Using deep transfer learning and satellite imagery to estimate urban air quality in data-poor regions

被引:0
|
作者
Yadav, Nishant [1 ,2 ]
Sorek-Hamer, Meytar [2 ,3 ]
Von Pohle, Michael [2 ,3 ]
Asanjan, Ata Akbari [2 ,3 ]
Sahasrabhojanee, Adwait [2 ,3 ]
Suel, Esra [4 ]
Arku, Raphael [5 ]
Lingenfelter, Violet [1 ,2 ]
Brauer, Michael [6 ]
Ezzati, Majid [4 ]
Oza, Nikunj [5 ]
Ganguly, Auroop R. [1 ,7 ,8 ]
机构
[1] Northeastern Univ, Sustainabil & Data Sci Lab, Boston, MA 02115 USA
[2] Univ Space Res Assoc USRA, Mountain View, CA USA
[3] NASA Ames Res Ctr, Moffett Field, CA USA
[4] Imperial Coll London, London, England
[5] Univ Massachusetts, Amherst, MA USA
[6] Univ British Columbia, Vancouver, BC, Canada
[7] Pacific Northwest Natl Lab PNNL, Richland, WA USA
[8] Northeastern Univ, Inst Experiential AI, Boston, MA USA
基金
英国惠康基金;
关键词
Deep learning; Air quality; Satellite imagery; Transfer learning; LAND-USE REGRESSION; POLLUTION;
D O I
10.1016/j.envpol.2023.122914
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Urban air pollution is a critical public health challenge in low-and-middle-income countries (LMICs). At the same time, LMICs tend to be data-poor, lacking adequate infrastructure to monitor air quality (AQ). As LMICs undergo rapid urbanization, the socio-economic burden of poor AQ will be immense. Here we present a globally scalable two-step deep learning (DL) based approach for AQ estimation in LMIC cities that mitigates the need for extensive AQ infrastructure on the ground. We train a DL model that can map satellite imagery to AQ in high-income countries (HICs) with sufficient ground data, and then adapt the model to learn meaningful AQ estimates in LMIC cities using transfer learning. The trained model can explain up to 54% of the variation in the AQ distribution of the target LMIC city without the need for target labels. The approach is demonstrated for Accra in Ghana, Africa, with AQ patterns learned and adapted from two HIC cities, specifically Los Angeles and New York.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] DOWNSCALING OF SATELLITE AIR QUALITY DATA USING DEEP LEARNING
    Rapuzzi, Andrea
    Nattero, Cristiano
    Menapace, Marco
    Campanella, Paolo
    Cademartori, Linda
    Lomonaco, Carola
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 6606 - 6609
  • [2] Developing a framework for urban flood modeling in Data-poor regions
    Xu, Shichao
    Chen, Yangbo
    Zhang, Yueyuan
    Chen, Lingfang
    Sun, Huaizhang
    Liu, Jun
    [J]. JOURNAL OF HYDROLOGY, 2023, 617
  • [3] Nowcasting Air Quality by Fusing Insights from Meteorological Data, Satellite Imagery and Social Media Images using Deep Learning
    Khaefi, Muhammad Rizal
    Pramestri, Zakiya
    Amin, Imaduddin
    Lee, Jong Gun
    [J]. 2018 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM), 2018, : 393 - 396
  • [4] Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning
    Oshri, Barak
    Hu, Annie
    Adelson, Peter
    Chen, Xiao
    Dupas, Pascaline
    Weinstein, Jeremy
    Burke, Marshall
    Lobell, David
    Ermon, Stefano
    [J]. KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 616 - 625
  • [5] Monitoring of urban ecological environment including air quality using satellite imagery
    Wang, Yuan
    Cai, Guoyin
    Yang, Liuzhong
    Zhang, Ning
    Du, Mingyi
    [J]. PLOS ONE, 2022, 17 (08):
  • [6] Machine learning driven by environmental covariates to estimate high-resolution PM2.5 in data-poor regions
    Jin, Xiaoye
    Ding, Jianli
    Ge, Xiangyu
    Liu, Jie
    Xie, Boqiang
    Zhao, Shuang
    Zhao, Qiaozhen
    [J]. PEERJ, 2022, 10
  • [7] Rule-based, hierarchical land use and land cover classification of urban and peri-urban agriculture in data-poor regions with RapidEye satellite imagery: a case study of Nakuru, Kenya
    Willkomm, Maximilian
    Follmann, Alexander
    Dannenberg, Peter
    [J]. JOURNAL OF APPLIED REMOTE SENSING, 2019, 13 (01)
  • [8] Using Deep Learning to Estimate Tropical Cyclone Intensity from Satellite Passive Microwave Imagery
    Wimmers, Anthony
    Velden, Christopher
    Cossuth, Joshua H.
    [J]. MONTHLY WEATHER REVIEW, 2019, 147 (06) : 2261 - 2282
  • [9] A Deep Learning Approach for Meter-Scale Air Quality Estimation in Urban Environments Using Very High-Spatial-Resolution Satellite Imagery
    Sorek-Hamer, Meytar
    Von Pohle, Michael
    Sahasrabhojanee, Adwait
    Asanjan, Ata Akbari
    Deardorff, Emily
    Suel, Esra
    Lingenfelter, Violet
    Das, Kamalika
    Oza, Nikunj C.
    Ezzati, Majid
    Brauer, Michael
    [J]. ATMOSPHERE, 2022, 13 (05)
  • [10] Quantitative assessment of background pollutants using a modified method in data-poor regions
    Duan, Maoqing
    Du, Xia
    Peng, Wenqi
    Jiang, Cuiling
    Zhang, Shijie
    Ding, Yang
    [J]. ENVIRONMENTAL MONITORING AND ASSESSMENT, 2020, 192 (03)