284 results about "Runoff volume" patented technology

The present disclosure relates to the technical field of landslide hazard model tests, and in particular to a landslide model test method and device for realizing multi-variable synchronous monitoring. In the test device, a soil slope simulation unit is configured to pile up a soil slope and simulate different inclinations of the slope. A rainfall simulation unit is configured to simulate rainfall of different intensities and induce a landslide. A runoff-seepage separation unit is configured to realize separation of runoff from seepage of the slope under the effect of rainfall. A monitoring module is configured to monitor runoff and seepage flow rates of the slope, changes in water content and pore water pressure within the slope, and a morphological change of the slope under the effect of rainfall, to obtain a mechanism of rainfall-induced landslide deformation and damage based on changes in the flow rate.

The invention provides a plateau lake agricultural non-point source pollution treatment method which comprises the following steps: acquiring vegetation indexes and surface temperature field data by using a remote sensing satellite, and generating a pollution source space thermodynamic diagram in combination with water quality and soil parameters of ground sampling points; performing space-time alignment and data fusion on the thermodynamic diagram and real-time runoff and soil permeability data acquired by the hydrological sensor network, and constructing a structured pollution migration database; on the basis of the database, a hybrid neural network model embedded with physical constraints is utilized to predict pollutant concentration distribution within 72 hours in the future; inputting the predicted value into a multi-stage optimization controller, and generating a control parameter set comprising treatment intensity, engineering parameters and a fertilization ratio; generating a treatment strategy map covering the drainage basin through a GIS; and deploying an Internet of Things monitoring node to collect the treated water quality data to form a closed-loop control link. The treatment efficiency and effect can be improved, the treatment cost is reduced, and the negative influence on the ecological environment is reduced.

The invention provides a medium and long term hydrological probability forecasting method and system considering interpretable deep learning model nested combination, and relates to the technical field of hydrological forecasting. The method comprises the following steps: collecting historical reservoir runoff data and an atmospheric circulation index of a target station; analyzing the correlation of the runoff time sequence, and determining the lag time of the medium-and-long-term runoff combined prediction model; constructing an input matrix containing the initial factor set, screening medium and long-term hydrological forecasting factors from the input matrix, and reconstructing the screened medium and long-term hydrological forecasting factors and the warehousing runoff data to form reconstructed combined data; constructing a multi-model nested structure as a medium-and-long-term runoff combined prediction model; and obtaining a deterministic prediction result and a probability prediction result of the medium-and-long-term runoff under different synchronization lengths by taking the reconstructed combined data as an input item of the medium-and-long-term runoff combined prediction model and taking the predicted future runoff volume as an output quantity. Compared with the prior art, the method has remarkable advantages in the aspect of forecasting result precision.

The invention discloses a water and soil loss telemetry data analysis method and system based on deep learning, and relates to the technical field of data analysis, and the method comprises the steps: extracting soil loss data, surface runoff data and topographic data; fusing the soil loss data, the surface runoff data and the topographic data, and obtaining water and soil loss risk index data and soil erosion rate data through a feature extraction technology; calculating weight values of the water and soil loss risk index data and the soil erosion rate data by using a feature evaluation technology; and based on the water and soil loss risk index data, the soil erosion rate data and the weight value, constructing a water and soil loss prediction model by using a deep learning framework and a space-time analysis algorithm. According to the invention, through telemetry data collection and feature extraction, key water and soil loss information can be rapidly obtained, the data processing flow is simplified, and the accuracy and reliability of data are ensured.

The invention relates to the technical field of hydrological forecasting, in particular to a deep learning-based short-term rainfall and flood forecasting method and system, and the method comprises the following steps: constructing a deep learning-based radar echo epitaxial prediction model and a rainfall and flood forecasting model, training and testing the two constructed models by adopting the first data set and the second data set respectively; inputting the rainfall radar echo data of the target watershed in a certain period of time into the radar echo epitaxial prediction model, and predicting the change trend of the rainfall radar echo in a future period of time; and inputting the change trend of the rainfall radar echo in the future period of time into the rainfall and flood forecasting model, and forecasting the rainfall and runoff of the target drainage basin in the future period of time. According to the method, the precipitation and the runoff of the target drainage basin can be predicted more accurately in a short time, and the prediction capability and the decision level of regional water resource management are effectively improved.

