225 results about "Watershed" patented technology

The invention discloses a grading, zoning and differentiating risk early warning method for mountain torrent disasters in medium and small watershed. Firstly, a drainage basin risk area is determined through mountain torrent disaster data analysis; the drainage basin delay time is calculated, the section water level and the drainage basin submerging range are simulated through the simplified hydrodynamic model, and quantitative analysis is conducted on the model; according to the method, a high-precision grid database is formed by combining unstructured grid division and risk source identification, and then clustering grading is performed on multi-dimensional characteristics of grids through a Gaussian mixture model (GMM) to obtain risk levels of the grids in a drainage basin. Finally, a differential early warning threshold value and a response strategy are formulated according to a grid partition grading result, and dynamic updating and linkage issuing are achieved on a GIS platform in combination with actual measurement data. According to the method, limited real conditions of small and medium-sized basin data and precision requirements of model simulation are taken into consideration, fine setting of the early warning threshold value is realized on the basis of grading and partitioning, and the accuracy of mountain torrent risk identification is also remarkably improved.

The invention relates to the technical field of hydrological data analysis, in particular to a dynamic hydrological coupling data analysis method and system for a complex watershed. The method comprises the following steps: acquiring historical meteorological data, historical hydrological data and historical remote sensing data, and performing hydrological cycle simulation analysis to generate a rainfall-evaporation-permeation-runoff hydrological cycle simulation model; performing drainage basin gridding processing on the rainfall-evaporation-permeation-runoff hydrological cycle simulation model to generate a hydrological cycle gridding model; obtaining actually measured meteorological data and actually measured hydrological data, and carrying out space-time simulation division and hydrological space-time correlation analysis to obtain a hydrological change space-time correlation correlation relationship among the sub-partitions of each drainage basin; and performing drainage basin space-time coupling early warning processing on the hydrological cycle gridding model to generate a hydrological change space-time coupling early warning response result corresponding to the complex drainage basin. The method can accurately analyze and predict the hydrological change and the mutual coupling relation thereof in the complex watershed.

The invention discloses an ecological restoration quantification method based on a watershed ecological safety complex network. The method comprises the following steps: S1, obtaining multi-time-sequence watershed multi-source heterogeneous spatial data of a target area; s2, taking the grid as an evaluation unit, establishing a drainage basin ecosystem service function evaluation system, and obtaining spatial-temporal change characteristics of an ecological safety function; s3, analyzing the spatial-temporal change characteristics of the ecological land scale of the watershed; s4, constructing a drainage basin ecological resistance surface; s5, identifying an ecological corridor; s6, constructing an ecological safety complex network model by taking the ecological source as a node, the ecological corridor as an edge, the scale of the ecological source as a point weight and the proportional relation between the connection efficiency of the ecological corridor and the corridor resistance as an edge weight, and extracting spatial-temporal evolution characteristics of an ecological safety structure; s7, a coupling coordination degree model is adopted to simulate and analyze the characteristic relation among the safety function, the safety structure and the land use scale, and the coupling coordination degree is obtained; and S8, guiding and optimizing an ecological restoration implementation strategy. According to the method, ecological security network structure features on the watershed system scale are quantified.

The invention discloses a drainage basin hydrological multivariable prediction method based on a meta-learning TFT architecture, and relates to the technical field of hydrological prediction, and the method comprises the steps: collecting multivariable water quality data, external driving force data and static drainage basin attribute data of a plurality of hydrological observation stations; splicing and processing missing values, and dividing the missing values into a training set, a test set and a verification set which are arranged in time as input; the capture of the model on the long-term dependency relationship is enhanced by enhancing the gating circulation unit; capturing a multi-level dependency relationship in the time sequence by using a multi-scale image attention network; and integrating the meta-learning framework, fusing a plurality of subtasks, and outputting a predicted value. Model fusion enhanced meta learning and improved Temporal Fusion Transformer are combined, a multi-scale map attention network and a dynamic model fusion mechanism are fused, the defects of a hydrological prediction model in the aspects of capturing a long-term dependency relationship and generalization ability in a complex watershed environment are overcome, and the precision and reliability of multivariable hydrological prediction are improved.

A method for inverse traceability of non-point source pollution in a watershed and a computer device are provided. The method includes: acquiring basic data of a studied watershed; determining a location-weighted landscape contrast index (LWLI) of each landscape type in the studied watershed and a pollutant load of the studied watershed in a predetermined time cycle according to the basic data; and determining, according to the pollutant load and the LWLI, based on a pre-constructed pollution traceability model, an amount of non-point source pollutants entering a river for each landscape type in the studied field.

