Iterative Optimization of a Multi-compartmental Air Quality Modelling System

Investor logo


Year of publication 2015
Type Article in Proceedings
Conference Tenth Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2015)
MU Faculty or unit

Institute of Computer Science

Field Informatics
Keywords Persistent Organic Pollutants;POP;CMAQ iterative optimization;neural networks; BaP concentrations in soil
Description In this paper, we present an application for iterative optimization of a multi-compartment environmental fate and transport modelling system based on atmospheric measurements of Persistent Organic Pollutants (POPs) from the European Monitoring and Evaluation Programme (EMEP). The modelling framework involved linking science models such as the Weather Research and Forecasting (WRF) model and an experimental version of the Community Multiscale Air Quality System (CMAQ) that includes treatment of POPs species in the atmosphere, and an soil compartment that simulates the soil-air exchange. The initialization step of multi-compartment models for POPs is plagued by uncertainties in estimating the current soil burden and spatial distributions. The goal of this work is to demonstrate a first application of the modelling framework which aims to improve the reliability of modelled POP estimates in air by controlling the additional fluxes from the soil compartment. Using several machine learning methods, the system is able to make the current simulations better correspond to real complex processes occurring in the environment.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info