Improving mountain snow predictions in the desert southwest by using machine learning

Charles Andrew Hoopes1, Christopher C. Castro1
1Department of Hydrology and Atmospheric Sciences, University of Arizona
 

Snowfall, in the Madrean Sky Islands is a crucial process sustaining and recharging the groundwater supply of the deserts of Southeastern Arizona, but a lack of in situ observations and poor forecasting of events hinder hydrological modeling of the recharge process. Attempts at improving forecasts have been made, but skill is still poor, with snowfall routinely overpredicted. A major reason for this overprediction has been a failure to accurately predict snow-liquid ratios (SLR) ahead of major events. This research proposes, develops, and tests multiple machine learning methods for dynamic SLR prediction for the Sky Islands region in the form of a simple feed-forward neural network, a support vector machine, and a k-nearest neighbor algorithm. Input parameters were chosen based off variables found by previous studies to have a regression-based relationship with SLR, with a focus on the lower-mid levels of the troposphere. These parameters were also used to construct a multiple linear regression model, and its performance was compared with the machine learning methods. Each of the machine learning methods showed significant improvement compared to the multiple linear regression. When tested on historical events, nearly 95% of the network-predicted SLR values fell within the margin of error of observed SLRs, calculated using verification data from Broxton et al (2017), with slightly higher accuracy for both the SVM and KNN algorithms. Each showed significant gain in skill compared to the multiple linear regression model. Current and future work is focusing on shifting to higher resolution data, as well as adjusting the model to look at a wider region within the mountainous Western US in order to achieve greater operational benefit.

Go to All Abstracts | 2021 El Día Home Page