Roberto Verdecchia

Justus Bogner, Roberto Verdecchia

The scientific peer review system has been slowly deteriorating over the last years, and not just within empirical software engineering (ESE) research. Increased submission numbers, high workload, and the rise of generative AI use with all its associated issues have made many cracks in the system more visible. To get a better understanding of the current state of peer review in the ESE community, we conducted a questionnaire survey, which accumulated 120 responses. We report on (i) the perceived review load of community members, (ii) review quality perception as well as frequent challenges for and issues with reviews, (iii) the use of LLM-based tools in the reviewing process, and (iv) the community's suggestions for improving the peer review system. We hope that these community opinions can facilitate more evidence-based discussions about how people want to see the review system change for the better.

Roberto Verdecchia, June Sallou, Luís Cruz

With the ever-growing adoption of AI-based systems, the carbon footprint of AI is no longer negligible. AI researchers and practitioners are therefore urged to hold themselves accountable for the carbon emissions of the AI models they design and use. This led in recent years to the appearance of researches tackling AI environmental sustainability, a field referred to as Green AI. Despite the rapid growth of interest in the topic, a comprehensive overview of Green AI research is to date still missing. To address this gap, in this paper, we present a systematic review of the Green AI literature. From the analysis of 98 primary studies, different patterns emerge. The topic experienced a considerable growth from 2020 onward. Most studies consider monitoring AI model footprint, tuning hyperparameters to improve model sustainability, or benchmarking models. A mix of position papers, observational studies, and solution papers are present. Most papers focus on the training phase, are algorithm-agnostic or study neural networks, and use image data. Laboratory experiments are the most common research strategy. Reported Green AI energy savings go up to 115%, with savings over 50% being rather common. Industrial parties are involved in Green AI studies, albeit most target academic readers. Green AI tool provisioning is scarce. As a conclusion, the Green AI research field results to have reached a considerable level of maturity. Therefore, from this review emerges that the time is suitable to adopt other Green AI research strategies, and port the numerous promising academic results to industrial practice.

Tomaso Trinci, Simone Magistri, Roberto Verdecchia et al.

With the ever-growing adoption of AI, its impact on the environment is no longer negligible. Despite the potential that continual learning could have towards Green AI, its environmental sustainability remains relatively uncharted. In this work we aim to gain a systematic understanding of the energy efficiency of continual learning algorithms. To that end, we conducted an extensive set of empirical experiments comparing the energy consumption of recent representation-, prompt-, and exemplar-based continual learning algorithms and two standard baseline (fine tuning and joint training) when used to continually adapt a pre-trained ViT-B/16 foundation model. We performed our experiments on three standard datasets: CIFAR-100, ImageNet-R, and DomainNet. Additionally, we propose a novel metric, the Energy NetScore, which we use measure the algorithm efficiency in terms of energy-accuracy trade-off. Through numerous evaluations varying the number and size of the incremental learning steps, our experiments demonstrate that different types of continual learning algorithms have very different impacts on energy consumption during both training and inference. Although often overlooked in the continual learning literature, we found that the energy consumed during the inference phase is crucial for evaluating the environmental sustainability of continual learning models.

Roberto Verdecchia, Luís Cruz, June Sallou et al.

With the growing availability of large-scale datasets, and the popularization of affordable storage and computational capabilities, the energy consumed by AI is becoming a growing concern. To address this issue, in recent years, studies have focused on demonstrating how AI energy efficiency can be improved by tuning the model training strategy. Nevertheless, how modifications applied to datasets can impact the energy consumption of AI is still an open question. To fill this gap, in this exploratory study, we evaluate if data-centric approaches can be utilized to improve AI energy efficiency. To achieve our goal, we conduct an empirical experiment, executed by considering 6 different AI algorithms, a dataset comprising 5,574 data points, and two dataset modifications (number of data points and number of features). Our results show evidence that, by exclusively conducting modifications on datasets, energy consumption can be drastically reduced (up to 92.16%), often at the cost of a negligible or even absent accuracy decline. As additional introductory results, we demonstrate how, by exclusively changing the algorithm used, energy savings up to two orders of magnitude can be achieved. In conclusion, this exploratory investigation empirically demonstrates the importance of applying data-centric techniques to improve AI energy efficiency. Our results call for a research agenda that focuses on data-centric techniques, to further enable and democratize Green AI.

