The title of this project asks what pathways lead to a compound rain-on-snow flood. A year in, there is something to report — though not yet something to conclude. Rather than assume that relationships can be governed by a few parameters — maybe that runoff responds to its drivers through a linear mean with normally distributed error, or that named copula families are enough to store the dependence — I’m letting machine learning do what it does best and find the patterns itself. The model learns the whole conditional distribution: give it a rainfall and a snowmelt, and it returns a full distribution over runoff. You can then turn the question around and ask which combinations of rain and snow most likely produced an event of a given return period.
Earlier this year my computer broke, and every output of the project’s data analysis went with it. Fitted models, diagnostic plots, the probability contours, the figures I had been building slides around — all of it.
Launching the Probaverse packages last December has for sure streamlined my workflow around distributions. But one critical thing was missing: native support for discrete distributions more generally.
One great thing about moving into an academic position has been the space that’s available for finishing up half-baked initiatives.
I’m excited to launch this new project website as we begin the research project, “Deciphering Compound Rain-on-Snow Flood Pathways as Observed from Satellites.” This project, supported by the European Space Agency’s Open Space Innovation Platform and the Politecnico di Milano, aims to enhance our understanding of compound climate events by advancing the analysis of satellite data.