Can I read An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks on EtoBox?

An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks by Miranda, Miro; Mena, Francisco; Dengel, Andreas is a scholarly article available to read on EtoBox.

What is An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks about?

Missing instances in time series data impose a significant challenge to deep learning models, particularly in regression tasks. In the Earth Observation field, satellite failure or cloud occlusion frequently results in missing time-steps, introducing uncertainties in the predicted output and causing a decline in predictive performance. While many studies address missing time-steps through data augmentation to improve model robustness, the uncertainty arising at the input level is commonly overlooked. To address this gap, we introduce Monte Carlo Temporal Dropout (MC-TD), a method that explicitly accounts for input-level uncertainty by randomly dropping time-steps during inference using a predefined dropout ratio, thereby simulating the effect of missing data. To bypass the need for costly searches for the optimal dropout ratio, we extend this approach with Monte Carlo Concrete Temporal Dropout (MC-ConcTD), a method that learns the optimal dropout distribution directly. Both MC-TD and MC-ConcTD are applied during inference, leveraging Monte Carlo sampling for uncertainty quantification. Experiments on three EO time-series datasets demonstrate that MC-ConcTD improves predictive perfo

Author

Miranda, Miro; Mena, Francisco; Dengel, Andreas

Published

2025

Language

EN