1073 results about "Rainout" patented technology

The invention relates to the technical field of data processing, and discloses a geological disaster meteorological risk early warning method and system based on machine learning. The method comprises the following steps: acquiring rainfall intensity, soil saturation, underground water level change and slope runoff coefficient by a multi-source sensor, and constructing a geological disaster meteorological data set; performing sensitivity weight distribution on the meteorological factors according to geological conditions to obtain a weight matrix; carrying out weighted fusion on the weight matrix and meteorological time series data, and extracting features through a geological constraint long-short-term memory network to obtain a risk probability vector; dynamically adjusting an early warning threshold value based on the safety coefficient change rate; and carrying out Bayesian fusion on the risk probability vector and an adaptive early warning threshold to obtain a graded early warning result. The technical problem that an existing geological disaster early warning technology lacks a multivariate meteorological factor intelligent weight distribution and geological condition adaptive threshold adjustment mechanism is solved.

The invention discloses a river flow missing data reconstruction method, which comprises the following steps of S1, constructing a river network topological structure, and quantifying hydraulic correlation; s2, spatio-temporal feature fusion and multi-source information extraction; s3, performing multi-task cooperative flow reconstruction and confidence coefficient prediction; s4, dynamic weighting and result correction of meteorological factors; and S5, performing anomaly detection and model dynamic updating. According to the method, a river flow missing data reconstruction method is set, the steps are mutually fused and used, and topology-aware space-time diagram convolution is performed: a river network topology structure is encoded into a weighted adjacency matrix for the first time, space correlation features are extracted through a diagram convolution network, and the problem that a traditional method ignores hydraulic connection is solved; a multi-task collaborative learning mechanism: synchronously outputting a flow reconstruction value and confidence, combining topological smooth constraints, and realizing reconstruction reliability quantification while ensuring precision; and meteorological dynamic weighted correction: dynamically adjusting the node weight based on the real-time rainfall intensity, and accurately adapting to the nonlinear response of the water flow in the heavy rainfall period.

The invention relates to the technical field of intelligent construction. The invention provides a rainwater garden construction control method and system based on BIM dynamic rainfall flood simulation. The method comprises the following steps: integrating target area data and real-time weather forecast, and constructing a fusion model; importing the fusion model into a coupling engine, simulating an extreme rainfall scene, and generating a dynamic hydrological load map; according to the dynamic hydrological load map, reverse iterative calculation is carried out, and a three-dimensional parameterized design model is output; decomposing the three-dimensional parameterized design model into a layered construction instruction set, and constructing a real-time twinborn body on a BIM platform; field data are collected and compared with real-time twinborn bodies, and when the soil layer permeability coefficient deviation is larger than a preset threshold value or the process conflict risk, a re-optimization instruction is triggered, and the mechanical operation sequence is adjusted. The problems that due to the fact that existing rainwater garden static design and experience construction cannot dynamically respond to the complex hydrological environment and construction disturbance, facility efficiency is low, failure is prone to occurring, and the construction rework rate is high are solved.

The invention discloses a loess slope stability intelligent monitoring method and system, and the method comprises the steps: carrying out the regional differentiation modeling of multi-source data of a target region, and outputting slope change data; according to the period-by-period displacement time sequence data, a slope deformation trend is obtained through prediction based on an LSTM algorithm; and inputting the slope change data, the slope deformation trend and the meteorological rainfall data into a slope stability evaluation model to predict a safety coefficient, and if the safety coefficient is lower than a preset threshold value, issuing early warning information. According to the loess slope stability intelligent monitoring method and system provided by the invention, data such as gradient change and deformation trend are accurately extracted, multi-source data and meteorological rainfall data are fused by means of cross-modal attention, a random forest model is used for learning a multi-factor coupling rule, and finally multi-factor data prediction is integrated to obtain a safety coefficient for early warning. The problem of low early warning reliability caused by difficulty in accurately evaluating the slope stability by fusing multiple factors such as gradient, deformation and meteorological rainfall can be solved.

