Ngôn ngữ:

A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication

Journal of exposure science & environmental epidemiology, 2021-02, Vol.31 (1), p.170-176 [Tạp chí có phản biện]

COPYRIGHT 2021 Nature Publishing Group ;US Govt 2020. ;ISSN: 1559-0631 ;EISSN: 1559-064X ;DOI: 10.1038/s41370-020-0246-y ;PMID: 32719441

Tài liệu số/Tài liệu điện tử

Trích dẫn Trích dẫn bởi

Gửi đến

Nhan đề:
A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication
Tác giả: Larsen, Alexandra ; Hanigan, Ivan ; Reich, Brian J ; Qin, Yi ; Cope, Martin ; Morgan, Geoffrey ; Rappold, Ana G
Chủ đề: Air Pollutants - analysis ; Air pollution ; Air quality ; Algorithms ; Artificial neural networks ; Australia ; Automation ; Communication ; Deep Learning ; Exposure ; Fire exposure ; Fire hazards ; Fires ; Health risk communication ; Health risks ; Humans ; Identification and classification ; Identification methods ; Image resolution ; Information management ; Information processing ; Machine learning ; Methods ; Neural networks ; Plumes ; Plumes (Fluid dynamics) ; Real time ; Risk analysis ; Risk communication ; Risk factors ; Satellite Imagery ; Satellite imaging ; Smoke ; Smoke - analysis ; Technology application ; Wildfires
Là 1 phần của: Journal of exposure science & environmental epidemiology, 2021-02, Vol.31 (1), p.170-176
Mô tả: Wildland fire (wildfire; bushfire) pollution contributes to poor air quality, a risk factor for premature death. The frequency and intensity of wildfires are expected to increase; improved tools for estimating exposure to fire smoke are vital. New-generation satellite-based sensors produce high-resolution spectral images, providing real-time information of surface features during wildfire episodes. Because of the vast size of such data, new automated methods for processing information are required. We present a deep fully convolutional neural network (FCN) for predicting fire smoke in satellite imagery in near-real time (NRT). The FCN identifies fire smoke using output from operational smoke identification methods as training data, leveraging validated smoke products in a framework that can be operationalized in NRT. We demonstrate this for a fire episode in Australia; the algorithm is applicable to any geographic region. The algorithm has high classification accuracy (99.5% of pixels correctly classified on average) and precision (average intersection over union = 57.6%). The FCN algorithm has high potential as an exposure-assessment tool, capable of providing critical information to fire managers, health and environmental agencies, and the general public to prevent the health risks associated with exposure to hazardous smoke from wildland fires in NRT.
Nơi xuất bản: United States: Nature Publishing Group
Ngôn ngữ: English
Số nhận dạng: ISSN: 1559-0631
EISSN: 1559-064X
DOI: 10.1038/s41370-020-0246-y
PMID: 32719441
Nguồn: AUTh Library subscriptions: ProQuest Central
MEDLINE

Trở lại danh sách kết quả


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication

COPYRIGHT 2021 Nature Publishing Group ;US Govt 2020. ;ISSN: 1559-0631 ;EISSN: 1559-064X ;DOI: 10.1038/s41370-020-0246-y ;PMID: 32719441

Đang tìm Cơ sở dữ liệu bên ngoài...