The invention discloses a non-linear production and confluence characteristic analysis method for a valley terrain extra-small watershed. The method comprises the steps that S1, valley terrain-hydrological data are acquired, and hydrological grid units are spatially divided; s2, identifying hydrological behavior characteristics of the hydrological grid units to form independent hydrological response units; s3, analyzing a first influence degree formed by rainfall infiltration, a second influence degree formed by surface runoff and a third influence degree formed by dynamic change of soil moisture in the hydrological response unit, and constructing a valley dynamic fluid model; s4, combining the valley dynamic fluid model with the underground water flow model and the surface water flow model to form a hydrological-hydrodynamic simulation framework; and S5, simulating various rainfall scenes by using a hydrological-hydrodynamic simulation framework, performing analysis in combination with valley microtopography factors, calculating flow change rates of different rainfall scenes, and identifying nonlinear features. According to the method, high-precision simulation and prediction of the valley terrain extra-small watershed are realized, and the accuracy and timeliness of productivity and confluence analysis are improved.

The invention discloses a physical mechanism and deep learning coupled flood forecasting method, device and system. The flood forecasting method comprises the steps of obtaining DEM data, hydro meteorological data and drainage basin static attribute data of a target drainage basin; based on the DEM data, dividing a target drainage basin into a plurality of sub-drainage basins, extracting a river network, and calculating static attribute data of the river network, the river network comprising a plurality of river channels; inputting the hydrometeorological data, the drainage basin static attribute data and the river network static attribute data of each sub-drainage basin into a pre-trained distributed hybrid hydrological model to obtain simulated flow of a hydrological observation station, and completing flood forecasting; the distributed hybrid hydrological model is coupled with a physical mechanism and deep learning. On the premise that the distributed hybrid hydrological model has good interpretability, high-precision daily runoff and flood simulation can be achieved, and high calculation efficiency is achieved.

The invention discloses a grid scale basin flood toughness evaluation method and system based on underlying surface functions and endurance capability, and the method comprises the steps: obtaining high-resolution remote sensing image data and POI data, obtaining a fine classification result through multi-level classification processing, and carrying out the calculation through combining with social economic data, thereby obtaining various underlying surface function weight values; performing statistical analysis and gridding calculation on the fine classification result and historical disaster data to obtain a grid unit endurance capacity value; a coupling hydrodynamic model is constructed for simulation calculation, and grid submerging water depth and submerging time data are obtained; calculating a system performance curve, and extracting toughness characteristic values to obtain a grid toughness characteristic value set; and calculating comprehensive toughness based on the toughness characteristic value set, and performing spatial integration in combination with the functional weight values of the underlying surface at different moments to obtain toughness evaluation results of different spatial and temporal scales. Accurate decision support is provided for urban flood control and disaster reduction.

The invention discloses a flood recovery method based on a distributed hydrological-hydrodynamic coupling mode. The method comprises the following steps: reorganizing a data set of historical mountain torrent disasters, determining a basin topological structure relationship, and drawing up key nodes of a corresponding basin; on the basis of the key nodes, constructing a hydrological model in the drainage basin above the key nodes, constructing N calculation units based on the data set and according to the topological relation of the drainage basin, and adjusting parameters and calibrating to obtain an optimal flood simulation result and a parameter result; constructing a hydrodynamic model in the flooding area drainage basin below the key node, and constructing the hydrodynamic model to perform simulation analysis on flooding area partition application and flood routing based on the optimal flood simulation result and parameter result driving; the generation, confluence and evolution process of the flood in the drainage basin is reflected more accurately, the application effect of the method in the aspects of flood simulation, early warning and coping is improved, the actual situation of the flood disaster can be restored more accurately in the flood recovery process, and a reliable basis is provided for post-disaster evaluation, reconstruction and planning.

The present invention discloses a large-scale basin total phosphorus simulation method based on deep learning and attention mechanism, including: collecting daily hydrological and meteorological time series data, water quality data and constant basin attribute data; preprocessing the collected data; creating and introducing the attention mechanism in the LSTM model to set hyperparameters; inputting the preprocessed data into the LSTM model containing the attention mechanism for model training and evaluation; outputting the simulated data set of the basin's daily total phosphorus concentration and flux. The present invention applies the deep learning algorithm to the training of the LSTM model, and introduces the attention mechanism to improve the model's attention to important time steps and features, realizing the simultaneous simulation of daily TP data of hundreds of basins, and learning of hundreds of basin characteristics and dynamic behaviors, which has the advantages of wide spatial range and large time span in water quality simulation.

