Learn conformal prediction techniques specifically applied to time series data in this 29-minute conference talk from the Computational Genomics Summer Institute. Explore advanced methodologies for creating prediction intervals and uncertainty quantification in temporal data, with particular focus on the JANET (Joint Adaptive predictioN-region Estimation for time-series) framework and JAPAN (Joint Adaptive Prediction Areas with Normalising-Flows) approaches. Discover how these novel methods address the unique challenges of time series forecasting by providing statistically valid prediction regions that adapt to the temporal structure of data. Gain insights into the theoretical foundations and practical applications of conformal prediction in sequential data analysis, including how normalizing flows can enhance adaptive prediction areas for improved uncertainty estimation in time-dependent scenarios.