Kernel extreme learning machine flood forecast method based on sparse self-encoding

Abstract

The invention discloses a kernel extreme learning machine flood forecast method based on sparse self-encoding. The method comprises the following steps that (1) medium and small river flood data are selected, and the data are collated and cleaned; (2) the appropriate forecast factors are selected and samples are collated, and the sample data are preprocessed; (3) unsupervised learning is performedon the original sample data through a multilayer sparse self-encoder, and the optimal network layer parameters are trained; and (4) the sample data through multilayer sparse self-encoding learning act as the input of a KELM model, an SAE_KELM model is constructed and the corresponding result is predicted and evaluated. The SAE method is fused on the basis of the KELM model, a deep network model is constructed, and the abundant intrinsic information between the complex data can be learnt by increasing the number of layers of the model. The "essential" characteristics of the original hydrological data can be learnt by the SAE_KELM model, the learnt characteristics have more essential depiction for the data, and the mapping relationship between the characteristic value and the target value can be better fit by the KELM model.

Description

technical field [0001] The invention relates to the technical field of hydrological forecasting, in particular to a kernel extreme learning machine flood forecasting method based on sparse self-encoding. Background technique [0002] Flood forecasting is the most important non-engineering measure for disaster prevention and mitigation. It has played an important role in flood control and drought relief, water resource management and protection, and water engineering operation management over the years, and has achieved remarkable economic and social benefits. However, the flood process is affected by many factors such as natural geography, hydrology, meteorology, human activities, etc., and has a high degree of complexity and uncertainty. Therefore, it is an urgent problem to be solved to accurately forecast the water and rainfall conditions in order to generate a dispatching plan. [0003] In recent years, deep learning has been widely studied and applied to various fields,...

AI Technical Summary

Problems solved by technology

However, the flood process is affected by many factors such as natural geography, hydrology, meteorology, and human activities in the basin, and has a high degree of complexity and uncertainty. Therefore, it is an urgent problem to be solved to accurately forecast the water and rain conditions in order to generate a dispatching plan.

[0003] In recent years, deep learning has been widely studied and applied to various fields, but the application of deep learning in hydrological forecasting is less, so the prospect of applying it in hydrological forecasting is optimistic

Images