Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Siwik, Leszek, Sikora, Maciej, Leszczyńska, Natalia, Ciesielski, Tomasz Maciej, Valseth, Eirik, Olivares, Manuela Bastidas, Łoś, Marcin, Służalec, Tomasz, Leszczyński, Jacek, Paszyński, Maciej
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913059854876672
author Siwik, Leszek
Sikora, Maciej
Leszczyńska, Natalia
Ciesielski, Tomasz Maciej
Valseth, Eirik
Olivares, Manuela Bastidas
Łoś, Marcin
Służalec, Tomasz
Leszczyński, Jacek
Paszyński, Maciej
author_facet Siwik, Leszek
Sikora, Maciej
Leszczyńska, Natalia
Ciesielski, Tomasz Maciej
Valseth, Eirik
Olivares, Manuela Bastidas
Łoś, Marcin
Służalec, Tomasz
Leszczyński, Jacek
Paszyński, Maciej
contents In this paper, we propose a Physics-Informed Neural Network framework for time-dependent simulations of pollution propagation originating from moving emission sources. We formulate a robust variational framework for the time-dependent advection-diffusion problem and establish the boundedness and inf-sup stability of the corresponding discrete weak formulation. Based on this mathematical foundation, we construct a robust loss function that is directly related to the true approximation error, defined as the difference between the neural network approximation and the (unknown) exact solution. Additionally, a collocation-based strategy is introduced to speed up neural network training. As a case study, we investigate pollution propagation caused by snowmobile traffic in Longyearbyen, Spitsbergen, supported by detailed in-field measurements collected using dedicated sensors. The proposed framework is applied to analyze the effects of thermal inversion on pollutant accumulation. Our results demonstrate that thermal inversion traps dense and humid air masses near the ground, significantly enhancing particulate matter (PM) concentration and worsening local air quality.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23003
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen
Siwik, Leszek
Sikora, Maciej
Leszczyńska, Natalia
Ciesielski, Tomasz Maciej
Valseth, Eirik
Olivares, Manuela Bastidas
Łoś, Marcin
Służalec, Tomasz
Leszczyński, Jacek
Paszyński, Maciej
Machine Learning
Neural and Evolutionary Computing
65, 35, 68T07
G.1.8; G.4; I.6.7; I.2.m
In this paper, we propose a Physics-Informed Neural Network framework for time-dependent simulations of pollution propagation originating from moving emission sources. We formulate a robust variational framework for the time-dependent advection-diffusion problem and establish the boundedness and inf-sup stability of the corresponding discrete weak formulation. Based on this mathematical foundation, we construct a robust loss function that is directly related to the true approximation error, defined as the difference between the neural network approximation and the (unknown) exact solution. Additionally, a collocation-based strategy is introduced to speed up neural network training. As a case study, we investigate pollution propagation caused by snowmobile traffic in Longyearbyen, Spitsbergen, supported by detailed in-field measurements collected using dedicated sensors. The proposed framework is applied to analyze the effects of thermal inversion on pollutant accumulation. Our results demonstrate that thermal inversion traps dense and humid air masses near the ground, significantly enhancing particulate matter (PM) concentration and worsening local air quality.
title Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen
topic Machine Learning
Neural and Evolutionary Computing
65, 35, 68T07
G.1.8; G.4; I.6.7; I.2.m
url https://arxiv.org/abs/2604.23003