The invention discloses a landslide risk assessment method based on an extreme rainfall and geology coupling model, and relates to the technical field of geological disasters. Comprising the following steps: S1, constructing a three-dimensional probability density field of a fracture network and a non-Gaussian random field model of a permeability coefficient tensor; s2, setting a physical kernel layer according to the non-Gaussian random field model, setting a data driving layer through space-time Transform coding, and constructing a graph attention network model; s3, generating an adversarial network through physical information, constructing extreme rainfall coupling data, and updating the non-Gaussian permeability coefficient random field model according to the graph attention network model; and S4, acquiring an entropy generation rate according to the mechanical field data, the seepage field data and the temperature field data, and determining a risk level. Physical interpretability grading early warning of landslide risks is realized, and meanwhile, risk space distribution can be visually displayed through a sliding surface probability cloud picture, so that accurate decision support is provided for disaster prevention and control.

The invention discloses a flood disaster risk intelligent early warning method fusing multi-source information, and relates to the technical field of flood disaster prediction.The method comprises the steps that multi-source data of meteorology, hydrology, terrain, remote sensing, ground monitoring terminals and the like are obtained, and a unified data set is constructed through time synchronization, space resampling, abnormal value elimination and missing data filling; constructing multi-dimensional spatio-temporal features based on factors such as rainfall process, topographic features, surface coverage, drainage capacity, river network structure and soil humidity; inputting the spatial-temporal characteristics into a multi-source information fusion model, and predicting a flood occurrence probability in a future time period; flood risk indexes are generated according to the prediction probability, real-time monitoring and historical samples, and regional risks are divided into different grades; early warning information is automatically generated and issued according to the risk level; and the early warning result is fed back and corrected through field monitoring and patrol data, so that self-adaptive updating of early warning parameters and a model structure is realized.

A digital twin-based intelligent slope monitoring method, system, and storage medium are provided. The method includes obtaining point cloud data of a surface of a slope, creating a digital twin model; dividing the digital twin model to generate a plurality of first grids, calculating a displacement change value of each first grid during a target duration; defining the first grid with a displacement change value greater than a first threshold as a first region, dividing the target duration into a plurality of first durations with different lengths; setting a plurality of rainfall patterns, determining an optimal pattern for each first duration, calculating representative rainfall, constructing a prediction model, predicting representative rainfall for a future duration based on the optimal pattern and the representative rainfall of the first duration; generating a safety factor of the first region during the future duration based on the representative rainfall and a pore water pressure.

The invention relates to the technical field of rainfall slope evaluation, in particular to a rainfall slope stability evaluation method based on a physical certainty coupling model. The method comprises the following steps: acquiring digital elevation model data, engineering geological survey data and historical rainfall data of a target area; extracting topographic features from the digital elevation model data to obtain basic topographic parameters; the method comprises the following steps: carrying out longitudinal layering division on a rock-soil body based on engineering geological survey data, and carrying out physical and mechanical parameter setting on each layered rock-soil body to obtain a rock-soil body layering parameter set; and performing frequency analysis on the historical rainfall data to obtain an extreme rainfall intensity sequence. According to the method, by fusing the multi-source data and the three-dimensional physical coupling model, dynamic and accurate rainfall induced slope stability evaluation and risk early warning are realized, and the prediction precision is effectively improved.

The invention provides a satellite scatterometer Ku wave band observation value rainfall influence correction method, and relates to the field of sea surface wind inversion methods, and the method comprises the steps: obtaining Ku wave band observation data, C wave band data and rainfall rate data of a satellite scatterometer, carrying out wind field matching and wind speed correction under a rain-free condition, so as to obtain an NRCS reference value corresponding to a sea surface real wind speed, and carrying out the calculation of the NRCS reference value; constructing to obtain a scatterometer rainfall matching data set; according to the scatterometer rainfall matching data set, the influence of rainfall on the scatterometer observation value is analyzed, and a Ku waveband rainfall influence conceptualization model is constructed; and calculating rainfall influence conceptualization model parameters and generating a deviation lookup table. According to the invention, on the basis of a classic scatterometer wind field inversion process, the problem of large inversion wind field deviation caused by the influence of rainfall on the observation value of the Ku wave band scatterometer in a medium-low rainfall rate range is solved.

