Putting Large Language Models into Environmental Context
- 1School of Sustainable Engineering and the Built Environment, Arizona State University, Tempe, Arizona 85287, United States
- 2Department of Civil and Environmental Engineering and Andlinger Center for Energy and the Environment, Princeton University, Princeton, New Jersey 08544, United States
Abstract
The emergence of large language models (LLMs) has fundamentally transformed information interaction, yet their application in environmental science and engineering (ESE) is hindered by multimodal data formats, dynamic context requirements, and hallucination risks. To transition from general-purpose models to domain expert agentic systems, this Perspective introduces a three-pillar framework for ESE-LLMs: domain perception, knowledge grounding, and action capability. Implementing these capabilities introduces potential pitfalls such as geographic representation bias, catastrophic forgetting, and source authenticity vulnerabilities, which require strategic model blending and careful data curation to overcome. Furthermore, rigorous evaluation must extend beyond standard knowledge benchmarks to systematically assess factuality, fairness, consistency, and safety using both human and automated metrics. Finally, we present a decision-guided deployment workflow that helps researchers in ESE fields integrate LLMs into their workflow. Ultimately, achieving trustworthy environmental intelligence relies on continuous evaluation, robust governance, and sustained interdisciplinary collaboration to safely deploy agentic ESE-LLMs for high-stakes environmental challenges.
Related
- GeoAgent: An Agent-Based QGIS Plugin for Natural-Language-Driven Geospatial Analysis with Multi-Backend Large Language Model Support
- Countering climate misinformation with large language models: Evidence from ChatGPT
- HydroCraft: an efficient online platform for hydrological modeling integrated with a large language model agent
- Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap
- Developing a FAIR data policy for chemical risk assessment and exploring future topics and stakeholder interests with large language models and data sciences.
BibTeX
@article{jiang2026putting,
title = {{Putting Large Language Models into Environmental Context}},
author = {Jinyue Jiang and Jun-Jie Zhu and Zhiyong Jason Ren},
journal = {Environmental Science \& Technology},
year = {2026},
month = oct,
doi = {10.1021/acs.est.6c06045},
url = {https://doi.org/10.1021/acs.est.6c06045},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Putting Large Language Models into Environmental Context
AU - Jinyue Jiang
AU - Jun-Jie Zhu
AU - Zhiyong Jason Ren
PY - 2026
DA - 2026/10/13
JO - Environmental Science & Technology
DO - 10.1021/acs.est.6c06045
UR - https://doi.org/10.1021/acs.est.6c06045
AB - The emergence of large language models (LLMs) has fundamentally transformed information interaction, yet their application in environmental science and engineering (ESE) is hindered by multimodal data formats, dynamic context requirements, and hallucination risks. To transition from general-purpose models to domain expert agentic systems, this Perspective introduces a three-pillar framework for ESE-LLMs: domain perception, knowledge grounding, and action capability. Implementing these capabilities introduces potential pitfalls such as geographic representation bias, catastrophic forgetting, and source authenticity vulnerabilities, which require strategic model blending and careful data curation to overcome. Furthermore, rigorous evaluation must extend beyond standard knowledge benchmarks to systematically assess factuality, fairness, consistency, and safety using both human and automated metrics. Finally, we present a decision-guided deployment workflow that helps researchers in ESE fields integrate LLMs into their workflow. Ultimately, achieving trustworthy environmental intelligence relies on continuous evaluation, robust governance, and sustained interdisciplinary collaboration to safely deploy agentic ESE-LLMs for high-stakes environmental challenges.
SN - 0013-936X
SN - 1520-5851
ER -