Thursday, November 11, 2010

Neuro-fuzzy Urban Air Quality Modelling

Haze over Kuala Lumpur.
Image via Wikipedia

Adaptive neuro-fuzzy modeling for prediction of ambient CO concentration at urban intersections and roadways (10 page pdf, Air Quality, Atmosphere & Health, May 19, 2010)

Modelling of urban air pollution has developed from purely statistical to deterministic but today’s article focuses on neuro-fuzzy techniques which bridges the use of “expert” modelling techniques from artifical intelligence research to estimate extremes as well as average concentrations- in this case, for carbon monoxide at the street/intersection level.

Key Quotes:

“There has been a substantial growth in road traffic over the years and that has resulted in increase in air pollution. In many cities across Europe, USA, Japan, China, and Singapore, vehicular exhaust emissions (VEEs) are now considered as one of the most important sources of urban air pollution”

“screening, assessment, and prediction of ambient air pollutant due to VEE in such urban corridors has become an essential requirement as a part of an efficient local/episodic urban air quality management plan”

“environmental damage is caused both by extreme as well as by the average concentrations of pollutants. Hence, the models should predict not only ‘extreme’ ranges but also the ‘middle’ ranges of pollutant concentrations, i.e., the entire range.”

“Two types of forecast models have been developed. The first model uses a fuzzy expert system and forecasts the possibility of high O3 concentration. The second model uses a neural network system to forecast daily maximum concentration of O3 on the following day”

“The fuzzy models are capable of analyzing linguistic information and efficiently carry out programming/processing with improved knowledge representation and uncertainty reasoning. In addition, the neuro-fuzzy modeling technique can interpret and analyze any kind of information (numeric, linguistic, and logical) and possesses self-learning, self-organizing, and self-tuning capabilities, thus improving the quality of forecasts. The present study was under taken to develop models for CO based on neuro-fuzzy approach for different seasons”


Enhanced by Zemanta

No comments:

Post a Comment