FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Han, Jinzhen, Lee, JinByeong, Han, Hak, Na, YeonJu, Lee, Jae-Joon
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911578065993728
author Han, Jinzhen
Lee, JinByeong
Han, Hak
Na, YeonJu
Lee, Jae-Joon
author_facet Han, Jinzhen
Lee, JinByeong
Han, Hak
Na, YeonJu
Lee, Jae-Joon
contents Accurate prediction of next-day wildfire spread is critical for disaster response and resource allocation. Existing deep learning approaches typically concatenate heterogeneous geospatial inputs into a single tensor, ignoring the fundamental physical distinction between static fuel/terrain properties and dynamic meteorological conditions. We propose FireSenseNet, a dual-branch convolutional neural network equipped with a novel Cross-Attentive Feature Interaction Module (CAFIM) that explicitly models the spatially varying interaction between fuel and weather modalities through learnable attention gates at multiple encoder scales. Through a systematic comparison of seven architectures -- spanning pure CNNs, Vision Transformers, and hybrid designs -- on the Google Next-Day Wildfire Spread benchmark, we demonstrate that FireSenseNet achieves an F1 of 0.4176 and AUC-PR of 0.3435, outperforming all alternatives including a SegFormer with 3.8* more parameters (F1 = 0.3502). Ablation studies confirm that CAFIM provides a 7.1% relative F1 gain over naive concatenation, and channel-wise feature importance analysis reveals that the previous-day fire mask dominates prediction while wind speed acts as noise at the dataset's coarse temporal resolution. We further incorporate Monte Carlo Dropout for pixel-level uncertainty quantification and present a critical analysis showing that common evaluation shortcuts inflate reported F1 scores by over 44%.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07675
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction
Han, Jinzhen
Lee, JinByeong
Han, Hak
Na, YeonJu
Lee, Jae-Joon
Computer Vision and Pattern Recognition
Accurate prediction of next-day wildfire spread is critical for disaster response and resource allocation. Existing deep learning approaches typically concatenate heterogeneous geospatial inputs into a single tensor, ignoring the fundamental physical distinction between static fuel/terrain properties and dynamic meteorological conditions. We propose FireSenseNet, a dual-branch convolutional neural network equipped with a novel Cross-Attentive Feature Interaction Module (CAFIM) that explicitly models the spatially varying interaction between fuel and weather modalities through learnable attention gates at multiple encoder scales. Through a systematic comparison of seven architectures -- spanning pure CNNs, Vision Transformers, and hybrid designs -- on the Google Next-Day Wildfire Spread benchmark, we demonstrate that FireSenseNet achieves an F1 of 0.4176 and AUC-PR of 0.3435, outperforming all alternatives including a SegFormer with 3.8* more parameters (F1 = 0.3502). Ablation studies confirm that CAFIM provides a 7.1% relative F1 gain over naive concatenation, and channel-wise feature importance analysis reveals that the previous-day fire mask dominates prediction while wind speed acts as noise at the dataset's coarse temporal resolution. We further incorporate Monte Carlo Dropout for pixel-level uncertainty quantification and present a critical analysis showing that common evaluation shortcuts inflate reported F1 scores by over 44%.
title FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.07675