Abstract: Rainfall forecasting plays an important role in increasing agricultural production and decreasing associated risks resulting from climate change. This is especially because traditional approaches to rainfall forecasting often do not adequately capture the complex and nonlinear features of climate change. Hence, this research examines the applicability of using machine learning algorithms, such as decision tree regressors, for the yearly and monthly rain events based on the historical climate and geographical information. Apart from incorporating agricultural analysis to advise potential appropriate crops in accordance with the expected amount of rainfall, type of soil, as well as its pH level, the proposed application also brings experimental results affording better tools for decision-making for farmers and other stakeholders in the agricultural field. This study illustrates the possibility of applying quantitative approaches to promote sustainable farming practices and, therefore, achieve food security in conditions when weather patterns become volatile.
Keywords: Rainfall Prediction, Machine Learning, Decision Tree Regressor, Agricultural Analysis, Crop Recommendation.
|
DOI:
10.17148/IJARCCE.2025.14123
