Articles | Volume 23, issue 5
https://doi.org/10.5194/nhess-23-1755-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/nhess-23-1755-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Reduced-order digital twin and latent data assimilation for global wildfire prediction
Caili Zhong
Department of Earth Science and Engineering, Imperial College London, London, United Kingdom
Data Science Institute, Imperial College London, London, United
Kingdom
Matthew Kasoar
Department of Physics, Imperial College London, London, United Kingdom
Rossella Arcucci
Department of Earth Science and Engineering, Imperial College London, London, United Kingdom
Related authors
No articles found.
Oliver Perkins, Olivia Haas, Matthew Kasoar, Apostolos Voulgarakis, and James D. A. Millington
EGUsphere, https://doi.org/10.5194/egusphere-2025-3728, https://doi.org/10.5194/egusphere-2025-3728, 2025
This preprint is open for discussion and under review for Earth System Dynamics (ESD).
Short summary
Short summary
Humans impact fire indirectly through climate change, but also directly through land use and different fire management strategies. We compare two recently-developed models of global burned area with very different assumptions about the role of direct human impacts on fire. We contrast their future projections and explore the implications of differences between them for climate change adaptation and fire science more broadly.
Arianna Olivelli, Rossella Arcucci, Mark Rehkämper, and Tina van de Flierdt
Earth Syst. Sci. Data, 17, 3679–3699, https://doi.org/10.5194/essd-17-3679-2025, https://doi.org/10.5194/essd-17-3679-2025, 2025
Short summary
Short summary
In this study, we use machine learning models to produce the first global maps of Pb concentrations and isotope compositions in the ocean. In line with observations, we find that (i) the surface Indian Ocean has the highest levels of pollution, (ii) pollution from previous decades is sinking in the North Atlantic and Pacific oceans, and (iii) waters carrying Pb pollution are spreading from the Southern Ocean throughout the Southern Hemisphere at intermediate depths.
Wenbo Yu, Anirbit Ghosh, Tobias Sebastian Finn, Rossella Arcucci, Marc Bocquet, and Sibo Cheng
EGUsphere, https://doi.org/10.5194/egusphere-2025-2836, https://doi.org/10.5194/egusphere-2025-2836, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
We introduce the first denoising diffusion model for wildfire spread prediction, a new kind of generative AI model that learns to simulate fires not just as one fixed outcome, but as a range of possible scenarios. This allows us to capture the inherent uncertainty of wildfire dynamics. Our model produces ensembles of forecasts that reflect physically meaningful distributions of where fire might go next.
Anastasios Rovithakis, Eleanor Burke, Chantelle Burton, Matthew Kasoar, Manolis G. Grillakis, Konstantinos D. Seiradakis, and Apostolos Voulgarakis
EGUsphere, https://doi.org/10.5194/egusphere-2025-274, https://doi.org/10.5194/egusphere-2025-274, 2025
Short summary
Short summary
JULES-INFERNO captures observed burned area across Greece fairly well for the present-day. Drastic future changes in burnt area in Eastern continental and southern Greece, especially under severe climate change scenarios. Static vegetation leads to larger burnt area compared to dynamic vegetation due to the lower concentration of flammable needleleaf trees.
Oliver Perkins, Matthew Kasoar, Apostolos Voulgarakis, Cathy Smith, Jay Mistry, and James D. A. Millington
Geosci. Model Dev., 17, 3993–4016, https://doi.org/10.5194/gmd-17-3993-2024, https://doi.org/10.5194/gmd-17-3993-2024, 2024
Short summary
Short summary
Wildfire is often presented in the media as a danger to human life. Yet globally, millions of people’s livelihoods depend on using fire as a tool. So, patterns of fire emerge from interactions between humans, land use, and climate. This complexity means scientists cannot yet reliably say how fire will be impacted by climate change. So, we developed a new model that represents globally how people use and manage fire. The model reveals the extent and diversity of how humans live with and use fire.
Katie R. Blackford, Matthew Kasoar, Chantelle Burton, Eleanor Burke, Iain Colin Prentice, and Apostolos Voulgarakis
Geosci. Model Dev., 17, 3063–3079, https://doi.org/10.5194/gmd-17-3063-2024, https://doi.org/10.5194/gmd-17-3063-2024, 2024
Short summary
Short summary
Peatlands are globally important stores of carbon which are being increasingly threatened by wildfires with knock-on effects on the climate system. Here we introduce a novel peat fire parameterization in the northern high latitudes to the INFERNO global fire model. Representing peat fires increases annual burnt area across the high latitudes, alongside improvements in how we capture year-to-year variation in burning and emissions.
