An international study calls for a balanced partnership between AI and Earth sciences to address environmental challenges

An international research team, including participation from the University of Valencia, has published an article in Nature Geoscience advocating for a more collaborative and balanced approach between artificial intelligence (AI) and Earth sciences. The study supports the creation of a new field-AIXES (Artificial Intelligence and Earth Sciences)--that will enhance both areas and provide benefits in tackling future environmental challenges.

The increasing application of AI across a wide range of sectors presents significant opportunities for advancement in Earth sciences. However, without an appropriate interdisciplinary collaborative framework, there is a risk of devaluing essential geoscientific methods and knowledge, which could hinder efforts to address environmental challenges.

Entitled "Towards scientific synergy between AI and Earth sciences", the article published in Nature Geoscience underlines the need to foster this interdisciplinary field that integrates AI advancements and the expertise and knowledge of Earth sciences.

The article explores how AI can improve the collection, processing and analysis of geospatial data while warning of the risks of relying solely on AI without considering traditional Earth science methodologies. According to the authors, this could lead to misinterpretations and untenable decisions.

"The use of AI in Earth sciences has often been seen as a magical solution to all challenges, which can result in a dangerous imbalance", says Min Chen, a researcher at Nanjing Normal University (China) and co-lead author of the study, alongside Zhen Qian, a scientist at the Potsdam Institute for Climate Impact Research.

"The relevance of our research lies in AI’s ability not only to process vast amounts of data but also to generate new ways of understanding and predicting complex Earth system processes. This interdisciplinary approach is crucial for developing more effective and sustainable solutions to the environmental challenges we face today", adds Gustau Camps-Valls, coordinator of Image & Signal Processing (ISP-IPL) at the University of Valencia and one of the article’s authors.

The study advocates for the development of this new field of research, AIXES, aimed at exploiting the mutual advantages of both disciplines and improving predictive capabilities in climate modelling, natural disaster prevention and the understanding of complex geophysical phenomena, while incorporating ethical and sustainable principles in the development and use of AI technologies.

The publication of the article in Nature Geoscience also seeks to inspire future research and policies that promote more responsible and effective use of artificial intelligence in science and society.

Reference:

Towards scientific synergy between AI and Earth sciences . Min Chen, Zhen Qian, Niklas Boers, Felix Creutzig, Gustau Camps-Valls, Klaus Hubacek, Christophe Claramunt, John P. Wilson, Stefano Nativi, Anthony J. Jakeman, R. Dietmar Müller, Michael Batty, Chenghu Zhou, Fahu Chen, Qiao Wang, Fan Zhang, C. Michael Barton, Josef Strobl, Michael Meadows, Carlo Ratti, Philipp Hess, Qingsong Xu, Zhixin Zhang, Qiushi Gu, A-Xing Zhu, Hui Lin, Linwang Yuan & Guonian Lü