The impact of artificial intelligence on environmental geoscience research

Abstract

The rapid integration of artificial intelligence (AI) and data-driven paradigms is profoundly reshaping environmental geoscience research. Based on insights from the “Frontiers of Earth System and Environmental Planning” session at the 6th Youth Forum on Frontiers of Environmental Science and Engineering, this paper synthesizes emerging perspectives on the opportunities, systemic disruptions, and future trajectory of AI in environmental geoscience. While AI offers unprecedented efficiency, shorter research cycles, and enhanced visual readability, it simultaneously creates tension with traditional, labor-intensive empirical approaches such as fieldwork and mechanistic experiments. Furthermore, the sustainability of AI models remains critically dependent on legacy datasets; over-reliance on unvalidated global secondary data threatens scientific reproducibility and risks future data scarcity under changing climate conditions. Ultimately, while AI can automate routine data processing, it cannot substitute for human critical thinking in formulating fundamental scientific questions. We advocate for a balanced, diversified research ecosystem that responsibly integrates AI while safeguarding the foundational role of primary data collection and human-centric scientific inquiry.

Graphical abstract

Keywords

Artificial intelligence / Environmental geoscience / Data sustainability / Research paradigm / Empirical data / Scientific policy

References

[1] Bergen K J , Johnson P A , De Hoop M V , Beroza G C . (2019). Machine learning for data-driven discovery in solid Earth geoscience. Science, 363(6433): eaau0323

[2] Hao Q Y , Xu F L , Li Y , Evans J . (2026). Artificial intelligence tools expand scientists’ impact but contract science’s focus. Nature, 649(8099): 1237–1243

[3] Messeri L , Crockett M J . (2024). Artificial intelligence and illusions of understanding in scientific research. Nature, 627(8002): 49–58

[4] Schiller J , Stiller S , Ryo M . (2025). Artificial intelligence in environmental and Earth system sciences: explainability and trustworthiness. Artificial Intelligence Review, 58(10): 316

[5] Wang H C , Fu T F , Du Y Q , Gao W H , Huang K X , Liu Z M , Chandak P , Liu S C , Van Katwyk P , Deac A . et al. (2023). Scientific discovery in the age of artificial intelligence. Nature, 620(7972): 47–60

Rights & permissions

Higher Education Press 2026