Segmentation of Any Fire Event (SAFE): A Rapid and High-Precision Approach for Burned Area Extraction Using Sentinel-2 Imagery DOI Creative Commons
Shuaijun Liu, Yong Xue, Hui Chen

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 17(1), P. 54 - 54

Published: Dec. 27, 2024

The timely and accurate monitoring of wildfires other sudden natural disasters is crucial for safeguarding the safety residents their property. Satellite imagery wildfire offers a unique opportunity to obtain near-real-time disaster information through rapid, large-scale remote sensing mapping. However, existing methods are constrained by temporal spatial limitations imagery, preventing comprehensive fulfillment need high resolution in early warning. To address this gap, we propose high-precision extraction method without training—SAFE. SAFE combines generalization capabilities Segmentation Anything Model (SAM) effectiveness hotspot product data such as MODIS VIIRS. employs two-step localization strategy incrementally identify burned areas pixels post-wildfire thereby reducing computational load providing high-resolution impact areas. area generated can subsequently be used train lightweight regional models, establishing detection models applicable various regions, ultimately undetected We validated four test regions representing two typical scenarios—grassland forest. results showed that SAFE’s F1-score was, on average, 9.37% higher than alternative methods. Additionally, application scenarios demonstrated its potential capability detect fine distribution impacts global scale.

Language: Английский

An interpretable wheat yield estimation model using an attention mechanism-based deep learning framework with multiple remotely sensed variables DOI
Mingqi Li, Pengxin Wang, Kevin Tansey

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 140, P. 104579 - 104579

Published: May 8, 2025

Language: Английский

Citations

0
Remote Sensing Identification of Picea schrenkiana var. tianschanica in GF-1 Images Based on a Multiple Mixed Attention U-Net Model DOI Open Access
Jian Zheng, Donghua Chen,

Hanchi Zhang

et al.

Forests, Journal Year: 2024, Volume and Issue: 15(11), P. 2039 - 2039

Published: Nov. 19, 2024

Remote sensing technology plays an important role in woodland identification. However, mountainous areas with complex terrain, accurate extraction of boundary information still faces challenges. To address this problem, paper proposes a multiple mixed attention U-Net (MMA-U-Net) semantic segmentation model using 2015 and 2022 GF-1 PMS images as data sources to improve the ability extract features Picea schrenkiana var. tianschanica forest. The architecture serves its underlying network, feature is improved by adding hybrid CBAM replacing original skip connection DCA module accuracy segmentation. results show that on remote dataset images, compared other models, increased 5.42%–19.84%. By statistically analyzing spatial distribution well their changes, area was 3471.38 km2 3726.10 2022. Combining predicted DEM data, it found were most distributed at altitude 1700–2500 m. method proposed study can accurately identify provides theoretical basis research direction for forest monitoring.

Language: Английский

Citations

0
Segmentation of Any Fire Event (SAFE): A Rapid and High-Precision Approach for Burned Area Extraction Using Sentinel-2 Imagery DOI Creative Commons
Shuaijun Liu, Yong Xue, Hui Chen

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 17(1), P. 54 - 54

Published: Dec. 27, 2024

The timely and accurate monitoring of wildfires other sudden natural disasters is crucial for safeguarding the safety residents their property. Satellite imagery wildfire offers a unique opportunity to obtain near-real-time disaster information through rapid, large-scale remote sensing mapping. However, existing methods are constrained by temporal spatial limitations imagery, preventing comprehensive fulfillment need high resolution in early warning. To address this gap, we propose high-precision extraction method without training—SAFE. SAFE combines generalization capabilities Segmentation Anything Model (SAM) effectiveness hotspot product data such as MODIS VIIRS. employs two-step localization strategy incrementally identify burned areas pixels post-wildfire thereby reducing computational load providing high-resolution impact areas. area generated can subsequently be used train lightweight regional models, establishing detection models applicable various regions, ultimately undetected We validated four test regions representing two typical scenarios—grassland forest. results showed that SAFE’s F1-score was, on average, 9.37% higher than alternative methods. Additionally, application scenarios demonstrated its potential capability detect fine distribution impacts global scale.

Language: Английский

Citations

0