The embodiment of the invention provides an intelligent water conservancy informatization management method and platform, and belongs to the technical field of intelligent management. The method comprises the following steps: acquiring hydrological data, equipment state data and equipment health data; and constructing a drainage basin level graph according to the hydrological data, the equipment state data and the equipment health data. Wherein the drainage basin level graph comprises a plurality of equipment level sub-graphs. And according to the preset data driving loss and the preset physical consistency loss, constructing a physical consistency regularization item. And inputting the drainage basin level graph, the device level sub-graph and the physical consistency regularization item into a preset graph neural fusion model to obtain a scheduling strategy of each edge device. And sending the scheduling strategy to each corresponding edge device. And therefore, collaborative optimization scheduling among the cross-basin and multiple devices can be realized.

The invention discloses a space-time deep learning-based data-free watershed runoff prediction method and system. The method comprises the following steps: collecting static geographic raster data and dynamic hydro meteorological time series data of multiple watersheds, and performing preprocessing; constructing a double-flow deep learning model fusing space and time features; training a double-flow deep learning model based on the multi-region large-sample watershed data to obtain a general hydrological model; evaluating the adaptability of each network layer in the general hydrological model to a target watershed through a layered unfreezing test, and screening out a key adaptive layer; and under a leave-one-out method cross validation framework, layered progressive unfreezing transfer learning is carried out on the general hydrological model based on the key adaptation layer, and data-free drainage basin runoff prediction is realized. According to the method, multi-basin data driving, spatio-temporal feature fusion and a transfer learning mechanism are organically combined, the conversion of a hydrological modeling norm from local adaptation to global generalization is promoted, and a new path is provided for intelligent prediction of data-free basin runoff.

The invention discloses a watershed disaster comprehensive prevention and early warning method and system based on multi-source data, and the method comprises the steps: S1, carrying out the grid map division of a watershed according to the rainfall, and carrying out the further segmentation according to the terrain, and forming a plurality of different regions; s2, respectively constructing corresponding flood disaster early warning models according to the geological features of different areas in the S1; s3, calculating the critical rainfall of different areas based on the consideration of the flood disaster early warning model on topographic and geological elements, and judging the respective corresponding early warning information; and S4, calculating the water volume information of the whole drainage basin by adopting a mathematical model algorithm of overlay analysis in combination with the early warning information of different regions, and comprehensively evaluating the risk level of the whole drainage basin. According to the invention, more comprehensive and accurate monitoring, early warning and management of watershed disasters are effectively realized, and reliable support and decision basis are provided for disaster prevention and reduction work.

The invention discloses a landslide-debris flow disaster chain assessment method based on a graph neural network, and the method comprises the steps: generating a composite ground feature unit through the watershed segmentation of a composite curvature field and hydrological analysis, abstracting the composite ground feature unit as a geographic node, optimizing a multi-source environment factor through mutual information screening, constructing a directed weighted graph in combination with spatial similarity, and carrying out the reconstruction of a landslide-debris flow disaster chain. An improved GraphSAGE model which introduces neighbor weight, self-loop and residual error information and cancels random sampling is adopted, a sample set adaptive to a less-data area is constructed through a unit splitting-feature matching-terrain fitting mechanism, and model training and risk prediction are completed. The method solves the problems of single disaster assessment, strong sample dependence and high missed judgment rate in the traditional technology, has excellent performance indexes, effectively reduces the missed judgment risk of a high-risk area, and provides accurate and efficient technical support for disaster chain risk assessment of a small watershed in a small-data mountainous area.

The invention relates to the technical field of remote sensing technology and geographic information system application, and discloses a watershed water and soil loss monitoring method, which comprises the following steps of: firstly, acquiring and preprocessing a multispectral image, a DEM (Digital Elevation Model) and land utilization data of a target watershed, and then extracting and grading vegetation coverage and gradient information from the multispectral image, the DEM and the land utilization data; and then integrating the dominant factors, the land utilization types and the auxiliary factors, judging the water and soil loss grade according to rules, and finally generating a verified water and soil loss spatial distribution diagram. Through combination of remote sensing image processing, multi-factor quantitative extraction and standardized analysis, comprehensive and systematic evaluation of the water and soil loss condition of the drainage basin is realized, the locality of traditional monitoring point data is overcome, grade judgment is performed by referring to the national standard, the normalization and comparability of a monitoring result and the consistency of repeated monitoring are improved, and the method is suitable for popularization and application. Meanwhile, remote sensing and GIS technologies are utilized, and an efficient and low-cost technical scheme is provided for large-range and medium-and-long-term water and soil loss monitoring.

