Prof. Elio Masciari

Abstract:

Accurately assessing the environmental impact of Artificial Intelligence (AI) systems is essential to promoting sustainable development within the field. However, existing carbon emission tracking tools often rely on divergent assumptions, limited hardware compatibility, and inconsistent measurement granularity, leading to fragmented and often incomparable results. In this paper, we propose a hybrid methodology that integrates a weighted aggregation of ten widely-used emission estimation tools with a dynamic model-to-tool matching procedure. The weighted strategy assigns normalized importance scores to each tool based on six criteria. In parallel, the dynamic matching component identifies the most context-appropriate estimation tool for a given AI model. We evaluate our methodology on multiple architectures, including MobileNet, DenseNet, and GPT-3, deployed in different computing environments. Results demonstrate that our combined approach enhances both estimation accuracy and interpretability, outperforming single-tool assessments and offering a scalable solution for transparent carbon accounting in AI research 

Brief Bio: 

Elio Masciari is currently an associate professor at the University Federico II of Naples. Previously, he was a senior researcher at the Institute for High Performance Computing and Networks (ICAR-CNR) of the National Research Council of Italy. He has been an advisor for several master's theses at the University of Calabria and at the University Magna Graecia in Catanzaro. He was an advisor for a PhD thesis in computer engineering at the University of Calabria. He has served as a member of the program committee of several international conferences. He served as a reviewer for several scientific journals of international relevance. He is the author of over 140 publications in journals and at both national and international conferences. He also holds "Abilitazione Scientifica Nazionale" for the Full Professor role.