Rainfall Prediction Using Logistic Regression and Random Forest Algorithm
Authors:
- 9 February 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5, 663-668
Abstract
Accurate rainfall forecasts are important throughout Agriculture, Water Resources, and Disaster preparation. In this example, we use two complex devices study design, Logistic Regression and Random Forest classifier, to predict rainfall in Australia. The data set source for this study came from Kagle, which provides a complete summary of climate changes over time. The aim of our research is to develop a robust prediction model concerning possible precipitation types Australian territories. Logistic Regression provides a baseline model, while the Random Forest Classifier provides an ensemble based the technique improves accuracy. We look for the content engineering and hyperparameter tuning to improve the model performance. The results of this study are important for decision makers and stakeholders, as accurate rainfall forecasts can provide to strengthen resource management, risk reduction and sustainability planning in different areas. The results of our models is that it will contribute to a better understanding of Australian rainfall Patterns, therefore helps in effective decision making and preparation.Keywords
This publication has 6 references indexed in Scilit:
- Rainfall Prediction using Machine LearningInternational Journal for Research in Applied Science and Engineering Technology, 2022
- Machine learning techniques to predict daily rainfall amountJournal of Big Data, 2021
- Comparison of random forests and support vector machine for real-time radar-derived rainfall forecastingJournal of Hydrology, 2017
- Heuristic prediction of rainfall using machine learning techniques2017
- A rainfall prediction model using artificial neural network2012
- A prominent pattern of year-to-year variability in Indian Summer Monsoon RainfallProceedings of the National Academy of Sciences, 2012