A RBF-FD Physics-Informed Machine Learning Approach to Air Pollution Source Estimation

被引：0

作者：

Georges, Didier ^{[1
]}

Leirens, Sylvain ^{[2
]}

Lopez-Ferber, Roman ^{[2
]}

机构：

[1] Univ Grenoble Alpes, Grenoble INP Inst Engn & Management, GIPSA Lab, CNRS, F-38000 Grenoble, France

[2] Univ Grenoble Alpes, Leti, CEA, F-38000 Grenoble, France

来源：

IFAC PAPERSONLINE | 2024年 / 58卷 / 25期

关键词：

air pollution; source term estimation; advection-diffusion PDE; physics-informed machine learning; RBF-FD approximation;

D O I：

10.1016/j.ifacol.2024.10.245

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we propose a source term estimation approach for air pollution monitoring based on a physics-informed machine learning approach using radial basis function-generated finite differences (RBF-FD) approximations, rather than using neural network-based approximations. This approach looks promising for detecting a static pollution source, at a particularly low computing cost and based on a network of fixed or mobile sensors. A 3D case study demonstrates the effectiveness of the approach.

引用

页码：102 / 107

页数：6

共 20 条

[1] [Anonymous], 2019, Air Pollution in Asia and the Pacific: Science-based Solutions, DOI DOI 10.13140/2.1.4203.8569
[2] Improving Numerical Dispersion Modelling in Built Environments with Data Assimilation Using the Iterative Ensemble Kalman Smoother
Defforge, Cecile L.
Carissimo, Bertrand
Bocquet, Marc
Bresson, Raphael
Armand, Patrick
[J]. BOUNDARY-LAYER METEOROLOGY, 2021, 179 (02) : 209 - 240
[3] A guide to RBF-generated finite differences for nonlinear transport: Shallow water simulations on a sphere
Flyer, Natasha
Lehto, Erik
Blaise, Sebastien
Wright, Grady B.
St-Cyr, Amik
[J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2012, 231 (11) : 4078 - 4095
[4] Fornberg B., 2015, PRIMER RADIAL BASIS, DOI DOI 10.1137/1.9781611974041
[5] Iske A., 2004, Lecture Notes in Computational Science and Engineering (LNCSE)
[6] Reconstruction of an atmospheric tracer source in an urban-like environment
Kumar, Pramod
Feiz, Amir-Ali
Singh, Sarvesh Kumar
Ngae, Pierre
Turbelin, Gregory
[J]. JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2015, 120 (24) : 12589 - 12604
[7] Complexity reduction in explicit MPC: A reachability approach
Kvasnica, Michal
Bakarac, Peter
Klauco, Martin
[J]. SYSTEMS & CONTROL LETTERS, 2019, 124 : 19 - 26
[8] The application of machine learning to air pollution research: A bibliometric analysis
Li, Yunzhe
Sha, Zhipeng
Tang, Aohan
Goulding, Keith
Liu, Xuejun
[J]. ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY, 2023, 257
[9] Lopez-Ferber R., 2024, P EUROPEAN CONTROL C
[10] Lopez-Ferber R., 2024, Ph.D. thesis

← 1 2 →