Forest Fire Detection Based on Digital Imagery Using Convolutional Neural Network (CNN) Model
DOI:
https://doi.org/10.70609/g-tech.v10i2.9422Keywords:
Detection, Digital Imagery, Convolutional Neural Network (CNN)Abstract
This study explores the implementation of a Convolutional Neural Network (CNN) for automated forest fire identification using digital image processing. Utilizing the USTC 'Forest Fire' dataset, the research framework involved systematic data preprocessing, including a 70:30 training-validation split and the application of image augmentation techniques to enhance model robustness. The proposed architecture features a sequential design with dual convolution and pooling layers, integrated with ReLU and Sigmoid activations. Although initial training over seven epochs yielded a deceptive validation accuracy of 99%, granular performance analysis exposed critical limitations. Evaluation via a Confusion Matrix revealed that while the model excelled at identifying 'non-fire' scenarios, it struggled significantly with actual fire detection, failing to recognize 301 out of 331 fire instances. These results highlight a severe class imbalance issue, suggesting that standard accuracy metrics are insufficient for this application and emphasizing the need for more balanced sampling or advanced architectural adjustments in future fire detection systems.
References
Ahdiat, A. (2023). No Title. https://databoks.katadata.co.id/datapublish/2023/09/20/luas-kebakaran-hutan-indonesia-capai-267-ribu-hektare-sampai-agustus-2023
Amri, A., Akhirman, Zaharani, A., Rizki, C., Harianja, L. M., Prameswari, N., Vauzia, & Putri, W. N. (2024). Dampak bencana kebakaran hutan terhadap lingkungan dan upaya penanggulangan di indonesia. JRTI (Jurnal Riset Tindakan Indonesia, 9(2), 159–166. DOI: https://doi.org/10.29210/30035130000
Anhar, & Putra, R. A. (2023). Perancangan dan Implementasi Self-Checkout System pada Toko Ritel menggunakan Convolutional Neural Network ( CNN ). ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi & Teknik Elektronika, 11(2), 466–478. DOI: https://doi.org/10.26760/elkomika.v11i2.466
Azmi, K., Defit, S., & Sumijan. (2023). Implementasi Convolutional Neural Network ( CNN ) Untuk Klasifikasi Batik Tanah Liat Sumatera Barat. Jurnal Unitek, 16(1), 2580–2582. DOI: https://doi.org/10.52072/unitek.v16i1.504
Barmpoutis, P., Papaioannou, P., Dimitropoulos, K., & Grammalidis, N. (2020). A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing. Sensors, 20(6442), 1–26. DOI: https://doi.org/10.3390/s20226442
Cahyaningtyas, C., Mira, Gudiato, C., & Sari, M. (2025). Deteksi Ekspresi Wajah Manusia Menggunakan Metode Convolutional Neural Network. Jurnal FASILKOM, 15(1), 138–145. DOI: https://doi.org/10.37859/jf.v15i1.9119
Firmansyah, F., Budianto, E., Yulianto, A., Sudrajat, B., & Wigandi, D. P. (2019). Rancang Bangun Sistem Informasi Bank Sampah (SIBAS) Berbasis Desktop Dengan Metode Waterfall. REMIK (Riset Dan E-Jurnal Manajemen Informatika Komputer), 4(1), 44. https://doi.org/10.33395/remik.v4i1.10229 DOI: https://doi.org/10.33395/remik.v4i1.10229
Ghosh, R., & Kumar, A. (2022). A hybrid deep learning model by combining convolutional neural network and recurrent neural network to detect forest fire. Multimedia Tools and Applications, 81(27), 38643–38660. https://doi.org/10.1007/s11042-022-13068-8 DOI: https://doi.org/10.1007/s11042-022-13068-8
