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

Alexandra LarsenIvan HaniganBrian J ReichYi QinMartin CopeGeoffrey MorganAna G Rappold

Published in: Journal of exposure science & environmental epidemiology (2020)

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.

Keyphrases

health risk
deep learning
human health
healthcare
heavy metals
mental health
health information
drinking water
machine learning
public health
risk assessment
artificial intelligence
convolutional neural network
social media
climate change
health promotion
emergency department
adverse drug
neural network