Industry

From Climate Change AI Wiki
This is the approved revision of this page, as well as being the most recent.
Jump to navigation Jump to search

This page is about the intersection of industrial systems and machine learning in the context of climate change mitigation. For an overview of industry as a whole, please see the Wikipedia page on this topic.

Selected opportunities to use machine learning to reduce greenhouse gas emissions in industry.

Industrial production is a major cause of difficult-to-eliminate GHG emissions[1], representing over 30% of global GHG emissions in 2010.[2] The IPCC estimates that energy density can be reduced by up to 25% simply through energy efficiency measures such as replacing and upgrading older equipment, but getting to carbon neutral will require switching carbon-intensive feedstocks, new materials science, improving product life cycles, streamlining supply chains, and even reducing consumer demand.[2]

The global industrial sector – dominated by large firms – spends billions of dollars annually gathering data on their own factory operations and and supply chains[3], which can potentially be fed into ML algorithms to help improve production efficiency and decrease carbon-intensive energy use. Such data collection has been facilitated by rapid improvements in sensors, automation technologies, and image recognition, assisted by the growing accessibility and cost of computing infrastructure. This notion of interconnected factory equipment, real-time data collection, and autonomous feedback loops has been referred to variously as "Industry 4.0" (or "Industrie 4.0" to recognize its German roots), "Smart/Connected Factories", "Industrial Internet of Things (IIoT)", and "digital thread" (connectivity across the supply chain/product life cycle).

By intelligently analyzing these emerging factory and supply chain data, ML can lower industrial emissions by helping industry in the following ways: switching to low-carbon fuel sources[4] [5]; optimizing heating, ventilation, and air conditioning (HVAC) systems[6]; improving production quality and efficiency; predicting equipment failures ahead of time; facilitating discoveries in material science and chemical engineering; designing for more efficient material use[7]; and streamlining supply chains.

Nonetheless, improving industrial emissions requires the availability and sharing of high-quality data (which is often proprietary to firms), as well as the alignment of firms' incentives with actually reducing emissions instead of simply producing more goods at a lower cost.[8] In addition, ML is most useful when factory processes or complex supply chains can actually be adjusted accordingly, and when objective functions are clear.

Machine Learning Application Areas[edit | edit source]

Optimizing supply chains[edit | edit source]

  • Freight consolidation: Optimizing the shipping and transportation of goods across today's globalized supply chains is a complex, multifaceted challenge – especially for perishable goods. Bundling shipments together through freight consolidation can dramatically reduce the number of trips and associated GHG emissions. ML can optimize complex relationship between the various dimensions involved in shipping decisions, such as shipment mode and origin-destination pairs.
  • Goods demand forecasting: The production, shipment, and climate-controlled warehousing of excess products is a major source of industrial GHG emissions. ML may be able to mitigate overproduction and/or the overstocking of goods by improving models for forecasting consumer demand, especially for perishable goods or "fashionable" items that quickly become obsolete.
  • Greenhouse gas emissions mapping for supply chains: While some factories release publicly-available data on their emissions, this data is not available (or is misreported) in many cases, especially in emerging markets. ML can help map greenhouse gas emissions using a combination of remote sensing and on-the-ground data, leading both consumers and upstream suppliers to make greener decisions in sourcing products.

Developing cleaner products and materials[edit | edit source]

  • Accelerated science for clean energy technologies: Designing new materials is important for many applications, including concrete and steel alternatives, energy storage via batteries, and solar/chemical fuels. ML can help suggest promising materials to try, thereby speeding up the materials discovery process.
  • Generative design: ML-enabled 3D design software can can help create new designs for physical structures that reduce the need for carbon-intensive materials – especially cement and steel.
  • Additive manufacturing: Novel additive manufacturing techniques such as 3D printing allow for the production of unusual shapes that use less material and/or more carbon-friendly types of material, but may be impossible to produce through traditional manufacturing methods. ML can improve the algorithms controlling the printing process, leading to more faster and more accurate production.

Optimizing factory operations[edit | edit source]

  • Electricity supply and demand forecasting: The supply and demand of power must both be forecast ahead of time to inform industry's electricity planning and scheduling, thus helping factories optimize their electrical usage for renewable energy. ML can help make these forecasts more accurate, improve temporal and spatial resolution, and quantify uncertainty.
  • Demand response: By accurately predicting and quickly responding to changes in the supply of electricity, factories can reduce their electricity usage during peak periods and diminish the need for utilities to resort to fossil fuels. ML can assist with helping factories optimize the timing of their production to take advantage of inconsistent solar and wind power.
  • Methane leak detection: Fertilizer factories and other chemical plants often leak methane, a powerful greenhouse gas. ML can help detect and prevent these leaks.
  • Adaptive systems control: Most factories today rely on complex networks of disconnected production equipment, leading to inefficiencies in control systems such as temperature control, power usage, and material flow. ML techniques such as image recognition, regression trees, and time delay neural networks can help optimize the control and efficient automation of industrial systems.
  • Predictive maintenance: Quickly detecting machinery faults can help reduce electricity and materials waste. ML can help detect faults in real time from machinery sensor data, or even forecast them ahead of time to enable preemptive repair or replacement.

