Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An intelligent ensemble assessment method and system for basin water and sediment research models

A technology for studying models and watersheds, applied in the field of ensemble assessment, which can solve problems such as inability to guarantee, model structure errors, and inaccurate human activity contribution rates.

Active Publication Date: 2021-07-20
TSINGHUA UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In addition, the existing methods have certain limitations. The disadvantage of the empirical model method is: for the sake of simplicity of calculation, the empirical model usually only selects the precipitation P or other forms of precipitation that have the greatest correlation with the output (runoff or sediment transport) As an input, other factors are neglected, resulting in insufficient interpretation of the input data; the research period is divided into the base period and the period affected by human activities, that is, it is assumed that the watershed is not affected by human activities during the base period, and the basin is not affected by human activities during the period affected by human activities. , the river basin is affected by the same degree of human activities every year, but in fact the runoff or sediment transport in the river basin is affected by human activities in different degrees in different years; According to the principle, the calculated value of runoff or sediment transport during the period affected by human activities is calculated, and the difference between the calculated value and the actual value is interpreted as the error caused by human activities, but in fact it also includes the error caused by the model structure. The contribution rate of human activities calculated by the empirical model is not accurate
If you choose a fixed rate period, the obtained model parameters are the optimal parameters in the rate period, but it cannot be guaranteed to be the optimal parameter in the simulation period, which may cause overfitting
Therefore, when using the parameters obtained regularly by the rate to simulate the future situation, it may cause a large error

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An intelligent ensemble assessment method and system for basin water and sediment research models
  • An intelligent ensemble assessment method and system for basin water and sediment research models
  • An intelligent ensemble assessment method and system for basin water and sediment research models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1-4 and comparative example 1-2

[0096] Examples 1-4 and Comparative Examples 1-2: An ensemble evaluation method for research models of runoff change in the Huangfuchuan River Basin

[0097] The first step is to establish the research object: a study on the runoff change in the Huangfuchuan River Basin from 1982 to 2015, with a total of 408 samples. On the annual and monthly scales, this paper selects three methods: Multiple Linear Regression (MLR), kNN Regression (kNNR) and Support Vector Regression (SVR). The output variable is selected as runoff, and the input variables are precipitation, evapotranspiration, and human activities. There are three types of variables. The time scale is selected as annual scale and monthly scale, and the established research objects are shown in Table 1.

[0098] Table 1 Selection of variables related to water-sediment change in the Huangfuchuan River Basin

[0099]

[0100] The second step is to screen the optimal model: use three different machine learning methods to ob...

Embodiment 5-8 and comparative example 3-4

[0125] Examples 5-8 and Comparative Examples 3-4: An ensemble evaluation method for research models on sediment transport changes in the Huangfuchuan River Basin

[0126] The first step is to establish the research object: to study the change of sediment discharge in the Huangfuchuan River Basin, three models of multiple linear regression, kNN regression and support vector regression are selected on the annual and monthly scales.

[0127] The second step is to screen the optimal model: At the same time, different types of independent variable combinations are selected, and a total of 12 groups of sand transport models are trained, covering 12 situations, as shown in Table 6.

[0128] Table 6 Multi-angle research on sediment transport changes in the Huangfuchuan River Basin

[0129]

[0130]

[0131] Remarks: The monthly sediment discharge data from 1991 to 1994 are missing.

[0132] Models were generated in the same manner as in Examples 1-4, and an optimal model for ea...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An intelligent ensemble evaluation method and system for water and sediment research models in a watershed, comprising the following steps: (1) establishing the research object, including the watershed, dependent variable, independent variable and time scale; (2) screening the optimal model: the watershed to be established After random scrambling, the water and sand dataset is divided into training set and test set. Different machine learning methods are selected and divided into multiple groups under different time scales and different combinations of independent variables to cover all possible situations. Each situation is passed Obtain parameters and screen to obtain a set of optimal models, each method then selects a set of best results as the final optimal model; (3) Evaluate the final optimal model based on three different index systems, the index system includes infinite The dimension index and dimension index are used to evaluate the goodness of the model, and the evaluation index based on the minimum information criterion is used to balance the goodness and complexity of the model fitting results. A unified standard is used to give quantitative evaluation results on the applicability of various types of models in the collection.

Description

technical field [0001] The invention belongs to an aggregate evaluation technical system, and in particular relates to an intelligent aggregate evaluation method and system for a river basin water and sediment research model. Background technique [0002] Since the 21st century, the water and sediment conditions of the Yellow River have undergone unprecedented drastic changes. The in-depth analysis of the water and sediment situation of the Yellow River is of great significance. It is related to the direction of the wide reach of the lower reaches of the Yellow River, the allocation and utilization strategies of the Yellow River's water resources, the layout of the water and sediment control projects, and the establishment of the overall Yellow River control strategy. Commonly used empirical models and process-based physical models, etc., can all show that the change of water and sediment in the Yellow River is the result of the combined effects of human activities and clima...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/18G06Q10/06G06Q50/00
CPCG06F17/18G06Q10/06393G06Q50/00
Inventor 徐梦珍刘星傅旭东张晓明王紫荆赵阳
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products