PM10 Data Assimilation on Real-time Agent-based Simulation using Machine Learning Models: case of Dakar Urban Air Pollution Study

被引：5

作者：

Ngom, Bassirou ^{[1
,3
]}

Diallo, Moussa ^{[2
]}

Seyc, Madoune Robert ^{[1
,3
]}

Drame, Mamadou Simina ^{[1
]}

Cambier, Christophe ^{[3
]}

Marilleau, Nicolas ^{[3
]}

机构：

[1] Univ Cheikh Anta Diop, Fac Sci & Tech, Dakar, Senegal

[2] Univ Cheikh Anta Diop, Polytech Inst ESP, Dakar, Senegal

[3] UMI UMMISCO IRD UCAD, Paris, France

来源：

PROCEEDINGS OF THE 2021 IEEE/ACM 25TH INTERNATIONAL SYMPOSIUM ON DISTRIBUTED SIMULATION AND REAL TIME APPLICATIONS (DS-RT 2021) | 2021年

关键词：

Data Assimilation; Machine learning; times series models; Auto-regession; multi-agent Simulation; real-time Multi-agent Simulation;

D O I：

10.1109/DS-RT52167.2021.9576143

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

High air pollution is a major health risk. Heavy urbanisation favours the degradation of air quality in large cities such as Dakar. In this city, the annual rate of PM10 exposure in the city is above the threshold recommended by the World Health Organisation (WHO). However, in order to set up a national pollution monitoring network, our approach consists in combining system observations (data from different stations) with a multi-agent simulation. In this paper, we present a model for assimilating PM10 pollution data coupled with a multi-agent real-time simulation. This assimilation model is based on a machine learning method. We performed several simulations to show that the autoregressive ARIMA model is better suited for predicting PM10 pollution data. Then we discussed the relevance of studying other parameters of the model.

引用

页数：4

共 8 条

[1]

[Anonymous], 2002, INTRO TIME SERIES FO

[2]

[Anonymous], 1999, MULTIAGENT SYSTEMS I

[3] Individual exposure level following indoor and outdoor air pollution exposure in Dakar (Senegal) [J].