Stephanie Fiedler, Vaishali Naik, Fiona M. O'Connor, Christopher J. Smith, Paul Griffiths, Ryan J. Kramer, Toshihiko Takemura, Robert J. Allen, Ulas Im, Matthew Kasoar, Angshuman Modak, Steven Turnock, Apostolos Voulgarakis, Duncan Watson-Parris, Daniel M. Westervelt, Laura J. Wilcox, Alcide Zhao, William J. Collins, Michael Schulz, Gunnar Myhre, and Piers M. Forster
Geosci. Model Dev., 17, 2387–2417, https://doi.org/10.5194/gmd-17-2387-2024, https://doi.org/10.5194/gmd-17-2387-2024, 2024
Short summary
Short summary
Climate scientists want to better understand modern climate change. Thus, climate model experiments are performed and compared. The results of climate model experiments differ, as assessed in the latest Intergovernmental Panel on Climate Change (IPCC) assessment report. This article gives insights into the challenges and outlines opportunities for further improving the understanding of climate change. It is based on views of a group of experts in atmospheric composition–climate interactions.
Christopher D. Wells, Matthew Kasoar, Majid Ezzati, and Apostolos Voulgarakis
Atmos. Chem. Phys., 24, 1025–1039, https://doi.org/10.5194/acp-24-1025-2024, https://doi.org/10.5194/acp-24-1025-2024, 2024
Short summary
Short summary
Human-driven emissions of air pollutants, mostly caused by burning fossil fuels, impact both the climate and human health. Millions of deaths each year are caused by air pollution globally, and the future trends are uncertain. Here, we use a global climate model to study the effect of African pollutant emissions on surface level air pollution, and resultant impacts on human health, in several future emission scenarios. We find much lower health impacts under cleaner, lower-emission futures.
Christopher D. Wells, Matthew Kasoar, Nicolas Bellouin, and Apostolos Voulgarakis
Atmos. Chem. Phys., 23, 3575–3593, https://doi.org/10.5194/acp-23-3575-2023, https://doi.org/10.5194/acp-23-3575-2023, 2023
Short summary
Short summary
The climate is altered by greenhouse gases and air pollutant particles, and such emissions are likely to change drastically in the future over Africa. Air pollutants do not travel far, so their climate effect depends on where they are emitted. This study uses a climate model to find the climate impacts of future African pollutant emissions being either high or low. The particles absorb and scatter sunlight, causing the ground nearby to be cooler, but elsewhere the increased heat causes warming.
Yawei Qu, Apostolos Voulgarakis, Tijian Wang, Matthew Kasoar, Chris Wells, Cheng Yuan, Sunil Varma, and Laura Mansfield
Atmos. Chem. Phys., 21, 5705–5718, https://doi.org/10.5194/acp-21-5705-2021, https://doi.org/10.5194/acp-21-5705-2021, 2021
Short summary
Short summary
The meteorological effect of aerosols on tropospheric ozone is investigated using global atmospheric modelling. We found that aerosol-induced meteorological effects act to reduce modelled ozone concentrations over China, which brings the simulation closer to observed levels. Our work sheds light on understudied processes affecting the levels of tropospheric gaseous pollutants and provides a basis for evaluating such processes using a combination of observations and model sensitivity experiments.
Cited articles
acse-cz421: DL-WG/Digital-twin-LA-global-wildfire: Reduced-order digital twin and latent data assimilation for global wildfire prediction (v1.1.1), Zenodo [data set] and [code], https://doi.org/10.5281/zenodo.7866704, 2023.
Amendola, M., Arcucci, R., Mottet, L., Casas, Q. C., Fan, S., Pain, C.,
Linden, P., and Guo, Y.: Data Assimilation in the Latent Space of a
Convolutional Autoencoder, ICCS 2021, Lect. Notes Comput. Sc.,
12746, 373–386, https://doi.org/10.1007/978-3-030-77977-1_30, 2021.
Bauer, P., Stevens, B., and Hazeleger, W.: A digital twin of Earth for the
green transition, Nat. Clim. Change, 11, 80–83,
https://doi.org/10.1038/s41558-021-00986-y, 2021.
Best, M. J., Pryor, M., Clark, D. B., Rooney, G. G., Essery, R. L. H., Ménard, C. B., Edwards, J. M., Hendry, M. A., Porson, A., Gedney, N., Mercado, L. M., Sitch, S., Blyth, E., Boucher, O., Cox, P. M., Grimmond, C. S. B., and Harding, R. J.: The Joint UK Land Environment Simulator (JULES), model description – Part 1: Energy and water fluxes, Geosci. Model Dev., 4, 677–699, https://doi.org/10.5194/gmd-4-677-2011, 2011.
