TY - JOUR
T1 - Deep-MAPS
T2 - Machine-Learning-Based Mobile Air Pollution Sensing
AU - Song, Jun
AU - Han, Ke
AU - Stettler, Marc E. J.
N1 - Funding information:
This work was supported in part by the National Natural Science Foundation of China under Grant 72071163. The work of Jun Song’s was supported in part by the China Scholarship Council.
Publisher copyright:
© 2020 IEEE.
PY - 2021/5/1
Y1 - 2021/5/1
N2 - Mobile and ubiquitous sensing of urban air quality (AQ) has received increased attention as an economically and operationally viable means to survey atmospheric environment with high spatial–temporal resolution. This article proposes a machine-learning-based mobile air pollution sensing framework, coined Deep-MAPS, and demonstrates its scientific and financial values in the following aspects: 1) based on a combination of fixed and mobile AQ sensors, we perform spatial inference of PM 2.5 concentrations in Beijing (3025 km 2 , June 19–July 16, 2018) for a spatial–temporal resolution of 1 km × 1 km and 1 h, with under 15% SMAPE; 2) we leverage urban big data to generate insights regarding the potential cause of pollution, which facilitates evidence-based sustainable urban management; and 3) to achieve such spatial–temporal coverage and accuracy, Deep-MAPS can save up to 90% hardware investment, compared with ubiquitous sensing that relies primarily on fixed sensors.
AB - Mobile and ubiquitous sensing of urban air quality (AQ) has received increased attention as an economically and operationally viable means to survey atmospheric environment with high spatial–temporal resolution. This article proposes a machine-learning-based mobile air pollution sensing framework, coined Deep-MAPS, and demonstrates its scientific and financial values in the following aspects: 1) based on a combination of fixed and mobile AQ sensors, we perform spatial inference of PM 2.5 concentrations in Beijing (3025 km 2 , June 19–July 16, 2018) for a spatial–temporal resolution of 1 km × 1 km and 1 h, with under 15% SMAPE; 2) we leverage urban big data to generate insights regarding the potential cause of pollution, which facilitates evidence-based sustainable urban management; and 3) to achieve such spatial–temporal coverage and accuracy, Deep-MAPS can save up to 90% hardware investment, compared with ubiquitous sensing that relies primarily on fixed sensors.
KW - Air quality (AQ)
KW - big data
KW - machine learning
KW - ubiquitous sensing
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097389289&doi=10.1109%2fJIOT.2020.3041047&partnerID=40&md5=9cfad055e3d8cd44e0b953575d7a140f
U2 - 10.1109/JIOT.2020.3041047
DO - 10.1109/JIOT.2020.3041047
M3 - Journal article
SN - 2327-4662
VL - 8
SP - 7649
EP - 7660
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 9
ER -