Large language models reveal big disparities in current wildfire research
Abstract Contemporary fire-human-climate nexus has led to a surge in publication numbers across diverse research disciplines beyond the capability of experts from a single discipline. Here, we employed a generalized large language model to capture the dynamics of wildfire research published between...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Communications Earth & Environment |
| Online Access: | https://doi.org/10.1038/s43247-024-01341-7 |
| _version_ | 1827291315063226368 |
|---|---|
| author | Zhengyang Lin Anping Chen Xuhui Wang Zhihua Liu Shilong Piao |
| author_facet | Zhengyang Lin Anping Chen Xuhui Wang Zhihua Liu Shilong Piao |
| author_sort | Zhengyang Lin |
| collection | DOAJ |
| description | Abstract Contemporary fire-human-climate nexus has led to a surge in publication numbers across diverse research disciplines beyond the capability of experts from a single discipline. Here, we employed a generalized large language model to capture the dynamics of wildfire research published between 1980 and 2022. More than 60,000 peer-reviewed papers were scanned and analyzed. Through integrating geographical metadata extracted by the artificial intelligence and satellite wildfire datasets, we found large disparities in geographic patterns and research themes. The hottest spot of wildfire research is western United States, accounting for 15% of publications but only 0.5% of global burnt area, while the world’s most widely burnt region, like Siberia and Africa are largely underrepresented by contemporary publications. Similar discrepancies are found between the fuel of wildfire and its ignition and climatic drivers, between socioeconomic development and wildfire mitigation, raising concerns on sustainable wildfire managements and calling for further artificial intelligence-aided transdisciplinary collaborations. |
| first_indexed | 2024-04-24T12:34:51Z |
| format | Article |
| id | doaj.art-2cc81e2686454c6297c48362a78468bd |
| institution | Directory Open Access Journal |
| issn | 2662-4435 |
| language | English |
| last_indexed | 2024-04-24T12:34:51Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Earth & Environment |
| spelling | doaj.art-2cc81e2686454c6297c48362a78468bd2024-04-07T11:31:54ZengNature PortfolioCommunications Earth & Environment2662-44352024-04-01511610.1038/s43247-024-01341-7Large language models reveal big disparities in current wildfire researchZhengyang Lin0Anping Chen1Xuhui Wang2Zhihua Liu3Shilong Piao4Institute of Carbon Neutrality, Sino-French Institute for Earth System Science, College of Urban and Environmental Sciences, Peking UniversityDepartment of Biology and Graduate Degree Program in Ecology, Colorado State UniversityInstitute of Carbon Neutrality, Sino-French Institute for Earth System Science, College of Urban and Environmental Sciences, Peking UniversityCAS Key Laboratory of Forest Ecology and Management, Institute of Applied Ecology, Chinese Academy of SciencesInstitute of Carbon Neutrality, Sino-French Institute for Earth System Science, College of Urban and Environmental Sciences, Peking UniversityAbstract Contemporary fire-human-climate nexus has led to a surge in publication numbers across diverse research disciplines beyond the capability of experts from a single discipline. Here, we employed a generalized large language model to capture the dynamics of wildfire research published between 1980 and 2022. More than 60,000 peer-reviewed papers were scanned and analyzed. Through integrating geographical metadata extracted by the artificial intelligence and satellite wildfire datasets, we found large disparities in geographic patterns and research themes. The hottest spot of wildfire research is western United States, accounting for 15% of publications but only 0.5% of global burnt area, while the world’s most widely burnt region, like Siberia and Africa are largely underrepresented by contemporary publications. Similar discrepancies are found between the fuel of wildfire and its ignition and climatic drivers, between socioeconomic development and wildfire mitigation, raising concerns on sustainable wildfire managements and calling for further artificial intelligence-aided transdisciplinary collaborations.https://doi.org/10.1038/s43247-024-01341-7 |
| spellingShingle | Zhengyang Lin Anping Chen Xuhui Wang Zhihua Liu Shilong Piao Large language models reveal big disparities in current wildfire research Communications Earth & Environment |
| title | Large language models reveal big disparities in current wildfire research |
| title_full | Large language models reveal big disparities in current wildfire research |
| title_fullStr | Large language models reveal big disparities in current wildfire research |
| title_full_unstemmed | Large language models reveal big disparities in current wildfire research |
| title_short | Large language models reveal big disparities in current wildfire research |
| title_sort | large language models reveal big disparities in current wildfire research |
| url | https://doi.org/10.1038/s43247-024-01341-7 |
| work_keys_str_mv | AT zhengyanglin largelanguagemodelsrevealbigdisparitiesincurrentwildfireresearch AT anpingchen largelanguagemodelsrevealbigdisparitiesincurrentwildfireresearch AT xuhuiwang largelanguagemodelsrevealbigdisparitiesincurrentwildfireresearch AT zhihualiu largelanguagemodelsrevealbigdisparitiesincurrentwildfireresearch AT shilongpiao largelanguagemodelsrevealbigdisparitiesincurrentwildfireresearch |