Mohammed Alswaitti, Roberto Verdecchia, Grégoire Danoy et al.

The substantial increase in AI model training has considerable environmental implications, mandating more energy-efficient and sustainable AI practices. On the one hand, data-centric approaches show great potential towards training energy-efficient AI models. On the other hand, instance selection methods demonstrate the capability of training AI models with minimised training sets and negligible performance degradation. Despite the growing interest in both topics, the impact of data-centric training set selection on energy efficiency remains to date unexplored. This paper presents an evolutionary-based sampling framework aimed at (i) identifying elite training samples tailored for datasets and model pairs, (ii) comparing model performance and energy efficiency gains against typical model training practice, and (iii) investigating the feasibility of this framework for fostering sustainable model training practices. To evaluate the proposed framework, we conducted an empirical experiment including 8 commonly used AI classification models and 25 publicly available datasets. The results showcase that by considering 10% elite training samples, the models' performance can show a 50% improvement and remarkable energy savings of 98% compared to the common training practice.

Luís Cruz, João Paulo Fernandes, Maja H. Kirkeby et al.

The environmental impact of Artificial Intelligence (AI)-enabled systems is increasing rapidly, and software engineering plays a critical role in developing sustainable solutions. The "Greening AI with Software Engineering" CECAM-Lorentz workshop (no. 1358, 2025) funded by the Centre Européen de Calcul Atomique et Moléculaire and the Lorentz Center, provided an interdisciplinary forum for 29 participants, from practitioners to academics, to share knowledge, ideas, practices, and current results dedicated to advancing green software and AI research. The workshop was held February 3-7, 2025, in Lausanne, Switzerland. Through keynotes, flash talks, and collaborative discussions, participants identified and prioritized key challenges for the field. These included energy assessment and standardization, benchmarking practices, sustainability-aware architectures, runtime adaptation, empirical methodologies, and education. This report presents a research agenda emerging from the workshop, outlining open research directions and practical recommendations to guide the development of environmentally sustainable AI-enabled systems rooted in software engineering principles.

Niccolò Marini, Leonardo Pampaloni, Filippo Di Martino et al.

AI is demanding an evergrowing portion of environmental resources. Despite their potential impact on AI environmental sustainability, the role that programming languages play in AI (in)efficiency is to date still unknown. With this study, we aim to understand the impact that programming languages can have on AI environmental sustainability. To achieve our goal, we conduct a controlled empirical experiment by considering five programming languages (C++, Java, Python, MATLAB, and R), seven AI algorithms (KNN, SVC, AdaBoost, decision tree, logistic regression, naive bayses, and random forest), three popular datasets, and the training and inference phases. The collected results show that programming languages have a considerable impact on AI environmental sustainability. Compiled and semi-compiled languages (C++, Java) consistently consume less than interpreted languages (Python, MATLAB, R), which require up to 54x more energy. Some languages are cumulatively more efficient in training, while others in inference. Which programming language consumes the most highly depends on the algorithm considered. Ultimately, algorithm implementation might be the most determining factor in Green AI, regardless of the language used. As conclusion, while making AI more environmentally sustainable is paramount, a trade-off between energy efficiency and implementation ease should always be considered. Green AI can be achieved without the need of completely disrupting the development practices and technologies currently in place.

Giulia Bertazzini, Chiara Albisani, Daniele Baracchi et al.

With the growing adoption of AI image generation, in conjunction with the ever-increasing environmental resources demanded by AI, we are urged to answer a fundamental question: What is the environmental impact hidden behind each image we generate? In this research, we present a comprehensive empirical experiment designed to assess the energy consumption of AI image generation. Our experiment compares 17 state-of-the-art image generation models by considering multiple factors that could affect their energy consumption, such as model quantization, image resolution, and prompt length. Additionally, we consider established image quality metrics to study potential trade-offs between energy consumption and generated image quality. Results show that image generation models vary drastically in terms of the energy they consume, with up to a 46x difference. Image resolution affects energy consumption inconsistently, ranging from a 1.3x to 4.7x increase when doubling resolution. U-Net-based models tend to consume less than Transformer-based one. Model quantization instead results to deteriorate the energy efficiency of most models, while prompt length and content have no statistically significant impact. Improving image quality does not always come at the cost of a higher energy consumption, with some of the models producing the highest quality images also being among the most energy efficient ones.

