Prediksi Curah Hujan Di Kabupaten Kupang Menggunakan Metode Simple Linear Regression

BATARA, Zenonissya Galwan (2024) Prediksi Curah Hujan Di Kabupaten Kupang Menggunakan Metode Simple Linear Regression. Undergraduate thesis, Universitas Katolik Widya Mandira Kupang.

	Text ABSTRAK.pdf Download (1MB)
	Text BAB I.pdf Download (319kB)
	Text BAB II.pdf Restricted to Repository staff only Download (605kB) | Request a copy
	Text BAB III.pdf Restricted to Repository staff only Download (438kB) | Request a copy
	Text BAB IV.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text BAB V.pdf Download (197kB)
	Text DAFTAR PUSTAKA.pdf Download (555kB)

Abstract

Kupang Regency is experiencing the challenges of an uncertain rainy season that will have a significant impact on residents' daily activities. Rainfall plays a pivotal role in the socio-economic dynamics, from clean water management to disaster mitigation. This research investigates how temperature affects rainfall in Kupang Regency. The objective is to assess the degree to which air temperature can account for changes in rainfall patterns. In machine learning, linear regression algorithms are used to predict continuous values for one predictor variable used. Rainfall modeling has been applied to data obtained from Tardamu Meteorological Station, Kupang Regency involving two variables, namely total rainfall per month as the response variable and average air temperature per month as the predictor variable. The research dataset consists of 3773 climates over a 10-year period (2011-2021). The data source is the BMKG website which can be accessed on the online data platform (www.bmkg.go.id). The dataset is partitioned into training and testing subsets, with 80% allocated for training and 20% for testing. A linear regression algorithm was developed using the Python programming language by the Google Colab service and the following equation was obtained Y = -658.508 + 26.314X. The model evaluation is shown by the Mean Square Error (MSE) value was 12810.603, Root Mean Square Error (RMSE) was 113.183 and Mean Absolute Error (MAE) was 83.966. Based on accuracy metrics, the development of prediction models in this study has not been able to grasp the relationship between average temperature and rainfall. The analysis clearly shows that temperature does not make a considerable contribution in explaining rainfall variations. As a result, the resulting prediction model tends to provide higher than actual rainfall estimates (over-forecast). Thus, it can be said that the simple linear regression method has a low performance for predicting rainfall events in Kupang Regency.

Actions (login required)

View Item