IBM is testing a prototype computer system that is capable of learning to predict the severity of air pollution in different parts of Beijing, which is surrounded by many factories fueled by coal.
The system uses large quantities of data from several different models, and could eventually offer specific recommendations on how to reduce pollution. For example, the system could recommend closing certain factories or temporarily restricting the number of vehicles on the road.
The system can generate high-resolution forecasts 72 hours ahead of time. "Our researchers are currently expanding the capability of the system to provide medium- and long-term [up to 10 days ahead] as well as pollutant-source tracking, 'what-if' scenario analysis, and decision support on emission reduction actions," says IBM Research China director Xiaowei Shen.
IBM's cognitive computing approach encompasses natural-language processing and statistical techniques originally developed for the Watson supercomputer. IBM uses data provided by the Beijing Environmental Protection Bureau to refine its models, and Shen says the predictions have a resolution of a kilometer and are 30 percent more precise than those derived through conventional approaches. He also notes the system uses "adaptive machine learning" to determine the best mix of models to use.
From Technology Review
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found