Recent advances in Large Language Models (LLMs), Natural Language Processing (NLP), multimodal AI, and AI agents are rapidly changing geosciences research. These technologies offer new opportunities for knowledge discovery, data analysis, evidence synthesis, and real-time monitoring. At the same time, the rapid growth of digital archives, from scientific literature and news articles to social media and historical documents or photographs, offers opportunities to explore new data sources in geosciences research.
This session examines how geoscientists are using LLMs, NLP, AI agents and text-as-data approaches across hydrology, climate, natural hazards, and the broader earth system sciences research fields. We invite contributions that develop or apply such methods to extract, organize, and interpret information from unstructured data sources; address methodological challenges such as uncertainty, bias, and validation; or integrate text and image mining approaches into geoscientific workflows.
We particularly welcome submissions on topics including, but not limited to:
- Text and image-based analysis of geoscientific data, e.g. assessment of natural hazard impacts and real-time disaster monitoring.
- Chatbots and AI agents in geosciences
- Evidence synthesis and literature mapping
- Public sentiment and perception analysis
- Policy tracking and narrative analysis
- Social media analyses
- Enhancement of metadata and data descriptions
- AI agents for automated or semi-automated geoscientific workflows
- Integration of LLMs with remote sensing or image data
- Methodological challenges in using LLMs and NLP-based analyses, including bias, reproducibility, and interpretability

By sharing case studies, technical developments, and lessons learned, we aim to promote the effective use of these tools while also highlighting the challenges that newcomers may encounter, including issues with data coverage, quality control, and reproducibility concerns. By sharing best practices, this session aims to inspire collaboration and innovation in harnessing LLMs, NLP, and text-as-data in geosciences.