Large Language Models: Tools for New Environmental Decision-Making
Abstract
This study represents the first exploration of Large Language Models (LLMs) in environmental decision-making, examining their potential benefits and limitations. To address environmental issues, we propose and compare two generalizable frameworks: an LLMs-assisted framework that leverages LLMs to augment human expertise and coding in traditional decision workflows, and an LLMs-driven framework that aims to automate optimization. Through a water engineering case study focusing on PFAS control, where Environmental Fluid Dynamics Code (EFDC) was used for water environment simulation, we illustrate how to instantiate these frameworks and assess their performance. The case study reveals generalizable insights about these frameworks. Results indicate that both frameworks can contribute to environmental decision-making optimization to varying degrees, though their applicability differs significantly when facing complex decision scenarios. The LLMs-assisted framework, which effectively regulates flow rates and achieves higher PFAS interception, demonstrates how AI can enhance human decision-making while preserving the essential role of domain expertise and professional judgment. In contrast, the LLMs-driven framework faces challenges in handling complex parameter optimization tasks due to constraints such as context window and maximum output length. The findings emphasize the advantages of integrating Artificial Intelligence (AI) with conventional environmental modeling and management practices. This work confirms a crucial principle: LLMs should enhance rather than replace human expertise, with the ultimate responsibility for environmental decisions remaining with humans. The originality of this research lies in its innovative methodological approach, which leverages process design and prompt engineering to integrate cutting-edge AI with conventional environmental models, establishing a foundation for responsible human-AI collaboration in environmental decision-making. While examining current strengths and limitations, this framework robustly generates optimized environmental decision strategies, marking a new exploration in the field.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The EU revised Drinking Water Directive requires Member States to ensure PFAS concentrations in drinking water remain below 0.5 μg/L total PFAS and limit the sum of 20 priority PFAS to 0.1 μg/L by January 2026.
“To safeguard public health, the European Union has recently taken regulatory action in the form of the revised Drinking Water Directive (EU 2020/2184), under which Member States must ensure PFAS concentrations in drinking water remain below 0.5 µg/L total PFAS and limit the sum of 20 priority PFAS to 0.1 µg/L by January 2026 [13,14,15].”
From Exposure to Per- and Polyfluoroalkyl Substances (PFASs) in Healthcare: Environmental and Clinical Insights (2025) · cites this paper as [14]
Cites
A fast and elitist multiobjective genetic algorithm: NSGA-II
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.996017 · Cited by 50,053 · see citing works
A review of multi-objective optimization: Methods and its applications
Gunantara, N. (2018) · Cogent Engineering · doi:10.1080/23311916.2018.1502242 · Cited by 1,150 · see citing works
Pre-trained models: Past, present and future
Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., et al. (2021) · AI Open · doi:10.1016/j.aiopen.2021.08.002 · Cited by 994 · see citing works
Prompt Engineering in Large Language Models
Marvin, G., Hellen, N., Jjingo, D., & Nakatumba-Nabende, J. (2024) · Algorithms for Intelligent Systems · doi:10.1007/978-981-99-7962-2_30 · Cited by 403 · see citing works
Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs
Li, W., Chen, X., Deng, X., Wen, H., You, M., Liu, W., Li, Q., & Li, J. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01029-4 · Cited by 400 · see citing works
AI literacy and its implications for prompt engineering strategies
Knoth, N., Tolzin, A., Janson, A., & Leimeister, J. M. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100225 · Cited by 368 · see citing works
The CLEAR path: A framework for enhancing information literacy through prompt engineering
Lo, L. S. (2023) · The Journal of Academic Librarianship · doi:10.1016/j.acalib.2023.102720 · Cited by 347 · see citing works
Saif, N., Khan, S. U., Shaheen, I., ALotaibi, F. A., Alnfiai, M. M., & Arif, M. (2024) · Computers in Human Behavior · doi:10.1016/j.chb.2023.108097 · Cited by 301 · see citing works