Bianchi, F. M., De Santis, E., Rizzi, A., and Sadeghian, A.: Short-Term
Electric Load Forecasting Using Echo State Networks and PCA Decomposition,
IEEE, 3, 1931–1943, https://doi.org/10.1109/ACCESS.2015.2485943, 2015.
Bonavita, M., Hólm, E., Isaksen, L., and Fisher, M.: The evolution of the
ECMWF hybrid data assimilation system, Royal Meteorological Society, 142,
287–303, https://doi.org/10.1002/qj.2652, 2015.
Burton, C., Betts, R., Cardoso, M., Feldpausch, T. R., Harper, A., Jones, C. D., Kelley, D. I., Robertson, E., and Wiltshire, A.: Representation of fire, land-use change and vegetation dynamics in the Joint UK Land Environment Simulator vn4.9 (JULES), Geosci. Model Dev., 12, 179–193, https://doi.org/10.5194/gmd-12-179-2019, 2019.
Cheng, S., Argaud, J. P., Iooss, B., Lucor, D., and Ponçot, A.: Error
covariance tuning in variational data assimilation: application to an
operating hydrological model, Stoch. Env. Res. Risk. A., 35, 1019–1038,
https://doi.org/10.1007/s00477-020-01933-7, 2020.
Cheng, S., Prentice, I. C., Huang, Y., Jin, Y., Guo, Y. K., and Arcucci, R.:
Data-driven surrogate model with latent data assimilation: Application to
wildfire forecasting, J. Comput. Phys., 464,
111302, https://doi.org/10.1016/j.jcp.2022.111302, 2022a.
Cheng, S., Chen, J., Anastasiou, C., Angeli, P., Matar, K. O. Guo, Y. K.
Pain, C. C., and Arcucci, R.: Generalized Latent Assimilation in
Heterogeneous Reduced Spaces with Machine Learning Surrogate Models, J.
Sci. Comput.,
arXiv [preprint], https://doi.org/10.48550/arXiv.2204.03497, 2022b.
Cheng, S., Quilodrán-Casas, C., Ouala, S., Farchi, A., Liu, C., Tandeo, P., Fablet, R., Lucor, D., Iooss, B., Brajard, J., Xiao, D., Janjic, T., Ding, W., Guo, Y., Carrassi, A., Bocquet, M., and Arcucci, R.:
Machine learning with data assimilation 65 and uncertainty quantification for dynamical systems: a review, arXiv [preprint],
https://doi.org/10.48550/arXiv.2303.10462, 2023.
Clark, D. B., Mercado, L. M., Sitch, S., Jones, C. D., Gedney, N., Best, M. J., Pryor, M., Rooney, G. G., Essery, R. L. H., Blyth, E., Boucher, O., Harding, R. J., Huntingford, C., and Cox, P. M.: The Joint UK Land Environment Simulator (JULES), model description – Part 2: Carbon fluxes and vegetation dynamics, Geosci. Model Dev., 4, 701–722, https://doi.org/10.5194/gmd-4-701-2011, 2011.
Claussen, M., Mysak, L., Weaver, A., Crucifix, M., Fichefet, T., Loutre, M. F., Weber, S., Alcamo, J., Alexeev, V., Berger, A., Calov, R., Ganopolski, A., Goosse, H., Lohmann, G., Lunkeit, F., Mokhov, I., Petoukhov, V., Stone, P., and Wang, Z.: Earth system models of intermediate complexity:
closing the gap in the spectrum of climate system models, Clim. Dynam.,
18, 579–586, https://doi.org/10.1007/s00382-001-0200-1, 2002.
Fulton, W.: Eigenvalues, invariant factors, highest weights, and Schubert
calculus, B. Am. Math. Soc., 37, 209–250, https://doi.org/10.1090/S0273-0979-00-00865-X, 2000.
Gong, H., Yu, Y., Li, Q., and Quan, C.: An inverse-distance-based fitting
term for 3D-Var data assimilation in nuclear core simulation, Ann. Nucl. Energy, 141, 107346, https://doi.org/10.1016/j.anucene.2020.107346, 2020.
Gong, H., Cheng, S., Chen, Z., and Li, Q.: Data-Enabled Physics-Informed
Machine Learning for Reduced-Order Modeling Digital Twin: Application to
Nuclear Reactor Physics, Nucl. Sci. Eng., 196, 668–693,
https://doi.org/10.1080/00295639.2021.2014752, 2022a.
