Recent advances in advanced machine learning models, agentic systems, and generative AI are opening up possibilities for addressing complex geoscientific challenges. These approaches enable novel ways to analyse data, support decision-making, and enhance scientific workflows, while raising important questions about alignment with human expertise, values, and responsibility. Generative AI enables the creation of new content across modalities, agentic AI allows autonomous systems of agents to act with minimal supervision and leverage tools, and hybrid intelligence integrates human contextual, causal, and ethical reasoning with AI’s computational power. In practice, causal reasoning is often where stakeholders' experience and domain insight are most naturally expressed, beyond what can be captured by model architectures, metrics, or post-hoc explainability alone.

This session explores both practical applications and conceptual frameworks of generative, agentic, and hybrid AI (inclusive of advanced ML/DL models) in the geosciences, with a strong emphasis on human-centred design. Topics include AI-assisted data analysis and modelling, knowledge discovery and curation, decision support, science communication, and AI-enhanced workflows guided by domain expertise. We particularly encourage contributions that demonstrate how human insight and causal reasoning complement AI.

The session also addresses ethical and societal aspects of AI deployment in geosciences, including transparency, bias mitigation, accountability, sustainability, and trustworthiness. The overarching goal is to highlight AI as a tool to empower and extend human expertise—keeping scientists and domain experts at the centre of innovation. Contributions from research, industry, and policy communities are all welcome.