The invention discloses a watershed sediment connectivity evaluation method based on an MATLAB platform and considering relative surface roughness. The method comprises the following steps: acquiring digital elevation model (DEM) data of a target watershed; obtaining a digital elevation model DEMF after depression filling based on the DEM; calculating a flow direction matrix FD; calculating a catchment area A of a catchment area above each DEM cell, and extracting water system position vector data S; calculating a surface roughness factor RRF and a surface undulation factor SLF based on the DEMF, and generating a surface relative roughness factor RRSF; calculating a weighted confluence path length DISTW based on the FD and the RRSF; calculating a sediment'source 'component Dup and a sediment'sink' component Ddown based on A, S, DISTW and FD; and calculating a connectivity index RIC of the target drainage basin based on the Dup and the Ddown. According to the method, the influence of micro-topography evolution of the erosion-driven drainage basin on the sediment connectivity can be more comprehensively represented.

The invention provides a rapid generation method and device for a typical vegetation pattern of a watershed, electronic equipment and a storage medium, and belongs to the technical field of data processing.The method comprises the steps that the resolution of a digital elevation model is determined based on the area of a target watershed; acquiring digital elevation data of the target drainage basin based on the resolution; based on the vegetation distribution morphological characteristics of the target watershed, determining a topographic index which is used for performing topographic unit demarcation of the target watershed; and based on the topographic indexes and the digital elevation data, differentially configuring the same kind of vegetation to different topographic units to obtain a typical vegetation pattern of the target watershed. According to distribution morphological characteristics of the basin vegetation pattern to be designed, proper topographic indexes are selected to delimit the basin topographic units, and the same number of similar vegetation is distributed in different topographic units in a differentiated manner to form a plurality of vegetation-topographic superposed patterns, so that rapid generation of grid data of the typical basin vegetation pattern is realized.

The present invention relates to the technical field of soil and water conservation. Disclosed is a vegetation configuration adjustment method applicable to a hilly and gully area. The method comprises: on the basis of a digital elevation model and remote sensing image data of a target watershed, dividing the target watershed into a plurality of afforestation areas, wherein each afforestation area corresponds to one site type; conducting surveying and sampling on existing vegetation in the target watershed, and determining ecological service functions of the afforestation areas, wherein the ecological service functions comprise biodiversity, a water resource conservation function and a soil improvement function; on the basis of a soil loss amount of each area in the target watershed, determining the priority degree of water and soil loss control in each area; and for areas where ecological service functions of the existing vegetation in the target watershed do not match site types, using an analytic hierarchy process to adjust vegetation in the afforestation area in view of the priority degree of current water and soil loss control in the watershed. The present invention improves the efficiency of vegetation configuration.

The invention discloses a hydrological data processing method, a model training method and electronic equipment, and relates to the field of data prediction. The method comprises the steps that monitored hydrological data monitored in a drainage basin are acquired, and the monitored hydrological data are used for representing hydrological data having an incidence relation with the flow of the drainage basin; generating hydrological features of the watershed based on the monitored hydrological data by using a feature generation model to obtain target hydrological features of the watershed; and performing flow simulation based on the target hydrological characteristics and the monitored hydrological data by using a hydrological physical model to obtain target simulation flow of the drainage basin. According to the method and the device, the technical problem of relatively low accuracy of flow simulation of a specified drainage basin in related technologies is solved.

The invention discloses a large-scale watershed ecosystem health evaluation method based on a VORS model, and belongs to the technical field of watershed ecosystem evaluation management, and the method comprises the following steps: S1, determining a watershed boundary, and dividing evaluation units; s2, collecting and standardizing multi-source data; s3, calculating each index in the VORS model; s4, calculating a comprehensive health index of the large-scale watershed; and S5, performing drainage basin ecosystem health grade division and spatial distribution evaluation. According to the method, high-resolution spatial mapping and hierarchical management of watershed ecosystem health are realized, and powerful technical support is provided for accurately identifying ecological health risk areas and scientifically configuring ecological protection and restoration resources. The method has good expandability and universality, and can be widely applied to health evaluation practices of drainage basin ecosystems of different regions and scales.

