EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Putting Large Language Models into Environmental Context

Jinyue Jiang iD, Jun-Jie Zhu iD, Zhiyong Jason Ren iD

Environmental Science & Technology · 27.10.2026 · 60 (42) · 29791-29801

DOI: 10.1021/acs.est.6c06045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 13.10.2026. Verfasst von Jinyue Jiang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Sustainable Engineering and the Built Environment, Arizona State University, Tempe, Arizona85287, United States. Hauptthemen laut MEDLINE: Environmental Science. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Environmental ScienceLarge Language ModelsEnvironmentHumans

Stichwörter der Autor:innen

Agentic systemEnvironmental domain modelKnowledge groundingLarge language modelMultimodal learningTrustworthy AI

Autor:innen und Institutionen

  • School of Sustainable Engineering and the Built Environment, Arizona State University, Tempe, Arizona85287, United States.
  • Department of Civil and Environmental Engineering and Andlinger Center for Energy and the Environment, Princeton University, Princeton, New Jersey08544, United States.

ORCID-Profile: Jinyue Jiang, Jun-Jie Zhu, Zhiyong Jason Ren

Zitieren

APA

Jiang, J., Zhu, J. J., & Ren, Z. J. (2026). Putting Large Language Models into Environmental Context. Environmental Science & Technology, 60(42), 29791-29801. https://doi.org/10.1021/acs.est.6c06045

Vancouver

Jiang J, Zhu JJ, Ren ZJ. Putting Large Language Models into Environmental Context. Environmental Science & Technology. 2026;60(42):29791-29801. doi:10.1021/acs.est.6c06045

BibTeX
@article{Jiang2026,
  author = {Jiang, Jinyue and Zhu, Jun-Jie and Ren, Zhiyong Jason},
  title = {Putting Large Language Models into Environmental Context},
  journal = {Environmental Science & Technology},
  year = {2026},
  volume = {60},
  number = {42},
  pages = {29791--29801},
  doi = {10.1021/acs.est.6c06045}
}
Kostenlos starten →