Flood Prediction and Analysis on the Relevance of Features using Explainable Artificial Intelligence

Abstract

This paper presents flood prediction models for the state of Kerala in India by analyzing the monthly rainfall data and applying machine learning algorithms including Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forests, and Support Vector Machine. Although these models have shown high accuracy prediction of the occurrence of flood in a particular year, they do not quantitatively and qualitatively explain the prediction decision. This paper shows how the background features are learned that contributed to the prediction decision and further extended to explain the models with the development of explainable artificial intelligence modules such as SHAP and LIME. The obtained results have confirmed the validity of the findings uncovered by the explainer modules basing on the historical flood monthly rainfall data in Kerala