[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122964-en":3,"doc-seo-122964-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122964,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Engineering Carbon Emission-aware Machine Learning Pipelines - Paper","Machine learning advancements raise environmental concerns, especially carbon emissions. This paper introduces CEMAI, a carbon emission-aware ML pipeline that monitors and analyzes emissions across the full lifecycle, from data preparation to training and deployment. The study uses three industrial case studies for tool-wear prediction, remaining useful lifetime estimation, and anomaly detection in IIoT using CNC machining and broaching sensor data. Results show emissions can serve as a dependable metric for configuring ML pipelines to balance predictive performance and significantly reduced carbon footprint.","2024 IEEE/ACM 3rd International Conference on AI Engineering – Software Engineering for AI (CAIN)  \nEngineering Carbon Emission-aware Machine Learning Pipelines  \nErik Johannes Husom  \nSINTEF Oslo, Norway  \n[erik.johannes.husom@sintef.no](erik.johannes.husom@sintef.no)  \nSagar Sen  \nSINTEF Oslo, Norway [sagar.sen@sintef.no](sagar.sen@sintef.no)  \nArda Goknil  \nSINTEF Oslo, Norway [arda.goknil@sintef.no](arda.goknil@sintef.no)  \nABSTRACT  \nThe proliferation of machine learning (ML) has brought unprecedented advancements in technology, but it has also raised concerns about its environmental impact, particularly concerning carbon emissions. To address the imperative of environmentally responsible ML, we present in this paper a novel ML pipeline, named CEMAI, designed to monitor and analyze carbon emissions across the entire lifecycle of ML model development, from data preparation to training and deployment. Our endeavor involves an exhaustive evaluation process underpinned by three industrial case studies. These case studies are structured around the application of ML models to predict tool wear, estimate remaining useful lifetimes, and detect anomalies in the Industrial Internet of Things (IIoT) . Leveraging sensor data originating from CNC machining and broaching operations, our research shows empirically the efficacy of carbon emissions as a dependable metric guiding the configuration of an ML development process. The essence of our approach lies in striking a balance between superior performance and minimal carbon emissions. Our findings reveal the potential to optimize pipeline configurations for ML models in a manner that not only enhances performance but also drastically reduces carbon emissions, thereby underlining the significance of adopting ecologically responsible engineering practices.  \nACM Reference Format:  \nErik Johannes Husom, Sagar Sen, and Arda Goknil. 2024. Engineering Carbon Emission-aware Machine Learning Pipelines. In Conference on AI Engineering Software Engineering for AI (CAIN 2024), April 14–15, 2024, Lisbon, Portugal. ACM, New York, NY, USA, 11 pages. [https://doi.org/10.1145/](https://doi.org/10.1145/)[ ](https://doi.org/10.1145/)3644815.3644943  \n1 INTRODUCTION  \nThe carbon footprint of AI, largely associated with the training and operation of machine learning (ML) models, has been a contentious issue. Deep learning, a prominent subfield of AI, often relies on vast computational resources, with energy-hungry data centers powering the training of massive neural networks. The consequence of this computational might is substantial carbon emissions, contributing to the ever-increasing challenges posed by climate change and environmental sustainability. Amid this backdrop, it has become imperative for AI researchers and engineers to find ways to reconcile the remarkable advances in AI with a responsibility to  \nThis work licensed under Creative Commons Attribution International 4.0 License.  \nCAIN 2024, April 14–15, 2024, Lisbon, Portugal © 2024 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-0591-5/24/04 .  \n[https://doi.org/10.1145/3644815.3644943](https://doi.org/10.1145/3644815.3644943)  \nmitigate its environmental impact [32] . The pursuit of environmentally responsible AI engineering necessitates a fundamental shift in perspective that transcends the singular pursuit of ML model performance to embrace the intertwined objective of sustainability. Our goal in this paper is to address this shift by reimagining how we engineer ML pipelines and models.  \nWe stress the importance of a lifecycle analysis for ML pipelines, with a focus on carbon emissions. This approach heightens our environmental consciousness while exploring avenues to attain optimal predictive accuracy with minimal emissions. Considerable research has been devoted to developing tools for quantifying carbon emissions in ML pipelines. CodeCarbon [5], for instance, isan open-source tool that provides estimates of carbon emiss","cbCaihW3s67hbqVk","https://ap.wps.com/l/cbCaihW3s67hbqVk","pdf",1113384,1,11,"English","en",105,"# Abstract\n# Introduction\n## Motivation: carbon footprint of AI\n## Limitations of existing carbon accounting tools\n## Scope: lifecycle-aware carbon monitoring","[{\"question\":\"What problem does CEMAI address in machine learning?\",\"answer\":\"CEMAI addresses the environmental impact of machine learning by monitoring and analyzing carbon emissions throughout the entire ML lifecycle, not only during training.\"},{\"question\":\"Which industrial use cases are evaluated in the paper?\",\"answer\":\"The paper evaluates predicting tool wear, estimating remaining useful lifetime, and detecting anomalies in IIoT using sensor data from CNC machining and broaching operations.\"},{\"question\":\"How do the results support configuring ML pipelines for sustainability?\",\"answer\":\"Empirical findings indicate that carbon emissions can guide ML pipeline configuration, enabling optimization that improves performance while substantially reducing carbon emissions.\"}]","Engineering Carbon Emission-aware Machine Learning Pipelines - Paper | PDF",1785813932,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"engineering-carbon-emission-aware-machine-learning-pipelines-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/engineering-carbon-emission-aware-machine-learning-pipelines-paper/122964/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does CEMAI address in machine learning?","Question",{"text":75,"@type":76},"CEMAI addresses the environmental impact of machine learning by monitoring and analyzing carbon emissions throughout the entire ML lifecycle, not only during training.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which industrial use cases are evaluated in the paper?",{"text":80,"@type":76},"The paper evaluates predicting tool wear, estimating remaining useful lifetime, and detecting anomalies in IIoT using sensor data from CNC machining and broaching operations.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the results support configuring ML pipelines for sustainability?",{"text":84,"@type":76},"Empirical findings indicate that carbon emissions can guide ML pipeline configuration, enabling optimization that improves performance while substantially reducing carbon emissions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]