Next Article in Journal
Intensity Values of Terrestrial Laser Scans Reveal Hidden Black Rock Art Pigment
Previous Article in Journal
Automatic Cotton Mapping Using Time Series of Sentinel-2 Images
Previous Article in Special Issue
Decreased Anthropogenic CO2 Emissions during the COVID-19 Pandemic Estimated from FTS and MAX-DOAS Measurements at Urban Beijing
Article

Local PM2.5 Hotspot Detector at 300 m Resolution: A Random Forest–Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology

1
Department of Civil and Environmental Engineering, Duke University, 121 Hudson Hall, Science Dr, Durham, NC 27708, USA
2
Amazon Alexa AI, 300 Pine St, Seattle, WA 98181, USA
3
Department of Biostatistics and Bioinformatics, Duke University Medical Center, Suite 1102 Hock Plaza, 2424 Erwin Rd, Durham, NC 27710, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Zhao-Cheng Zeng
Received: 18 February 2021 / Revised: 25 March 2021 / Accepted: 29 March 2021 / Published: 1 April 2021
(This article belongs to the Special Issue Remote Sensing of Air Pollutants and Carbon Emissions in Megacities)
Satellite-based rapid sweeping screening of localized PM2.5 hotspots at fine-scale local neighborhood levels is highly desirable. This motivated us to develop a random forest–convolutional neural network–local contrast normalization (RF–CNN–LCN) pipeline that detects local PM2.5 hotspots at a 300 m resolution using satellite imagery and meteorological information. The RF–CNN joint model in the pipeline uses three meteorological variables and daily 3 m/pixel resolution PlanetScope satellite imagery to generate daily 300 m ground-level PM2.5 estimates. The downstream LCN processes the estimated PM2.5 maps to reveal local PM2.5 hotspots. The RF–CNN joint model achieved a low normalized root mean square error for PM2.5 of within ~31% and normalized mean absolute error of within ~19% on the holdout samples in both Delhi and Beijing. The RF–CNN–LCN pipeline reasonably predicts urban PM2.5 local hotspots and coolspots by capturing both the main intra-urban spatial trends in PM2.5 and the local variations in PM2.5 with urban landscape, with local hotspots relating to compact urban spatial structures and coolspots being open areas and green spaces. Based on 20 sampled representative neighborhoods in Delhi, our pipeline revealed an annual average 9.2 ± 4.0 μg m−3 difference in PM2.5 between the local hotspots and coolspots within the same community. In some cases, the differences were much larger; for example, at the Indian Gandhi International Airport, the increase was 20.3 μg m−3 from the coolest spot (the residential area immediately outside the airport) to the hottest spot (airport runway). This work provides a possible means of automatically identifying local PM2.5 hotspots at 300 m in heavily polluted megacities and highlights the potential existence of substantial health inequalities in long-term outdoor PM2.5 exposures even within the same local neighborhoods between local hotspots and coolspots. View Full-Text
Keywords: fine particulate matter; machine learning; remote sensing; computer vision; satellite imagery; convolutional neural network (CNN); random forest (RF); hotspot; exposure; risk fine particulate matter; machine learning; remote sensing; computer vision; satellite imagery; convolutional neural network (CNN); random forest (RF); hotspot; exposure; risk
Show Figures

Graphical abstract

MDPI and ACS Style

Zheng, T.; Bergin, M.; Wang, G.; Carlson, D. Local PM2.5 Hotspot Detector at 300 m Resolution: A Random Forest–Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology. Remote Sens. 2021, 13, 1356. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13071356

AMA Style

Zheng T, Bergin M, Wang G, Carlson D. Local PM2.5 Hotspot Detector at 300 m Resolution: A Random Forest–Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology. Remote Sensing. 2021; 13(7):1356. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13071356

Chicago/Turabian Style

Zheng, Tongshu, Michael Bergin, Guoyin Wang, and David Carlson. 2021. "Local PM2.5 Hotspot Detector at 300 m Resolution: A Random Forest–Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology" Remote Sensing 13, no. 7: 1356. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13071356

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop