Towards Climate Variable Prediction with Conditioned Spatio-Temporal Normalizing Flows
This addresses climate modeling for scientists, but it appears incremental as it applies an existing method to a new domain.
The study tackled climate variable prediction by applying conditioned spatio-temporal normalizing flows to remote sensing data, achieving stable extrapolation beyond training horizons and surpassing deterministic and stochastic baselines in prolonged rollout scenarios.
This study investigates how conditional normalizing flows can be applied to remote sensing data products in climate science for spatio-temporal prediction. The method is chosen due to its desired properties such as exact likelihood computation, predictive uncertainty estimation and efficient inference and sampling which facilitates faster exploration of climate scenarios. Experimental findings reveal that the conditioned spatio-temporal flow surpasses both deterministic and stochastic baselines in prolonged rollout scenarios. It exhibits stable extrapolation beyond the training time horizon for extended rollout durations. These findings contribute valuable insights to the field of spatio-temporal modeling, with potential applications spanning diverse scientific disciplines.