Artificial intelligence for geoscience: Progress, challenges, and perspectives

• Published in: Innovation (New York, NY) Vol. 5; no. 5; p. 100691
• Main Authors: Zhao, Tianjie, Wang, Sheng, Ouyang, Chaojun, Chen, Min, Liu, Chenying, Zhang, Jin, Yu, Long, Wang, Fei, Xie, Yong, Li, Jun, Wang, Fang, Grunwald, Sabine, Wong, Bryan M., Zhang, Fan, Qian, Zhen, Xu, Yongjun, Yu, Chengqing, Han, Wei, Sun, Tao, Shao, Zezhi, Qian, Tangwen, Chen, Zhao, Zeng, Jiangyuan, Zhang, Huai, Letu, Husi, Zhang, Bing, Wang, Li, Luo, Lei, Shi, Chong, Su, Hongjun, Zhang, Hongsheng, Yin, Shuai, Huang, Ni, Zhao, Wei, Li, Nan, Zheng, Chaolei, Zhou, Yang, Huang, Changping, Feng, Defeng, Xu, Qingsong, Wu, Yan, Hong, Danfeng, Wang, Zhenyu, Lin, Yinyi, Zhang, Tangtang, Kumar, Prashant, Plaza, Antonio, Chanussot, Jocelyn, Zhang, Jiabao, Shi, Jiancheng, Wang, Lizhe
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 09.09.2024; Elsevier
• Subjects: artificial intelligence; deep learning; geoscience; machine learning; Review; deep learning; geoscience; machine learning; artificial intelligence
• ISSN: 2666-6758; 2666-6758
• DOI: 10.1016/j.xinn.2024.100691

This paper explores the evolution of geoscientific inquiry, tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence (AI) and data collection techniques. Traditional models, which are grounded in physical and numerical frameworks, provide robust explanations by explicitly reconstructing underlying physical processes. However, their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world applicability. In contrast, contemporary data-driven models, particularly those utilizing machine learning (ML) and deep learning (DL), leverage extensive geoscience data to glean insights without requiring exhaustive theoretical knowledge. ML techniques have shown promise in addressing Earth science-related questions. Nevertheless, challenges such as data scarcity, computational demands, data privacy concerns, and the “black-box” nature of AI models hinder their seamless integration into geoscience. The integration of physics-based and data-driven methodologies into hybrid models presents an alternative paradigm. These models, which incorporate domain knowledge to guide AI methodologies, demonstrate enhanced efficiency and performance with reduced training data requirements. This review provides a comprehensive overview of geoscientific research paradigms, emphasizing untapped opportunities at the intersection of advanced AI techniques and geoscience. It examines major methodologies, showcases advances in large-scale models, and discusses the challenges and prospects that will shape the future landscape of AI in geoscience. The paper outlines a dynamic field ripe with possibilities, poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration. [Display omitted] •What does AI bring to geoscience? AI has been accelerating and deepening our understanding of Earth Systems in an unprecedented way, including the atmosphere, lithosphere, hydrosphere, cryosphere, biosphere, anthroposphere and the interactions between spheres.•What are the noteworthy challenges of AI in geoscience? As we embrace the huge potential of AI in geoscience, several challenges arise including reliability and interpretability, ethical issues, data security, and high demand and cost.•What is the future of AI in geoscience? The synergy between traditional principles and modern AI-driven techniques holds immense promise and will shape the trajectory of geoscience in upcoming years.