# Uncertainty estimation via ensembles of deep learning models and dropout layers for seismic traces

arXiv: https://arxiv.org/abs/2410.06120 · HTML: https://mlsanity.com/paper/2410.06120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 4 of 4)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Label Noise Types and Their Effects on Deep Learning](https://mlsanity.com/paper/2003.10471/) (2020)

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

- [Perspective Transition of Large Language Models for Solving Subjective Tasks](https://mlsanity.com/paper/2501.09265/) (2025)
- [HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model](https://mlsanity.com/paper/2510.05054/) (2025)

## Abstract (arXiv)

Deep learning models have demonstrated remarkable success in various fields, including seismology. However, one major challenge in deep learning is the presence of mislabeled examples. Additionally, accurately estimating model uncertainty is another challenge in machine learning. In this study, we develop Convolutional Neural Networks (CNNs) to classify seismic waveforms based on first-motion polarity. We trained multiple CNN models with different settings. We also constructed ensembles of networks to estimate uncertainty. The results showed that each training setting achieved satisfactory performances, with the ensemble method outperforming individual networks in uncertainty estimation. We observe that the uncertainty estimation ability of the ensembles of networks can be enhanced using dropout layers. In addition, comparisons among different training settings revealed that the use of dropout improved the robustness of networks to mislabeled examples.