Controlling Weather Field Synthesis Using Variational Autoencoders
This addresses the problem of improving weather forecast and generation algorithms for climate researchers and meteorologists, but it appears incremental as it applies an existing method to a specific domain.
The paper tackles the challenge of generating weather scenarios that account for uncertain biases due to climate change, using variational autoencoders to map climate data to a known distribution for controlling synthesis towards more extreme scenarios, reporting compelling results with efficient control.
One of the consequences of climate change is anobserved increase in the frequency of extreme cli-mate events. That poses a challenge for weatherforecast and generation algorithms, which learnfrom historical data but should embed an often un-certain bias to create correct scenarios. This paperinvestigates how mapping climate data to a knowndistribution using variational autoencoders mighthelp explore such biases and control the synthesisof weather fields towards more extreme climatescenarios. We experimented using a monsoon-affected precipitation dataset from southwest In-dia, which should give a roughly stable pattern ofrainy days and ease our investigation. We reportcompelling results showing that mapping complexweather data to a known distribution implementsan efficient control for weather field synthesis to-wards more (or less) extreme scenarios.