AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models

2026-02-17

AI Summary

This work addresses the critical gap in current AI model evaluation, which predominantly emphasizes performance metrics while neglecting energy consumption and carbon emissions, thereby hindering sustainable deployment. To this end, we propose AI-CARE, a novel evaluation framework that integrates carbon emissions into the model assessment paradigm for the first time. By combining energy modeling, carbon accounting, and multi-objective optimization, AI-CARE establishes a joint carbon-performance evaluation mechanism. Its key innovation lies in an interpretable visualization of the carbon-performance Pareto frontier, which explicitly reveals the trade-offs between model accuracy and carbon footprint. Empirical results demonstrate that the framework can substantially alter conventional model rankings, thereby guiding the development of green AI systems that achieve both high accuracy and low carbon emissions.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Computer Vision: Large Vision Models

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

As machine learning (ML) continues its rapid expansion, the environmental cost of model training and inference has become a critical societal concern. Existing benchmarks overwhelmingly focus on standard performance metrics such as accuracy, BLEU, or mAP, while largely ignoring energy consumption and carbon emissions. This single-objective evaluation paradigm is increasingly misaligned with the practical requirements of large-scale deployment, particularly in energy-constrained environments such as mobile devices, developing regions, and climate-aware enterprises. In this paper, we propose AI-CARE, an evaluation tool for reporting energy consumption, and carbon emissions of ML models. In addition, we introduce the carbon-performance tradeoff curve, an interpretable tool that visualizes the Pareto frontier between performance and carbon cost. We demonstrate, through theoretical analysis and empirical validation on representative ML workloads, that carbon-aware benchmarking changes the relative ranking of models and encourages architectures that are simultaneously accurate and environmentally responsible. Our proposal aims to shift the research community toward transparent, multi-objective evaluation and align ML progress with global sustainability goals. The tool and documentation are available at https://github.com/USD-AI-ResearchLab/ai-care.

Problem

• carbon emissions
• energy consumption
• model evaluation
• sustainability
• machine learning

Innovation

• carbon-aware evaluation
• energy consumption
• carbon emissions
• Pareto frontier
• sustainable AI