Emilio Cruciani, Roberto Verdecchia

Artificial Intelligence is increasingly pervasive across domains, with ever more complex models delivering impressive predictive performance. This fast technological advancement however comes at a concerning environmental cost, with state-of-the-art models - particularly deep neural networks and large language models - requiring substantial computational resources and energy. In this work, we present the intuition of Green AI dynamic model selection, an approach based on dynamic model selection that aims at reducing the environmental footprint of AI by selecting the most sustainable model while minimizing potential accuracy loss. Specifically, our approach takes into account the inference task, the environmental sustainability of available models, and accuracy requirements to dynamically choose the most suitable model. Our approach presents two different methods, namely Green AI dynamic model cascading and Green AI dynamic model routing. We demonstrate the effectiveness of our approach via a proof of concept empirical example based on a real-world dataset. Our results show that Green AI dynamic model selection can achieve substantial energy savings (up to ~25%) while substantially retaining the accuracy of the most energy greedy solution (up to ~95%). As conclusion, our preliminary findings highlight the potential that hybrid, adaptive model selection strategies withhold to mitigate the energy demands of modern AI systems without significantly compromising accuracy requirements.

Justus Bogner, Roberto Verdecchia, Ilias Gerostathopoulos

Background: With the rising popularity of Artificial Intelligence (AI), there is a growing need to build large and complex AI-based systems in a cost-effective and manageable way. Like with traditional software, Technical Debt (TD) will emerge naturally over time in these systems, therefore leading to challenges and risks if not managed appropriately. The influence of data science and the stochastic nature of AI-based systems may also lead to new types of TD or antipatterns, which are not yet fully understood by researchers and practitioners. Objective: The goal of our study is to provide a clear overview and characterization of the types of TD (both established and new ones) that appear in AI-based systems, as well as the antipatterns and related solutions that have been proposed. Method: Following the process of a systematic mapping study, 21 primary studies are identified and analyzed. Results: Our results show that (i) established TD types, variations of them, and four new TD types (data, model, configuration, and ethics debt) are present in AI-based systems, (ii) 72 antipatterns are discussed in the literature, the majority related to data and model deficiencies, and (iii) 46 solutions have been proposed, either to address specific TD types, antipatterns, or TD in general. Conclusions: Our results can support AI professionals with reasoning about and communicating aspects of TD present in their systems. Additionally, they can serve as a foundation for future research to further our understanding of TD in AI-based systems.

Steffen Herbold, Alexander Trautsch, Benjamin Ledel et al.

Context: Tangled commits are changes to software that address multiple concerns at once. For researchers interested in bugs, tangled commits mean that they actually study not only bugs, but also other concerns irrelevant for the study of bugs. Objective: We want to improve our understanding of the prevalence of tangling and the types of changes that are tangled within bug fixing commits. Methods: We use a crowd sourcing approach for manual labeling to validate which changes contribute to bug fixes for each line in bug fixing commits. Each line is labeled by four participants. If at least three participants agree on the same label, we have consensus. Results: We estimate that between 17% and 32% of all changes in bug fixing commits modify the source code to fix the underlying problem. However, when we only consider changes to the production code files this ratio increases to 66% to 87%. We find that about 11% of lines are hard to label leading to active disagreements between participants. Due to confirmed tangling and the uncertainty in our data, we estimate that 3% to 47% of data is noisy without manual untangling, depending on the use case. Conclusion: Tangled commits have a high prevalence in bug fixes and can lead to a large amount of noise in the data. Prior research indicates that this noise may alter results. As researchers, we should be skeptics and assume that unvalidated data is likely very noisy, until proven otherwise.