Claim Missing Document
Check
Articles

Development of Post Fire Severity Assessment Module in Indonesian Forest and Land Fire Prevention Patrol System Sitanggang, Imas Sukaesih; Hidayat, Assad; Syaufina, Lailan
Jurnal Manajemen Hutan Tropika Vol. 32 No. 1 (2026)
Publisher : Institut Pertanian Bogor (IPB University)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.7226/jtfm.32.1.97

Abstract

The severity of forest and land fires is a crucial indicator for assessing their impact on ecosystems, particularly vegetation and soil. The assessment results serve as a foundation for forest and land restoration, rehabilitation, and conservation efforts. This study employs a deep learning algorithm to develop a forest and land fire severity assessment module. The CNN model used is MobileNetV2 that has an accuracy of 88.8%. The smart module is integrated into the Indonesian Forest and Land Fire Prevention Patrol Mobile Application and follows the Software Development Life Cycle approach in its development. Field observation images are input to the CNN module in the mobile application. The module then analyzes the fire severity and classifies it into very light, light, moderate, severe, and very severe categories. Testing results indicate that the module accurately predicts fire severity based on established assessment standards. The optimal time for capturing images is a few days after the fire, during daylight hours, to ensure the majority of images depict burned areas. Additionally, the findings highlight that lighting conditions and image quality significantly influence the accuracy of severity predictions. Further development is required to enhance the module's compatibility and flexibility, enabling its use across various devices.
Hyperparameter tuning of MobileNetV2 on forest and land fire severity classification Hidayat, Assad; Sitanggang, Imas Sukaesih; Syaufina, Lailan
International Journal of Electrical and Computer Engineering (IJECE) Vol 16, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v16i2.pp964-972

Abstract

Forest and land fires pose significant environmental challenges, causing economic and ecological damage depending on their severity. This study proposes a deep learning-based classification model to assess fire severity using the MobileNetV2 architecture. A dataset of 560 post-fire images was categorized into five severity levels, with dataset preprocessing involving resizing, rescaling, and image augmentation. To enhance model performance, K-means clustering was applied for balanced data distribution across classes. The model was trained using grid search for hyperparameter tuning, with the optimal combination being a batch size of 8, learning rate of 0.0001, and dropout of 0.3. Training was conducted in 50 epochs, and evaluation using the confusion matrix demonstrated an accuracy of 85%, precision of 86%, and recall of 81%. The results indicate that MobileNetV2 effectively classifies post-fire severity levels, offering a reliable tool for post-disaster assessment. This study highlights the significance of dataset preprocessing and hyperparameter tuning in improving model accuracy. Future research should explore alternative architectures and expand the dataset to enhance model generalization. These findings can aid authorities in assessing fire impact, supporting mitigation strategies, and improving post-fire land management.
Forest and Peatland Fire Severity Assessment at Siak Regency, Riau Province using Sentinel-2 Imagery Afina, Fakhri Sukma; Syaufina, Lailan; Sitanggang, Imas Sukaesih
Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) Vol 11 No 4 (2021): Journal of Natural Resources and Environmental Management
Publisher : Pusat Penelitian Lingkungan Hidup, IPB (PPLH-IPB) dan Program Studi Pengelolaan Sumberdaya Alam dan Lingkungan, IPB (PS. PSL, SPs. IPB)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jpsl.11.4.621-630

Abstract

Siak Regency, Riau Province is one of the most forest and land fire-prone regencies in Indonesia. Most of the fires occur in peatland areas which contributes to the transboundary haze pollution in the region. Despite limited studies, fire severity assessment is an essential step in post-fire activities to estimate ecological impacts and economic impacts and law enforcement. This study aims to estimate fire severity using Sentinel-2 imagery at Siak Regency, Riau Province. The methods applied Normalized Burn Ratio on Sentinel-2 Imagery as an identification model based on reflectance value for 2019 imagery. The study revealed that burned areas in Siak Regency could be classified into four fire severity classes: low fire severity, moderate-low fire severity, moderate-high fire severity, and high fire severity. High fire severity was found mainly at Sungai Apit and Mempura Districts.
Sustainable analysis of integrated cajuput oil business development as a sustainable forestry multi-business at PT Inhutani I Syaufina, Lailan; Hariyadi; Ernawati, Titik
Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management) Vol 11 No 4 (2021): Journal of Natural Resources and Environmental Management
Publisher : Pusat Penelitian Lingkungan Hidup, IPB (PPLH-IPB) dan Program Studi Pengelolaan Sumberdaya Alam dan Lingkungan, IPB (PS. PSL, SPs. IPB)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jpsl.11.4.631-637