The invention relates to the technical field of geotechnical engineering disaster monitoring and early warning, and discloses a stratum rainfall seepage deformation coupling numerical simulation method and system and a storage medium, and the method comprises the steps: building a three-dimensional geologic model reflecting soft and hard rock interbed characteristics; converting the on-site rainfall data into hydraulic boundary conditions in real time; calculating a rock mass shear expansion volume change rate, determining a chemical damage acceleration factor, and updating a total damage variable; reconstructing a permeation tensor representing the dominant flow channel according to the space gradient of the damage variable; solving a fluid-solid coupling equation based on the permeability tensor, obtaining pore water pressure and calculating a displacement field; building a likelihood function by using field monitoring data to perform inversion correction on model parameters; and evaluating the stability based on the corrected calculation result and outputting an early warning signal. By constructing a mechanical coupling mechanism and a dominant flow channel model, precise simulation of a landslide evolution process in a complex geological environment is realized.

A temperature-rainfall-reservoir water combined testing system for a permafrost landslide model includes a tempered glass case with a permafrost landslide model and reservoir water provided therein; a temperature control system provided on the tempered glass case and including an incubator temperature control module, a landslide mass rear edge water tank temperature control module and an air circulation temperature control module; a seepage control system configured to realize seepage of the permafrost landslide model, and form the reservoir water in front of a landslide mass; a rainfall control system including a water tube, a flow controller and a nozzle, where the nozzle is provided in the tempered glass case, and located above the permafrost landslide model; and a multi-field monitoring system including a temperature sensor, a pore water pressure gauge, a moisture meter and a grating strain gauge that are provided in the permafrost landslide model.

The invention relates to the technical field of rainstorm early warning, in particular to a deep learning-based rainstorm terminal early warning method and system, which introduces an image perception and semantic recognition mechanism to carry out consistency judgment on an overturning state of a rain gauge and image features such as a rain curtain and a water mark so as to realize effective elimination of unnatural trigger factors (such as manual water pouring and the like). And the reliability of rainfall sensing data is improved. A double-branch deep learning model capable of being deployed locally is adopted, multi-source data such as rainfall, temperature and humidity and topographic factors are fused, feature extraction and recurrence period prediction are performed based on a cross attention mechanism, and a threshold correction coefficient is dynamically generated in combination with historical events, so that self-adaptive adjustment of an early warning standard is realized, and misinformation and missing report risks are effectively reduced. The system supports low-power-consumption local operation, early warning decision is executed, and timeliness and accuracy of local early warning response are effectively improved.

The invention relates to the technical field of strategy optimization, and discloses a regional weather prediction method and system based on a meteorological large model, and the method comprises the steps: obtaining a terrain influence weight matrix; inputting into a spatial distribution feature model, outputting an optimized spatial distribution feature set, and realizing space-time registration through Kriging interpolation to obtain a spatial distribution feature set of local weather; extracting a seasonal change trend, and executing deviation correction to obtain a deviation correction coefficient; updating the weight matrix and performing coupling calculation to generate a coupling parameter set; generating a prediction result according to the coupling parameter set, and if the precision is lower than a threshold value, generating computing resource configuration; combining the resource configuration, the updating weight matrix and the spatial feature set to carry out weather prediction to obtain a prediction result; and finally, generating a rainfall intensity distribution diagram, performing differentiation correction, and outputting a regional weather prediction result. The method can achieve the high-precision prediction of the weather in the complex region.