The invention provides a flood runoff forecasting method based on an LSTM-SWAT coupling model, and the method comprises the steps: constructing an SWAT distributed hydrological model, and analyzing the calibration and parameter sensitivity of the SWAT distributed hydrological model; a BiLSTM deep learning model is introduced, the constructed SWAT distributed hydrological model and the BiLSTM deep learning model are coupled, and based on physical mechanism operation of the SWAT distributed hydrological model, expansion of input meteorological data is completed in space and time; and taking the multi-feature data output by the SWAT distributed hydrological model as the input data of the BiLSTM deep learning model, and forecasting the runoff. According to the method, the hydrological elements are disassembled, the input characteristic parameter screening problem caused by poor interpretability of a deep learning model is solved, the runoff forecasting model effect is further improved, meanwhile, the influence of multi-dimensional characteristic parameters on forecasting performance is explored, and a new solution can be provided for research of the estuary environment in the flood period.

The invention discloses a river water ecological health monitoring method and a river water ecological health monitoring system, relates to the technical field of ecological health monitoring, and aims to solve the problem that a traditional water quality monitoring method mainly depends on water sample collection and laboratory analysis, and judges the water quality by measuring indexes such as dissolved oxygen, pH value, ammonia nitrogen, total phosphorus, heavy metal and dissolved organic matters in water; the river runoff is calculated from the precipitation and the drainage basin area, and the monitoring points are set in combination with the environmental information, so that an accurate data basis can be provided for subsequent water quality health assessment. The water quality condition is predicted by utilizing the water flow speed and the pollution point discharge amount and then compared with an actual monitoring result, so that potential problems can be found in time and a monitoring strategy can be optimized.

The invention discloses a runoff prediction model based on multi-source information integration of an Informer model, and belongs to the technical field of hydropower station runoff prediction. The invention aims to solve the problem of poor accuracy of medium and long term runoff prediction, especially for runoff sequences with multi-source, non-linear and non-stationary characteristics. The monitoring power station range is selected, and historical runoff data of the hydropower station and hydrological information such as rainfall and temperature of a surrounding area are obtained; adopting a Pearson correlation analysis method to select strong correlation features as multi-source time sequence feature input of an Informer model; preprocessing the data by using an STL seasonal decomposition method, and extracting characteristics of a period term and a trend term; runoff prediction is carried out by adopting a sparse attention mechanism and a self-attention distillation mechanism of an Informer model; according to the method, the prediction speed and feature capture can be enhanced, the runoff prediction accuracy is improved, and powerful support is provided for water resource management and scheduling of the hydropower station.

The invention discloses a watershed pollution prediction method based on multi-source data fusion, and belongs to the technical field of watershed pollution prediction. According to the method, water quality, runoff, land utilization and meteorological data sequences are firstly constructed, and then features of the sequences are extracted and spliced to form a fusion feature vector. And forming a training set by using a plurality of fusion feature vectors, inputting the training set into a random forest regression model for training, performing performance evaluation on the trained model by using a verification set, and finally using the model meeting evaluation conditions to predict the drainage basin pollution degree. According to the invention, through multi-source data fusion and scientific model training and evaluation processes, the accuracy of drainage basin pollution prediction is effectively improved.

The invention discloses a river organic carbon flux inversion method based on multi-source data and related equipment. The method comprises the following steps: acquiring multi-source data of a river basin range in a target research area; obtaining a normalized difference index based on remote sensing image conversion; river parameters of the target research area are obtained based on the normalized difference water body indexes and multi-source data processing, and river runoff is obtained through conversion of a hydraulic geometrical relationship; on the basis of the remote sensing image, the normalized difference chlorophyll index and the normalized difference turbidity index, the particle organic carbon concentration is obtained through inversion by means of a first inversion model; based on the population number and the rainfall capacity, a second inversion model is used for inversion to obtain the concentration of dissolved organic carbon; and converting the river runoff, the particle organic carbon concentration and the dissolved organic carbon concentration to obtain the river organic carbon flux. The method can significantly improve the accuracy and reliability of monitoring on a high-dynamic river, accurately realizes the inversion of the organic carbon flux of the river, and can be widely applied to the technical field of data processing.

The invention relates to the technical field of slope stability analysis and landslide disaster prevention and control, in particular to a slope three-dimensional stability calculation method and system based on a potential sliding direction. The method comprises the following steps: acquiring slope point cloud data, and constructing a digital elevation model according to the slope point cloud data; geologic structure data are obtained, and a side slope three-dimensional geologic model is constructed according to the geologic structure data and the digital elevation model; according to the digital elevation model, side slope flow direction and slope runoff characteristics are obtained, and according to the side slope flow direction and the slope runoff characteristics, the potential sliding direction of the side slope is determined; and according to the potential sliding direction of the slope and the three-dimensional geological model of the slope, constructing a three-dimensional stability calculation model of the slope, and according to the three-dimensional stability calculation model of the slope, calculating the three-dimensional stability of the slope. According to the method, the problem that the calculation result is not accurate enough due to the fact that calculation of the three-dimensional stability of the side slope is not comprehensively considered in the prior art is solved.

