170 results about "Flood forecasting" patented technology

The invention discloses a cascade reservoir combined flood scheduling optimization method coupled with flood control and power generation, which can coordinate flood control and power generation goals in flood scheduling, and adopt corresponding models for different standard floods, timely power generation pre-discharging and closing gates and staggered peaks, reducing flood seasons It is useless to abandon water to maximize the benefits of cascade reservoir flood control and power generation. The technical solution is: judge the level of the flood according to the real-time hydrometeorological information and flood forecast results. When the average inflow flow during the flood period is greater than the full flow of the power station, it will be judged as a major flood, otherwise it will be judged as a small flood; according to the different levels Different models are used to optimize the scheduling of different control objectives; under each different flow, constraint settings and control objectives, a number of different flood control schemes are obtained, which constitute a set of flood control schemes corresponding to a flood, as the basis for decision-making, if In the flood control scheme set, it is necessary to modify the inflow flow, so the simulated flood control calculation under various inflow conditions is repeated.

The invention relates to a hydrological model calibrating method used for small watershed individual flood forecasting, comprising the following steps: collecting and treating data of a typical rainfall flood process; selecting a hydrologic catchment model with a mixed runoff generation mechanism; determining an objective function used for small watershed individual flood simulation; optimally selecting parameters for calibrating a hydrological model; and judging the applicability of the calibrated hydrological model to individual flood simulation. Aiming at defects in calibration of the hydrological model and by combining with the rainfall runoff generation characteristics of small watersheds in the north, a concentrated hydrological model with a mixed runoff generation mechanism is selected; by taking SCE-UA algorithm as basis and comprehensively considering three flood elements including flood peak, flood volume and flood hygrograph, parameters of the hydrological model can be calibrated by constructing a comprehensive objective function with variable weight; and on the basis of evaluating the calibrating effect of the hydrological model, a three-level judgment criteria comprehensively considering rainfall characteristics, drainage area and engineering requirements is provided, so that the calibrated hydrological model can better meet the requirement of flood forecasting ofsmall watersheds in the north.

The invention provides a dynamic optimization based neural network flood warning device and a method. The device comprises an information processing unit, an information collection module, a GPS satellite positioning module, a GIS geographic information module, a wireless network module and a client, wherein the information collection module, the GPS satellite positioning module, the GIS geographic information module and the wireless network module are connected with the information processing unit, and the client is connected with the wireless network module. The information processing unit is used for carrying out data assimilation on matched information, assimilated data comprises historical information data and implementation information data, a network flood forecasting model is established by using the historical information data, the established network flood forecasting model is corrected by using implementation information so as to acquire a dynamic network flood forecasting model, and a disaster evaluation result is outputted by using the network flood forecasting model; and the wireless network module sends the disaster evaluation result to the client. According to the invention, mountain flood disaster analysis and judgment are carried out timely and accurately through the network flood forecasting model, thereby providing a reliable basis for making and selecting defense solutions in real time.

The embodiment of the invention discloses a flood forecasting method and system based on historical data to solve a problem of low flood forecasting precision and accuracy. The method comprises the following steps: analyzing the GIS (Geographic Information System) data and the DEM (Digital Elevation Model) data of a forecasting drainage basin, and dividing the forecasting drainage basin into various hydrologic units; carrying out rainfall comparison on historical meteorological hydrologic data under each hydrologic unit with corresponding practical meteorological hydrologic data, determining the historical meteorological hydrologic data matched with rainfall, and weighting with runoff volume obtained by analog computation to obtain a forecasting result of each hydrologic unit; if a certainty coefficient of the forecasting result of each hydrologic unit and the corresponding practical meteorological hydrologic data is greater than or equal to an effective threshold value, utilizing the rainfall capacity of each hydrologic unit and a parameter adopted by analog computation under each hydrologic unit to calculate the flood element of each hydrologic unit; and according to the flood element of each hydrologic unit, carrying out flood forecasting. Floor forecasting precision and accuracy can be improved.

