Scientific capabilities and deployment sustainability of small-scale LLMs in biological wastewater treatment
Abstract
Large language models (LLMs) are emerging as scientific assistants, yet their computational demands and limited domain specialization constrain sustainable deployment in environmental engineering. Here, we investigate whether domain-specialized small-scale LLMs can combine scientific capability with sustainable deployment in biological wastewater treatment. We developed a benchmark evaluating three scientific capabilities of LLMs: retrospective cognition, comprehension fidelity, and prospective extrapolation. BioWater (8 billion parameters, fine-tuned on specialized domain knowledge) achieved higher comprehension-fidelity scores than participating human experts and performance comparable to a 397-billion-parameter general-purpose LLM in retrospective cognition and prospective extrapolation. Human-BioWater collaboration generated a scientific hypothesis that was subsequently supported by laboratory experiments, demonstrating its potential to contribute to prospective scientific research. We further evaluated the economic and environmental implications of LLM deployment across global wastewater treatment plants (WWTPs). Locally deployed small-scale LLMs became more sustainable than cloud-based large-scale LLMs as inference demand increased in intelligent WWTPs. These findings highlight domain-specialized small-scale LLMs as a promising pathway towards scientifically capable, computationally efficient, and sustainably deployable artificial intelligence for wastewater treatment.
Related
- The impact of big data capabilities and business model innovation on new venture performance
- Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment
- Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach
- Causal DAG-Guided Reinforcement Learning for Long-Term Physical Activity Maintenance: Using Prior Data to Inform Future Deployment
- Development and operational deployment of a staff rostering system using mathematical optimisation in a municipal water utility
BibTeX
@misc{xu2026scientific,
title = {{Scientific capabilities and deployment sustainability of small-scale LLMs in biological wastewater treatment}},
author = {Run-Ze Xu and Chu-Kuan Jiang and Dylan Ming-Han Li and Hong-Xiao Guo and Jia-Shun Cao and Guang-Hao Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25774},
eprint = {2609.25774},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25774},
}
RIS
TY - UNPB
TI - Scientific capabilities and deployment sustainability of small-scale LLMs in biological wastewater treatment
AU - Run-Ze Xu
AU - Chu-Kuan Jiang
AU - Dylan Ming-Han Li
AU - Hong-Xiao Guo
AU - Jia-Shun Cao
AU - Guang-Hao Chen
PY - 2026
DA - 2026/09/26
PB - arXiv
DO - 10.48550/arxiv.2609.25774
UR - https://arxiv.org/abs/2609.25774
AB - Large language models (LLMs) are emerging as scientific assistants, yet their computational demands and limited domain specialization constrain sustainable deployment in environmental engineering. Here, we investigate whether domain-specialized small-scale LLMs can combine scientific capability with sustainable deployment in biological wastewater treatment. We developed a benchmark evaluating three scientific capabilities of LLMs: retrospective cognition, comprehension fidelity, and prospective extrapolation. BioWater (8 billion parameters, fine-tuned on specialized domain knowledge) achieved higher comprehension-fidelity scores than participating human experts and performance comparable to a 397-billion-parameter general-purpose LLM in retrospective cognition and prospective extrapolation. Human-BioWater collaboration generated a scientific hypothesis that was subsequently supported by laboratory experiments, demonstrating its potential to contribute to prospective scientific research. We further evaluated the economic and environmental implications of LLM deployment across global wastewater treatment plants (WWTPs). Locally deployed small-scale LLMs became more sustainable than cloud-based large-scale LLMs as inference demand increased in intelligent WWTPs. These findings highlight domain-specialized small-scale LLMs as a promising pathway towards scientifically capable, computationally efficient, and sustainably deployable artificial intelligence for wastewater treatment.
ER -