The invention discloses a modularized distributed cold region hydrothermal coupling hydrological model which comprises the following steps: S1, dividing a drainage basin into a plurality of grids, and preparing a file required by a confluence process; s2, preparing driving data and grid feature description data of each grid; s3, calculating an energy balance process of the soil and vegetation surfaces by using an energy balance module; s4, calculating an evapotranspiration process by using an evapotranspiration module; s5, calculating an ice and snow melting process by using an ice and snow melting water module and adopting a degree-day factor method; s6, calculating soil moisture infiltration and an internal hydrothermal transmission process by utilizing a soil hydrothermal transmission and infiltration module; s7, calculating the runoff volume by using a runoff production calculation and confluence module; and S8, evaluating the simulation performance of the model through the model evaluation index. The device has a flexible modular structure, can automatically adjust the time step length, improves the simulation capability of the runoff process in the cold region, and can provide scientific guidance for water resource management in the river source region.

The invention discloses a drainage basin nitrogen and phosphorus pollution prediction method based on rainfall runoff migration, and relates to the technical field of water quality pollution prediction, and the method comprises the steps: accurately obtaining land utilization and water body distribution through a remote sensing technology, carrying out the space division of a pollution source through combining a nitrogen and phosphorus load coefficient, and constructing a rainfall runoff model. The runoff volume and time and space distribution under different rainfall events are reflected, and the spatial dynamic change of pollutants is captured through a hydrodynamic model, in combination with a convection diffusion equation and by introducing a conversion model of nitrogen and phosphorus in various forms. By integrating remote sensing data, rainfall runoff simulation, hydrodynamic force and nitrogen and phosphorus form transformation, the space-time migration and transformation process of nitrogen and phosphorus pollution in a drainage basin is described, so that the coupling relation between pollution source distribution and runoff power is revealed, the conveying and diffusion rule of pollutants in a river network is dynamically reflected, and the drainage effect is improved. And refining to transformation evolution of different nitrogen and phosphorus forms, and generating intuitive concentration distribution and thermodynamic diagrams through spatial interpolation.

The invention relates to the technical field of hydrological prediction, in particular to a drainage basin distributed runoff prediction method and system based on a graph neural network, and the method comprises the following steps: obtaining a drainage basin multi-source runoff data set to construct a multi-relation dynamic graph structure, and extracting node feature vectors; based on the node feature vector, obtaining a watershed evolution trend forward feature by establishing a watershed diffusion fitting architecture; constructing a distributed runoff probability prediction model, and taking the watershed trend forward features as model input to obtain runoff initial condition probability distribution of each sub-watershed in multiple periods in the future; establishing a mixed loss function, and performing physical constraint optimization on the runoff initial condition probability distribution to obtain distributed runoff optimization probability distribution; and performing uncertainty quantification on the distributed runoff optimization probability distribution to obtain a drainage basin distributed runoff prediction result. According to the method, the hydrological process simulation capability of the complex watershed is improved, and accurate prediction of the distributed runoff volume is realized.

The invention discloses a runoff prediction method for optimizing a neural network based on a hybrid optimization algorithm, and belongs to the technical field of hydrological forecasting. Neural network parameters are optimized through an SAPSO algorithm (simulated annealing particle swarm optimization), and daily runoff prediction is further carried out. The method comprises the following steps: setting parameters of a neural network and an optimization algorithm, including the number of input layer nodes, the number of hidden layer nodes, the number of training times, the population scale and the like; the method comprises the following steps: dividing ten-year daily runoff actual measurement data of a Taojiang station into a training set and a test set, and carrying out normalization processing to prepare for training and testing of a neural network; the weight and the threshold of the neural network are randomly initialized, parameters are transmitted to a simulated annealing particle swarm optimization algorithm for iterative optimization, optimal network parameters are obtained, and a prediction network model is established; and training the network model by using the grouped training set data, and predicting the runoff volume of the Taojiang station by using the training model. And the prediction precision of the runoff volume is obviously improved.

