How big will the next eruption be?

Table 1 Model Attributes. Attributes used for prediction. Type of attribute can be “Cat” for Categorical or “Num” for Numeric. For categorical data, the number of unique classes are listed for each attribute. To provide context on relative data size, the number of values (N) available for the post-1500 VEI ≥ 0 dataset are provided. This is an example dataset and the number of values available for the other dataset can be read from the white numbers in the bar graphs of Figs. 1–2

Attribute	Type	Number of classes	Models Using Attribute	N in post-1500 historied VEI ≥ 0 dataset	N in post-1500 unhistoried VEI ≥ 0 dataset
Intrinsic Predictors
Dominant Rock Type	Cat	10	All Attributes Categorical Data Dominant Rock Type	424	133
Morphology	Cat	6	All Attributes Categorical Data Morphology	431	145
Tectonic Setting	Cat	10	All Attributes Categorical Data Tectonic Setting	431	145
Additional History Predictors
Repose Time	Num	N/A	All Attributes All Numeric Data Repose Time	321	N/A
Eruption Duration (previous eruption)	Num	N/A	All Attributes All Numeric Data Eruption Duration	281	N/A
Simple Predictors
Last VEI	Num	N/A	All Attributes All Numeric Data Last VEI	431	N/A
Median VEI	Num	N/A	All Attributes All Numeric Data Median VEI	431	N/A
Mode VEI	Num	N/A	All Attributes All Numeric Data Mode VEI	431	N/A
Minimum VEI	Num	N/A	All Attributes All Numeric Data Minimum VEI	431	N/A
Maximum VEI	Num	N/A	All Attributes All Numeric Data Maximum VEI	431	N/A

ISSN: 2191-5040