The invention discloses a multi-source data fusion method based on a water conservancy rain measuring radar, and belongs to the technical field of meteorological observation. Historical rainfall inversion, short temporary rainfall forecast and short-term rainfall forecast are realized based on multi-source data fusion, and a space-air-ground integrated rainfall observation and prediction system is constructed. According to the method, innovative technologies such as multi-source data, multi-parameter inversion, AI intelligent optimization and manual correction are fused, the limitation of a traditional rainfall inversion method is broken through, and the precision and service efficiency of quantitative rainfall estimation are remarkably improved; through multi-modal fusion and full-link integration, the method has significant technical advancement and business value in application in the fields of water conservancy and meteorology.

The invention discloses an urban road rainwater runoff stage treatment system and method, and relates to the technical field of urban rainwater pollution treatment. In order to solve the problems that an existing system is difficult to monitor multi-index water quality in real time, the pollution degree is accurately recognized, and distribution control lacks dynamics, the system is provided with a multi-source spectrum water quality monitor at the tail end of a pipe network, turbidity, COD, TOC and heavy metal concentration are monitored in real time, rainfall intensity data are accessed into a control center, the pollutant load instantaneous rate L is calculated through a weighted summation formula, and the real-time monitoring of the pollution degree is achieved. A controllable flow distribution module in the flow distribution well distributes the rainwater to an enhanced treatment unit, a biological aerated filter system or a horizontal flow sedimentation tank, wherein the enhanced treatment unit comprises a rotational flow sand setting unit, an electrochemical heavy metal degradation unit and a chemical flocculation unit. The system is mainly used for realizing quality-divided efficient treatment and resource recycling of rainwater and guaranteeing the safety of a receiving water body.

The invention relates to the technical field of mine environment risks, and discloses a mine environment risk multi-modal analysis and early warning decision-making method, which comprises the following steps of: performing time and space reference alignment on multi-source observation data, constructing a unified spatio-temporal data set, and establishing a troposphere disturbance model to realize observation disturbance coupling. And constructing a physical evolution operator and a rainfall-driven external input operator based on a seepage mechanical relationship, and generating a state evolution mechanism. Semantic direction parameters are generated by mapping semantic query information to a target attention dimension, and a lagging propagation operator is constructed by setting a rainstorm ending moment as a starting point. And determining a non-regular spectrum transition index and a peak lag moment through the non-regularity measurement and the dynamic change rate of each lag propagation operator, and setting a reference threshold value based on the spectrum transition index of a historical non-risk time period. Finally, when the early warning intensity meets the condition, early warning is output, and a query result is generated in combination with the lagging propagation operator and the semantic direction parameters.

The invention discloses a deep learning-based less-data small-watershed water level forecasting method. The method comprises the following steps of: acquiring historical hourly rainfall data of a plurality of upstream rainfall stations of a small watershed and historical hourly water level data of a downstream water level station; preprocessing the acquired data, and screening rainfall sessions with the rainfall capacity of over 15mm per hour within 24 hours and corresponding water level data; the method comprises the following steps: performing data enhancement through a double-generation GAN model, generating simulated rainfall data by a first GAN model by taking white noise as input, generating simulated water level data by a second GAN model by taking rainfall data as input, combining historical data and simulated data, performing normalization, and dividing the data into a training set, a verification set and a test set according to a proportion; constructing a CNN-LSTM hybrid prediction model, training the model by taking a Nash coefficient as an optimization target, and verifying the prediction model by adopting a progressive verification strategy; and deploying the model for real-time water level prediction to obtain a water level prediction result. The method can break through the bottleneck of few data, and achieves the high-precision mountain torrent early warning of the small watershed water level.

