• Brun et al. map? Premature wilting
• temporal trends for pixels in this map)
• compare temporal trends for models
• leave site out cross validation (for performance range)
• center values

The premise of the manuscript would be that the physiological basis of fLUE can be used as a target for a new drought index through machine learning. Two caveats remain.

1. potential data leakage and circularity in the use of the data.

• i.e. MODIS is used as input in both analysis (fLUE, this work)
• this has been addressed by showing sensitivity to fLUE by Landsat data, therefore decoupling the calculated index and the input data (while keeping all other things static). It must be noted that the model structure does change when using landsat data.

2. how does this more complex model compare to known indices? The idea in this work has been that a ML model trained on fLUE should outperform existing indices when it comes to its relation to fLUE. Is this the case?

• it seems that the model generally outperforms the bulk of the indices, but there are exceptions. One needs to check if the same indices return on the top of the list across clusters and sites. The parsimonious solution of the ML model might be a benefit in comparison to a tailored site / vegetation specific index.

Point 1. has been answered through the use of landsat data with results which hold up. Number 2. has been proven by a cross comparison to a zoo of indices - but needs nuances wrt to the indices.

See vignettes
https://geco-bern.github.io/index_based_drought_monitoring/

A third caveat remains, but is part of any simple index, mainly the fact that this metric/model is diagnostic only (calculated for each time step) and not prognostic.

The analysis needs contextualization. Basically, there is a zoo of indices out there:
https://awesome-ee-spectral-indices.readthedocs.io/en/latest/index.html#r

Many of them, relating to soil/vegetation/water have an S2 (MODIS B7) component to them. I would not be surprised that the model including all these indices would surface one of these in a VIP analysis if including them outright.

For example the Normalized Multi-band Drought Index is defined as:
(NIR - (S1 - S2))/(N + (S1 - S2))

Which includes 3 out of 4 most important variables of the ML model. Point being that there must be marked improvement over something with a physical basis (and a simple transfer function).

https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2007GL031021

Country list needs to be expanded, missing countries to the east and micro-states (created lichtenstein hole).