Background Readings[edit | edit source]

  • The IPCC's Climate Change 2014 section on Industry[2]: A comprehensive summary of the sources of industrial emissions worldwide and their potential for mitigation. Available here.
  • Industry 4.0: Wikipedia's article on the nebulous concept of Industry 4.0. Available here.
  • Life Cycle Assessment (2004)[9]: A friendly paper introducing the concept of measuring carbon emissions along the entire supply chain and life-cycle of physical products. Available here.
  • Machine Learning Applications for Data Center Optimization (2016)[6]: A technical paper explaining how Google optimized their data center power usage using ML. Available here.
  • Global Food Losses and Food Waste (2011): The UN Food and Agriculture Organization's manual on how food gets wasted across supply chains. Available here.
  • Building a New Carbon Economy (2020): Carbon180's manual on research and business opportunities for creating a carbon-neutral United States, including substantial references to industry. Available here.

Online Courses and Course Materials[edit | edit source]

  • "Introduction to Manufacturing Systems": MIT's introductory course on factory operations, taught by a seasoned professor with extensive industry experience. "This course provides ways to analyze manufacturing systems in terms of material flow and storage, information flow, capacities, and times and durations of events. Fundamental topics include probability, inventory and queuing models, optimization, and linear and dynamic systems. Factory planning and scheduling topics include flow planning, bottleneck characterization, buffer and batch-size analysis, and dynamic behavior of production systems." Course materials available here.
  • Autodesk Sustainability Workshop: "free online learning resources that teach the principles and practice of sustainability in engineering and design. This site was created to help students, educators and professionals learn more about sustainability in engineering and architecture professions." Practical videos on sustainable product design, materials selection, and engineering available here.

Conferences, Journals, and Professional Organizations[edit | edit source]

Major conferences[edit | edit source]

🌎 This section is currently a stub. You can help by adding resources, as well as 1-2 sentences of context for each resource.

Major journals[edit | edit source]

  • Journal of Cleaner Production: "[A]n international, transdisciplinary journal focusing on Cleaner Production, Environmental, and Sustainability research and practice. Through our published articles, we aim at helping societies become more sustainable. 'Cleaner Production' is a concept that aims at preventing the production of waste, while increasing efficiencies in the uses of energy, water, resources, and human capital." Website here.
  • International Journal of Advanced Manufacturing Technology: "[B]ridges the gap between pure research journals and the more practical publications on advanced manufacturing and systems. It therefore provides an outstanding forum for papers covering applications-based research topics relevant to manufacturing processes, machines and process integration." Website here.
  • Energy and Buildings: "[A]n international journal publishing articles with explicit links to energy use in buildings. The aim is to present new research results, and new proven practice aimed at reducing the energy needs of a building and improving indoor environment quality." Website here.

Major professional organizations[edit | edit source]

  • Institute of Industrial and Systems Engineers: "IISE is the world's largest professional society dedicated solely to the support of the industrial engineering profession and individuals involved with improving quality and productivity. Founded in 1948, IISE is an international, nonprofit association that provides leadership for the application, education, training, research, and development of industrial engineering." Website here.
  • BlueGreen Alliance's Clean Economy Manufacturing Center (USA): "The Clean Economy Manufacturing Center (CEMC) helps manufacturers, public officials, and economic development organizations capitalize on the opportunities presented by the fast-growing clean economy." Website here.

Libraries and Tools[edit | edit source]

  • Industrial Assessment Centers (USA): "Industrial Assessment Centers (formerly called the Energy Analysis and Diagnostic Centers) were created by the Department of Commerce in 1976 in response to the oil embargo and rising energy costs. The program was specifically focused on helping small and medium-sized manufacturing facilities cut back on unnecessary costs from inefficient energy use." This database provides a wealth of energy-saving solutions resulting from university collaborations with small factories, available here.

Data[edit | edit source]

🌎 This section is currently a stub. You can help by adding resources, as well as 1-2 sentences of context for each resource.

See the subpages listed above (e.g., the subpage on accelerated science) for application-specific datasets.

Most industrial information is proprietary, so it may be useful for researchers to connect directly with factories, to negotiate confidential access to relevant data.

