Insights into the vulnerability of vegetation to tephra fallouts from interpretable machine learning and big Earth observation data

Biass, Sébastien; Jenkins, Susanna F.; Aeberhard, William H.; Delmelle, Pierre; Wilson, Thomas

doi:https://doi.org/10.5194/nhess-22-2829-2022

Articles | Volume 22, issue 9

https://doi.org/10.5194/nhess-22-2829-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/nhess-22-2829-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 22, issue 9

Research article

|

31 Aug 2022

Research article |

| 31 Aug 2022

Insights into the vulnerability of vegetation to tephra fallouts from interpretable machine learning and big Earth observation data

Sébastien Biass, Susanna F. Jenkins, William H. Aeberhard, Pierre Delmelle, and Thomas Wilson

Data sets

Data for NHESS manuscript by Biass et al. (2022): Insights into the vulnerability of vegetation to tephra fallouts from interpretable machine learning and big Earth observation data (1.0) S. Biass https://doi.org/10.5281/zenodo.6976234

MOD13Q1 MODIS/Terra Vegetation Indices 16-Day L3 Global 250m SIN Grid V006 K. Didan https://doi.org/10.5067/MODIS/MOD13Q1.006

ERA5-Land monthly averaged data from 1981 to present J. Muñoz Sabater https://doi.org/10.24381/cds.68d2bb30

Copernicus Global Land Service: Land Cover 100 m: collection 3: epoch 2018: Globe M. Buchhorn, B. Smets, L. Bertels, B. D. Roo, M. Lesiv, N.-E. Tsendbazar, M. Herold, and S. Fritz https://doi.org/10.5281/ZENODO.3518038

Model code and software

pandas-dev/pandas The pandas development team https://doi.org/10.5281/zenodo.3509134

geopandas/geopandas: v0.8.1 K. Jordahl, J. V. den Bossche, M. Fleischmann, J. Wasserman, J. McBride, J. Gerard, J. Tratner, M. Perry, A. G. Badaracco, C. Farmer, G. A. Hjelle, A. D. Snow, M. Cochran, S. Gillies, L. Culbertson, M. Bartos, N. Eubank, maxalbert, A. Bilogur, S. Rey, C. Ren, D. Arribas-Bel, L. Wasser, L. J. Wolf, M. Journois, J. Wilson, A. Greenhall, C. Holdgraf, Filipe, and F. Leblanc https://doi.org/10.5281/zenodo.3946761

matplotlib/matplotlib: REL: v3.5.2 T. A. Caswell, M. Droettboom, A. Lee, E. S. de Andrade, T. Hoffmann, J. Klymak, J. Hunter, E. Firing, D. Stansby, N. Varoquaux, J. H. Nielsen, B. Root, R. May, P. Elson, J. K. Seppänen, D. Dale, J.-J. Lee, D. McDougall, A. Straw, P. Hobson, hannah, C. Gohlke, A. F. Vincent, T. S. Yu, E. Ma, S. Silvester, C. Moad, N. Kniazev, E. Ernest, and P. Ivanov https://doi.org/10.5281/zenodo.6513224

oegedijk/explainerdashboard O. Dijk https://doi.org/10.5281/zenodo.6408776

Short summary

We present a methodology that combines big Earth observation data and interpretable machine learning to revisit the impact of past volcanic eruptions recorded in archives of multispectral satellite imagery. Using Google Earth Engine and dedicated numerical modelling, we revisit and constrain processes controlling vegetation vulnerability to tephra fallout following the 2011 eruption of Cordón Caulle volcano, illustrating how this approach can inform the development of risk-reduction policies.