Explainability can foster trust in artificial intelligence in geoscience

IF 15.7 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

Nature Geoscience Pub Date : 2025-02-05 DOI:10.1038/s41561-025-01639-x

Jesper Sören Dramsch, Monique M. Kuglitsch, Miguel-Ángel Fernández-Torres, Andrea Toreti, Rustem Arif Albayrak, Lorenzo Nava, Saman Ghaffarian, Ximeng Cheng, Jackie Ma, Wojciech Samek, Rudy Venguswamy, Anirudh Koul, Raghavan Muthuregunathan, Arthur Hrast Essenfelder

引用次数: 0

Abstract

Uptake of explainable artificial intelligence (XAI) methods in geoscience is currently limited. We argue that such methods that reveal the decision processes of AI models can foster trust in their results and facilitate the broader adoption of AI.

Abstract Image

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Nature Geoscience 地学-地球科学综合

CiteScore

26.70

自引率

1.60%

发文量

187

审稿时长

3.3 months

期刊介绍： Nature Geoscience is a monthly interdisciplinary journal that gathers top-tier research spanning Earth Sciences and related fields. The journal covers all geoscience disciplines, including fieldwork, modeling, and theoretical studies. Topics include atmospheric science, biogeochemistry, climate science, geobiology, geochemistry, geoinformatics, remote sensing, geology, geomagnetism, paleomagnetism, geomorphology, geophysics, glaciology, hydrology, limnology, mineralogy, oceanography, paleontology, paleoclimatology, paleoceanography, petrology, planetary science, seismology, space physics, tectonics, and volcanology. Nature Geoscience upholds its commitment to publishing significant, high-quality Earth Sciences research through fair, rapid, and rigorous peer review, overseen by a team of full-time professional editors.