The invention discloses a less-data watershed runoff prediction method fusing multi-scale features and prediction results. Determining a watershed with data most similar to the watershed with less data; dividing the watershed with data into different watershed clusters by using a clustering algorithm, and determining the watershed cluster to which the watershed with less data belongs; constructing a multi-scale watershed LSTM model, namely a regional watershed LSTM model, a cluster watershed LSTM model and an individual watershed LSTM model; extracting multi-scale features of the less-data watershed by using a multi-scale watershed LSTM model and obtaining a multi-scale runoff prediction result of the less-data watershed; and by taking the multi-scale features and the runoff prediction result of the less-data watershed as input features and taking the final runoff prediction result of the less-data watershed as an output label, constructing a less-data watershed runoff prediction model. The method can effectively improve the runoff prediction precision and generalization ability of the watershed with less data, and has a wide application prospect in the field of runoff prediction.

The invention discloses a hydrological time sequence anomaly detection method based on spatio-temporal characteristics. The method comprises the following steps: firstly, according to digital elevation model (DEM) data of a drainage basin, extracting spatial information such as elevation and gradient in the drainage basin and a river channel distance between hydrological stations, and constructing a spatial characteristic matrix of the drainage basin according to the spatial information; meanwhile, accumulated convergence time is calculated to preprocess the input data; constructing a variational auto-encoder (VAE) according to the spatial feature matrix and the preprocessed input data, and learning spatial and temporal features in combination with a time domain convolutional network (TCN) and a graph convolutional neural network (GCN); and finally, inputting the test data set into the pre-trained network model, calculating an abnormal score, and judging abnormal data in the hydrological time sequence according to the abnormal score. According to the invention, the problems of difficult detection of multi-site hydrological time series data, difficult learning of spatial-temporal characteristics and the like in the prior art can be solved.

The invention relates to the technical field of water ecological protection, in particular to a river type division method based on a small watershed water ecological environment protection stage. The method comprises the following steps: acquiring historical river water area data; obtaining a target watershed image by using a machine vision technology; performing water flow path analysis on the target watershed image to generate a water flow path network structure; carrying out biological sample collection on the target river, and carrying out genome sequencing treatment to generate biological genome data; performing memory information mining on the biological genome data to obtain watershed memory data; performing environmental transition correlation analysis on the watershed memory data to generate gene-environmental evolution data; performing drainage basin evolution trajectory reconstruction on the gene-environment evolution data based on historical river water area data to construct a drainage basin evolution trajectory; and performing drainage basin evolution form analysis on the water flow path network structure through the drainage basin evolution trajectory to generate drainage basin evolution form data. According to the method, efficient and accurate river division is realized.

The invention discloses a multi-period non-stationary hydrological variable valuation method, and relates to the technical field of hydrological prediction. Comprising the steps of obtaining hydrological variables of a plurality of observation stations in a drainage basin at different time points as hydrological time sequences of the observation stations; constructing an experimental variation function according to the hydrological time sequence of each observation station; selecting a drift model through a trend surface analysis method and model inspection; constructing a multi-period non-stationary variable equation set comprising a Lagrange multiplier and a hydrological variable weight based on the experimental variation function and the drift model; expressing the multi-period non-stationary variable equation set as a matrix form, and calculating a Lagrange multiplier and a hydrological variable weight through a matrix inversion method; and constructing an estimation formula according to the calculation result of the Lagrange multiplier and the hydrological variable weight, and performing multi-period spatial estimation on the hydrological variable of the to-be-measured drainage basin through the estimation formula. Dependence on the number of observation stations can be reduced, and accurate estimation can be achieved only through a small amount of observation station data.

The invention discloses a mountain and valley type stream ecological flow threshold value calculation method based on a hydrological set legitimacy, and the method comprises the steps: obtaining the monthly average flow data of a watershed for more than 30 years, determining the boundary node of the periodic change time period of the watershed, and calculating the ecological flow threshold values of different time periods through eight hydrological methods; a hydrology set percentage method and a quantile method are used to carry out calculation and segmentation expression on the threshold set after dividing the boundary nodes; and establishing a comprehensive quantitative index evaluation system of the ecological flow threshold by using a geometric averaging method. The beneficial effects of the method are that through a hydrology set percentage and quantile calculation mode, the periodic change of the drainage basin is finely divided and expressed in a segmented manner, and the calculation precision of the ecological flow threshold value under the seasonal change of the alpine and gorge type stream is improved; and the identification and description capabilities of dynamic change characteristics in an ecological flow threshold period are obviously enhanced.