The invention discloses a flood lake wetland heat flux simulation method in a watershed hydrological model, and relates to the technical field of heat flux simulation, and the method comprises the following steps: dispersing a watershed space into a slope river channel and a lake wetland, simulating the water movement of a slope river channel unit, and simulating the water movement of the lake wetland; the method comprises the following steps: simulating surface energy exchange for a lake wetland unit on the basis of simulating a hydrological process, simulating land hydrology and lake inflow runoff of a sub-basin by adopting a grid-based distributed hydrological model, respectively dividing simulation grid units for a slope river channel and a lake wetland, establishing evapotranspiration, infiltration and surface runoff models, and establishing an evapotranspiration, infiltration and surface runoff model; a two-dimensional shallow water equation is used for processing slope confluence, a one-dimensional hydrodynamic model is used for calculating river channel confluence, a lake water quantity balance model is established for calculating the lake water level, the lake submerging process is simulated, and the lake wetland distributed heat flux process is simulated. And the technical blank of flooding wetland hydrothermal simulation is filled.

The invention discloses a drainage basin seasonal runoff change prediction and attribution method and system and a medium, and the method comprises the steps: carrying out the seasonal division of a hydrological year based on the monthly scale rainfall, potential evapotranspiration and land water reserve change rules in a drainage basin; establishing a plurality of coupling models of the GCM and the ABCD so as to predict the runoff process of the drainage basin under the conditions that only future climate change scenes are considered and climate change and human activity influence scenes are considered at the same time; a seasonal-scale Buddyko model is considered, and the relative influence of seasonal-scale climate change and human activities on future runoff change is quantified. The method has a strong statistical basis, can objectively reflect the change rule of the watershed hydrologic runoff, can fully decouple the complex relationship between climate change and human activity and other factors on a seasonal time scale, and provides a new technology for the research of a water circulation process driving mechanism in a changing environment.

The invention relates to an experimental method for researching slope surface erosion of a waste dump slope under rainfall conditions, which comprises the following steps: laying simulated soil in an experimental tank in layers and compacting the simulated soil, the inner core of the simulated soil is a slag mixture in an actual open pit coal mine waste dump, and the surface covering soil of the simulated soil is humus covering soil of the waste dump slope; performing manual slope cutting to obtain a side slope, so that the longitudinal section of the simulated soil body is in a right trapezoid shape; planting vegetation on the surface layer of the side slope, and culturing the vegetation to grow; an artificial rainfall device is arranged above the simulated soil body and comprises a plurality of sprayers, and the pitch diameter and the end point velocity of raindrops are calibrated before artificial rainfall; starting an artificial rainfall device, spraying water to the upper surface of the simulated soil body by a nozzle, simulating rainfall, and recording the total runoff volume; the soil on the surface of the side slope is subjected to water loss under the action of simulated rainfall and slides to the sample collecting device at the bottom of the side slope, the sediment yield in the sample collecting device is recorded, and the water and soil loss condition is judged.

The invention belongs to the technical field of hydrological forecasting, and relates to a reservoir flood peak flow and time prediction method and system considering rainfall center movement. The method comprises the following steps: acquiring topographic data, historical meteorological data and historical runoff data of a target drainage basin; the target drainage basin is divided into a plurality of sub-drainage basins based on topographic data, hydrological models are constructed respectively, and parameters of the hydrological models of the sub-drainage basins are calibrated through historical meteorological data and historical runoff data; acquiring a moving track and rainfall intensity change of a rainfall center of the target drainage basin and real-time meteorological data and real-time runoff data of each sub-drainage basin, and inputting the moving track and the rainfall intensity change and the real-time meteorological data and the real-time runoff data into a hydrological model of the corresponding sub-drainage basin to obtain flood flow hydrograph corresponding to rainfall of a plurality of preset time steps; and superposing the flood flow hydrograph of a plurality of preset time steps to obtain a reservoir flood peak flow and time prediction result. According to the method, the flood prediction precision and reliability are improved, and a scientific basis is provided for flood scheduling and safety management of the hydropower station.

The invention provides a water resource optimal allocation method and system, and relates to the technical field of water resource optimal allocation, and the method comprises the steps: firstly obtaining the hydrological historical data of a research area, and then inputting the hydrological historical data into a preset river runoff prediction model, outputting a monthly runoff sequence in a specific year region by the river runoff prediction model; on the basis of the monthly runoff sequence, a multi-condition constraint water resource optimal configuration model based on user distribution of the research area under the extreme climate condition is established; and finally, solving the multi-condition constraint water resource optimal configuration model to obtain a solving result, and carrying out water resource optimal configuration on users in the research area according to the solving result. According to the method, accurate and reasonable optimal allocation of water resources of users under the multi-target constraint condition is effectively realized.

