Prediksi Kebakaran Hutan Ibu Kota Nusantara Menggunakan Produk MODIS dengan Algoritma Regresi Linear, Gradient Boosting dan Decision Tree
Abstract
Forest Fires in the Capital City of the Archipelago (IKN) threaten environmental sustainability and sustainable development, but accurate predictions are still hampered by the complexity of trigger factors such as weather variability and data uncertainty, so this study aims to develop a machine learning-based forest fire prediction model by utilising MODIS (Moderate Resolution Imaging Spectroradiometer) data, including surface temperature and thermal anomalies, by comparing three algorithms namely Linear Regression, Gradient Boosting Regressor (GBR), and Decision Tree Regressor (DTR). Performance evaluation using RMSE (Root Mean Square Error) and accuracy metrics showed GBR as the best model with 98.84% accuracy followed by DTR 96.39%, while R² values close to 1.0 in both models indicated the ability to explain data variability optimally, in contrast to linear regression which showed significant limitations. Thus, these findings prove the superiority of ensemble algorithms such as GBR in handling non-linearity of forest fire data and have practical implications on its potential integration into early warning systems to improve the effectiveness of fire mitigation around the IKN region.
Kebakaran Hutan di Ibu Kota Nusantara (IKN) mengancam kelestarian lingkungan dan pembangunan berkelanjutan, namun prediksi akurat masih terhambat oleh kompleksitas faktor pemicu seperti variabilitas cuaca dan ketidakpastian data, sehingga penelitian ini bertujuan mengembangkan model prediksi kebakaran hutan berbasis machine learning dengan memanfaatkan data MODIS (Moderate Resolution Imaging Spectroradiometer), termasuk suhu permukaan dan anomali termal, dengan membandingkan tiga algoritma yaitu Regresi Linear, Gradient Boosting Regressor (GBR), dan Decision Tree Regressor (DTR). Evaluasi performa menggunakan metrik RMSE (Root Mean Square Error) dan akurasi yang menunjukan GBR sebagi model terbaik dengan akurasi 98,84% diikuti DTR 96,39%, sementara nilai R² mendekati 1.0 pada kedua model mengindikasikan kemampuan menjelaskan variabilitas data secara optimal, berbeda dengan regresi linear yang menunjukkan keterbatasan signifikan, sehingga temuan ini membuktikan keunggulan algoritma seperti GBR dalam menangani non-linearitas data kebakaran hutan dan berimplikasi praktis pada potensi integrasinya ke dalam sistem peringatan dini untuk meningkatkan efektivitas mitigasi kebakaran di sekitar wilayah IKN.
Keywords
Full Text:
PDFReferences
Daffa, M., Satria Yudha Kartika, D., Permatasari, R., Pembangunan Nasional, U., Timur, J., Rungkut Madya, J., & Anyar, G. (2022). Penerapan folium untuk visualisasi hasil clustering persebaran tindakan kriminal di Kota Surabaya. JUITIK, 2(3). https://journal.sinov.id/index.php/juitik/index
Halbouni, A., Gunawan, T. S., Habaebi, M. H., Halbouni, M., Kartiwi, M., & Ahmad, R. (2022). Machine Learning and Deep Learning Approaches for cybersecurity: A review dalam IEEE Access (Vol. 10, hlm. 19572–19585). Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ACCESS.2022.3151248
Husen, D., Sandi, D., & Bumbungan, S. (2022). Analisis Prediksi Kebakaran Hutan dengan Menggunakan Algoritma Random Forest Classifier. 16(1). https://journal.uniku.ac.id/index.php/ilkom
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2021). 1D convolutional neural networks and applications: A survey. Mechanical Systems and Signal Processing, 151. https://doi.org/10.1016/j.ymssp.2020.107398
López, O. A. M., Montesinos López, A., & Crossa, J. (2022). Multivariate statistical machine learning methods for genomic prediction. Dalam Multivariate Statistical Machine Learning Methods for Genomic Prediction. Springer International Publishing. https://doi.org/10.1007/978-3-030-89010-0
Najicha, F. U., Gusti, I., Ketut, A., & Handayani, R. (2021). Analysis of law enforcement and control effort about forest fire in west Kalimantan Province. https://doi.org/10.33172/jmb.v7i1.692
Saidani, O., Menzli, L. J., Ksibi, A., Alturki, N., & Alluhaidan, A. S. (2022). Predicting student employability through the internship context using gradient boosting models. IEEE Access, 10, 46472–46489. https://doi.org/10.1109/ACCESS.2022.3170421
Salam, M. A., Azar, A. T., Elgendy, M. S., & Fouad, K. M. (2021). The effect of different dimensionality reduction techniques on machine learning overfitting problem. International Journal of Advanced Computer Science and Applications, 12(4), 641–655. https://doi.org/10.14569/IJACSA.2021.0120480
Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random forest algorithm overview. Babylonian Journal of Machine Learning, 2024, 69–79. https://doi.org/10.58496/bjml/2024/007
Shen Ruiyun. (2022). Application of MODIS data-based forest fire monitoring and assessment. Dalam Highlights in Science, Engineering and Technology MSESCS (Vol. 2022).
Tran, M. K., Panchal, S., Chauhan, V., Brahmbhatt, N., Mevawalla, A., Fraser, R., & Fowler, M. (2022). Python based scikit learn machine learning models for thermal and electrical performance prediction of high-capacity lithium-ion battery. International Journal of Energy Research, 46(2), 786–794. https://doi.org/10.1002/er.7202
Wahyu, A., & Frinaldi, A. (2024). Analisa dampak lingkungan ibu Kota Nusantara. 01(2), 29–33. https://jurnal.kopusindo.com/index.php/jkhkb
Wicaksono, A., Prihatin, P. S., Febrian, R. A., & Mulianto, B. (2024). Sipongi system: Navigating and fostering collaboration in Indonesia. Journal of Infrastructure, Policy and Development, 8(3). https://doi.org/10.24294/jipd.v8i3.2875
Xiong, X., Angal, A., Chang, T., Chiang, K., Lei, N., Li, Y., Sun, J., Twedt, K., & Wu, A. (2020). Modis and viirs calibration and characterization in support of producing long term high-quality data products. Remote Sensing, 12(19), 1–28. https://doi.org/10.3390/rs12193167
Nurpratama, Y. F., Dhian Satria Yudha Kartika, & Reisa Permatasari. (2023). Implementasi folium pada hasil klaster diabetes mellitus di Puskesmas Modopuro. Jurnal Ilmiah Teknik Informatika dan Komunikasi, 3(3), 74–85. https://doi.org/10.55606/juitik.v3i3.623
Zheng, Y., Zhang, G., Tan, S., & Feng, L. (2023). Research on progress of forest fire monitoring with satellite remote sensing. Agricultural & Rural Studies, 1(2), 0008. https://doi.org/10.59978/ar01020008
Zou, D., Yan, K., Pu, J., Gao, S., Li, W., Mu, X., Knyazikhin, Y., & Myneni, R. B. (2022). Revisit the performance of MODIS and VIIRS. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 8958–8973. https://doi.org/10.1109/JSTARS.2022.3214224
DOI: https://doi.org/10.37905/jji.v1i1.30926
Refbacks
- There are currently no refbacks.
JJIhas been indexed by:
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Editorial Office |
Engineering Faculty Building, 1st Floor Jl. Prof. Dr. Ing. B. J. Habibie, Bone Bolango, Gorontalo, 96119, Indonesia. Whatsapp: +6281314270499 Email: jji.ft@ung.ac.id |
![]() |
|