ChatGPT and Environmental Research
Zhu, J., Jiang, J., Yang, M., & Ren, Z. J. (2023) · Environmental Science & Technology · doi:10.1021/acs.est.3c01818 · Cited by 246 · see citing works
Li, Y., Xiong, W., Zhang, W., Wang, C., & Wang, P. (2015) · Water Research · doi:10.1016/j.watres.2015.11.030 · Cited by 150 · see citing works
CancerGPT for few shot drug pair synergy prediction using large pretrained language models
Li, T., Shetty, S., Kamath, A., Jaiswal, A. K., Jiang, X., Ding, Y., & Kim, Y. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01024-9 · Cited by 116 · see citing works
Semantic understanding and prompt engineering for large-scale traffic data imputation
Zhang, K., Zhou, F., Wu, L., Xie, N., & He, Z. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102038 · Cited by 109 · see citing works
LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
Parmar, M., Patel, N., Varshney, N., Nakamura, M., Luo, M., Mashetty, S., Mitra, A., & Baral, C. (2024) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2024.acl-long.739 · Cited by 108 · see citing works
Zhou, Y., Guo, S., Hong, X., & Chang, F. (2017) · Journal of Hydrology · doi:10.1016/j.jhydrol.2017.08.039 · Cited by 107 · see citing works
A Survey on Search Strategy of Evolutionary Multi-Objective Optimization Algorithms
Wang, Z., Pei, Y., & Li, J. (2023) · Applied Sciences · doi:10.3390/app13074643 · Cited by 103 · see citing works
A Framework for Understanding and Improving Environmental Decision Making
Tonn, B. E., English, M. R., & Travis, C. B. (2000) · Journal of Environmental Planning and Management · doi:10.1080/09640560010658 · Cited by 95 · see citing works
Parameter uncertainty and sensitivity analysis of water quality model in Lake Taihu, China
Jiang, L., Li, Y., Zhao, X., Tillotson, M. R., Wang, W., Zhang, S., Sarpong, L., Asmaa, Q., & Pan, B. (2018) · Ecological Modelling · doi:10.1016/j.ecolmodel.2018.02.014 · Cited by 90 · see citing works
Li, J., Liu, Y., Fan, W., Wei, X.-Y., Liu, H., Tang, J., & Li, Q. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3393356 · Cited by 85 · see citing works
IMPROVING ENVIRONMENTAL DECISION‐MAKING THROUGH COLLABORATIVE METHODS
Randolph, J. C., & Bauer, M. R. (1999) · Review of Policy Research · doi:10.1111/j.1541-1338.1999.tb00882.x · Cited by 84 · see citing works
PROCESSING OCEANOGRAPHIC DATA BY PYTHON LIBRARIES NUMPY, SCIPY AND PANDAS
Lemenkova, P. (2019) · AQUATIC RESEARCH · doi:10.3153/ar19009 · Cited by 75 · see citing works
How can LLMs transform the robotic design process?
Stella, F., Santina, C. D., & Hughes, J. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00669-7 · Cited by 69 · see citing works
Software review: DEAP (Distributed Evolutionary Algorithm in Python) library
Kim, J.-H., & Yoo, S. (2018) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-018-9341-4 · Cited by 65 · see citing works
Environmental Decision-Making and Lake Management
Gough, J., & Ward, J. C. (1996) · Journal of Environmental Management · doi:10.1006/jema.1996.0063 · Cited by 64 · see citing works
Battle of the Wordsmiths: Comparing ChatGPT, GPT-4, Claude, and BardPreprint
Borji, A., & Mohammadian, M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4476855 · Cited by 53 · see citing works
Management approaches to conserve Australia’s marine ecosystem under climate change
Bay, L. K., Gilmour, J., Muir, B., & Hardisty, P. E. (2023) · Science · doi:10.1126/science.adi3023 · Cited by 44 · see citing works
Environmental economic, political and ethical integration in a common decision-making framework
de Anguita, P. M., Alonso, E. G., & Martín, M. Á. (2007) · Journal of Environmental Management · doi:10.1016/j.jenvman.2007.02.002 · Cited by 33 · see citing works
Hesamfar, F., Ketabchi, H., & Ebadi, T. (2023) · Journal of Environmental Management · doi:10.1016/j.jenvman.2023.117785 · Cited by 29 · see citing works
Liu, T., Qian, X., Wang, S., Wang, H., Wei, S., & Chen, H. (2021) · Water Research · doi:10.1016/j.watres.2021.117662 · Cited by 28 · see citing works
Self-citationDai, H., Wang, Z., Zhao, J., Jia, X., Liu, L., Wang, J., Abbasi, H. N., Guo, Z., Chen, Y., Geng, H., et al. (2022) · Journal of Environmental Management · doi:10.1016/j.jenvman.2022.116924 · Cited by 24 · see citing works
Zhong, S., & Guan, X. (2023) · Environmental Science & Technology Letters · doi:10.1021/acs.estlett.3c00599 · Cited by 21 · see citing works
Jordan, W. R. (1994) · Science · doi:10.1126/science.263.5145.305.b · Cited by 19 · see citing works
Can data science achieve the ideal of evidence-based decision-making in environmental regulation?