Gong, H., Cheng, S., Chen, Z., Li, Q., Quilodrán-Casas, C., Xiao, D., and
Arcucci, R.: An efficient digital twin based on machine learning SVD
autoencoder and generalised latent assimilation for nuclear reactor physics,
Ann. Nucl. Energy, 179, 109431,
https://doi.org/10.1016/j.anucene.2022.109431, 2022b.
Graves, A. and Schmidhuber, J.: Framewise phoneme classification with
bidirectional LSTM and other neural network architectures, Neural Networks,
18, 602–610, https://doi.org/10.1016/j.neunet.2005.06.042, 2005a.
Graves, A. and Schmidhuber, J.: Framewise phoneme classification with
bidirectional LSTM networks, Neural Networks, 4, 2047–2052,
https://doi.org/10.1109/IJCNN.2005.1556215, 2005b.
Grillakis, M, Voulgarakis, A., Rovithakis, A., Seiradakis, K. D., Koutroulis,
A., Field, R. D., Kasoar, M., Papadopoulos, A., and Lazaridis, M.: Climate
Drivers of Global Wildfire Burned Area, 17, 045021,
https://doi.org/10.1088/1748-9326/ac5fa1, 2022.
Huang, Z., Xue, W., Mao, Q., and Zhan, Y.: Unsupervised domain adaptation for
speech emotion recognition using PCANet, Multimed. Tools Appl.,
76, 6785–6799, https://doi.org/10.1007/s11042-016-3354-x, 2017.
Jain, P., Coogan, P. S., Subramanian, G. S., Crowley, M., Taylor, S., and
Flannigan, D. M.: A review of machine learning applications in wildfire
science and management, Environ. Rev., 28, 478–505,
https://doi.org/10.1139/er-2020-0019, 2020.
Jauhiainen, J., Hooijer, A., and Page, S. E.: Carbon dioxide emissions from an Acacia plantation on peatland in Sumatra, Indonesia, Biogeosciences, 9, 617–630, https://doi.org/10.5194/bg-9-617-2012, 2012.
JASMIN Site: JASMIN The UK's data analysis facility for environmental science, https://jasmin.ac.uk/, last access: 26 October 2022.
Kim, S.: Particulate Matter and Ozone: Remote Sensing and Source Attribution, ProQuest Dissertations Publishing, https://dash.harvard.edu/handle/1/17467177 (last access: 21 April 2023), 2015.
Lasslop, G., Coppola, A. I., Voulgarakis, A., Yue, C., and Veraverbeke, S.:
Influence of Fire on the Carbon Cycle and Climate, Current Climate Change
Reports, 5, 112–123, https://doi.org/10.1007/s40641-019-00128-9, 2019.
Lawless, A. S., Gratton, S., and Nichols, N. K.: Approximate iterative method
for variational data assimilation, Int. J. Numer.
Meth. Fl., 1, 1129–1135, https://doi.org/10.1002/fld.851, 2005.
Lawrence, B. N. and Bennett, V. L. and Churchill, J. and Juckes, M. and Kershaw, P. and Pascoe, S. and Pepler, S. and Pritchard, M., and Stephens, A.: Storing and manipulating environmental big data with JASMIN, 2013 IEEE International Conference on Big Data, Silicon Valley, CA, USA, 6–9 October 2013, https://doi.org/10.1109/BigData.2013.6691556, 2013.
Li, H., Li, Y., Wang, Z., and Li, Z.: Remaining Useful Life Prediction of
Aero-Engine Based on PCA-LSTM, 2021 7th International Conference on Condition Monitoring of Machinery in Non-Stationary Operations (CMMNO), IEEE, Guangzhou, China, 11–13 June 2021, 63–66,
https://doi.org/10.1109/CMMNO53328.2021.9467643, 2021.
Lorenc, C. A., Ballard, P. S., Bell, S. R., Ingleby, B. N., Andrews, F. L.
P., Barker, D. M., Bray, R. J., Clayton, M. A., Dalby, T., Li, D., Payne, J.
T., and Saunders, W. F.: The Met. Office global three-dimensional variational
data assimilation scheme, Royal Meteorological Society, 126, 2991–3012,
https://doi.org/10.1002/qj.49712657002, 2000.
Ma, X., Lu, X., Yu, Y., Zhu, J., and Chen, J.: Progress on hybrid
ensemble-variational data assimilation in numerical weather prediction,
J. Trop. Meteorol., 20, 1188–1195, 2014.
Mangeon, S., Voulgarakis, A., Gilham, R., Harper, A., Sitch, S., and Folberth, G.: INFERNO: a fire and emissions scheme for the UK Met Office's Unified Model, Geosci. Model Dev., 9, 2685–2700, https://doi.org/10.5194/gmd-9-2685-2016, 2016.