The invention discloses a multi-model integrated flood forecasting method based on propagation time clustering analysis and belongs to the technical field of hydrologic forecasting. The method includes adopting a derived dynamic time warp matching method for floor process similarity analysis; estimating flow propagation time of each station in the upstream and the downstream; decomposing a sample into a plurality of clusters by performing clustering analysis on the flow propagation time; respectively building an SVM regression model for each sub-flow sequence to simulate the flood forming process; combining the sub-models into a comprehensive model. Comparing a comprehensive forecasting result acquired by the method with a model forecasting result acquired by a single model under conventional conditions and on the basis of flow clustering, the comparison result shows that the comprehensive model is better in comprehensive performance.

The invention discloses a flood forecasting method based on cluster analysis and real time correction, which comprises the following steps: 1) using PCA(Principal Component Analysis) to perform dimensionality reduction to the input of a model; 2) using the K-means clustering method to conduct clustering analysis on original data; dividing the flood data into different classifications; and then training different SVM models; when a testing sample is inputted, using the clustering center to determine the classification of the test sample and predicting the corresponding model to obtain a predicted value q; and 3) using a BP neural network for real time correction; calculating the error sequence between the predicated value and the actual value; using the error sequence data to train the BP neural network error correction model to obtain the error correction value qe. The final forecasting result is the model predicted value q plus the error correction value qe. According to the invention, the original hydrological data are divided into several classifications by cluster analysis, and through the training of the models, forecasting can be available by the multiple models. Then, real-time correction is achieved by the BP neural network to improve the forecasting accuracy for the time of flood peak.

The invention discloses a flood forecasting method based on depth learning model and BP neural network correction, including: 1.normalizing the historical flood process data, 2. analyzing the normalized historical flood process data to obtain the influence time of each monitoring point on the outlet flow; 3. establishing the input and output values of the forecasting model from the historical flood data by using the sliding window, and establishing the training data set TRSet1 of the model, 4. using TRSet1 to train and establish the flood forecasting model CNNFM; 5, establishing a real-time error correction model training data set TRSet2; 6. training and establishing BP neural network based error correction model BPCM by TRSet2, 7. forecasting the real-time data with CNNFM and correcting them with BPCM to get the final forecast value for the real-time monitoring flow and rainfall. The invention models the training data through the characteristics of automatic extraction of data features by depth learning, and carries out real-time correction through BP neural network to improve the accuracy of model prediction.

The invention discloses an LSTM-based medium and small river short-term flood forecasting method, which comprises the following steps of: constructing an intelligent flood forecasting model by using historical hydrological data, and excavating medium and small river basin rainfall; the hidden information of the runoff is used for forecasting the short-term river outlet flow in the future on the basis of known or unknown future rainfall. The method comprises the following steps: firstly, preprocessing hydrological historical data, including data missing completion, normalization and the like; secondly, constructing an LSTM model, training the model through the selected training set, and adjusting parameters to improve the model precision; and finally, evaluating the performance of the modelthrough the performance of the model in the test set. The method has the advantages that the forecasting precision of the flood forecasting model based on the LSTM is superior to that of a traditional support vector machine model, and particularly the peak appearance time and peak forecasting precision of the model in the flood peak stage are greatly improved.

The invention provides an intelligent sponge city flood forecasting method, which belongs to the technical field of city management, and comprises the following steps: constructing a research area plane calculation grid; determining a hydrological hydrodynamic time history continuous calculation time interval between the grids; extracting high spatial resolution grid elevation and land utilization/coverage information; assigning values to the grid precipitation time history data; assigning values to the grid production and confluence parameters; taking the grid elevation, the land utilization/coverage information and the rainfall and runoff production and confluence parameters as a model operation database, integrating a hydrological hydrodynamic theory, and constructing a hydrological hydrodynamic model by using the method; verifying the hydrological hydrodynamic model; and based on the simulation result of the hydrological hydrodynamic model, performing basin runoff production and confluence and flood disaster prediction. According to the method, the urban flood problem can be quickly, intelligently and flexibly dealt with by realizing real-time quick forecasting of rain conditions and water conditions, real-time quick forecasting of urban flood, intelligent regulation and control of a water system and refined management.

