Predicting the Occurrence of Haze Events in Southeast Asia using Machine Learning Algorithms
Abstract
Severe local- and regional-scale air pollution episodes typically originate from 1) high emissions of air pollutants, 2) poor dispersion conditions, and 3) trans-boundary pollutant transport. Biomass burning activities have become more frequent in Southeast Asia, especially in Sumatra, Borneo, and the mainland Southeast. Trans-boundary transport of biomass burning aerosols often lead to air quality problems in the region. Furthermore, particulate pollutants from human activities besides biomass burning also play an important role in the air quality of Southeast Asia. Singapore, for example, has a dynamic industrial sector including chemical, electric and metallurgic industries, and is the region's major petroleum-refining center. In addition, natural gas and oil power plants, waste incinerators, active port traffic, and a major regional airport further complicate Singapore's air quality issues. In this study, we compare five Machine Learning algorithms: k-Nearest Neighbors, Linear Support Vector Machine, Decision Tree, Random Forest and Artificial Neural Network, to identify haze patterns and determine variable importance. The algorithms were trained using local atmospheric data (i.e. months, atmospheric conditions, wind direction and relative humidity) from three observation stations in Singapore (Changi, Seletar and Paya Labar). We find that the algorithms reveal the associations in data within and between the stations, and provide in-depth interpretation of the haze sources. The algorithms also allow us to predict the probability of haze episodes in Singapore and to determine the correlation between this probability and atmospheric conditions.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2017
- Bibcode:
- 2017AGUFMPA31C..02L
- Keywords:
-
- 0493 Urban systems;
- BIOGEOSCIENCES;
- 1964 Real-time and responsive information delivery;
- INFORMATICS;
- 4329 Sustainable development;
- NATURAL HAZARDS;
- 6334 Regional planning;
- POLICY SCIENCES