•  
  •  
 

Corresponding Author ORCID Identifer

Sellappan Palaniappan https://orcid.org/0009-0009-1168-2864

Section

Regular Issue

Abstract

In this paper, we present a Random Forest classifier machine learning model for predicting short-range weather in in tropical regions like Malaysia. Our model uses environmental factors such as temperature, humidity, wind speed, and cloud cover to predict weather conditions like clear skies, rain, and thunderstorms. Tropical weather, influenced by high humidity, fluctuating temperatures, and frequent rainfall, present unique challenges for forecasting accurately. To address these challenges, we trained a Random Forest classifier on a synthetic (simulated) dataset comprising 1,500 samples, each representing a specific weather scenario. Our model achieved an accuracy of 98.66% in predicting short-term weather conditions, identifying cloud cover, precipitation intensity, and humidity as the most influential factors. Our model’s high accuracy demonstrates its potential for predicting short-range weather conditions in tropical regions. Potential applications of the model spans sectors like agriculture, energy, tourism, disaster management, and public health. In agriculture, the model can be used to optimize irrigation schedules and crop management. In the energy sector, it can be used to optimize energy production and distribution. In disaster management, it can alert residents of impending bad weather, so they are more prepared. In the health sector, it can provide timely weather alerts and assist those who are more prone to arthritis and migraine attacks. We can enhance the model by using real-world data and regional customization.

Download

Share

COinS