The invention provides an intelligent reservoir safety management system comprising a rainfall condition monitoring module, a dam safety monitoring module, a gate monitoring module, a flood forecasting and dispatching module, a video monitoring module and an automatic data reporting module. The hardware structure of the management system is divided into three layers, a data acquisition layer is arranged on a corresponding position of a reservoir area of each reservoir, and the data acquisition layer transmits the collected data to a cloud service platform via a mobile communication device; thecloud service platform provides data processing, data storage and GIS application service, and functional modules run on the cloud service platform; and the user accesses the cloud service platform via various terminal devices to use the services of the functional modules of the management system. The monitoring functions of the management system are rich, only the data collection devices are arranged at the corresponding positions of the reservoir, the monitoring data of the reservoirs are transmitted to the cloud service platform for centralized processing, the system maintenance is simple,and the provincial level joint control and joint prevention of safety of reservoirs are achieved easily.

The invention relates to a flood forecasting method based on a water level sample. The flood forecasting method is characterized by comprising the following steps of S01: simulating a runoff formation process by adopting a water tank mode, and abstracting the process of converting rainfall into runoff into a relation between the water storage and the outflow of a drainage basin; S02: establishing a function relation between the flow and the water level, performing function fitting on the water level and the average velocity of the cross section first by adopting a zero-crossing power function, and then establishing a relation between the water level of the cross section and the flow; S03: obtaining a relation between the rainfall capacity and the outflow water level; S04: continuously improving the accuracy of a hydrological model by comparing an obtained outflow water level process with an actually measured water level value and adjusting parameters of the hydrological model; S05: inputting the rainfall capacity and the surface evaporation quantity of the upstream drainage basin by aiming at the calibrated hydrological model, so as to obtain the downstream outlet water level process, judging whether a forecasting area is flooded according to a water level peak value, and analyzing the lag time between a rainfall peak and a flood peak according to existing water level rainfall data, so as to determine the peak time.

The invention discloses a rainfall runoff forecasting system. An innovative rainfall runoff forecasting technical scheme is adopted, short, medium and long term rainfall runoff forecasting can be achieved, the real-time flood forecasting process can be displayed in forecasting, which is beneficial for accurately estimating the flood peak, the flood volume and the process of flood, the processes of discharge out of a reservoir and the water level are simulated in the forecasting process, short, medium and long term runoff forecasting scheduling including real-time flood forecasting of a user is achieved, and the problems that at present, the forecasting process of most runoff forecasting software is too short, and the medium and long term forecasting function is poor are solved. The system comprises a water regimen database, a user parameter configuration module, a rainfall runoff forecasting and calculating module, a forecasting result statistics module and a forecasting graph module. The system has the automatic forecast correcting function and is not provided with a gauging station and capable of achieving real-time rainfall flood forecasting as well, software and hardware cost of the system is greatly reduced, and the problem that most small and medium-sized reservoirs, hydropower stations and some large and medium-sized hydropower stations are short of medium and long term forecasting is solved.

The invention discloses a variation reasoning Bayesian neural network-based flood ensemble forecasting method. The method comprises the following steps of: setting dimensions of each layer of a Bayesian neural network; Selecting the prior probability distribution of the weight parameters of the Bayesian neural network, and parameterizing the weight parameters of the Bayesian neural network throughthe variational parameters to approximate the posterior probability distribution of the weight parameters of the Bayesian neural network; Calculating the relative entropy of the prior probability distribution and the variation posterior probability distribution, and calculating an expected log-likelihood function according to the training data set; Constructing an objective function according tothe relative entropy and the expected log-likelihood function; maximizing a target function, and training variational reasoning parameters; And carrying out ensemble forecasting on unknown flood by using the trained variational reasoning Bayesian neural network. According to the method, the variational reasoning is combined with the BNN model, and the posterior probability of the weight parametersof the Bayesian network model is approximated through variational distribution, so that the calculation process is simplified, the uncertainty of flood forecasting is quantitatively described, and the accuracy is improved.