The invention discloses a post-raining side slope seepage characteristic testing method based on waveform inversion of nano-iron concentration distribution, and belongs to the field of seepage characteristic determination in foundation pit side slope stability monitoring, the method comprises the following steps: spraying a mixture of nano-iron particles and a surfactant into cumulonimbus to make nano-iron permeate into a side slope soil body along with rainfall; a radio frequency coil is arranged in the orthogonal direction of the selected section of the slope, an electromagnetic field is applied to excite nano iron resonance, and electromagnetic wave signals are collected; dividing the selected section of the slope into a plurality of grid units, and inverting the concentration distribution of the nano-iron in each grid unit by using an iterative optimization algorithm based on the electromagnetic wave signal to obtain an inversion result; and generating a seepage cloud picture based on the inversion result and calculating the seepage speed. According to the method, economic loss caused by large-area laying of nano-iron and interference to follow-up monitoring are avoided, the seepage position and size are determined, and complete and clear information is provided for monitoring seepage changes in slope engineering.

The invention relates to the technical field of data processing, in particular to a river pollution monitoring management method fused with environmental information perception. According to the method, monitoring points are classified according to information collected in a non-rainfall period, and a plurality of monitoring point clusters are obtained. In the target rainfall period, the rainfall influence degree of the monitoring points is determined by analyzing pollutant concentration data changes before and after analysis and rainfall information, and then the target monitoring points needing data correction are screened out. A time correction method is adopted, reference time periods are selected in the non-rainfall time periods, the reference weight of each reference time period is determined by analyzing the time sequence position of the reference time periods and the rainfall influence degree of the latest rainfall time period, and then time correction is conducted; and further performing space correction by using other monitoring points in the monitoring point cluster obtained by classification to finally obtain corrected pollutant concentration data. According to the method, the influence of rainfall on pollutant concentration data is eliminated, and the data reference is increased while the data coherence is ensured.

The invention provides a multi-source rainfall prediction method and device fusing GNSS and communication satellites, and the method comprises the steps: building a plurality of satellite-ground microwave links which are used for transmitting GNSS data and communication satellite data; gNSS data and communication satellite data on the multiple satellite-ground microwave links are acquired; performing atmospheric rainfall inversion on the plurality of satellite-ground microwave links based on GNSS data, and constructing a two-dimensional water vapor field according to an inversion result; performing rainfall intensity inversion on the plurality of satellite-ground microwave links based on communication satellite data, and constructing a two-dimensional rainfall field according to an inversion result; and fusing the two-dimensional water vapor field and the two-dimensional rainfall field by adopting Bayesian-maximum posteriori estimation to obtain a fusion field, and converting the fusion field to obtain a rainfall prediction field. According to the method, the rainfall field and the water vapor field are fused for rainfall prediction, so that the whole rainfall process can be accurately predicted.

The invention discloses a rainfall intensity rapid identification method and system based on multi-sensor data fusion, and relates to the technical field of hydro-meteorological monitoring and urban drainage scheduling, and the method comprises the steps: obtaining a historical rainfall data set, drawing a peak curve, and extracting an evolution sequence feature before a peak value; correlation analysis is carried out on the data and complete rainfall process characteristics to establish a historical rule model; rainfall intensity data are collected in real time through multiple sensors, and space-time dimension features are fused; matching the fusion features with historical features, and screening target historical events; constructing a rainfall reproduction prediction model to reconstruct a current rainfall evolution process; and finally, calculating an inflow load based on a reconstruction result, and generating a dynamic drainage scheduling scheme. According to the invention, accurate prediction of the rainfall process and intelligent scheduling of the drainage system are realized, and the urban waterlogging prevention capability is improved.

The invention provides an extreme rainfall prediction method and device based on deep learning and electronic equipment, and the method comprises the steps: collecting multi-source data, carrying out the preprocessing of the multi-source data, and constructing a multi-source heterogeneous fusion data set; inputting the multi-source heterogeneous fusion data set into a multi-scale feature extraction network, and extracting space-time evolution features of the rainfall process; generating a synthetic extreme rainfall sample through a generative adversarial network, carrying out mixed training on the synthetic extreme rainfall sample and a real sample, and strengthening extreme rainfall feature learning through a weighted loss function; a channel attention and space attention mechanism is introduced, the feature weight is dynamically adjusted, and the time sequence dependency relationship of the rainfall process is captured. According to the invention, accurate prediction and early warning of the extreme rainfall event are realized, and the problem of poor extreme rainfall prediction accuracy in the prior art is solved.

