The weather has a significant impact on many life aspects, one of which is agricultural industry and because of that, being able to predict it helps farmers in their day-to-day decisions such as how to plan efficiently, minimize costs and maximize yields.
A major agricultural company needs to have an accurate rain prediction algorithm that will improve their decision-making on typical farming activities such as planting and irrigating.
Using historical rain information from Australia regions in 10 years as research data, it is necessary to predict weather(rain) in next day.
- What factors and conditions in current day that will cause rain in the next day?
- What machine learning algorithms are suitable for predicting rain in the next day?
- Where is the location that has the highest frequency of rain?
- What is the impact of the predictive model for business problems that operating in the agricultural sector?
- Based on Heatmap and SHAP values for feature importances, Humidity at 3pm and Sunshine has the big impact to cause rain in the next day.
- Random Forest classifier is the best model algorithm for predicting rain the next day because have the highest AUC score than other classifier algorithm.
- The location with the most rain frequency is Portland with rain season tend to happen in May until August.
- Based on simulation, model performance can help saving company cost for water supply by 32%.