Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Adaptive multimodal transformer for wildfire spread prediction using feature-weighted attention

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 4 (2026) · hlm. 3197–3206

DOI
10.11591/eei.v15i4.11326
ISSN
2089-3191, 2302-9285
Terbit
2026-08-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Hazard modelling technology has evolved quickly in recent years to predict wildfires, which are an important class of natural disaster for accurate forecasting and proactive control. The combination of remote sensing and machine learning has been playing an important role in this area. Yet traditional models fail to accommodate the sophisticated spatiotemporal dynamics in fire-affected areas and tend to be agnostic toward individual predictors. This study utilizes a multimodal dataset comprising normalized difference vegetation index (NDVI), wind vectors, surface temperature, humidity, land cover, and elevation from sources such as moderate resolution imaging spectroradiometer (MODIS), Sentinel-2, ERA5, and shuttle radar topography mission (SRTM). These inputs were normalized within spatial grids, and temporally-aligned for day-ahead prediction. We introduce an adaptive multimodal transformer (AMT) with a feature weighting module (FWM) to adaptively emphasize informative features. The transformer architecture allows for long-range spatial learning, and the FWM strengthens contextual sensitivity. The novelty of this approach lies in its interpretable feature reweighting mechanism for dynamic environmental conditions. Model performance was evaluated using F1-score, intersection over union (IoU), mean absolute error (MAE), and mean average precision (MAP). Results show that the proposed model outperforms the MA-Net baseline, achieving a 5% improvement in F1-score and a 14.7% reduction in MAE, demonstrating superior accuracy, generalization, and interpretability.

Kata kunci

Jaringan kolaborasi para penulis

19 penulis · 64 tautan kepenulisan bersama · 43 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
  • Amity University Chhatisgarh
  • Guru Nanak Dev University
  • Pandit Sundarlal Sharma Open University
  • Yashwantrao Chavan Maharashtra Open University
  • 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
Hitesh GehaniAfiliasi tidak diketahui5
Vinay KeswaniRaisoni Group of Institutions4
Ashwini KukadeRaisoni Group of Institutions3
Akshita ChanchlaniMIT World Peace University2
Parul DubeySymbiosis International University2
Murtuza MurtuzaMIT World Peace University2
Titiksha Tulsidas BhagatAfiliasi tidak diketahui2
Ankit V. KokareMIT World Peace University2
Poonam Ramesh ChaudhariYashwantrao Chavan Maharashtra Open University2
Umesh K. RautMIT World Peace University2
Amit MishraMIT World Peace University1
Aruna SinghNoida International University1
Gaurav Vishnu LondheSymbiosis International 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">Adaptive multimodal transformer for wildfire spread prediction using feature-weighted attention</dc:title><dc:creator>Parul Dubey</dc:creator><dc:creator>Gunjan Keswani</dc:creator><dc:creator>Amit Mishra</dc:creator><dc:creator>Manjushree Nayak</dc:creator><dc:creator>Rashid Mahmood</dc:creator><dc:creator>Pushkar Dubey</dc:creator><dc:subject>wildfire spread prediction</dc:subject><dc:subject>feature reweighting</dc:subject><dc:subject>NDVI</dc:subject><dc:subject>wind vector</dc:subject><dc:subject>surface temperature</dc:subject><dc:subject>humidity</dc:subject><dc:subject>land cover</dc:subject><dc:subject>altitude</dc:subject><dc:subject>spatiotemporal dynamics</dc:subject><dc:subject>remote sensing data fusion</dc:subject><dc:subject>model interpretability</dc:subject><dc:description xml:lang="en">Hazard modelling technology has evolved quickly in recent years to predict wildfires, which are an important class of natural disaster for accurate forecasting and proactive control. The combination of remote sensing and machine learning has been playing an important role in this area. Yet traditional models fail to accommodate the sophisticated spatiotemporal dynamics in fire-affected areas and tend to be agnostic toward individual predictors. This study utilizes a multimodal dataset comprising normalized difference vegetation index (NDVI), wind vectors, surface temperature, humidity, land cover, and elevation from sources such as moderate resolution imaging spectroradiometer (MODIS), Sentinel-2, ERA5, and shuttle radar topography mission (SRTM). These inputs were normalized within spatial grids, and temporally-aligned for day-ahead prediction. We introduce an adaptive multimodal transformer (AMT) with a feature weighting module (FWM) to adaptively emphasize informative features. The transformer architecture allows for long-range spatial learning, and the FWM strengthens contextual sensitivity. The novelty of this approach lies in its interpretable feature reweighting mechanism for dynamic environmental conditions. Model performance was evaluated using F1-score, intersection over union (IoU), mean absolute error (MAE), and mean average precision (MAP). Results show that the proposed model outperforms the MA-Net baseline, achieving a 5% improvement in F1-score and a 14.7% reduction in MAE, demonstrating superior accuracy, generalization, and interpretability.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-08-01</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.v15i4.11326</dc:identifier><dc:identifier>10.11591/eei.v15i4.11326</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 4 (2026); 3197-3206</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/11326/4943</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>