Irfanianingrum, I., Chaidir, A. rizal, Sumardi, Rahardi, G. A., & Herdiyanto, D. W. (2023). Sistem Pendeteksi Dini Kebakaran hutan Berbasis Logika Fuzzy. MITOR: Jurnal Teknik Elektro, 23(2), 120–127. https://doi.org/10.23917/emitor.v22i2.22019 DOI: https://doi.org/10.23917/emitor.v22i2.22019
Joseph, F. J. J., Nonsiri, S., & Monsakul, A. (2021). Keras and Tensorflow: A Hands On Experience. In Advanced Deep Learning for Engineers and Scientist (pp. 85–111). DOI: https://doi.org/10.1007/978-3-030-66519-7_4
Komalasari, T. D. (2025). No Title. https://katadata.co.id/ekonomi-hijau/ekonomi-sirkular/659ca314b6936/kebakaran-hutan-jadi-bencana-terbanyak-pada-2023-capai-1802-kejadian
Mahameru, I. A., Ravly Dwi Septian, M., Roliawati, D., Yusuf, A., & Ridwan, M. (2025). Implementasi Algoritma Convolutional Neural Network ( CNN ) Untuk Klasifikasi Kerapihan Ruangan. Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI), 4(2), 1264–1271. DOI: https://doi.org/10.62712/juktisi.v4i2.606
Paraijun, F., Aziza, R. N., & Kuswardani, D. (2022). Implementasi Algoritma Convolutional Neural Network Dalam Mengklasifikasi Kesegaran Buah Berdasarkan Citra Buah. KILAT, 11(1), 1–9. DOI: https://doi.org/10.33322/kilat.v10i2.1458
Pasai, M. (2020). Dampak Kebakaran Hutan Dan Penegakan Hukum. Jurnal Pahlawan, 3(1), 36–46. http://190.119.145.154/handle/20.500.12773/11756
Reis, H. C., & Turk, V. (2023). Detection of forest fire using deep convolutional neural networks with transfer learning approach. Applied Soft Computing, 143, 110362. https://doi.org/https://doi.org/10.1016/j.asoc.2023.110362 DOI: https://doi.org/10.1016/j.asoc.2023.110362
Saharjo, B. H., & Hasanah, U. (2023). Analisis Faktor Penyebab Terjadinya Kebakaran Hutan dan Lahan di Kabupaten Pulang Pisau, Kalimantan Tengan. Journal of Tropical Silviculture, 14(01), 25–29. https://doi.org/10.29244/j-siltrop.14.01.25-29 DOI: https://doi.org/10.29244/j-siltrop.14.01.25-29
Setiawan, D., Putra, A. D., Stefani, K., & Felisa, J. (2021). Implementasi Covolutional Neural Network Untuk Facial Recognition. Media Informatika, 20(2), 66–79. DOI: https://doi.org/10.37595/mediainfo.v20i2.68
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(60), 1–48. https://doi.org/10.1186/s40537-019-0197-0 DOI: https://doi.org/10.1186/s40537-019-0197-0
Subasri, P., & Nithya, B. (2025). Forest Fire Detection Using Convolutional Neural Networks (CNN). International Journal For Multidisciplinary Research (IJFMR), 7(4), 1–8. DOI: https://doi.org/10.36948/ijfmr.2025.v07i04.52281
Wiranda, N., Purba, H. S., & Sukmawati, R. A. (2020). Survei Penggunaan Tensorflow pada Machine Learning untuk Identifikasi Ikan Kawasan Lahan Basah. Indonesian Journal of Electronics and Instrumentation System (IJEIS), 10(2), 179–188. DOI: https://doi.org/10.22146/ijeis.58315
Zheng, X., Chen, F., Lou, L., Cheng, P., & Huang, Y. (2022). Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network. Remote Sensing, 14(536), 1–15. DOI: https://doi.org/10.3390/rs14030536
Zuhri, A. S. M., Nafiiyah, N., & Budi, A. S. (2025). Identification of Road Damage Using the Convolutional Neural Network ( CNN ) Method. Jurnal Ilmiah Sistem Informasi (JUSI), 4(3), 802–817. DOI: https://doi.org/10.51903/jgn2sd35
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Candra Gudiato, Aditya Pratama, Christian Cahyaningtyas
This work is licensed under a Creative Commons Attribution 4.0 International License.
