Deep-MAPS: Machine-Learning-Based Mobile Air Pollution Sensing

Mobile and ubiquitous sensing of urban air quality has received increased attention as an economically and operationally viable means to survey atmospheric environment with high spatial-temporal resolution. This paper proposes a machine learning based mobile air pollution sensing framework, called Deep-MAPS, and demonstrates its scientific and financial values in the following aspects. (1) Based on a network of fixed and mobile air quality sensors, we perform spatial inference of PM2.5 concentrations in Beijing (3,025 km2, 19 Jun-16 Jul 2018) for a spatial-temporal resolution of 1km-by-1km and 1 hour, with over 85% accuracy. (2) We leverage urban big data to generate insights regarding the potential cause of pollution, which facilitates evidence-based sustainable urban management. (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.

[1]  Alberto Martilli,et al.  A methodology to urban air quality assessment during large time periods of winter using computational fluid dynamic models , 2010 .

[2]  Mysore G. Satish,et al.  Dispersion model evaluation of PM2.5, NOx and SO2 from point and major line sources in Nova Scotia, Canada using AERMOD Gaussian plume air dispersion model , 2013 .

[3]  Ron Chi-Wai Kwok,et al.  Study of pollution dispersion in urban areas using Computational Fluid Dynamics (CFD) and Geographic Information System (GIS) , 2005, Environ. Model. Softw..

[4]  Vijay Sivaraman,et al.  HazeEst: Machine Learning Based Metropolitan Air Pollution Estimation From Fixed and Mobile Sensors , 2017, IEEE Sensors Journal.

[5]  Igor Paprotny,et al.  Sensors and 'apps' for community-based: Atmospheric monitoring , 2012 .

[6]  Edward Ng,et al.  Developing Street-Level PM2.5 and PM10 Land Use Regression Models in High-Density Hong Kong with Urban Morphological Factors. , 2016, Environmental science & technology.

[7]  Haibo He,et al.  A Hierarchical Distributed Fog Computing Architecture for Big Data Analysis in Smart Cities , 2015, ASE BD&SI.

[8]  Jieping Ye,et al.  Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction , 2018, AAAI.

[9]  Alvear Alvear,et al.  Mobile Sensing Architecture for Air Pollution Monitoring , 2018 .

[10]  Lothar Thiele,et al.  On Rendezvous in Mobile Sensing Networks , 2013, REALWSN.

[11]  Rui Ma,et al.  Fine-Grained Air Pollution Inference with Mobile Sensing Systems , 2020, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[12]  Steve Hankey,et al.  Land Use Regression Models of On-Road Particulate Air Pollution (Particle Number, Black Carbon, PM2.5, Particle Size) Using Mobile Monitoring. , 2015, Environmental science & technology.

[13]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[14]  Yu Zheng,et al.  U-Air: when urban air quality inference meets big data , 2013, KDD.

[15]  Julie Wallace,et al.  Mobile monitoring of air pollution in cities: the case of Hamilton, Ontario, Canada. , 2009, Journal of environmental monitoring : JEM.

[16]  M. Brauer,et al.  High-Resolution Air Pollution Mapping with Google Street View Cars: Exploiting Big Data. , 2017, Environmental science & technology.

[17]  Derya Birant,et al.  ST-DBSCAN: An algorithm for clustering spatial-temporal data , 2007, Data Knowl. Eng..

[18]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[19]  Gb Stewart,et al.  The use of electrochemical sensors for monitoring urban air quality in low-cost, high-density networks , 2013 .

[20]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[21]  Joaquin Quiñonero Candela,et al.  Practical Lessons from Predicting Clicks on Ads at Facebook , 2014, ADKDD'14.

[22]  Peter C. Y. Chen,et al.  LSTM network: a deep learning approach for short-term traffic forecast , 2017 .

[23]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[24]  Ali Marjovi,et al.  High Resolution Air Pollution Maps in Urban Environments Using Mobile Sensor Networks , 2015, 2015 International Conference on Distributed Computing in Sensor Systems.

[25]  Matthias Ketzel,et al.  Analysis of the impact of inhomogeneous emissions in the Operational Street Pollution Model (OSPM) , 2015 .

[26]  Ole Hertel,et al.  The Operational Street Pollution Model (OSPM) , 1991 .

[27]  Ali Marjovi,et al.  Extending Urban Air Quality Maps Beyond the Coverage of a Mobile Sensor Network: Data Sources, Methods, and Performance Evaluation , 2017, EWSN.

[28]  Roland Zengerle,et al.  Computational fluid dynamics (CFD) software tools for microfluidic applications – A case study , 2008 .

[29]  R. Prinn,et al.  Estimation of atmospheric methane emissions between 1996 and 2001 using a three-dimensional global chemical transport model , 2006 .

[30]  L. Morawska,et al.  The rise of low-cost sensing for managing air pollution in cities. , 2015, Environment international.

[31]  Chee-Yee Chong,et al.  Sensor networks: evolution, opportunities, and challenges , 2003, Proc. IEEE.

[32]  Leichao Liang,et al.  Air Pollution Exposure and Physical Activity in China: Current Knowledge, Public Health Implications, and Future Research Needs , 2015, International journal of environmental research and public health.

[33]  Zhongfei Zhang,et al.  Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-Grained Air Quality , 2017, IEEE Transactions on Knowledge and Data Engineering.

[34]  Robert P. Dick,et al.  Multi-Group Encoder-Decoder Networks to Fuse Heterogeneous Data for Next-Day Air Quality Prediction , 2019, IJCAI.

[35]  Michael Heimbinder,et al.  Mapping urban air quality using mobile sampling with low-cost sensors and machine learning in Seoul, South Korea. , 2019, Environment international.

[36]  Lothar Thiele,et al.  Deriving high-resolution urban air pollution maps using mobile sensor nodes , 2015 .

[37]  Lothar Thiele,et al.  SCAN: Multi-Hop Calibration for Mobile Sensor Arrays , 2017, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[38]  Zhijun Li,et al.  AirCloud: a cloud-based air-quality monitoring system for everyone , 2014, SenSys.

[39]  Yafeng Yin,et al.  Robust signal timing optimization with environmental concerns , 2013 .

[40]  Tong Zhu,et al.  Use of a mobile laboratory to evaluate changes in on-road air pollutants during the Beijing 2008 Summer Olympics , 2009 .

[41]  Cláudio T. Silva,et al.  Visual Exploration of Big Spatio-Temporal Urban Data: A Study of New York City Taxi Trips , 2013, IEEE Transactions on Visualization and Computer Graphics.

[42]  M. Gauß,et al.  The EMEP MSC-W chemical transport model -- technical description , 2012 .