The invention relates to a novel distributed Hebei model construction method and application thereof. The novel distributed Hebei model construction method comprises the following steps that firstly, drainage basin generalization is carried out; secondly, grids serve as study units, a Hebei model is used for establishing a grid runoff producing module; thirdly, a lag-and-route method and a Muskingum method are used for establishing grid-by-grid distributed confluence modules. The mature Hebei model is used for conducting grid runoff producing calculation, then, grid-by-grid confluence calculation is carried out, the situation that the space distribution of factors such as an underlying surface is uneven is fully considered in the model, the model can be coupled with an atmospheric mode, the forecast accuracy of storm flood is improved, the meeting period is prolonged, and the novel distributed Hebei model construction method has important significance for storm flood forecasting, a drainage basin water circulation mechanism, water resource planning, unified water resource management scheduling in the northern semiarid and semihumid regions in China.

The invention relates to a dynamic operation water level control method for a 3D or higher cascaded reservoirs in flood season. The method comprises the steps that 1) the relation of upper pre-impounded water level limits among the 3D or higher cascaded reservoirs is analyzed on the basis of an aggregation-decomposition theory and a pre-impounding pre-discharge method; 2) an optimized scheduling module which takes the minimal flood prevention risk rate, the minimal under-generation risk rate and the minimal under-impounding risk rate in the effective forecast period of a flood forecast as target functions, the operation water level in the flood season as a decision variable, and a manual fish swarm algorithm as an optimized solution algorithm is established, a non-inferior solution set is provided for dynamic operation water level control in the flood season, and a decision scheme set is provided for a multi-target decision module; and 3) the multi-target decision module which takes the minimal flood prevention risk rate, the minimal under-generation risk rate, the minimal under-impounding risk rate, the maximal generation capacity and the maximal impounding rate as evaluation indexes and a network analysis method as a multi-target evaluation method is established, and a preferable decision scheme of the dynamic operation water level control in the flood season is selected. Thus, theoretical basis and technical support are provided for scientifically making a combined dynamic operation water level control scheme for the cascaded reservoirs in the flood season.

The invention discloses a flood forecasting scheme real-time optimization method based on machine learning. The flood forecasting scheme real-time optimization method comprises the following steps: 1)collection and processing of basin hydrological data; 2) rainfall and flood session division and association; 3) generation of a rainfall flood event sample set; 4) flood grading; 5) construction ofa flood forecasting scheme; 6) classifier training based on machine learning; and 7) forecasting scheme real-time optimization based on early rainfall. According to the flood forecasting scheme real-time optimization method, the sample set is divided into subsets on the basis of flood levels, and the flood forecasting schemes are compiled respectively and associated with the early rainfall processthrough a machine learning method, and optimization of the flood forecasting schemes during real-time forecasting is achieved, and the real-time flood forecasting precision of the drainage basin canbe effectively improved.

The invention discloses a typical- empirical-model-based emergency flood forecasting method. The method comprises: a statistical analysis is carried out on historical practically-measured flood elements to form a basic basis data set for emergency flood forecasting; refining processing is carried out on floods below a once-in-a-ten-year level by using an interpolation method and a designed flood process line table is obtained according to a refined interpolation method; view processing is carried out on main relevant elements of historical practically-measured floods and a historical flood scatter diagram is established by using values of process precipitation P plus early-stage influence rainfall Pa as horizontal coordinates and flooding starting flows as longitudinal coordinates; and according to the historical practically-measured floods and designed flood characteristics values, qualitative and quantitative water-break forecasting is carried out. Therefore, forecasting can be carried out timely and accurately under any circumstance; the timeliness and integrity requirements on drainage basin rainfall data by real-time flood forecasting can be reduced; and the method is simple and is easy to implement.

