Runoff prediction method based on attention mechanism and LSTM

Abstract

The invention discloses a runoff prediction method based on an attention mechanism and LSTM by using a deep learning algorithm. The method comprises the following steps: firstly, collecting influence characteristics related to runoff in a drainage basin, then constructing a time sequence data set corresponding to the characteristics and runoff, obtaining a runoff prediction model based on an attention mechanism and LSTM through training, and predicting the subsequent runoff according to the obtained runoff prediction model. Meanwhile, some short-term important features are ignored when the LSTM memorizes a long-term sequence mode, so that an attention mechanism is added, key elements in a runoff sequence are selectively concerned, the capability of capturing effective features by the LSTM is improved, and the prediction precision is relatively high. In addition, a deep learning method driven by data is used, dependence on a hydrological and physical mechanism in a drainage basin is reduced, and the application range of the model is effectively expanded.

Description

technical field [0001] The invention belongs to the field of hydrology and water resources, and more specifically, relates to a deep neural network based on attention mechanism and LSTM to predict the change of runoff. Background technique [0002] Water resources are the main carrier of life on earth and one of the important natural resources supporting social and economic development and the progress of ecological civilization. Water resources are different from other resources in that it is a dynamic resource that changes with time and space. my country has a vast territory. Due to the extremely uneven distribution of water resources in time and space, this will lead to dry weather and little rain in some areas, while natural disasters such as floods will occur in other areas. For example, the South-to-North Water Diversion Project was built to solve the water shortage in some areas in the north. Therefore, water resources management and protection, planning and utiliza...

AI Technical Summary

Problems solved by technology

However, the simulation of hydrological models requires an accurate understanding of the hydrological structure within the watershed, such as the underlying surface conditions of the watershed, the temporal and spatial variation conditions of rainfall, and the boundary conditions of the watershed, etc. There are many input variables and parameters, such as time, space, and geographical conditions, which are difficult to apply universally.

However, various complex conditions and the impact of human activities make the hydrological time series have more complex patterns. Therefore, it is difficult for traditional runoff prediction methods to accurately simulate highly complex nonlinear hydrological series.

Images