Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm

<p>Simulating aerosol chemistry and interactions (ACI) is crucial in climate and atmospheric modeling, yet conventional numerical schemes are computationally intensive due to the stiff differential equations and iterative methods involved. While artificial intelligence (AI) has demonstrated p...

Full description

Saved in:
Bibliographic Details
Main Authors: Z. Xia, C. Zhao, Z. Yang, Q. Du, J. Feng, C. Jin, J. Shi, H. An
Format: Article
Language:English
Published: Copernicus Publications 2025-06-01
Series:Atmospheric Chemistry and Physics
Online Access:https://acp.copernicus.org/articles/25/6197/2025/acp-25-6197-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434622663852032
author Z. Xia
C. Zhao
C. Zhao
C. Zhao
Z. Yang
Q. Du
J. Feng
C. Jin
J. Shi
H. An
H. An
author_facet Z. Xia
C. Zhao
C. Zhao
C. Zhao
Z. Yang
Q. Du
J. Feng
C. Jin
J. Shi
H. An
H. An
author_sort Z. Xia
collection DOAJ
description <p>Simulating aerosol chemistry and interactions (ACI) is crucial in climate and atmospheric modeling, yet conventional numerical schemes are computationally intensive due to the stiff differential equations and iterative methods involved. While artificial intelligence (AI) has demonstrated potential in accelerating photochemistry simulations, it has not been applied for simulating the full ACI processes, which encompass not only chemical reactions but also other processes, such as nucleation and coagulation. To bridge this gap, we develop a novel Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI), focusing initially on inorganic aerosols. Trained based on a conventional scheme, it has been validated in both offline and online modes (referring to whether it is coupled into a three-dimensional atmospheric model). Results demonstrate that AIMACI is not only comparable with conventional schemes in spatial distributions, temporal variations, and evolution of particle size distribution of main aerosol species, including water content in aerosols, but also exhibits robust generalization ability, reliably simulating one month under different environmental conditions across four seasons despite being trained on limited data from merely 16 d. Notably, it exhibits <span class="inline-formula">∼</span>5<span class="inline-formula">×</span> speedup with a single CPU and <span class="inline-formula">∼</span>277<span class="inline-formula">×</span> speedup with a single GPU, compared with conventional schemes. However, the stability of AIMACI for year-scale global simulations remains to be seen, requiring further testing. AIMACI's generalization capability and its modular design suggest potential for future coupling to global climate models, which are expected to enhance the precision and efficiency of ACI simulations in climate modeling that neglects or simplifies ACI processes.</p>
format Article
id doaj-art-72ef9acbd7b54be09fc3b3a968fa44b9
institution Kabale University
issn 1680-7316
1680-7324
language English
publishDate 2025-06-01
publisher Copernicus Publications
record_format Article
series Atmospheric Chemistry and Physics
spelling doaj-art-72ef9acbd7b54be09fc3b3a968fa44b92025-08-20T03:26:35ZengCopernicus PublicationsAtmospheric Chemistry and Physics1680-73161680-73242025-06-01256197621810.5194/acp-25-6197-2025Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithmZ. Xia0C. Zhao1C. Zhao2C. Zhao3Z. Yang4Q. Du5J. Feng6C. Jin7J. Shi8H. An9H. An10Deep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software, University of Science and Technology of China, Hefei, ChinaDeep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software, University of Science and Technology of China, Hefei, ChinaLaoshan Laboratory, Qingdao, ChinaCAS Center for Excellence in Comparative Planetology, University of Science and Technology of China, Hefei, ChinaDeep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software, University of Science and Technology of China, Hefei, ChinaDeep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software, University of Science and Technology of China, Hefei, ChinaDeep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software, University of Science and Technology of China, Hefei, ChinaDeep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software, University of Science and Technology of China, Hefei, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, ChinaLaoshan Laboratory, Qingdao, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China<p>Simulating aerosol chemistry and interactions (ACI) is crucial in climate and atmospheric modeling, yet conventional numerical schemes are computationally intensive due to the stiff differential equations and iterative methods involved. While artificial intelligence (AI) has demonstrated potential in accelerating photochemistry simulations, it has not been applied for simulating the full ACI processes, which encompass not only chemical reactions but also other processes, such as nucleation and coagulation. To bridge this gap, we develop a novel Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI), focusing initially on inorganic aerosols. Trained based on a conventional scheme, it has been validated in both offline and online modes (referring to whether it is coupled into a three-dimensional atmospheric model). Results demonstrate that AIMACI is not only comparable with conventional schemes in spatial distributions, temporal variations, and evolution of particle size distribution of main aerosol species, including water content in aerosols, but also exhibits robust generalization ability, reliably simulating one month under different environmental conditions across four seasons despite being trained on limited data from merely 16 d. Notably, it exhibits <span class="inline-formula">∼</span>5<span class="inline-formula">×</span> speedup with a single CPU and <span class="inline-formula">∼</span>277<span class="inline-formula">×</span> speedup with a single GPU, compared with conventional schemes. However, the stability of AIMACI for year-scale global simulations remains to be seen, requiring further testing. AIMACI's generalization capability and its modular design suggest potential for future coupling to global climate models, which are expected to enhance the precision and efficiency of ACI simulations in climate modeling that neglects or simplifies ACI processes.</p>https://acp.copernicus.org/articles/25/6197/2025/acp-25-6197-2025.pdf
spellingShingle Z. Xia
C. Zhao
C. Zhao
C. Zhao
Z. Yang
Q. Du
J. Feng
C. Jin
J. Shi
H. An
H. An
Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm
Atmospheric Chemistry and Physics
title Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm
title_full Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm
title_fullStr Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm
title_full_unstemmed Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm
title_short Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm
title_sort toward a learnable artificial intelligence model for aerosol chemistry and interactions aimaci based on the multi head self attention algorithm
url https://acp.copernicus.org/articles/25/6197/2025/acp-25-6197-2025.pdf
work_keys_str_mv AT zxia towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT czhao towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT czhao towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT czhao towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT zyang towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT qdu towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT jfeng towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT cjin towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT jshi towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT han towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm
AT han towardalearnableartificialintelligencemodelforaerosolchemistryandinteractionsaimacibasedonthemultiheadselfattentionalgorithm