This invention provides decision makers with an auxiliary system for flood defense dispatching decision serving as a basis of decision making. The auxiliary system for flood defense dispatching decision comprises a basic module database used for storing historical flood hydrograph and relevant rainfall amount as well as rainfall duration of each historical flood hydrograph; a basic database used to store units parameters; a flood forecasting module to forecast flood by scaling the adopted historical flood hydrograph in according with the total rainfall amount and rainfall duration predicted by weather forecast; a flood dispatching module used to set present parameters of flood releasing units and flood releasing facilities to simulate flood defense dispatching accordingly as well as in according with the total rainfall amount and rainfall duration predicted by weather forecast and the historical flood hydrograph. The auxiliary system for flood defense dispatching decision applicates to a technology field of computer-based flood defense dispatching.

The invention discloses a flood forecasting method based on synthetic flow and shape fitting and relates to the technical field of hydrological simulation and forecasting. The method comprises the steps that a correlation between target cross section flow and upstream cross section flow is inquired and forecasted; distributed hydrological model modeling is conducted on forecasting drainage basin,and obtained runoff generation and confluence parameters of each calculation unit in a distributed hydrological model are calibrated; according to flood peak data of each time and flood volume data ofeach time of a forecasting target cross section, the corresponding relation of the flood peak and the flood volume is fit; corresponding exponential-type water subsiding curve parameters in the actual water subsiding process are inquired; a flow forecasting result of the forecasting target cross section in the confluence forecast period is obtained through flow synthesis; the forecasting flood volume and the forecasting flood peak of the forecasting target cross section in the flood on the spot are acquired; the corresponding flow forecasting result which meets a preset requirement is used asa final result of flood forecasting of each time. According to the flood forecasting method, the forecast period of flood forecasting is prolonged, so that the forecasting result is more reasonable and precise.

The invention belongs to the technical field of flood prediction, and discloses a flood prediction model, an information processing method, a storage medium, and computer equipment. The flood prediction model comprises a spatial-temporal feature abstraction layer used for extracting features from terrain-rainfall spatial-temporal features, a feature fusion layer used for combining space-time features abstracted by the convolutional network with historical trend features through Concat connection operation, and a prediction output layer used for predicting the flow change condition in the future T hours. The method aims to solve the problems that a traditional model needs a large number of parameter calibration and a data driving model cannot accurately predict the flood process. A convolutional neural network CNN based on two-dimensional convolution is introduced into the field of flood forecasting, the feature abstraction capability of the CNN is utilized, rainfall space-time distribution features, landform features and flow change trend features are fused, and a flood forecasting model with the forecasting period of 24 hours and 36 hours is constructed. Through inspection, the model meets the requirements of flood forecasting.

The invention discloses a real-time flood forecasting intelligent model forecasting method for medium and small rivers. The method comprises the steps: firstly collecting historical hydrological dataof all stations of a research basin, and storing the historical hydrological data into a hydrological historical database; secondly, performing data cleaning, data conversion and data set division onhydrological history data; thirdly, constructing a three-stage real-time flood forecasting model. In the first stage, a data driving model based on a support vector machine is used for forecasting flood. In the second stage, a Markov method is adopted to intelligently adjust the state of the initial forecasting model. In the third stage, a historical flood flow mode the same as the historical flood flow mode in the real-time flood process is searched in a flood mode library. After that, the overall form of the flood hydrograph forecasted in real time is adjusted. The performance of the intelligent model is evaluated by using the test set data. Finally, real-time forecasts are made. The method has the advantages that the flood peak precision and the flood trend can be effectively forecasted, and the method is an effective tool for real-time forecasting of flood of medium and small rivers.