Combining Passive Microwave and Optical Data to Estimate Snow Water Equivalent in Afghanistan’s Hindu Kush

Abstract:

The task is to estimate spatiotemporally distributed estimates of snow water equivalent (SWE) in snow-dominated mountain environments, including those that lack on-the-ground measurements such as the Hindu Kush range in Afghanistan. During the snow season, we can use two measurements: (1) passive microwave estimates of SWE, which generally underestimate in the mountains; (2) fractional snow-covered area from MODIS. Once the snow has melted, we can reconstruct the accumulated SWE back to the last significant snowfall by calculating the energy used in melt. The reconstructed SWE values provide a training set for predictions from the passive microwave SWE and snow-covered area. We examine several machine learning methods—regression-boosted decision trees, bagged trees, neural networks, and genetic programming—to estimate SWE. All methods work reasonably well, with R² values greater than 0.8. Predictors built with multiple years of data reduce the bias that usually appears if we predict one year from just one other year’s training set. Genetic programming tends to produce results that additionally provide physical insight. Adding precipitation estimates from the Global Precipitation Measurements mission is in progress.