Article Per Year (5 Year)
p-Index From 2020 - 2025
1.325
P-Index
This Author published in this journals
All Journal CARTESIUS : Jurnal Pendidikan Matematika Jurnal Kridatama Sains dan Teknologi Jurnal Crystal : Publikasi Penelitian Kimia dan Terapannya Leibniz: Jurnal Matematika Cartesius Balance : Media Informasi Akuntansi dan Keuangan Jurnal kiprah pendidikan
Sukmarini, Mita Akbar
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Economics, Econometrics & Finance Education Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Kridatama Sains dan Teknologi

 1 
Extreme Gradient Boosting pada Peramalan Pola Curah Hujan Bulanan Kabupaten Banyuwangi Fauziah, Ana; Hermanto, Hermanto; Sukmarini, Mita Akbar
Jurnal Kridatama Sains dan Teknologi Vol 6 No 02 (2024): JURNAL KRIDATAMA SAINS DAN TEKNOLOGI
Publisher : Universitas Ma'arif Nahdlatul Ulama Kebumen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53863/kst.v6i02.1154

Abstract

Long-term meteorological data is very useful for identifying signs of climate change phenomena. The phenomenon refers to long-term changes in the physical conditions of the Earth's atmosphere, such as temperature and weather patterns. This has a huge impact, especially in Banyuwangi, which is one of the largest rice production areas in East Java. Predicting monthly rainfall trends is important to anticipate crop failures due to extreme weather and natural disasters such as floods and landslide. This research uses weather parameters on a global scale, such as temperature, rain, evaporation, surface humidity, and sea level pressure, while for local-scale information, it uses monthly rainfall data in the Banyuwangi area from 2011 to 2023.The extreme gradient boosting (XGBoost) method will be used to predict monthly rainfall in an ensemble learning model based on the boosting approach. In particular, this study emphasizes its ability to build predictive models on limited time series and the impact of data splitting on model performance. The best results were shown by the model with a data split ratio of 1:12, or covering 80% of the data as training data. The model accuracy achieved a MAE of 72.579 mm in training and 80.777 mm in testing. In addition, the RMSE was 95.940 mm in training and 95.775 mm in testing. The results of this study are expected to be a reference for building a more optimal long-term weather forecast model.
Co-Authors Ana Fauziah Hermanto Hermanto Hermanto Hermanto Hermanto Mahar, Alicia Christina Muh. Husriadi Nurjanah, Ana Wilda, Robiatul Witari