# Scalable Deep Convolutional Neural Networks for Sparse, Locally Dense Liquid Argon Time Projection Chamber Data

arXiv: https://arxiv.org/abs/1903.05663 · HTML: https://mlsanity.com/paper/1903.05663/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2019.

## Built on by (most cited first, 16 of 16)

- [Machine Learning in the Search for New Fundamental Physics](https://mlsanity.com/paper/2112.03769/) (2021)
- [Scalable, End-to-End, Deep-Learning-Based Data Reconstruction Chain for Particle Imaging Detectors](https://mlsanity.com/paper/2102.01033/) (2021)
- [Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning](https://mlsanity.com/paper/2209.07559/) (2022)
- [Particle Trajectory Representation Learning with Masked Point Modeling](https://mlsanity.com/paper/2502.02558/) (2025)
- [Trigger-Level Event Reconstruction for Neutrino Telescopes Using Sparse Submanifold Convolutional Neural Networks](https://mlsanity.com/paper/2303.08812/) (2023)
- [Physics Community Needs, Tools, and Resources for Machine Learning](https://mlsanity.com/paper/2203.16255/) (2022)
- [Panda: Self-distillation of Reusable Sensor-level Representations for High Energy Physics](https://mlsanity.com/paper/2512.01324/) (2025)
- [Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pre-training](https://mlsanity.com/paper/2604.07037/) (2026)
- [Automated Segmentation of Computed Tomography Images with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/2212.02854/) (2022)
- [Submanifold Sparse Convolutional Networks for Automated 3D Segmentation of Kidneys and Kidney Tumours in Computed Tomography](https://mlsanity.com/paper/2511.04334/) (2025)
- [Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics](https://mlsanity.com/paper/2609.00611/) (2026)
- [Deep Learning strategies for ProtoDUNE raw data denoising](https://mlsanity.com/paper/2103.01596/) (2021)
- [Rejecting noise in Baikal-GVD data with neural networks](https://mlsanity.com/paper/2210.04653/) (2022)
- [Enhancing Events in Neutrino Telescopes through Deep Learning-Driven Super-Resolution](https://mlsanity.com/paper/2408.08474/) (2024)
- [SparsePixels: Efficient Convolution for Sparse Data on FPGAs](https://mlsanity.com/paper/2512.06208/) (2025)
- [HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction](https://mlsanity.com/paper/2606.20437/) (2026)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) show strong promise for analyzing scientific data in many domains including particle imaging detectors such as a liquid argon time projection chamber (LArTPC). Yet the high sparsity of LArTPC data challenges traditional CNNs which were designed for dense data such as photographs. A naive application of CNNs on LArTPC data results in inefficient computations and a poor scalability to large LArTPC detectors such as the Short Baseline Neutrino Program and Deep Underground Neutrino Experiment. Recently Submanifold Sparse Convolutional Networks (SSCNs) have been proposed to address this challenge. We report their performance on a 3D semantic segmentation task on simulated LArTPC samples. In comparison with standard CNNs, we observe that the computation memory and wall-time cost for inference are reduced by factor of 364 and 33 respectively without loss of accuracy. The same factors for 2D samples are found to be 93 and 3.1 respectively. Using SSCN, we present the first machine learning-based approach to the reconstruction of Michel electrons using public 3D LArTPC samples. We find a Michel electron identification efficiency of 93.9% with 96.7% of true positive rate. Reconstructed Michel electron clusters yield 95.4% in average pixel clustering efficiency and 95.5% in purity. The results are compelling to show strong promise of scalable data reconstruction technique using deep neural networks for large scale LArTPC detectors.