Kim, E. S. (2024) · Technology in Society · doi:10.1016/j.techsoc.2024.102615 · Cited by 19 · see citing works
Wang, D., Jia, Y., Niu, C., Yan, X. D., & Hao, C. (2023) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2023.169588 · Cited by 18 · see citing works
Comparison of multi-objective evolutionary algorithms applied to watershed management problem
Wang, S., Wang, Y., Wang, Y., & Wang, Z. (2022) · Journal of Environmental Management · doi:10.1016/j.jenvman.2022.116255 · Cited by 17 · see citing works
Mo, G. Y. (2016) · Information Communication & Society · doi:10.1080/1369118x.2016.1139611 · Cited by 16 · see citing works
Sarpong, L., Li, Y., Norgbey, E., Nwankwegu, A. S., Cheng, Y., Nasiru, S., Nooni, I. K., & Setordjie, V. E. (2020) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17114158 · Cited by 9 · see citing works
Wang, S., Liu, T., Qian, X., Wang, H., Wang, X., Wei, S., & Chen, H. (2023) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2023.164775 · Cited by 9 · see citing works
Self-citationAkinlotan, M. D., Warne, D. J., Helmstedt, K. J., Vollert, S. A., Chadès, I., Heneghan, R., Xiao, H., & Adams, M. P. (2024) · Ecological Indicators · doi:10.1016/j.ecolind.2024.111828 · Cited by 9 · see citing works
Hsueh, J. Y., Nethala, D., Singh, S. M., Linehan, W. M., & Ball, M. W. (2024) · Urologic Oncology Seminars and Original Investigations · doi:10.1016/j.urolonc.2024.04.010 · Cited by 8 · see citing works
A sediment diagenesis model on sediment oxygen demand in managing eutrophication on Taihu, China
Li, Y., Sarpong, L., Cheng, Y., Norgbey, E., Nooni, I. K., Nasiru, S., Setordjie, V. E., Duodu, R. A. B., & Dzakpasu, M. (2022) · Environmental Science and Pollution Research · doi:10.1007/s11356-022-24301-0 · Cited by 6 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Liu, 2024, Are LLMs capable of data-based statistical and causal reasoning?, Benchmarking Advanced Quantitative Reasoning with Data
- Tong, 2024, Can LLMs learn from previous mistakes?, Investigating LLMs’ Errors to Boost for Reasoning
Cited by
Sorted by citations
Xu, B., Wu, G., Li, Z., Xu, G., Zeng, H., Tong, R., & Ng, H. Y. (2025) · npj Clean Water · doi:10.1038/s41545-025-00509-8 · Cited by 23 · see citing works
Briassoulis, G., Ilia, S., & Briassouli, E. (2025) · Life · doi:10.3390/life15071057 · Cited by 15 · see citing works
Zhao, Z., Ma, Z., Chen, B., Li, P., Yu, W., Hu, W., Zhang, D., & Liao, J. (2026) · Journal of Environmental Management · doi:10.1016/j.jenvman.2026.128816 · Cited by 9 · see citing works
Large Language Models as Calibration Agents in Hydrological Modeling: Feasibility and Limitations
Zhu, Z., Tang, Y., Tang, X., Zhang, J., Gao, C., Zhang, S., Xu, H., & Guan, T. (2026) · Geophysical Research Letters · doi:10.1029/2025gl120043 · Cited by 8 · see citing works
Large language models for sustainable water management: A review
Arslan, M., & Munawar, S. (2026) · Sustainable Cities and Society Advances · doi:10.1016/j.scsadv.2026.100044 · Cited by 4 · see citing works
Zhang, Y., Li, Y., Yang, L., Zhao, L., & Yang, Y. (2025) · Toxics · doi:10.3390/toxics13070579 · Cited by 3 · see citing works
Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making
Chappidi, S., Singh, J. P., & Krauze, A. V. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791428 · Cited by 2 · see citing works
On using large language models to support social research for climate action
Nabavi, E., Maier, H. R., Razavi, S., Hindes, A., Howden, M. S., Grant, W. J., & Raman, S. (2026) · npj Climate Action · doi:10.1038/s44168-026-00375-1 · Cited by 2 · see citing works
Artificial Intelligence and Environmental Decision Support Systems
Gribkova, D., & Milshina, Y. (2026) · Springer eBooks · doi:10.1007/978-981-95-3767-9_11 · Cited by 1 · see citing works
Automating SWMM-based stormwater modelling and analysis through a tool-augmented single-agent system
Wang, J., Sun, C., Savic, D. A., & Fu, G. (2026) · Journal of Environmental Management · doi:10.1016/j.jenvman.2026.130619 · Cited by 1 · see citing works
Large language models for environmental modeling: Framework, capabilities, constraints
Nie, Q., & Liu, T. (2025) · Journal of Environmental Management · doi:10.1016/j.jenvman.2025.128417 · Cited by 1 · see citing works
Self-citationKpodo, J., Nejadhashemi, A. P., & Eeswaran, R. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.111533 · Cited by 1 · see citing works
Sustainable water information systems with LLMs and RAG: Opportunities and challenges
Arslan, M. (2026) · Green Technologies and Sustainability · doi:10.1016/j.grets.2026.100359 · Cited by 1 · see citing works
Leveraging Grok in Water Resource Management
Khaydarov, R. R. (2025) · World Water Policy · doi:10.1002/wwp2.70038
Adversarial Iterative Pre-enactment Framework for Air Combat Based on Mental Simulation Theory
Han, S., Zhang, X., Hu, T., & Ma, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3398-5_18
Agibayeva, A., Muratuly, A., Ibragimova, O., Tursun, K., Mukhamediya, A., Zollanvari, A., Almagambetov, A., Yenisoy, S., Baimatova, N., & Karaca, F. (2025) · Atmospheric pollution research · doi:10.1016/j.apr.2025.102839
Zhou, Z., Jiang, T., & Jin, Q. (2026) · Journal of Environmental Management · doi:10.1016/j.jenvman.2026.128718 · Cited by 1 · see citing works
Automated Power Dispatch Architecture Based on Multi-Agent Collaboration
Fan, J.-Y., Xiao, H.-B., Tan, P.-X., Zeng, J., Song, J.-H., Xiang, R., Zheng, K.-D., Song, J., & He, G.-N. (2026) · 2026 IEEE PES International Meeting (PES IM) · doi:10.1109/pesim67009.2026.11438861
Situating AI in Environmental Science: Perspectives Across Sectors and Career StagesPreprint
Makhlouf, B., Leiker, S., Mikkelsen, A. B., Levy, N., Holder, A., & Zimmerman, N. B. (2026) · doi:10.32942/x25m24
Xie, X., Kassem, M., Cabaneros, S. M., & Pan, H. (2026) · Journal of Environmental Management · doi:10.1016/j.jenvman.2026.129470
Unveiling LLMs for Advancing Long-Context Environmental Data Analysis
Samineni, B., Athota, V. S., Kona, T., & Doddipatla, M. (2026) · International Conference on Emerging Technologies and Future Innovations (ETFI) · doi:10.1109/etfi68128.2026.11484901
Zhang, X., Fu, D., Li, R., Li, K., Zhu, X., Chen, C., Deng, H., & Sun, L. (2026) · Water Research · doi:10.1016/j.watres.2026.126108
