Analisis Kontribusi Sensor IoT pada Deteksi Kebakaran Lahan Gambut Menggunakan Random Forest dan SHAP
-
Hirzen Hasfani
*
Universitas Tanjungpura, Pontianak,
Indonesia
- Kartika Sari Universitas Tanjungpura, Pontianak, Indonesia
- Rahmi Hidayati Universitas Tanjungpura, Pontianak, Indonesia (*) Corresponding Author
Abstract
Peatland fires are disasters that impact the environment, health, and socio economic activities. Internet of Things (IoT) based early detection enables real-time monitoring of environmental conditions through various sensors. However, the specific contribution of each sensor to the detection process remains unclear. This study aims to analyze the contribution of multiple sensors within an IoT-based peatland fire detection system using the Random Forest (RF) algorithm. The dataset comprises 2,000 primary data points obtained from AMG8833, MAX6677, MQ-2, DHT22, and Water Float sensors. The model was trained on the primary data and tested against data representing transitional (overlapping) conditions between normal states and fire events. Model performance was evaluated using accuracy, precision, recall, F1-score, and a confusion matrix, while sensor contributions were analyzed via Feature Importance and validated using SHapley Additive exPlanations (SHAP). The results indicate that the RF model achieved an accuracy of 87.50%, precision of 100.00%, recall of 75.00%, and an F1-score of 85.71%. Feature Importance and SHAP analyses revealed that the DHT22 sensor (measuring humidity and temperature) made the most significant contribution, followed by the MAX6677, MQ-2, AMG8833, and Water Float sensors. These findings demonstrate that temperature and humidity serve as key indicators for peatland fire detection and provide a foundation for developing IoT-based detection systems.
Downloads
References
S. Tarigan, N. P. Zamani, D. Buchori, and R. Kinseng, “Peatlands Are More Bene fi cial if Conserved and Restored than Drained for Monoculture Crops,” Front. Environ. Sci., vol. 9, no. November, pp. 1–12, 2021, doi: 10.3389/fenvs.2021.749279.
J. Loisel and A. Gallego-sala, “Ecological resilience of restored peatlands to climate change,” Commun. Earth Environ., vol. 3, no. September, pp. 1–8, 2022, doi: 10.1038/s43247-022-00547-x.
A. P. G. Hognogi and E. Hada, “Bridging Stakeholder Narratives for Sustainable Peatland Conservation,” Earth Syst. Environ., pp. 5–7, 2026, doi: https://doi.org/10.1007/s41748-026-01141-3.
M. Yunus, “A critical review of peatland ecosystem services research in Indonesia : Uncovering knowledge gaps and research needs,” J. Bulg. Geogr. Soc., vol. 50, pp. 169–190, 2024, doi: 10.3897/jbgs.e117635.
M. Osaki, N. Tsuji, N. Foead, and J. Rieley, Tropical Peatland Eco-management. Singapore: Springer, 2021. doi: https://doi.org/10.1007/978-981-33-4654-3.
B. Kartiwa et al., “Peat Hydrological Properties and Vulnerability to Fire Risk,” MDPI, vol. 9, no. 1, pp. 1–18, 2026, doi: https://doi.org/10.3390/fire9010024.
J. le Roux et al., Development Of Management And Rehabilitation Protocols For Peatlands In South Africa : Case Studies Of Peat Fires. Pretoria: Water Research Commision, 2023.
M. B. R. Prayoga, M. Karuniasa, and E. Frimawaty, “Peatland wetness as an indicator of fire occurrence in Forest and Land Fires ( FLFs ),” J. Earth Kingdom, vol. 2, no. 1, pp. 62–78, 2024, doi: doi.org/10.61511/jek.v2i1.2024.873.
S. L. A, Y. L. A, and X. H. A, “How to Build a Firebreak to Stop Smouldering Peat Fire : Insights from a Laboratory-Scale Study,” Int. J. Wildl. Fire, vol. 30, no. 6, pp. 454–461, 2021, doi: https://doi.org/10.1071/WF20155.
G. Rein and X. Huang, “ScienceDirect Smouldering wildfires in peatlands , forests and the arctic : Challenges and perspectives,” Curr. Opin. Environ. Sci. Heal., vol. 24, no. 100296, pp. 1–10, 2021, doi: 10.1016/j.coesh.2021.100296.
Rosyida and Y. Sopiana, “Dampak Kebakaran Lahan Gambut terhadap Perekonomian Masyarakat di Kecamatan Gambut Kabupaten Banjar,” JIEP J. Ilmu Ekon. dan Pembang., vol. 4, no. 2, pp. 463–475, 2021.
I. P. Anhar, R. Mardiana, and R. Sita, “Dampak Kebakaran Hutan dan Lahan Gambut terhadap Manusia dan Lingkungan Hidup ( Studi Kasus : Desa Bunsur , Kecamatan Sungai Apit , Kabupaten Siak , Provinsi Riau ) The Impact of Forest and Peatland Fires on Humans and The Environment ( Case Study : Villa,” J. Sains Komun. dan Pengemb. Masy., vol. 6, no. 1, pp. 75–85, 2022, doi: doi.org/10.29244/jskpm.v6i1.967.
