Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Deep spatiotemporal signal learning with transformers for multi-day wildfire forecasting

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 1 (2026) · hlm. 731–739

DOI
10.11591/eei.v15i1.10936
ISSN
2089-3191, 2302-9285
Terbit
2026-02-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Wildfire forecasting is a critical challenge in environmental signal processing and disaster response planning. The ability to interpret multimodal spatiotemporal signals is essential for early warning systems and resource deployment. This study addresses these limitations by proposing a unified prediction-to-action framework. We utilized four open-access datasets—wildland fire emissions database (WFED), fire information for resource management system (FIRMS), Sentinel Hub, and a custom moderate resolution imaging spectroradiometer+shuttle radar topography mission (ERA5+MODIS+SRTM) fusion—covering fire occurrences, vegetation indices, meteorological parameters, and topographic features. These heterogeneous signals were preprocessed, aligned, and transformed into structured tensors for model training and evaluation. We use a transformer-based system to understand long-term patterns in space and time, enhanced by a belief–desire–intention (BDI) reasoning module that connects our predictions to flexible wildfire response plans. The novelty lies in the integration of signal-aware attention mechanisms with symbolic decision modeling. Model performance was evaluated using F1-score, intersection over union (IoU), mean absolute error (MAE), and directional accuracy. The suggested framework did better than the basic convolutional neural network (CNN) models, reaching an F1-score of 0.74, a directional accuracy of 84.3%, and lowering the MAE to 7.6 km², while also providing clear and relevant action suggestions.

Kata kunci

Jaringan kolaborasi para penulis

32 penulis · 115 tautan kepenulisan bersama · 48 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • MIT World Peace University
  • Symbiosis International University
  • Raisoni Group of Institutions
  • Pandit Sundarlal Sharma Open University
  • Amity University Chhatisgarh
  • JIS University
  • Sathyabama Institute of Science and Technology
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Parul DubeySymbiosis International University5
Amit MishraMIT World Peace University4
Aruna SinghNoida International University4
Hitesh GehaniAfiliasi tidak diketahui3
Manjushree NayakAmity University Chhatisgarh3
Ashwini KukadeRaisoni Group of Institutions2
Nilesh M ShelkeSymbiosis International University1
Amit Purushottam PimpalkarAfiliasi tidak diketahui1
Amit R. WelekarAfiliasi tidak diketahui1
Abhrendu BhattacharyaJIS University1
R. Jeberson Retna RajSathyabama Institute of Science and Technology1
Akshat RajMIT World Peace University1
Durva Mahadeo ChavanMIT World Peace University1
Priyal AgarwalMIT World Peace University1
Jestin GigiMIT World Peace University1
Vinayak MusaleMIT World Peace University1
Murtaza Shabbirbhai DholkawalaMIT World Peace University1
Madhuri RaoMIT World Peace University1
Kulamala Vinod KumarMIT World Peace University1
Titiksha Tulsidas BhagatAfiliasi tidak diketahui1
Ankit V. KokareMIT World Peace University1
Poonam Ramesh ChaudhariYashwantrao Chavan Maharashtra Open University1
Umesh K. RautMIT World Peace University1
Gunjan KeswaniAfiliasi tidak diketahui1
Amit MishraMIT World Peace University1
Rashid MahmoodGuru Nanak Dev University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Deep spatiotemporal signal learning with transformers for multi-day wildfire forecasting</dc:title><dc:creator>Parul Dubey</dc:creator><dc:creator>Gaurav Vishnu Londhe</dc:creator><dc:creator>Vinay Keswani</dc:creator><dc:creator>Akshita Chanchlani</dc:creator><dc:creator>Murtuza Murtuza</dc:creator><dc:creator>Pushkar Dubey</dc:creator><dc:subject>wildfire prediction</dc:subject><dc:subject>transformer models</dc:subject><dc:subject>multimodal fusion</dc:subject><dc:subject>vegetation indices</dc:subject><dc:subject>meteorological parameters</dc:subject><dc:subject>topographic features</dc:subject><dc:subject>wildfire emissions</dc:subject><dc:subject>early warning systems</dc:subject><dc:subject>attention mechanism</dc:subject><dc:description xml:lang="en">Wildfire forecasting is a critical challenge in environmental signal processing and disaster response planning. The ability to interpret multimodal spatiotemporal signals is essential for early warning systems and resource deployment. This study addresses these limitations by proposing a unified prediction-to-action framework. We utilized four open-access datasets—wildland fire emissions database (WFED), fire information for resource management system (FIRMS), Sentinel Hub, and a custom moderate resolution imaging spectroradiometer+shuttle radar topography mission (ERA5+MODIS+SRTM) fusion—covering fire occurrences, vegetation indices, meteorological parameters, and topographic features. These heterogeneous signals were preprocessed, aligned, and transformed into structured tensors for model training and evaluation. We use a transformer-based system to understand long-term patterns in space and time, enhanced by a belief–desire–intention (BDI) reasoning module that connects our predictions to flexible wildfire response plans. The novelty lies in the integration of signal-aware attention mechanisms with symbolic decision modeling. Model performance was evaluated using F1-score, intersection over union (IoU), mean absolute error (MAE), and directional accuracy. The suggested framework did better than the basic convolutional neural network (CNN) models, reaching an F1-score of 0.74, a directional accuracy of 84.3%, and lowering the MAE to 7.6 km², while also providing clear and relevant action suggestions.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-02-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i1.10936</dc:identifier><dc:identifier>10.11591/eei.v15i1.10936</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 1 (2026); 731-739</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/10936/4597</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>