Comment
Author: Admin | 2025-04-27
Employed in offline physics analyses of LArTPC data. MicroBooNE is leading the development and application of DL techniques, including CNNs, for LArTPC data reconstruction (Acciarri et al., 2017a; Adams et al., 2019; Abratenko et al., 2021a,b), and CNN-based analyses and DL-based reconstruction are actively being developed for SBN and for DUNE (Acciarri et al., 2012; Abi et al., 2020e).In a previous study (Jwa et al., 2019), we have also shown that sufficiently high efficiencies can be reached by processing raw collection plane data from any given DUNE FD cell, prior to removing any detector effects or applying data reconstruction. As such, we proposed a CNN-based triggering scheme using streaming raw 2D image frames, whereby the images are pre-processed, downsized, and run through CNN inference to select ones containing SNB neutrino interactions or other rare interactions of interest on a frame-by-frame basis. The data pre-processing and CNN-based selection method demonstrated that target signal selection efficiency while reaching the needed 104 background rejection could be achieved, given sufficient parallelization in GPUs. As the DUNE FD DAQ and trigger design is subject to stringent power limitations and limited accessibility in the underground detector cavern, a particularly attractive option is to fully implement this pre-processing and CNN-based inference on FPGAs, in particular ones that will be part of the DUNE upstream DAQ readout unit design. We examine the viability of this option in this work.Specifically, we explore the accuracy of relatively small CNNs in classifying streaming DUNE FD LArTPC cell data, and proceed to employ network optimization in an effort to reduce its computational resource footprint while preserving network accuracy. The following subsections describe the CNN input image preparation (Section 3.1), CNN performance without (Section 3.2) and with (Section 3.3) network optimization, and with quantization-aware training (Section 3.4).3.1. Input Image Pre-processingBecause of the parallelism in the DUNE FD DAQ and trigger design, we only consider a single cell's worth of data at a time, and focus exclusively on raw collection plane waveforms. Following (Jwa et al., 2019), collection plane waveforms for a single cell in the DUNE FD are simulated in the LArSoft framework2 (Church, 2013), using the default configuration of the dunetpc software, and using an enhanced electronics noise level configuration, to be conservative. Besides electronics noise, the simulation includes radiological impurity background interactions that are intrinsic to the liquid argon volume. The radiological background interactions (predominantly from 39Ar decay) are expected to
Add Comment