Sustainable

This pioneering study examines the carbon footprint of training natural language processing models. The authors quantify the financial and environmental costs of training various NLP models. The study reveals that training a single BERT model can emit as much CO2 as a trans-Atlantic flight, and that the computational costs of NLP models double every 3-4 months. The authors provide concrete recommendations to reduce environmental impact, particularly by prioritizing energy efficiency in model design and using renewable energy sources for training.

This comprehensive review examines state-of-the-art approaches for making deep learning more energy-efficient across the entire stack, from hardware to algorithms. The research analyzes various efficiency techniques including model compression, neural architecture search, and hardware-software co-design for energy-efficient deep learning. The authors provide detailed case studies and empirical evaluations of different approaches, offering insights into their effectiveness for reducing energy consumption while maintaining model performance.

L’enquête annuelle “Pour un numérique soutenable” de l’Arcep analyse les enjeux environnementaux liés à la transformation numérique en France. Cette édition 2025 présente des données actualisées sur l’impact environnemental des infrastructures numériques, des terminaux et des usages, ainsi que les initiatives du secteur pour réduire son empreinte écologique.

This comprehensive study analyzes the environmental impact of data centers specifically used for AI training and inference. The research provides detailed measurements of energy consumption and carbon emissions from major AI computing facilities. The authors present innovative solutions for reducing the environmental footprint of AI infrastructure, including advanced cooling systems, renewable energy integration, and workload optimization strategies. The paper also introduces new metrics for measuring and comparing the environmental efficiency of different AI computing architectures and deployment strategies.

This paper bridges the gap between AI ethics and environmental sustainability, proposing a framework that considers both ethical and environmental implications of AI development. The research examines how ethical AI principles can be aligned with environmental sustainability goals, addressing issues such as computational efficiency, resource allocation, and environmental justice. The authors propose concrete guidelines for developing AI systems that are both ethically sound and environmentally sustainable.

The last decade saw the acceleration of new technologies adoption, shaping the digital landscape in terms of speed, quality and connectivity for multimedia contents and communication tools. While many activities have been able to benefit from the numerous innovations (4.0 industry, e-commerce, telecommunications, etc.) to develop, this growth has always been coupled with a significant increase of pressures on the environment and natural resources. The French Agency for Ecological Transition (ADEME) has proposed four scenarios for achieving carbon neutrality by 2050 in its study “Transition 2050, Choisir maintenant, Agir pour le Climat”. They aim to link the technical and economic dimensions with thoughts on the transformations in society that they imply or that they give rise to. This is the context for the study entitled “Assessment of the environmental impact of digital technology in France and prospective analysis”. The present report on the “prospective analysis for 2030 and 2050 and medium- and long-term courses of action”, is a continuation of Task 1 on the “state of play and courses of action” and Task 2 on the “environmental assessment of digital services in France”. Specifically, Task 3 aims to assess the environmental impact of the digital sector in France for the 2030 and 2050 timeframes according to a trend scenario and different scenarios for the mitigation of this impact. Like Task 2, it consists of an evaluation of the impacts using the Life Cycle Assessment (LCA) methodology. This methodology focuses on the three thirds of the digital world: user terminals, networks and data centers. The results are presented at the France-wide scale and are detailed under several levels of analysis in order to get a more acute interpretation and a better comprehension of direct environmental stakes related to digital technologies in France.

Cette étude explore les raisons pour lesquelles les Français changent de smartphone, en se concentrant sur les problèmes de dysfonctionnement et d’obsolescence. L’enquête révèle que 59% des Français ont été confrontés à un dysfonctionnement de leur smartphone au cours des deux dernières années, et que dans 37% des cas, le problème s’est manifesté au cours de la première année d’utilisation. Les résultats mettent en lumière les problèmes matériels et logiciels les plus fréquents, ainsi que les comportements des consommateurs face à ces dysfonctionnements. L’étude souligne également le rôle des fabricants et des politiques publiques dans la lutte contre l’obsolescence programmée des appareils numériques.

Cette étude vise à mettre à jour les données de l’étude menée avec l’Arcep en 2020 sur l’évaluation de l’impact environnemental du numérique en France, aujourd’hui et demain. En effet, n’avait été pris en compte dans les hypothèses de l’étude de 2020, que les data centers situés sur le territoire français. Or une partie importante des usages en France sont hébergés à l’étranger (environ 53 %) ce qui représente des impacts très loin d’être négligeables. Par ailleurs, entre 2020 et 2022, le mix entre les télévisions OLED et LCD-LED a varié au profit des télévisions OLED plus grandes et plus impactantes ainsi que les usages notamment due à l’arrivée massive de l’IA.

The rapid growth of artificial intelligence (AI), particularly Large Language Models (LLMs), has raised concerns regarding its global environmental impact that extends beyond greenhouse gas emissions to include consideration of hardware fabrication and end-of-life processes. The opacity from major providers hinders companies’ abilities to evaluate their AI-related environmental impacts and achieve net-zero targets. In this paper, we propose a methodology to estimate the environmental impact of a company’s AI portfolio, providing actionable insights without necessitating extensive AI and Life-Cycle Assessment (LCA) expertise. Results confirm that large generative AI models consume up to 4600x more energy than traditional models. Our modelling approach, which accounts for increased AI usage, hardware computing efficiency, and changes in electricity mix in line with IPCC scenarios, forecasts AI electricity use up to 2030. Under a high adoption scenario, driven by widespread Generative AI and agents adoption associated to increasingly complex models and frameworks, AI electricity use is projected to rise by a factor of 24.4. Mitigating the environmental impact of Generative AI by 2030 requires coordinated efforts across the AI value chain. Isolated measures in hardware efficiency, model efficiency, or grid improvements alone are insufficient. We advocate for standardized environmental assessment frameworks, greater transparency from the all actors of the value chain and the introduction of a “Return on Environment” metric to align AI development with net-zero goals.

Given the growing environmental concerns and significant resource consumption associated with video streaming on electronic devices, measuring the energy consumption is important to guide optimisation and to assess its relative environmental impact. In this paper, we provide comprehensive guidance to accurately measure the energy and power consumption in video communication technologies. We address the complexities inherent in measuring energy consumption across diverse software and hardware setups, with a focus on video communication tasks. We review current measurement techniques, identify limitations in existing practices, and propose a structured methodology that incorporates considerations for static and dynamic power consumption, appropriate sampling frequencies, and statistical rigor. Additionally, we introduce a reference workflow that is adaptable to various multimedia applications and demonstrate its applicability through a case study. By offering clear guidance and practical tools, this work aims to improve the reliability, reproducibility, and comparability of energy consumption measurements in video technologies, providing a strong foundation for the multimedia community to base decisions on.