This paper explores how Interpretable Machine Learning (IML) can benefit process understanding in the geosciences. IML offers new opportunities to improve our understanding of the complex Earth system by not only making predictions but also seeking to elucidate the reasoning behind those predictions. While IML has the potential to enhance scientific understanding, its broader implications for the field have yet to be fully appreciated. The paper identifies practical application scenarios for IML in typical geoscientific studies, such as quantifying relationships in specific contexts, generating hypotheses about potential mechanisms, and evaluating process-based models. It also presents a general and practical workflow for using IML to address specific research questions. The paper highlights common pitfalls in the use of IML that can lead to misleading conclusions and proposes corresponding good practices. The goal is to facilitate a broader, yet more careful and thoughtful integration of IML into Earth science research, positioning it as a valuable data science tool capable of enhancing our current understanding of the Earth system. The paper also discusses the relevance of IML for geoscientists, emphasizing its potential to benefit a much broader range of geoscientists, including those who have not engaged with ML models in their research. It highlights the potential of IML to benefit a much broader range of geoscientists, including those who have not engaged with ML models in their research. The paper also discusses the usefulness of IML for geoscientists, emphasizing its potential to benefit a much broader range of geoscientists, including those who have not engaged with ML models in their research.This paper explores how Interpretable Machine Learning (IML) can benefit process understanding in the geosciences. IML offers new opportunities to improve our understanding of the complex Earth system by not only making predictions but also seeking to elucidate the reasoning behind those predictions. While IML has the potential to enhance scientific understanding, its broader implications for the field have yet to be fully appreciated. The paper identifies practical application scenarios for IML in typical geoscientific studies, such as quantifying relationships in specific contexts, generating hypotheses about potential mechanisms, and evaluating process-based models. It also presents a general and practical workflow for using IML to address specific research questions. The paper highlights common pitfalls in the use of IML that can lead to misleading conclusions and proposes corresponding good practices. The goal is to facilitate a broader, yet more careful and thoughtful integration of IML into Earth science research, positioning it as a valuable data science tool capable of enhancing our current understanding of the Earth system. The paper also discusses the relevance of IML for geoscientists, emphasizing its potential to benefit a much broader range of geoscientists, including those who have not engaged with ML models in their research. It highlights the potential of IML to benefit a much broader range of geoscientists, including those who have not engaged with ML models in their research. The paper also discusses the usefulness of IML for geoscientists, emphasizing its potential to benefit a much broader range of geoscientists, including those who have not engaged with ML models in their research.