Abstract

One of the consequences of deforestation is the spread of critical land both inside and outside the forest area. Agroforestry or intercropping is developed to provide benefits and improve welfare for the community, and to optimize the results of a form of sustainable land use to ensure and improve food needs. Eucalyptus is one type of plant that is suitable for forest land rehabilitation because of its ability to live on marginal lands. The purpose of the study was to assess the feasibility of eucalyptus oil business and formulate business sustainability development from seven aspects/feasibility parameters, which are namely: (1) legal aspects, (2) social, economic and cultural aspects, (3) market aspects, (4) management and human resources, (5) risk management aspects, (6) technical aspects, and (7) financial aspects. Meanwhile, to find out whether the eucalyptus business activity as a whole can be sustainable, and its development model, a sustainability analysis was carried out using the cobweb (Amoeba) method. Within the framework of sustainability, eucalyptus concessions must make changes and innovations (Estimated business feasibility on a planting area of 5,200 ha obtained a Net Present Value (NPV) of Rp. 950,734,956,062, - with a discounted interest rate of 12% shows that the eucalyptus oil industry will get a net profit of Rp 7,076,409,779,281, - BC Ratio of 12.56, Interest Rate of Return (IRR) of 55%, Payback Period in the 5th year 4 months shows that in a period of 5 years and 4 months from the investment can be returned from business revenues. The results showed that the seven aspects/parameters were declared feasible and continued with a sustainability analysis and concluded that the eucalyptus oil concession was declared sustainable.
Co-Authors Afina, Fakhri Sukma Agus Buono Agus Siswono Agus Siswono Ahmad Ainuddin Nuruddin Aisyah Anggraini Albar, Israr Andi Gunawan Andini Tribuana Tunggadewi, Andini Tribuana Anggie Yohanna Mandalahi Anissa Rezainy Anita Zaitunah Annisa Puspa Kirana Arzyana Sunkar Asri Buliyansih Atfi Indriany Putri Atfi Indriany Putri Ati Dwi Nurhayati Awal, Elsa Elvira Bahruni . Bambang Hero Saharjo Boedi Tjahjono Chandrasa E Sjamsudin Daniel Happy Putra Denni Prasetia Diah Zuhriana Didik Suharjito Dinda Aisyah Fadhillah Hafni Drucella Benala Dyahati Eduardo Fernando Martins de Carvalho Efendi, Zuliar Eka Intan Kumala Putri Eko Heriyanto Entin Kartini Erfan Noor Yulian Erianto Indra Putra Ernawati, Titik Firman Ardiansyah Fransisxo GS Tambunan Gatot Setiawan Gatot Setiawana Gusti Zainal Anshari Hariyadi Hendra Rahmawan Hendra Rahmawan Hidayat, Assad I Nengah Surati Jaya Iin Ichwandi Imam Suyodono Imas Sukaesih Sitanggang Indah Prasasti Indah Prasasti Irdika Mansur Irwansyah, Muh Yosrilrafiq Istiqomah, Nalar Istomo . Jamaluddin Basharuddin James Thomas Erbaugh Jumani Jumani Khaira, Ulfa Khairia Nafia Khulfi M Khalwani Komarsa Gandasasmita Krisnanto, Ferdian Kurniawati Purwaka Putri Lai Food See LILIK BUDIPRASETYO M. Syamsul Maarif M. Taufan Tirkaamiana M. Taufan Tirkaamiana Meti Ekayani Mirzha Hanifah Mochamad Asep Maksum Mohid Rashid Mohd Yusof Muhammad Ardiansyah Muhammad Hawari Azka Muhammad Hudzaifah Rihuljihad Muhammad Ikhsan Muhammad Imam Nugraha Muhammad Nur Aidi Nadhifah, Putri Addini Arsya Nining Puspaningsih Noor Farikhah Haneda Nova Puspitasari Nuniek Sutanti Nurheni Wijayanto Prima Trie Wijaya Purwanti , Endang Yuni Purwanti, Endang Yuni Putra, Aditya Handoyo Putri Thariqa Rinenggo Siwi Rizaldi Boer Rizki, Yoze Samsuri Samsuri, Samsuri Sandhi Imam Maulana Satyawan, Verda Emmelinda Sigit Purwanto Sitanggang, Imas S. Siti Badriyah Rushayati Sobri Effendy Sofia Fitriana Sri Mulatsih Sugiarto, Dwi Putro Supriyadi, Andi Supriyanto Supriyanto Suryawan Ramadhan Syaiful Anwar Taihuttu, Helda Yunita Tri Tiana Ahmadi Putri Trisminingsih, Rina Unik, Mitra Vera Linda Purba Wahida Annisa Wardana Wardana Widiatmaka Wiwin Ambarwulan WULANDARI Wulandari, Ratu Mutiara Yenni Vetrita Yuli Sunarti