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

This repository contains the data produced in the context of the following paper:

Biass S, Jenkins SF, Aberhard WH, Delmelle P, Wilson T (2022): Insights into the vulnerability of vegetation to tephra fallouts from interpretable machine learning and big Earth observation data, Accepted in NHESS

Naming convention is: `run_date`_`landcover`_`impact_metrics`_`VI`_`anomaly`_test.pkl, where:

Landcover is either crops, shrubs, herbaceous vegetation (grass), forests (trees) or all together

Impact metrics is either minV (impact magnitude) or minT (impact duration)

VI is the vegetation index (here, EVI)

Anomaly is the impact indicator (here, cumulative difference index)

Refer to the associated paper for more information on the methodology.

Files are saved as .pkl and were generated by the explainerdashboard library. They are the result of XGBoost runs that were optimised with Optuna and analysed with the SHAP library. They contain:

The explanatory variables and observed and computed target variables for all features

The SHAP values

To load the files, use this method.