Global efforts to reduce emissions are hampered by incomplete and unreliable data from coal power plants regarding their release of greenhouse gases. This inability to acquire data, particularly relevant in regions lacking robust reporting mechanisms, hinders evidence-based policy-making and proper action against prominent emissions contributors. To address this issue, we propose using a transformer-based approach to determine the coal plant’s operational status – entirely through satellite images. This method leverages the readily available global coverage of satellite imagery to provide independent, real-time monitoring of coal plant operations, even in areas where traditional data collection methods are challenging. The model learns to identify visual indicators, such as cooling tower plumes in unseen test images. Our transformer-based approach outperforms the best prior work with statistical significance, reaching an 80% accuracy on a held-out set of unseen coal plant satellite images. These results have far-reaching implications for climate monitoring and regulations. By providing more accurate and independently sourced information on coal plant operations worldwide, our approach can support more effective emissions tracking, inform climate negotiations, and introduce greater transparency into the process of climate regulation.
References
[1]
Asia-Pacific Economic Cooperation (2008). Best Practices in Environmental Monitoring for Coal-Fired Power Plants: Lessons for Developing Asian APEC Economies. https://www.apec.org/docs/default-source/publications/2008/11/best-practices-in-environmental-monitoring-for-coalfired-power-plants-lessons-for-developing-asian-a/08_ewg_environ_coal.pdf
[2]
Bauckloh, T., Klein, C., Pioch, T., & Schiemann, F. (2023). Under Pressure? The Link between Mandatory Climate Reporting and Firms’ Carbon Performance. Organization&Environment,36, 126-149. https://doi.org/10.1177/10860266221083340
[3]
Birol, F., & Malpass, D. (2024). It’s Critical to Tackle Coal Emissions. International Energy Agency. https://coilink.org/20.500.12592/tv2ms6
[4]
Climate Works Australia (2018). Tracking Progress to Net Zero Emissions. Climate Works Australia. https://apo.org.au/node/249761
[5]
Datt, R. R., Luo, L., & Tang, Q. (2019). Corporate Voluntary Carbon Disclosure Strategy and Carbon Performance in the USA. AccountingResearchJournal,32, 417-435. https://doi.org/10.1108/arj-02-2017-0031
[6]
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T. et al. (2020). An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale. arXiv: 2010.11929. https://doi.org/10.48550/arXiv.2010.11929
[7]
Jacob, D. J., Varon, D. J., Cusworth, D. H., Dennison, P. E., Frankenberg, C., Gautam, R. et al. (2022). Quantifying Methane Emissions from the Global Scale down to Point Sources Using Satellite Observations of Atmospheric Methane. AtmosphericChemistryandPhysics,22, 9617-9646. https://doi.org/10.5194/acp-22-9617-2022
[8]
Li, B., & Kroese, B. (2022). Bridging Data Gaps Can Help Tackle the Climate Crisis. https://www.imf.org/en/Blogs/Articles/2022/11/28/bridging-data-gaps-can-help-tackle-the-climate-crisis
[9]
Maasakkers, J. D., Varon, D. J., Elfarsdóttir, A., McKeever, J., Jervis, D., Mahapatra, G. et al. (2022). Using Satellites to Uncover Large Methane Emissions from Landfills. ScienceAdvances,8, eabn9683. https://doi.org/10.1126/sciadv.abn9683
[10]
Mitchell, G., Söldner-Rembold, I., D’souza, D., Karra, K., Zhang, K., Kargar, A. et al. (2020). Towards Tracking the Emissions of Every Power Plant on the Planet. NeurIPS 2020 Workshop: Tackling Climate Change with Machine Learning (pp. 1-9).
[11]
Network for Greening the Financial System (NGFS) (2022) Final Report on Bridging Data Gaps. https://www.ngfs.net/sites/default/files/medias/documents/final_report_on_bridging_data_gaps.pdf
[12]
NSW EPA (2018). Review of Coal Fired Power Stations Air Emissions and Monitoring. https://www.epa.nsw.gov.au/-/media/epa/corporate-site/resources/air/18p0700-review-of-coal-fired-power-stations.pdf
[13]
Pu, Y., Apel, D. B., Szmigiel, A., & Chen, J. (2019). Image Recognition of Coal and Coal Gangue Using a Convolutional Neural Network and Transfer Learning. Energies, 12, Article 1735. https://doi.org/10.3390/en12091735
[14]
Rosenstock, T. S., Lamanna, C., Chesterman, S., Hammond, J., Kadiyala, S., Luedeling, E. et al. (2017). When Less Is More: Innovations for Tracking Progress toward Global Targets. CurrentOpinioninEnvironmentalSustainability,26, 54-61. https://doi.org/10.1016/j.cosust.2017.02.010
[15]
Singh, S. (2021). Energy Crisis and Climate Change: Global Concerns and Their Solutions. In P. Singh, S. Singh, G. Kumar, & P. Baweja (Eds.), Energy: Crises, Challenges and Solutions (pp. 1-17). Wiley. https://doi.org/10.1002/9781119741503.ch1
[16]
Varon, D. J., McKeever, J., Jervis, D., Maasakkers, J. D., Pandey, S., Houweling, S. et al. (2019). Satellite Discovery of Anomalously Large Methane Point Sources from Oil/gas Production. GeophysicalResearchLetters,46, 13507-13516. https://doi.org/10.1029/2019gl083798
[17]
Vaswani, A. (2017). Attention Is All You Need. In Association for Computing Machinery (Ed.), Proceedings of the 31st International Conference on Neural Information Processing Systems (pp. 6000-6010). Curran Associates Inc.