# An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks

arXiv: https://arxiv.org/abs/2504.06915 · HTML: https://mlsanity.com/paper/2504.06915/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 51 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [SAITS: Self-Attention-based Imputation for Time Series](https://mlsanity.com/paper/2202.08516/) (2022)
- [Lightweight, Pre-trained Transformers for Remote Sensing Timeseries](https://mlsanity.com/paper/2304.14065/) (2023)
- [DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks](https://mlsanity.com/paper/1906.04569/) (2019)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series](https://mlsanity.com/paper/2112.07558/) (2021)
- [EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task](https://mlsanity.com/paper/2104.10066/) (2021)
- [UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series](https://mlsanity.com/paper/2304.05464/) (2023)
- [I Find Your Lack of Uncertainty in Computer Vision Disturbing](https://mlsanity.com/paper/2104.08188/) (2021)
- [Deep Learning for Satellite Image Time Series Analysis: A Review](https://mlsanity.com/paper/2404.03936/) (2024)
- [Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations](https://mlsanity.com/paper/2012.02542/) (2020)
- [Spatial-temporal Multi-Task Learning for Within-field Cotton Yield Prediction](https://mlsanity.com/paper/1811.06665/) (2018)
- [Predicting Crop Yield With Machine Learning: An Extensive Analysis Of Input Modalities And Models On a Field and sub-field Level](https://mlsanity.com/paper/2308.08948/) (2023)
- [Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation](https://mlsanity.com/paper/2407.15512/) (2024)
- [Unified Uncertainties: Combining Input, Data and Model Uncertainty into a Single Formulation](https://mlsanity.com/paper/2406.18787/) (2024)
- [MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction](https://mlsanity.com/paper/2106.16009/) (2021)

## Built on by (most cited first, 2 of 2)

- [YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction](https://mlsanity.com/paper/2604.00940/) (2026)
- [Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images](https://mlsanity.com/paper/2603.14074/) (2026)

## Abstract (arXiv)

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 performance and uncertainty calibration compared to existing approaches. Additionally, we highlight the advantages of adaptive dropout tuning over manual selection, making uncertainty quantification more robust and accessible for EO applications.