Multi-strategy improved snow ablation optimizer: a case study of optimization of kernel extreme learning machine for flood prediction

Abstract

The Kernel Extreme Learning Machine (KELM) has the advantage of automatically extracting data features, learning and processing nonlinear problems from historical data, which can help achieve better prediction results for flood prediction problems with complex and sudden causes. Traditional flood disaster prediction usually only considers one influencing factor without considering the complex factors that affect flood occurrence. This article develops a new method for predicting the probability of flood occurrence based on 20 influencing factors. Firstly, in order to better utilize KELM performance, an improved snow ablation optimization algorithm (MESAO) was proposed for subsequent experiments by introducing a level based selection pressure mechanism, covariance matrix learning strategy, historical position based boundary adjustment strategy, and random centroid reverse learning strategy into snow ablation optimization (SAO). Secondly, MESAO is used to perform hyperparameter optimization on the regularization coefficient C and kernel function parameter S of the KELM model. Finally, the construction of a multi feature input–output model for the application of MESAO-KELM in flood prediction problems was completed. In terms of hyperparameter optimization, the numerical experimental results of this method were superior to the prediction results of 10 other intelligent algorithms and 5 regression prediction models. According to the evaluation index results, the best adaptability of MESAO optimized KELM and higher prediction accuracy and stability compared to other prediction models were demonstrated. This method overcomes the limitations of traditional prediction models based on a single influencing factor and can predict the probability of flood occurrence based on complex and variable factors. It can be said that MESAO-KELM has strong generalization ability. Accurate flood prediction can provide early warning and take measures in advance to protect and reduce the impact of floods on human and social development.