AirGPT: pioneering the convergence of conversational AI with atmospheric science
Abstract Large language models (LLMs) face significant limitations in specialized scientific domains due to their inability to perform data analysis and their tendency to generate inaccurate information. This challenge is particularly critical in air quality management, where precise analysis is ess...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | npj Climate and Atmospheric Science |
| Online Access: | https://doi.org/10.1038/s41612-025-01070-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849726194601164800 |
|---|---|
| author | Jun Song Chendong Ma Maohao Ran |
| author_facet | Jun Song Chendong Ma Maohao Ran |
| author_sort | Jun Song |
| collection | DOAJ |
| description | Abstract Large language models (LLMs) face significant limitations in specialized scientific domains due to their inability to perform data analysis and their tendency to generate inaccurate information. This challenge is particularly critical in air quality management, where precise analysis is essential for addressing climate change and pollution control initiatives. To bridge this gap, we present AirGPT, a computational framework that integrates conversational AI with atmospheric science expertise through a curated corpus of peer-reviewed literature and specialized data analysis capabilities. Through a novel architecture combining natural language processing and domain-specific analytical tools, AirGPT achieved higher accuracy in air quality assessments compared to standard LLMs, including GPT-4o. Experimental results demonstrate superior capabilities in providing accurate regulatory information, performing fundamental data analysis, and generating location-specific management recommendations, as validated through case studies in metropolitan areas such as Beijing. |
| format | Article |
| id | doaj-art-36304049f80145e699ca58320fc16fdd |
| institution | DOAJ |
| issn | 2397-3722 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Climate and Atmospheric Science |
| spelling | doaj-art-36304049f80145e699ca58320fc16fdd2025-08-20T03:10:16ZengNature Portfolionpj Climate and Atmospheric Science2397-37222025-05-018111210.1038/s41612-025-01070-4AirGPT: pioneering the convergence of conversational AI with atmospheric scienceJun Song0Chendong Ma1Maohao Ran2Department of Geography, Hong Kong Baptist UniversityDepartment of Geography, Hong Kong Baptist UniversityDepartment of Geography, Hong Kong Baptist UniversityAbstract Large language models (LLMs) face significant limitations in specialized scientific domains due to their inability to perform data analysis and their tendency to generate inaccurate information. This challenge is particularly critical in air quality management, where precise analysis is essential for addressing climate change and pollution control initiatives. To bridge this gap, we present AirGPT, a computational framework that integrates conversational AI with atmospheric science expertise through a curated corpus of peer-reviewed literature and specialized data analysis capabilities. Through a novel architecture combining natural language processing and domain-specific analytical tools, AirGPT achieved higher accuracy in air quality assessments compared to standard LLMs, including GPT-4o. Experimental results demonstrate superior capabilities in providing accurate regulatory information, performing fundamental data analysis, and generating location-specific management recommendations, as validated through case studies in metropolitan areas such as Beijing.https://doi.org/10.1038/s41612-025-01070-4 |
| spellingShingle | Jun Song Chendong Ma Maohao Ran AirGPT: pioneering the convergence of conversational AI with atmospheric science npj Climate and Atmospheric Science |
| title | AirGPT: pioneering the convergence of conversational AI with atmospheric science |
| title_full | AirGPT: pioneering the convergence of conversational AI with atmospheric science |
| title_fullStr | AirGPT: pioneering the convergence of conversational AI with atmospheric science |
| title_full_unstemmed | AirGPT: pioneering the convergence of conversational AI with atmospheric science |
| title_short | AirGPT: pioneering the convergence of conversational AI with atmospheric science |
| title_sort | airgpt pioneering the convergence of conversational ai with atmospheric science |
| url | https://doi.org/10.1038/s41612-025-01070-4 |
| work_keys_str_mv | AT junsong airgptpioneeringtheconvergenceofconversationalaiwithatmosphericscience AT chendongma airgptpioneeringtheconvergenceofconversationalaiwithatmosphericscience AT maohaoran airgptpioneeringtheconvergenceofconversationalaiwithatmosphericscience |