The goal of this study is to gain further insight into the mechanisms of cloud seeding and develop machine learning algorithms as a powerful predictive tool to better quantify the effects of cloud seeding. This research employs the Snow Growth Model for Rimed snowfall (SGMR) that predicts the vertical evolution of ice particle size spectra based on the relative humidity or supersaturation. The model is formulated in terms of analytically interrelated procedures involving ice crystal nucleation, vapor deposition, aggregation, and cloud updrafts and it thereby estimates snowfall rate. The model provides an accurate description of the microphysical processes with reduced computation time.
We aim to conduct various model experiments initialized with different meteorological conditions under seeding vs. non-seeding scenarios. We will use an ensemble of in-situ and satellite remotely sensed observations to develop an ML-based model in order to further investigate changes in snowfall due to cloud seeding.