J. Listari, P. Sudira, R. Ananda, R. F. Saputra, and Fatmawati, “Efek Kebakaran Hutan Terhadap Lingkungan Hidup Dan Sumber Daya Alam Di Pekanbaru,” Sci. J. Ilm. Sains dan Teknol., vol. 3, no. 1, pp. 658–671, 2024, [Online]. Available: https://jurnal.kolibi.org/index.php/scientica/article/view/3896
B. Sudrajat, F. R. Doni, and A. M. Lukman, “Pemanfaatan Internet of Things ( IoT ) dalam Sistem Pemantauan Prediktif Peralatan Industri,” REMIK Ris. Dan E-Jurnal Manaj. Inform. Komput., vol. 9, no. 4, pp. 1233–1240, 2025, doi: 10.33395/remik.v9i4.15319.
D. N. Azizah, S. Heranurweni, L. Ode, and M. Idris, “Internet of Things Based Air Quality Monitoring System with Automatic Notification,” Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 3, pp. 776–787, 2025, doi: https://doi.org/10.57152/malcom.v5i3.1945.
G. Deshpande et al., “IoT- Based Low-Cost Soil Moisture and Soil Temperature Monitoring System,” in ICCUBEA, 2022, p. 8. doi: https:doi.org/10.48550/arXiv.2206.07488.
H. Liu, R. Y. Chang, Y. Chen, and I. Fu, “Sensor-Based Satellite IoT for Early Wildfire Detection,” in IEEE Globecom Workshops, Madrid, Spain: IEEE, 2021. doi: 10.1109/GCWkshps52748.2021.9682098.
J. Waworundeng, “IoT-based Environmental Monitoring with Data Analysis of Temperature , Humidity , and Air Quality,” CogITo Smart J., vol. 10, no. 1, pp. 271–284, 2024, [Online]. Available: https://www.researchgate.net/publication/383009320_IoT-based_Environmental_Monitoring_with_Data_Analysis_of_Temperature_Humidity_and_Air_Quality
S. Usman, R. L. Atimi, M. Anhar, and A. Susanto, “Low-Cost LoRaWAN Solution for Groundwater Monitoring in Peatlands,” J. Inf. Syst. Informatics, vol. 6, no. 4, pp. 2777–2793, 2024, doi: 10.51519/journalisi.v6i4.923.
M. Irfan et al., “Peatland Hydro-Climatological Parameters Variability in Response to 2019 – 2022 Climate Anomalies in the OKI Regency,” Atmos. MDPI, vol. 16, no. 81, pp. 1–15, 2025, doi: https://doi.org/10.3390/atmos16010081.
K. Exaudi et al., “An Improved Forest Fire Detection Model Using Audio Classification and Machine Learning,” Comput. Mater., vol. 86, no. 1, pp. 1–24, 2026, doi: 10.32604/cmc.2025.069377.
S. Han, B. D. Williamson, and Y. Fong, “Improving Random Forest Predictions in Small Datasets From Two-Phase Sampling Designs,” BMC Med. Inform. Decis. Mak., vol. 21, no. 322, pp. 1–9, 2021, doi: https://doi.org/10.1186/s12911-021-01688-3.
E. Scornet, Trees, forests, and impurity-based variable importance. HAL Open Science, 2021, pp. 1–40. doi: https://doi.org/10.48550/arXiv.2001.04295.
M. Li, H. Sun, Y. Huang, and H. Chen, “Shapley Value: From Cooperative Game to Explainable Artificial Intelligence,” Auton. Intell. Syst., vol. 4, no. 2, pp. 1–12, 2025, doi: https://doi.org/10.1007/s43684-023-00060-8.
S. Moslehi, N. Rabiei, A. R. Soltanian, and M. Mamani, “Forest Fire Prediction using Random Forest Shahwan,” Eng. Technol. J., vol. 10, no. 5, pp. 5159–5164, 2022, doi: 10.1186/s12911-022-01939-x.
R. A. Disha and S. Waheed, “Application of machine learning models based on decision trees in classifying the factors affecting mortality of COVID-19 patients in Hamadan, Iran,” BMC Med. Inform. Decis. Mak., vol. 22, no. 192, pp. 1–12, 2022.
R. A. Disha and S. Waheed, “Performance Analysis Of Machine Learning Models For Intrusion Detection System Using Gini Impurity-Based Weighted Random Forest (GIWRF) Feature Selection Technique,” Disha and Waheed Cybersecurity, vol. 5, no. 1, pp. 1–22, 2022, doi: https://doi.org/10.1186/s42400-021-00103-8.
H. Yi-Xiao, S.-H. Lyu, and Y. Jiang, “Interpreting Deep Forest through Feature Contribution and MDI Feature Importance,” ACM J., vol. 20, no. 1, pp. 1–21, 2025, doi: https://doi.org/10.1145/3641108.
A. V. Ponce-Bobadilla, V. Schmitt, C. S. Maier, S. Mensing, and S. Stodtmann, “Practical Guide To SHAP Analysis: Explaining Supervised Machine Learning Model Predictions In Drug Development,” Clin. Transl. Sci. Publ., vol. 17, no. e70056, pp. 1–15, 2024, doi: 10.1111/cts.70056.
C. Molnar, Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, 3rd ed. 2025. [Online]. Available: https://christophm.github.io/interpretable-ml-book
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Kontribusi Sensor IoT pada Deteksi Kebakaran Lahan Gambut Menggunakan Random Forest dan SHAP
Pages: 1121-1128
Copyright (c) 2026 Hirzen Hasfani, Kartika Sari, Rahmi Hidayati
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
