Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products

Alicia Bao, Jiamian He, Angel Hsu, Diego Manya, Ji, Zhang

Abstract

As large language models (LLMs) are increasingly used in domain-specific applications, including climate change and environmental research, understanding their energy footprint has become an important concern. The growing adoption of retrieval-augmented (RAG) systems for climate-domain specific analysis raises a key question: how does the energy consumption of domain-specific RAG workflows compare with that of direct generic LLM usage? Prior research has focused on standalone model calls or coarse token-based estimates, while leaving the energy implications of deployed application workflows insufficiently understood. In this paper, we assess the inference-time energy consumption of two LLM-based climate analysis chatbots (ChatNetZero and ChatNDC) compared to the generic GPT-4o-mini model. We estimate energy use under actual user queries by decomposing each workflow into retrieval, generation, and hallucination-checking components. We also test across different times of day and geographic access locations. Our results show that the energy consumption of domain-specific RAG systems depends strongly on their design. More agentic pipelines substantially increase inference-time energy use, particularly when used for additional accuracy or verification checks, although they may not yield proportional gains in response quality. While more research is needed to further test these initial findings more robustly across models, environments and prompting structures, this study provides a new understanding on how the design of domain-specific LLM products affects both the energy footprint and quality of output.

The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products

Abstract

As large language models (LLMs) are increasingly used in domain-specific applications, including climate change and environmental research, understanding their energy footprint has become an important concern. The growing adoption of retrieval-augmented (RAG) systems for climate-domain specific analysis raises a key question: how does the energy consumption of domain-specific RAG workflows compare with that of direct generic LLM usage? Prior research has focused on standalone model calls or coarse token-based estimates, while leaving the energy implications of deployed application workflows insufficiently understood. In this paper, we assess the inference-time energy consumption of two LLM-based climate analysis chatbots (ChatNetZero and ChatNDC) compared to the generic GPT-4o-mini model. We estimate energy use under actual user queries by decomposing each workflow into retrieval, generation, and hallucination-checking components. We also test across different times of day and geographic access locations. Our results show that the energy consumption of domain-specific RAG systems depends strongly on their design. More agentic pipelines substantially increase inference-time energy use, particularly when used for additional accuracy or verification checks, although they may not yield proportional gains in response quality. While more research is needed to further test these initial findings more robustly across models, environments and prompting structures, this study provides a new understanding on how the design of domain-specific LLM products affects both the energy footprint and quality of output.

Paper Structure

This paper contains 19 sections, 7 equations, 9 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. ChatNetZero and ChatNDC - Climate-domain specific chatbots
  4. LLM energy consumption components: training, inference
  5. Previous research on measuring LLM inference methods
  6. Limitations of previous research
  7. Methods
  8. Dataset
  9. Energy Consumption Estimation
  10. Experiment Design
  11. LLM consumption estimation method
  12. Retrieval consumption estimation method
  13. Hallucination Check consumption estimation method
  14. Evaluation
  15. Results
  16. ...and 4 more sections

Figures (9)

  • Figure 1: Design of ChatNetZero hsu_evaluating_2024.
  • Figure 2: Architectures of (a) ChatNetZero and (b) ChatNDC.
  • Figure 3: Median answer token size by each model.
  • Figure 4: Median energy use of models per query.
  • Figure 5: Energy use across query steps: (a) Mean energy use of models by each step of the query; (b) Proportion of energy use by step of the query.
  • ...and 4 more figures