The invention discloses a thermal power generating unit decommissioning path planning method and device based on meteorological and hydrological risks, equipment, a medium and a product, and relates to the field of power system decision optimization. The method comprises the steps of obtaining meteorological and hydrological risk data and a decommissioning index of a thermal power generating unit; according to the decommissioning index and the meteorological and hydrological risk data under the climate change, a progressive hierarchical screening logic method is adopted for screening and constraint progressive correction processing; performing mapping and nonlinear correlation interaction analysis by adopting Monte Carlo simulation and a gradient boosting decision tree and combining multiple groups of parameter combination data, such as water temperature and runoff volume in meteorological and hydrological variables; and performing collaborative optimization processing based on the adaptive strategy model and a set analysis function to obtain an optimal strategy, and then performing mapping and analysis processing in combination with an analysis result to obtain targeted strategy list information for planning the decommissioning path of the thermal power generating unit. The invention aims to realize the planning of the decommissioning path of the thermal power generating unit.

The invention relates to the technical field of data processing and prediction, in particular to a large hydrological model construction method integrating multi-source fusion and dynamic optimization. The method comprises the following steps: acquiring hydrological monitoring data; performing data preprocessing on the hydrological monitoring data to obtain standard hydrological monitoring data; performing multi-dimensional feature recognition on the standard hydrological monitoring data to obtain multi-dimensional hydrological feature data; and carrying out runoff feature extraction on the multi-dimensional hydrological feature data to obtain hydrological runoff feature data. According to the invention, through a data processing technology, a mode identification technology, a geographic information system technology and a deep learning technology, seasonal change influence evaluation is carried out on hydrological monitoring data; and the hydrological monitoring model is dynamically optimized according to the hydrological geographic position information and the hydrological change evaluation data, so that the response speed of the hydrological monitoring model is higher, and the precision of a prediction result is higher.

The invention discloses an automatic dynamic measurement method and device for long-term forest eco-hydrology water volume in the technical field of eco-hydrology water volume measurement, and the method comprises the specific steps: 1, selecting a measurement point, building a sample plot according to a standard, and selecting a plurality of experiment points meeting conditions in the sample plot; 2, installing a water quantity monitoring device at the experiment point meeting the condition; 3, measuring the trunk runoff, the penetration precipitation, the water content of a surface fallen leaf layer and the soil water content of the forest in a preset time period by using a water quantity monitoring device, and recording a drainage time point; and 4, calculating the flow velocity, the total flow and the forest water conservation amount according to the measured data. The device is convenient and practical, penetrating rainfall is intercepted and measured through the plastic film, stem flow is intercepted and detected through the runoff ring, the fixing claws are continuously pushed to enter a tree trunk through the telescopic connecting rods by means of the gravity of water in the water measuring cylinder to fix the whole device, and the data quality stability of long-term hydrological water volume measurement and the safety of the device are improved.

This invention proposes a method and system for optimizing water resource allocation, which relates to the technical field of water resource optimization. The method includes first obtaining historical hydrological data for a study area, then inputting the data into a preset river runoff prediction model, which then outputs a monthly runoff sequence for a specific year within the region. Based on the monthly runoff sequence, a multi-conditional constrained water resource optimization allocation model based on user allocation is established for the study area under extreme climate conditions. Finally, the multi-conditional constrained water resource optimization allocation model is solved to obtain a solution result, and water resource optimization is performed for users in the study area based on the solution result. This invention effectively achieves accurate and reasonable optimal allocation of water resources to users under multi-objective constraints.

The invention discloses a rice irrigation district irrigation amount simulation method and system, and the method comprises the steps: taking a region controlled by a backbone channel and a drainage main ditch as a standard for dividing sub-units based on a DEM and a digital canal system, carrying out the grid division of the sub-units, and obtaining an irrigation district sub-basin division result; constructing a dynamic irrigation triggering mechanism of each irrigation area sub-basin, and determining a multi-water-source cooperative scheduling scheme of each irrigation area sub-basin based on the division result of the irrigation area sub-basin; and when each irrigation sub-basin is irrigated according to the multi-water-source cooperative scheduling scheme, calculating the canal system leakage amount in each irrigation sub-basin, and determining a water distribution scheme of each irrigation sub-basin according to the canal system leakage amount. The method can be used for quickly and accurately simulating the irrigation amount and the runoff volume of the rice irrigation area, and provides a scientific basis for formulating agricultural management measures and screening water-saving high-yield technical modes.

