Modelling Climate Data Factors Influencing Fine-Particulate Matter Density in the Near-Ground Atmosphere
| Autor: | A. Ghobakhlou, S Zandi, Philip Sallis |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Adaptive neuro fuzzy inference system
010504 meteorology & atmospheric sciences Fine particulate Humidity 010501 environmental sciences Particulates Atmospheric sciences 01 natural sciences Wind speed Atmosphere Multilayer perceptron Linear regression Environmental science 0105 earth and related environmental sciences |
| Zdroj: | 2017 Asia Modelling Symposium (AMS). |
| DOI: | 10.1109/ams.2017.15 |
| Popis: | this paper describes the relationship of climate toatmospheric particulate matter. The climate factors ofprecipitation, humidity, temperature and wind speed aremapped to the fine-particulate substances measured as being 2.5micrometers in diameter (PM2.5). Using the climate variablesas indicators, the paper illustrates a method for estimating theconcentration potential for PM2.5 in the near-groundatmosphere. The preferred method described is selected fromthree analytical approaches compared using a common data set.The three methods used are Multiple Linear Regression (MLR),Multilayer Perceptron (MLP) and Fuzzy Neural Networksmetho |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|