Published Paper Details:

Rainfall is of utmost importance in agriculture, but predicting it accurately has become a significant challenge in recent times. Accurate forecasts of precipitation provide valuable insights in advance, enabling individuals to take necessary precautions and devise better crop strategies. The impact of global warming on nature and humanity has accelerated changes in climatic conditions, resulting in adverse effects such as flooding and drought. As a result, accurately predicting rainfall has become one of the best techniques to understand the climate. However, forecasting precipitation is a demanding and uncertain task that significantly impacts human society. Precise and timely predictions can proactively mitigate potential human and financial losses. To address this issue, a series of experiments were conducted using prevalent machine learning methods to construct models that anticipate whether it will rain the following day based on weather data for that day in major Australian cities. The outcomes offer a comparison of diverse evaluation metrics of these machine learning approaches and their capability to predict precipitation by scrutinizing the weather data. The study aims to provide accurate climate descriptions to clients from various domains such as agriculture, research, power generation, etc., to comprehend the need for climate transformation and its parameters, such as temperature, humidity, precipitation, and wind speed, which ultimately lead to rainfall predictions. It is essential to note that predicting rainfall is a challenging task that also depends on geographic location.