Marlier, E. M., DeFries, S. R., Kim, S. P., Koplitz, N. S., Jacob, J. D.,
Mickley, J. L., and Myers, S. S.: Fire emissions and regional air quality
impacts from fires in oil palm, timber, and logging concessions in
Indonesia, Environ. Res. Lett., 10, 85005,
https://doi.org/10.1088/1748-9326/10/8/085005, 2015.
Masci, J., Meier, V., Ciregan, D., and Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction, International Conference on Artificial Neural Networks 2011, 6791, 52–59, https://doi.org/10.1007/978-3-642-21735-7_7, 2011.
Mohan, A. and Gaitonde, D.: A Deep Learning based Approach to Reduced Order
Modelling for Turbulent Flow Control using LSTM Neural Networks, arXiv [preprint], https://doi.org/10.48550/arXiv.1812.04951, 2018.
Nadeem, K., Taylor, S. W., Woolford, D., and Dean, C.: Mesoscale
spatiotemporal predictive models of daily human- and lightning-caused
wildland fire occurrence in British Columbia, Int. J.
Wildland Fire, 29, 11–27, https://doi.org/10.1071/WF19058, 2020.
Pais, C., Miranda, A., Carrasco, J., and Shen, Z. M.: Deep Fire Topology:
Understanding the role of landscape spatial patterns in wildfire
susceptibility, Environ. Modell. Softw., 143, 105–122,
https://doi.org/10.1016/j.envsoft.2021.105122, 2021.
Pechony, O. and Shindell, D. T.: Fire parameterization on a global scale,
J. Geophys. Res., 114, D16115, https://doi.org/10.1029/2009jd011927,
2009.
Peyron, M., Fillion, A., Gürol, S., Marchais, V., Gratton, S., Boudier,
P., and Goret, G.: Latent space data assimilation by using deep learning,
arXiv [preprint], https://doi.org/10.48550/arXiv.2104.00430, 2021.
Prentice, C. I. and Cowling, A. S.: Dynamic Global Vegetation Models,
Encyclopedia of Biodiversity, 2, 670–689,
https://doi.org/10.1016/B978-0-12-384719-5.00412-3, 2013.
Quilodrán-Casas, C., Silva, V., Arcucci, R., Heaney, C., Guo, Y., and
Pain, C.: Digital twins based on bidirectional LSTM and GAN for modelling
COVID-19, Neurocomputing, 470, 11–28,
https://doi.org/10.48550/arXiv.2102.02664, 2022.
Rabin, S. S., Melton, J. R., Lasslop, G., Bachelet, D., Forrest, M., Hantson, S., Kaplan, J. O., Li, F., Mangeon, S., Ward, D. S., Yue, C., Arora, V. K., Hickler, T., Kloster, S., Knorr, W., Nieradzik, L., Spessa, A., Folberth, G. A., Sheehan, T., Voulgarakis, A., Kelley, D. I., Prentice, I. C., Sitch, S., Harrison, S., and Arneth, A.: The Fire Modeling Intercomparison Project (FireMIP), phase 1: experimental and analytical protocols with detailed model descriptions, Geosci. Model Dev., 10, 1175–1197, https://doi.org/10.5194/gmd-10-1175-2017, 2017.
Teckentrup, L., Harrison, S. P., Hantson, S., Heil, A., Melton, J. R., Forrest, M., Li, F., Yue, C., Arneth, A., Hickler, T., Sitch, S., and Lasslop, G.: Response of simulated burned area to historical changes in environmental and anthropogenic factors: a comparison of seven fire models, Biogeosciences, 16, 3883–3910, https://doi.org/10.5194/bg-16-3883-2019, 2019.
Vallino, J. J.: Improving marine ecosystem models: Use of data assimilation
and mesocosm experiments, J. Mar. Res., 58,
117–164, https://doi.org/10.1357/002224000321511223, 2000.
Ward, D. S., Kloster, S., Mahowald, N. M., Rogers, B. M., Randerson, J. T., and Hess, P. G.: The changing radiative forcing of fires: global model estimates for past, present and future, Atmos. Chem. Phys., 12, 10857–10886, https://doi.org/10.5194/acp-12-10857-2012, 2012.
Short summary
This paper introduces a digital twin fire model using machine learning techniques to improve the efficiency of global wildfire predictions. The proposed model also manages to efficiently adjust the prediction results thanks to data assimilation techniques. The proposed digital twin runs 500 times faster than the current state-of-the-art physics-based model.
This paper introduces a digital twin fire model using machine learning techniques to improve the...
Special issue
Altmetrics
Final-revised paper
Preprint