The invention provides a subway tunnel water disaster risk evaluation method under extreme rainfall based on multi-source data, and belongs to the technical field of urban rail transit disaster prevention. The method comprises the following steps: establishing a grading evaluation system on the basis of field rainstorm monitoring data, hydrogeological parameters, field geological exploration, rock-soil physical and mechanical parameters, monitoring data of a tunnel lining structure and material strength parameters of a tunnel site area in combination with a plurality of developed tests, dividing corresponding grades and determining an influence index-; and S4, respectively carrying out weight calculation on the influence index-by adopting an analytic hierarchy process and an entropy weight method, then calculating a dynamic weight of the influence index-, correcting an abnormal dynamic weight, generating a comprehensive score, dividing risk grades, matching graded prevention and control measures, and optimizing and adjusting the prevention and control measures in real time through a parameter risk grade dynamic judgment and construction method matching mechanism. According to the method, minute-level accurate interpretation of a disaster evolution mechanism and dynamic optimization adaptation of a prevention and control scheme are realized.

The invention discloses a mountain tourism route planning method based on weather and natural disasters, and the method comprises the steps: 1, building a Markov game model based on POMDP, combining Mama multi-modal feature compression and RAG semantic enhancement, designing a dynamic risk matrix integrating geological disaster probability, weather trend and ecological sensitivity, and providing partial observable environment state perception; 2, establishing a Nash equilibrium constraint optimization model, sharing an extreme weather strategy through federal learning, introducing an NSGA-II-Actor-Critic architecture to optimize unmanned aerial vehicle inspection and path adjustment, and triggering dynamic communication when rainfall exceeds a threshold value; 3, fusing a security and experience income design reward function, processing continuous action planning by using improved DDPG, and accelerating multi-target Pareto frontier convergence in combination with NSGA-II; 4, constructing a user weather sensitivity portrait, and dynamically adjusting weight balance income and AR simulation preview preference; and 5, based on a GIS closed-loop decision engine, performing agent and environment feature complementation, recording an emergency log by a block chain, and constructing a disaster case library by meta-learning.

The invention discloses an urban heat island effect-based local short-term rainfall falling area rapid correction method, and belongs to the field of rainfall forecast, and the method comprises the steps: recognizing the position coordinates of a forecast rainfall center point, an actually measured rainfall center point and an urban heat island center point of each local short-term rainfall; respectively constructing a heat island center-forecast rainfall center vector and a heat island center-actual measurement rainfall center vector; based on the heat island center-forecast rainfall center vector and the heat island center-actual measurement rainfall center vector of each local short temporary rainfall, respectively calculating an offset direction angle and an offset distance of each local short temporary rainfall; according to the offset direction angle and the offset distance of each rainfall, extracting an average offset characteristic; constructing a correction vector according to the average offset feature; and obtaining a forecast rainfall center of the to-be-corrected short temporary rainfall, and performing spatial position correction based on the correction vector. According to the method, the problem of systematic deviation of the rainfall falling area caused by the urban heat island effect in the short-term and imminent forecast is solved.

The invention discloses an urban rainstorm waterlogging process simulation method based on deep learning, and relates to the technical field of flood disasters. Comprising the following steps: constructing an urban inland inundation rainfall-water depth data set; training a ConvLSTM deep learning model by using the rainfall-water depth data set, and constructing a flood forecasting system based on the deep learning model; and constructing a training set and a verification set based on simulation results under different rainfall scenes, carrying out comprehensive evaluation on the performance of the ConvLSTM model, and carrying out verification in an actual scene. The coupling model provided by the invention not only improves the accuracy and speed of urban flood forecasting, but also enhances the adaptability to extreme weather events, and the future research focuses on further optimization of the model structure.

