Negative Emissions Technologies: Difference between revisions

From Climate Change AI Wiki
(condensing last bullet in applications)
Line 27: Line 27:
==Libraries and Tools==
==Libraries and Tools==

Revision as of 14:29, 14 January 2021

This page is about the intersection of negative emissions technologies and machine learning in the context of climate change mitigation. For an overview of carbon dioxide removal as a whole, please see the Wikipedia page on this topic.

As described in the paper "Tackling Climate Change with Machine Learning"[1]:
Even if we could cut emissions to zero today, we would still face significant climate consequences from greenhouse gases already in the atmosphere. Eliminating emissions entirely may also be tricky, given the sheer diversity of sources (such as airplanes and cows). Instead, many experts argue that to meet critical climate goals, global emissions must become net-negative—that is, we must remove more CO2 from the atmosphere than we release [2][3]. Although there has been significant progress in negative emissions research [4][5][6][7][8], the actual CO2 removal industry is still in its infancy. As such, many of the ML applications we outline in this section are either speculative or in the early stages of development or commercialization. Some of the most commonly known negative emissions technologies include nature-based solutions such as afforestation (growing more trees and storing carbon in this biomass) and regenerative farming practices as well as highly engineered technologies such as direct air capture (DAC) with sequestration of the captured CO2 in underground geologic formations. Another commonly discussed negative emissions technology is biomass combustion with carbon capture and sequestration, described further in Electricity Systems.
Many DAC technologies are in early stages of commercialization.[4][5] The underlying chemical processes are fairly well understood and the design of these systems generally does not require machine learning; however, ML may be useful in designing more effective CO2 sorbents. ML also may have a number of applications in CO2 sequestration, namely in identifying, modeling, and monitoring CO2 sequestration sites.

Machine Learning Application Areas

  • Accelerated materials discovery of new chemical sorbents: One potentially promising ML application for DAC is accelerated materials discovery of new chemical sorbents that either bind to atmospheric CO2 with either greater selectivity or have lower energy input requirements.
  • CO2 migration modeling: For carbon capture and sequestration to be effective, it must sequester CO2 for hundreds or thousands of years. Thus, understanding the long-term migration of sequestered CO2, particularly in underground saline reservoir formations but also in basalts, is of critical importance. Machine learning can help speed up computationally intensive reservoir simulation models by orders of magnitude, accelerating the speed at which scientists can answer key questions.
  • Identification of CO2 sequestration locations: ML can help identify and characterize potential CO2 storage locations. In particular, oil and gas companies have had promising results using ML for subsurface imaging based on raw seismograph traces;[9] these models and the data behind them could likely be repurposed to help trap CO2 rather than release it.
  • CO2 sequestration site monitoring: ML can help monitor and maintain active sequestration sites by analyzing sensor measurements, and by monitoring for CO2 leaks.

Background Readings

  • Negative Emissions Technologies and Reliable Sequestration: A Research Agenda. [4]
  • Direct Air Capture of Carbon Dioxide: ICEF Roadmap 2018 [5]

Online Courses and Course Materials

  • Introduction to CO2 sequestration for negative emissions, lecture by Sally Benson at the International Conference on Negative CO2 Emissions [link]

Conferences, Journals, and Professional Organizations

Libraries and Tools

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



  1. Rolnick, David; Donti, Priya L.; Kaack, Lynn H.; Kochanski, Kelly; Lacoste, Alexandre; Sankaran, Kris; Ross, Andrew Slavin; Milojevic-Dupont, Nikola; Jaques, Natasha; Waldman-Brown, Anna; Luccioni, Alexandra (2019-11-05). "Tackling Climate Change with Machine Learning". arXiv:1906.05433 [cs, stat].
  2. Fuss, Sabine; Canadell, Josep G.; Peters, Glen P.; Tavoni, Massimo; Andrew, Robbie M.; Ciais, Philippe; Jackson, Robert B.; Jones, Chris D.; Kraxner, Florian; Nakicenovic, Nebosja; Le Quéré, Corinne (2014-10). "Betting on negative emissions". Nature Climate Change. 4 (10): 850–853. doi:10.1038/nclimate2392. ISSN 1758-6798. Check date values in: |date= (help)
  3. Gasser, T.; Guivarch, C.; Tachiiri, K.; Jones, C. D.; Ciais, P. (2015-08-03). "Negative emissions physically needed to keep global warming below 2 °C". Nature Communications. 6 (1): 1–7. doi:10.1038/ncomms8958. ISSN 2041-1723.
  4. 4.0 4.1 4.2 National Academies of Sciences, Engineering (2018-10-24). Negative Emissions Technologies and Reliable Sequestration: A Research Agenda. ISBN 978-0-309-48452-7.
  5. 5.0 5.1 5.2 ICEF. "Direct Air Capture of Carbon Dioxide: ICEF Roadmap 2018". Retrieved 2020-09-12.
  6. "ShieldSquare Captcha". Retrieved 2020-09-12.
  7. Fuss, Sabine; Lamb, William F.; Callaghan, Max W.; Hilaire, Jérôme; Creutzig, Felix; Amann, Thorben; Beringer, Tim; Garcia, Wagner de Oliveira; Hartmann, Jens; Khanna, Tarun; Luderer, Gunnar (2018-05). "Negative emissions—Part 2: Costs, potentials and side effects". Environmental Research Letters. 13 (6): 063002. doi:10.1088/1748-9326/aabf9f. ISSN 1748-9326. Check date values in: |date= (help)
  8. "ShieldSquare Captcha". Retrieved 2020-09-12.
  9. Araya-Polo, Mauricio; Jennings, Joseph; Adler, Amir; Dahlke, Taylor (2017-12-29). "Deep-learning tomography". The Leading Edge. 37 (1): 58–66. doi:10.1190/tle37010058.1. ISSN 1070-485X.