading evaluation on the roof turquoise caving risk. According to the method, identification and caving risk grading of the potential turpentine body of the underground mine roof surrounding rock can be realized.

The present application relates to the field of remote sensing technology and temperature sensor, and discloses a bay nutrient salt concentration inversion method based on multi-source optical remote sensing data fusion.The method comprises the following steps: dynamically triggering multi-source satellite emergency observation based on water quality anomaly index; fusing low-orbit, medium-orbit and geostationary-orbit optical remote sensing data, constructing a unified grid water-leaving reflectance cube after atmospheric correction and space-time registration; using convolution long short-term memory network to invert nitrate, phosphate and silicate concentrations; and coupling a hydrodynamic model to generate a dynamic evolution sequence with a 6-hour time step, a 30-minute time step and a 10-meter resolution.The present application improves the timeliness of emergency response and inversion accuracy through multi-source collaboration and physical constraint fusion.