The invention discloses a data migration method for a watershed with deficient hydrological data, and aims to migrate data of a watershed with dense data to a watershed with deficient data and solve the problem of insufficient data. The target drainage basin refers to a drainage basin with deficient data, and the source drainage basin refers to a drainage basin similar to the drainage basin with deficient data. The hydrological time sequence migration network based on Transform is provided from the angle of deviation of time sequences of different drainage basins in a value domain and time lag. And aiming at the value domain difference between the drainage basins, establishing a drainage basin value domain migration model based on Transform. The encoder is used for extracting value domain features of the water level time sequence and the rainfall time sequence of the source basin, and feature fusion is carried out on the value domain features of the source basin and the time sequence of the target basin in the decoder. And aiming at the time lag difference between the drainage basins, establishing a drainage basin time lag migration model based on Transform. An encoder is used for extracting a time-delay relation between a water level time sequence and a rainfall time sequence in a source drainage basin, and feature fusion is carried out on the time-delay relation of the source drainage basin and a target drainage basin time sequence subjected to value domain migration in a decoder. And through value domain migration and time delay migration, data migration from the source basin to the target basin is realized.

The invention discloses a watershed flood type identification method considering a topological relation, and the method comprises the steps: abstracting each hydrometric station in a watershed into graph nodes, and abstracting the upstream-to-downstream communication relation between the hydrometric stations into directed edges, thereby constructing a watershed directed topological graph; for each flood event, standardization processing is carried out on the multi-station features according to nodes and features, and flood identification features are added to each node. Then, a graph auto-encoder based on a graph attention mechanism is adopted to carry out unsupervised reconstruction learning on the graph structure sample so as to extract a graph-level embedded vector; and finally, performing K-Means clustering on the embedded vector, adaptively determining an optimal cluster number according to a contour coefficient, and finally outputting a type label of the flood sample. According to the method, drainage basin flood type supervision information can be generated without manual annotation, and the extracted feature representation can also be used for model training of downstream tasks such as subsequent flood type real-time prediction.

The application belongs to the technical field of data processing, and specifically discloses a watershed water and scenery uncertainty quantification method and device based on data driving. According to the application, based on a target watershed water and scenery prediction model, a watershed water and scenery prediction result is determined according to current watershed water and scenery data; and based on a data-driven watershed water and scenery uncertainty quantification model, the watershed water and scenery prediction result is quantified in uncertainty according to a target quantification algorithm. In the above manner, the target watershed water and scenery prediction model is determined based on the long-term dependence relationship of the watershed water and scenery data in time correlation and the dependence relationship in space correlation, the complex space-time relationship between the stations in the watershed is accurately expressed, and then the data-driven watershed water and scenery uncertainty quantification model is used for uncertainty quantification, so that the precision and reliability of the uncertainty quantification can be effectively improved without relying on data distribution assumptions and being able to cope with various complex environments.

The invention discloses a multi-period non-stationary multi-hydrological variable spatial valuation method, and relates to the technical field of hydrogeology. Comprising the steps of obtaining a univariate time sequence; combining the univariate time sequences of all observation stations in the drainage basin to obtain a multivariate random time sequence; calculating a long-term average level of each observation station through a space-time random function to obtain a long-term trend; subtracting the multivariable random time sequence of each observation station from the corresponding long-term trend to obtain a random residual error; according to the random residual error, determining a covariance function and a variation function between any two observation stations in the drainage basin; and on the basis, a multi-period non-stationary multivariable space valuation model is constructed by combining a multivariable Kriging model theory, and multi-hydrological variable valuation is performed on the drainage basin to be measured. According to the invention, internal correlation between variables can be revealed, and the prediction precision and reliability can be effectively improved.

The invention discloses a Yellow River basin midstream small watershed similarity discrimination and clustering method, system and device, and a storage medium, and the method comprises the steps: obtaining the static topographic index data and dynamic hydrological index data of a target small watershed, and carrying out the standardization processing of the static topographic index data and dynamic hydrological index data, and obtaining the standardized data; calculating variable coefficients of the static terrain indexes and the dynamic hydrological indexes, and determining weights of the static terrain indexes and the dynamic hydrological indexes according to the variable coefficients; on the basis of the weight and the standardized data, a weighted Euclidean distance algorithm is adopted to calculate the feature space distance between the small watersheds, and the similarity coefficient of the small watersheds is determined according to the feature space distance; and grouping the small watershed by using a K-means clustering algorithm, calculating a contour coefficient, determining an optimal clustering number, and obtaining a small watershed similarity clustering result. And the similarity degree between the drainage basins can be quantified comprehensively and accurately.