Wang, K., Wang, T., Wang, B., Li, Q., Liu, Y., Han, Q., Zhang, C. L., & Ren, Y. (2026) · Reviews in Fish Biology and Fisheries · doi:10.1007/s11160-026-10058-z
LLM-Augmented Conflict Prioritization and Strategy Selection for PCB Placement Refinement
Xu, J., Chen, C., Chen, S., Li, W., & Li, J. F. (2026) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3804601.3804665
Leitao, R., Podpečan, V., Cunha, L. F. N., Vazquez, C., David, F., Imbert, C., Symanczik, S., Sousa, J. P., Bünemann, E. K., Debeljak, M., et al. (2026) · Geoderma · doi:10.1016/j.geoderma.2026.117890
Liu, H., Jiang, Z., Zhong, H., Li, J., Pang, W., & Yuan, Y. (2026) · Water Research · doi:10.1016/j.watres.2026.126761
Zhao, J., Ju, M., Dong, M., Zhang, Y., Tang, K., Liu, X., Yang, K., Luo, H., Zhang, C., & Liu, G. (2026) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2026.149322
Carbon Chat: A Virtual Reality Game for Creating Awareness of the Environment Impact of LLMs
Hurst, W., Sallou, J., & Krampe, C. (2026) · International Conference on Virtual Reality · doi:10.1109/icvr70658.2026.11672397
Qiu, Y., Xie, J., Qiu, S., Li, J., Liang, C., Guo, S., Chen, H., & Zhao, P. (2026) · Fuel · doi:10.1016/j.fuel.2026.141378
Zhong, D., Chen, J., Zhou, J., Liu, C., & Zhan, R. (2026) · Sustainability Accounting Management and Policy Journal · doi:10.1108/sampj-02-2026-0384
Citizen science-Large Language Model alliance for automatic assessment of river hydromorphology
Grygoruk, M., & Marcinkowski, P. (2026) · Water Research · doi:10.1016/j.watres.2026.127082
Jiang, Y., Gao, Y., Zhang, Z., Zhang, Z., Yuan, Q., Li, X., & Zaoui, A. (2026) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2026.149565
- Authors
- Nie, Q., & Liu, T.
- Affiliations
- Hokkaido University (JP)
- Corresponding author
- Liu, Tong
- ORCID
- Venue
- Journal of Environmental Management
- Publisher
- Elsevier BV
- Published
- 2025-02
- Volume
- 375
- Pages
- 124373
- ISSN
- 0301-4797 (ISSN-L)
- OpenAlex
- W4407053194
- Cited by
- 34
- References
- 40
- Citations by year
- 2026: 27 · 2025: 7
- FWCI
- 11.08
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (am, 730 d)
- doi.org/10.15223/policy-017 (stm-asf)
- doi.org/10.15223/policy-037 (stm-asf)
- doi.org/10.15223/policy-012 (stm-asf)
- doi.org/10.15223/policy-029 (stm-asf)
- doi.org/10.15223/policy-004 (stm-asf)
- Locations
- Journal of Environmental Management (publishedVersion)
- PubMed (publishedVersion)
- Funders
- NextGenerationEU
- Japan Science and Technology Agency (JPMJSP2119)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- Social Sciences › Decision Sciences › Management Science and Operations Research › Impact of AI and Big Data on Business and Society
- Keywords
- large language models, environmental decision-making, human-AI collaboration, EFDC, flow rate optimization, prompt engineering, AI-assisted decision support, context window limitations, human expertise
- MeSH terms
- Large Language Models, Artificial Intelligence, Decision Making, Environment, Humans, Models, Theoretical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
