Generative Model Based Fine-Grained Air Pollution Inference for Mobile Sensing Systems

Rui Ma, Xiangxiang Xu, Hae Young Noh, Pei Zhang, Lin Zhang

Abstract

Mobile sensing systems are deployed for urban air pollution monitoring to increase coverage over a city. However, the sampling irregularity brings great challenges for fine-grained pollution field recovery. To address this problem, we proposed a generative model based inference algorithm. By modeling the air pollution evolution and data sampling process separately, the temporal-spatial correlation of pollution field can be considered with irregular sampled data. We use a convolutional long-short term memory structure in the generative model and train it with the scattered observations from mobile sensing. Evaluations on synthesized data and a deployment in the city of Tianjin show that our algorithm accurately captures fine-grained PM2.5 pollution patterns and changes. The average inference error is 6.7μg/m3, which achieves 23.8% improvement over existing techniques.
BibTeX
@inproceedings{ma2018generative,
  author = {Rui Ma and Xiangxiang Xu and Hae Young Noh and Pei Zhang and Lin Zhang},
  title = {{Generative Model Based Fine-Grained Air Pollution Inference for Mobile Sensing Systems}},
  booktitle = {SenSys},
  year = {2018},
  doi = {10.1145/3274783.3275216},
}

Loading related content...

Figure