RAINFALL PREDICTION USING MULTIPLE LINEAR REGRESSION ALGORITHM
In one sentence. Multiple linear regression predicts Yogyakarta daily rainfall from temperature, humidity, wind and sunshine, reaching an R2 of only 12.99%.
Abstract
Indonesia is a tropical region with ever-changing weather changes. It is necessary to conduct a research on weather prediction as a decision making regarding weather information that will occur in the future. Rainfall is one of the factors that cause changes in weather in an area. This research was conducted on the climate in the Yogyakarta region in the form of mountains and lowlands causing differences in rainfall. The variables that are used to make predictions are several parameters that affect rainfall, namely temperature, humidity, wind speed and duration of solar radiation. These 5 variables are processed through the data obtained then carried out research and comparisons with the previous data. Multiple linear regression is the algorithm used. This algorithm is one of the machine learning techniques by making rainfall data as the dependent variable and other parameters as independent variables. This study uses Yogyakarta City, Central Java climate data for 2010-2020. The results obtained are an R2 score of 12.99%. Prediction of rainfall is obtained at 14.41778516. Then the RMSE evaluation resulted in a deviation between predicted rainfall and actual rainfall of 14.78316110508722. Based on these results, it shows that there is light rain because it is in the intensity category of 5 mm – 20 mm/day.
Labels
- Topic
- Local & station forecasting
- Type
- Application study
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days
- Domain
- Local / station
- Data
- Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.33480/jitk.v9i1.4203 OpenAlex:W4385634029
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.