Neural network emulator for atmospheric chemical ODE
Year of publication
2025
Authors
Liu Zhi-Song; Clusius Petri; Boy Michael
Abstract
Modelling atmospheric chemistry is complex and computationally intense. Given the recent success of Deep neural networks in digital signal processing, we propose a Neural Network Emulator for fast chemical concentration modelling. We consider atmospheric chemistry as a time-dependent Ordinary Differential Equation. To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE, an Attention based Neural Network Emulator (NNE) that can model the atmospheric chemistry as a neural ODE process. To efficiently capture temporal patterns in chemical concentration changes, we implement sinusoidal time embedding to represent periodic tendencies over time. Additionally, we leverage the Fourier neural operator to model the ODE process, enhancing computational efficiency and facilitating the learning of complex dynamical behavior. We introduce three physics-informed loss functions, targeting conservation laws and reaction rate constraints, to guide the training optimization process. To evaluate our model, we introduce a unique, large-scale chemical dataset designed for neural network training and validation, which can serve as a benchmark for future studies. The extensive experiments show that our approach achieves state-of-the-art performance in modelling accuracy and computational speed.
Show moreOrganizations and authors
Publication type
Publication format
Article
Parent publication type
Journal
Article type
Original article
Audience
ScientificPeer-reviewed
Peer-ReviewedMINEDU's publication type classification code
A1 Journal article (refereed), original researchPublication channel information
Journal
Publisher
Volume
184
Article number
107106
ISSN
Publication forum
Open access
Open access in the publisher’s service
No
Self-archived
No
Other information
Fields of science
Computer and information sciences
Keywords
[object Object],[object Object],[object Object],[object Object],[object Object]
Internationality of the publisher
International
International co-publication
No
Co-publication with a company
No
DOI
10.1016/j.neunet.2024.107106
The publication is included in the Ministry of Education and Culture’s Publication data collection
Yes