The invention relates to the technical field of flood disaster early warning, in particular to a flood disaster flooding prediction and graded early warning method considering a flood peak process, and the method comprises the following steps: constructing the spatial data of an easy-to-flood region in a flood disaster; predicting future rainfall data; rainfall runoff simulation is carried out on each simulation calculation unit, and the river channel confluence runoff volume in each simulation calculation unit is analyzed; generating river boundary conditions and urban boundary conditions; constructing a flood routing model, and respectively predicting the propagation process of flood in the river region and the city region in each simulation calculation unit through a river shallow water equation and a city shallow water equation based on river boundary conditions and city boundary conditions; and according to a prediction result of the flood routing model, evaluating a risk level of a flood disaster, and generating a corresponding emergency plan. By adopting the scheme, accurate flood disaster prediction can be realized, the spreading process of flood in a city can be accurately described, and the risk level of the flood disaster can be accurately evaluated.

The invention provides a method for exploring performance goodness and generalization ability of various machine learning models in runoff sediment simulation. According to the method, the time sequence change trend of a river long-time sequence hydrological factor, a meteorological factor, a vegetation factor, an artificial activity factor and a runoff sediment transport change correlation factor is determined. Then identifying the correlation between each factor and the runoff sediment change, and selecting an important influence factor as an input factor of a machine learning model; the performance goodness of different machine learning models in simulation of runoff and sediment transport is evaluated, a sample data set is randomly divided to eliminate the influence of limited sample size and sample sequence on a simulation result, and each model is repeatedly trained and tested to determine the empirical risk, predictive ability and generalization ability of each model. And sorting the contribution degrees of the input factors in the runoff and sediment transport simulation process by applying a local interpretation method so as to reveal the main driving factors influencing the water and sediment change of the drainage basin.

A method and system for tracing the source of non-point source heavy metal pollution in a watershed, the method first determines the spatial distribution of soil heavy metal content under various land use types in the watershed, the sediment enrichment ratio and water solubility factor of soil heavy metals, and simulates the spatial and temporal distribution of rainfall runoff and soil erosion sand production, and then calculates the loss of land surface heavy metal pollution, and then combines the migration of heavy metal pollution in the river channel to calculate the loss of non-point source heavy metal pollution in the outflowing river section under various land use types, so as to obtain the contribution ratio of each land use type to the non-point source heavy metal pollution in the watershed, and finally determines the main source of the loss of heavy metal pollution in the watershed according to the contribution ratio. The present invention comprehensively considers the impact of land loss and river migration process on non-point source heavy metal pollution in the watershed, and can realize the accurate calculation of the loss load of non-point source heavy metal pollution at the watershed scale and the rapid and precise identification of pollution sources.

The invention provides a water and soil loss early warning method and device based on climate change, and relates to the technical field of machine learning, and the method comprises the steps: collecting the surface temperature data and freeze-thaw state data of a target region in real time, and determining the freeze-thaw cycle state of a surface active layer based on a set freeze-thaw state criterion; calculating the melt water runoff generation amount of the surface active layer based on the freeze-thaw cycle state, and calculating the comprehensive runoff yield by combining rainfall forecast data; dynamically calculating the unit surface scouring force based on the comprehensive runoff runoff yield, and judging whether the unit surface scouring force reaches an erosion starting state or not based on a soil instability limit shear threshold value under the freezing-thawing interface; and triggering water and soil loss early warning when the superposing effective melt water runoff volume of the earth surface freeze-thaw conversion state reaches a preset percentile and the earth surface unit scouring force exceeds a soil instability limit shear threshold value. According to the invention, early warning can be carried out according to climate change for water and soil loss in alpine regions.

The invention relates to the technical field of water runoff prediction, and particularly discloses a VMD-CEEDMAN-based multi-mode daily runoff prediction method and system, aiming at the characteristics of periodicity and randomness of daily runoff, firstly, VMD and CEEMDAN are adopted to decompose historical runoff and water level data respectively, information of different frequency bands is extracted, the complexity of an original data sequence is reduced, and the data sequence is optimized; the advantages of different decomposition algorithms are exerted, and the fluctuation trend is more completely highlighted; dividing the decomposed daily runoff data into a stationary sequence and a non-stationary sequence, wherein the stationary sequence comprises a low and medium frequency sequence and a high frequency sequence; different prediction models are adopted for different sequences; and finally, reconstructing prediction results of different subsequences to obtain a daily runoff prediction result.