arXiv subjects

Sangwon Suh

Publications and source records attributed to Sangwon Suh.

3 recordsLinked to original sources

arXiv2026

Estimating GHG Emissions from AI Use: Framework for Corporate-Level Measurement

Electricity demand from data centers is expected to grow from roughly 5% of U.S. consumption in 2025 to between 9% and 17% by 2030, and corporate artificial intelligence (AI) use is following a similar trajectory, spanning employee productivity assistants, direct access to large language models (LLMs), and AI features embedded in enterprise software. AI emissions today are a small share of footprints for many enterprises, but that share is unlikely to remain small for long. Without reasonable estimates, companies cannot set reduction targets or identify effective decarbonization levers as emissions grow. Companies, regulators, and auditors are asking for emissions estimates that withstand scrutiny, but no widely accepted methodology exists today. Published per-query estimates can differ by several orders of magnitude depending on what is counted, which provider is measured, and what assumptions are made about electricity use and the grid mix. This white paper proposes a standardized framework for corporate-level AI emissions accounting. The framework is designed to be defensible with current data constraints, tiered to meet companies where their data are, transparent about its assumptions, updatable as provider disclosure matures, and built for action rather than disclosure alone. Since AI emissions accounting is still nascent, it has the opportunity to design for actionability from the outset, so that measurement incentivizes responsible choices during AI's rapid buildout.

physics.soc-ph↗

arXiv2025

Criteria for Credible AI-assisted Carbon Footprinting Systems: The Cases of Mapping and Lifecycle Modeling

As organizations face increasing pressure to understand their corporate and products' carbon footprints, artificial intelligence (AI)-assisted calculation systems for footprinting are proliferating, but with widely varying levels of rigor and transparency. Standards and guidance have not kept pace with the technology; evaluation datasets are nascent; and statistical approaches to uncertainty analysis are not yet practical to apply to scaled systems. We present a set of criteria to validate AI-assisted systems that calculate greenhouse gas (GHG) emissions for products and materials. We implement a three-step approach: (1) Identification of needs and constraints, (2) Draft criteria development and (3) Refinements through pilots. The process identifies three use cases of AI applications: Case 1 focuses on AI-assisted mapping to existing datasets for corporate GHG accounting and product hotspotting, automating repetitive manual tasks while maintaining mapping quality. Case 2 addresses AI systems that generate complete product models for corporate decision-making, which require comprehensive validation of both component tasks and end-to-end performance. We discuss the outlook for Case 3 applications, systems that generate standards-compliant models. We find that credible AI systems can be built and that they should be validated using system-level evaluations rather than line-item review, with metrics such as benchmark performance, indications of data quality and uncertainty, and transparent documentation. This approach may be used as a foundation for practitioners, auditors, and standards bodies to evaluate AI-assisted environmental assessment tools. By establishing evaluation criteria that balance scalability with credibility requirements, our approach contributes to the field's efforts to develop appropriate standards for AI-assisted carbon footprinting systems.

cs.CY↗

arXiv2022

The ReturnZero System for VoxCeleb Speaker Recognition Challenge 2022

In this paper, we describe the top-scoring submissions for team RTZR VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22) in the closed dataset, speaker verification Track 1. The top performed system is a fusion of 7 models, which contains 3 different types of model architectures. We focus on training models to learn extra-temporal information. Therefore, all models were trained with 4-6 second frames for each utterance. Also, we apply the Large Margin Fine-tuning strategy which has shown good performance on the previous challenges for some of our fusion models. While the evaluation process, we apply the scoring methods with adaptive symmetric normalization (AS-Norm) and matrix score average (MSA). Finally, we mix up models with logistic regression to fuse all the trained models. The final submission achieves 0.165 DCF and 2.912% EER on the VoxSRC22 test set.

eess.AS↗