A Hyperparameter Optimization Framework Using Optuna for XGBoost-based Drought Zone Classification in Flores Island

DOI

10.2991/978-94-6463-924-7_7How to use a DOI?

Keywords

Classification; XGBoost; Optuna; Hyperparameter; Drought Zone

Abstract

The purpose of this study is to classify drought zones on Flores Island, Indonesia, using the Extreme Gradient Boosting (XGBoost) algorithm. XGBoost is well known for its ability to handle tabular data with high complexity. However, previous studies have shown that the performance of XGBoost largely depends on the choice of hyperparameters. Therefore, in this study, XGBoost was combined with Optuna to identify the optimal hyperparameters during the modeling stage. The dataset was obtained from NASA POWER, covering the period 2015–2024, with a total of 27,214 daily climate records, which were preprocessed and categorized into wet, normal, and dry zones. The model was trained and tested using an 80/20 split, while Optuna was applied with 100 trials for hyperparameter tuning. The final model achieved 99.3% accuracy with balanced precision, recall, and F1-scores across all classes. Feature importance analysis highlighted humidity and maximum temperature, along with precipitation, as the most influential factors in classification. Overall, the study demonstrates that combining XGBoost with Optuna provides a robust framework for drought zone classification and offers valuable insights to support drought mitigation efforts on Flores Island.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Alfredo Ananta Turkaemli
AU  - Irfan Dwiguna Sumitra
PY  - 2025
DA  - 2025/12/16
TI  - A Hyperparameter Optimization Framework Using Optuna for XGBoost-based Drought Zone Classification in Flores Island
BT  - Proceedings of the 8th International Conference on Informatics, Engineering, Science & Technology (INCITEST 2025)
PB  - Atlantis Press
SP  - 64
EP  - 76
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-924-7_7
DO  - 10.2991/978-94-6463-924-7_7
ID  - Turkaemli2025
ER  -