Machine learning and air quality modeling

TY - GEN

T1 - Machine learning and air quality modeling

AU - Keller, Christoph A.

AU - Evans, Mathew J.

AU - Kutz, J. Nathan

AU - Pawson, Steven

PY - 2018/1/12

Y1 - 2018/1/12

N2 - Air quality models are limited by the computational costs associated with the simulation of the complex chemical and dynamical processes of reactive pollutants in the atmosphere. We discuss here the potential usage of machine learning and reduced-order modeling techniques to mitigate some of these limitations. We first give an overview of three new methods emerging from the field of signal processing - sparse sampling, randomized matrix decompositions and the construction of reduced order models - and discuss them in the context of air quality modeling. In the second part we discuss the substitution of the standard chemical solver of the chemistry model with a random forest regression model trained through machine learning. We find that this approach shows promising initial results for important air pollutants such as ozone (O3), predicting concentrations that deviate less than 10% from the values computed by the traditional model. The here highlighted methods all have the potential to significantly reduce the computational burden of air quality models while maintaining the model's capability to capture all features relevant to air quality. Such lightweight air quality models offer new opportunities for air quality forecasting and to assimilate the rapidly increasing array of air quality observations.

AB - Air quality models are limited by the computational costs associated with the simulation of the complex chemical and dynamical processes of reactive pollutants in the atmosphere. We discuss here the potential usage of machine learning and reduced-order modeling techniques to mitigate some of these limitations. We first give an overview of three new methods emerging from the field of signal processing - sparse sampling, randomized matrix decompositions and the construction of reduced order models - and discuss them in the context of air quality modeling. In the second part we discuss the substitution of the standard chemical solver of the chemistry model with a random forest regression model trained through machine learning. We find that this approach shows promising initial results for important air pollutants such as ozone (O3), predicting concentrations that deviate less than 10% from the values computed by the traditional model. The here highlighted methods all have the potential to significantly reduce the computational burden of air quality models while maintaining the model's capability to capture all features relevant to air quality. Such lightweight air quality models offer new opportunities for air quality forecasting and to assimilate the rapidly increasing array of air quality observations.

KW - Air Quality Modeling

KW - Big Data Analytics

KW - Machine Learning

KW - Statistical Sub-sampling

UR - http://www.scopus.com/inward/record.url?scp=85047778870&partnerID=8YFLogxK

U2 - 10.1109/BigData.2017.8258500

DO - 10.1109/BigData.2017.8258500

M3 - Conference contribution

VL - 2018-January

SP - 4570

EP - 4576

BT - Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017

PB - IEEE

T2 - 5th IEEE International Conference on Big Data, Big Data 2017

Y2 - 11 December 2017 through 14 December 2017

ER -