Relevant Groups and Organizations[edit | edit source]

  • Ellen MacArthur Foundation: "[W]e develop and promote the idea of a circular economy. We work with, and inspire, business, academia, policymakers, and institutions to mobilise systems solutions at scale, globally." This Foundation is a UK-based business consortium focused on sustainable, zero-waste supply chains and materials development. Website here.
  • Sustainability Accounting Standards Board (SASB): A popular global standards board that has developed a "complete set of globally applicable industry-specific standards which identify the minimal set of financially material sustainability topics and their associated metrics for the typical company in an industry." Website here.
  • Carbon180's New Carbon Economy Consortium: "[A]n alliance of universities, national labs, and NGOs working in partnership with industry leaders to build a carbon-conscious world." The Consortium has a particular focus on carbon capture and sequestration, including industry, agriculture and forestry. Website here.

References[edit | edit source]

  1. Davis, Steven J.; Lewis, Nathan S.; Shaner, Matthew; Aggarwal, Sonia; Arent, Doug; Azevedo, Inês L.; Benson, Sally M.; Bradley, Thomas; Brouwer, Jack; Chiang, Yet-Ming; Clack, Christopher T. M. (2018-06-29). "Net-zero emissions energy systems". Science. 360 (6396): eaas9793. doi:10.1126/science.aas9793. ISSN 0036-8075.
  2. 2.0 2.1 2.2 Fischedick M., J. Roy, A. Abdel-Aziz, A. Acquaye, J.M. Allwood, J.-P. Ceron, Y. Geng, H. Kheshgi, A. Lanza, D. Perczyk, L. Price, E. Santalla, C. Sheinbaum, and K. Tanaka, 2014: Industry. In: Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change [Edenhofer, O., R. Pichs-Madruga, Y. Sokona, E. Farahani, S. Kadner, K. Seyboth, A. Adler, I. Baum, S. Brunner, P. Eickemeier, B. Kriemann, J. Savolainen, S. Schlömer, C. von Stechow, T. Zwickel and J.C. Minx (eds.)]. Cambridge University Press, Cambridge, United Kingdom and New York, NY, USA. Available from https://www.ipcc.ch/site/assets/uploads/2018/02/ipcc_wg3_ar5_chapter10.pdf.
  3. Mike Gualtieri, Noel Yuhanna, Holger Kisker, Rowan Curran, Brandon Purcell, Sophia Christakis, Shreyas Warrier, and Matthew Izzi. The Forrester Wave: Big data streaming analytics, Q1 2016. Forrester.com, January 2016.
  4. Berral, Josep Ll.; Goiri, Íñigo; Nou, Ramón; Julià, Ferran; Guitart, Jordi; Gavaldà, Ricard; Torres, Jordi (2010). "Towards energy-aware scheduling in data centers using machine learning". Proceedings of the 1st International Conference on Energy-Efficient Computing and Networking - e-Energy '10. New York, New York, USA: ACM Press. doi:10.1145/1791314.1791349. ISBN 978-1-4503-0042-1.
  5. Zhang, Xiao; Hug, Gabriela; Kolter, J. Zico; Harjunkoski, Iiro (2016-07). "Model predictive control of industrial loads and energy storage for demand response". 2016 IEEE Power and Energy Society General Meeting (PESGM). IEEE. doi:10.1109/pesgm.2016.7741228. ISBN 978-1-5090-4168-8. Check date values in: |date= (help)
  6. 6.0 6.1 Richard Evans and Jim Gao. DeepMind AI reduces Google data centre cooling bill by 40%. DeepMind blog, 20, 2016.
  7. Kazi, Rubaiat Habib; Grossman, Tovi; Cheong, Hyunmin; Hashemi, Ali; Fitzmaurice, George (2017-10-20). "DreamSketch: Early stage 3D design explorations with sketching and generative design". Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology. New York, NY, USA: ACM. doi:10.1145/3126594.3126662. ISBN 978-1-4503-4981-9.
  8. Sorrell, Steve (2009-04). "Jevons' Paradox revisited: The evidence for backfire from improved energy efficiency". Energy Policy. 37 (4): 1456–1469. doi:10.1016/j.enpol.2008.12.003. ISSN 0301-4215. Check date values in: |date= (help)
  9. Rebitzer, G.; Ekvall, T.; Frischknecht, R.; Hunkeler, D.; Norris, G.; Rydberg, T.; Schmidt, W. -P.; Suh, S.; Weidema, B. P.; Pennington, D. W. (2004-07-01). "Life cycle assessment: Part 1: Framework, goal and scope definition, inventory analysis, and applications". Environment International. 30 (5): 701–720. doi:10.1016/j.envint.2003.11.005. ISSN 0160-4120.