A Physically Driven Long Short Term Memory Model for Estimating Snow Water Equivalent over the Continental United States
This work addresses the need for efficient and scalable SWE estimation for land surface modeling, offering a data-driven alternative to computationally expensive reanalysis products and sparse in situ measurements.
The paper tackles the problem of estimating snow water equivalent (SWE) over the continental United States by developing a Long Short-Term Memory (LSTM) model that uses physical and meteorological inputs, achieving a classification accuracy of ≥93% for snow presence and a correlation coefficient of ~0.9 for SWE estimates.
Snow is an essential input for various land surface models. Seasonal snow estimates are available as snow water equivalent (SWE) from process-based reanalysis products or locally from in situ measurements. While the reanalysis products are computationally expensive and available at only fixed spatial and temporal resolutions, the in situ measurements are highly localized and sparse. To address these issues and enable the analysis of the effect of a large suite of physical, morphological, and geological conditions on the presence and amount of snow, we build a Long Short-Term Memory (LSTM) network, which is able to estimate the SWE based on time series input of the various physical/meteorological factors as well static spatial/morphological factors. Specifically, this model breaks down the SWE estimation into two separate tasks: (i) a classification task that indicates the presence/absence of snow on a specific day and (ii) a regression task that indicates the height of the SWE on a specific day in the case of snow presence. The model is trained using physical/in situ SWE measurements from the SNOw TELemetry (SNOTEL) snow pillows in the western United States. We will show that trained LSTM models have a classification accuracy of $\geq 93\%$ for the presence of snow and a coefficient of correlation of $\sim 0.9$ concerning their SWE estimates. We will also demonstrate that the models can generalize both spatially and temporally to previously unseen data.