The invention provides a slope stability prediction method and device under a rainfall condition, and relates to the technical field of slope stability prediction, and the method comprises the steps: employing a regular grid to divide a slope, and constructing a spatial-temporal feature data set containing geological, hydrological and topographic parameters; calculating a regional cooperation index based on the multi-dimensional feature vector, and dividing the slope into a plurality of communities and isolated risk areas; calculating the dynamic safety coefficient of each community by taking the mass center sub-region as a representative, and dividing the stability level according to a threshold value; and establishing a three-dimensional digital twinborn model to realize risk visualization, triggering early warning for a continuous three-period safety coefficient decreasing area, and displaying an evolution track. According to the method, accurate monitoring and early warning of slope stability are realized through multi-source data fusion and dynamic partition evaluation.

The invention relates to the technical field of data processing, and discloses a rainfall runoff pollution early warning system and method.The system comprises a sample analysis module, a pollutant model construction module, a water quality prediction module, an early warning signal generation module and a pollution control module; carrying out physicochemical property analysis on the pavement sediment sample and the rainfall runoff sample of the service area to obtain pollutant concentration data and pollutant composition data; constructing a pollutant migration and transformation model based on dynamic changes of pollutants in the pollutant concentration data and the pollutant composition data in the runoff process; hydrology and hydrodynamic force of the service area are predicted based on the pollutant migration and transformation model, and runoff water quality change trends under different rainfall scenes are obtained; when the water quality prediction index in the flow water quality change trend exceeds a pollution early warning threshold value, a pollution early warning signal is generated; the pollution early warning signal is pushed to a management terminal, and a corresponding runoff pollution control measure is triggered; the rainfall runoff pollution early warning method can improve the accuracy of rainfall runoff pollution early warning.

The invention discloses an urban low-altitude gridding management process control method and system based on unmanned aerial vehicle analysis, and belongs to the technical field of unmanned aerial vehicle flight management.The urban low-altitude gridding management process control method comprises the steps that urban three-dimensional data are obtained, an urban area is divided into multiple grid units, meteorological data are obtained, and a building interference evaluation model is constructed; importing the open angle and the building surrounding rate of each grid unit into a building interference evaluation model to calculate the building intensity, evaluating the reflection interference on the unmanned aerial vehicle through the number and intensity of reflection paths, constructing a meteorological interference model, obtaining the cloud cluster humidity distribution, raindrop particle size and wind parameters of the grid units, and calculating the building intensity. The method comprises the following steps: importing meteorological data into a meteorological interference model to evaluate a rainfall interference condition and a wind disturbance condition, constructing a flight risk evaluation model, and importing building density, a multi-path reflection error index, a rainfall interference index and wind disturbance intensity into the flight risk evaluation model to evaluate the flight risk degree of the unmanned aerial vehicle. And the safety of the flight path of the unmanned aerial vehicle is improved.

Three-dimensional target detection in complex weather is a key problem in intelligent driving, and extreme weather is easy to interfere with a sensor, so that the detection precision is reduced. The invention provides a three-dimensional target detection method in complex weather based on millimeter wave radar and vision fusion, and designs an image generation module for simulating complex environment images such as rainfall, snowfall and the like aiming at the problem of scarcity of bad weather image data in a public data set. And by adopting a self-distillation mechanism, multi-modal knowledge learned by the teacher model in normal weather is migrated to the student model trained in bad weather, so that the detection performance in a complex environment is improved. Besides, in order to enhance the multi-modal information fusion capability, gating fusion modules are introduced into the teacher model and the student model, and a learnable gating fusion mechanism is utilized to dynamically adjust weight distribution of multi-modal feature fusion. According to the method, the robustness and the detection precision of the model under the complex weather condition are effectively improved.