SPARKESX: Single-dish PARKES data sets for finding the uneXpected - Part 2

We present the Single-dish PARKES data sets for finding the uneXpected (SPARKESX), a compilation of real and simulated high-time resolution observations. SPARKESX comprises three mock surveys from the Parkes ''Murriyang'' radio telescope. A broad selection of simulated and injected expected signals (such as pulsars, fast radio bursts), poorly known signals (such as the features expected from flare stars) and unknown unknowns are generated for each survey. We provide a baseline by presenting how successful a typical pipeline based on the standard pulsar search software, PRESTO, is at finding the injected signals.\n\nThe dataset is designed to aid in the development of new search algorithms, including image processing, machine learning, and deep learning. The raw data, ground truth labels, and baseline are provided.\n\nThe collection is split into 4 parts. See collections in related links.\nPart 1 - Ground truth labels, injected images, multibeam dataset\nPart 2 - PAF dataset\nPart 3 - PAF dataset\nPart 4 - PAF dataset\n\nPublication: SPARKESX: Single-dish PARKES data sets for finding the uneXpected - A data challenge (Yong et a. 2022, submitted)\nLineage: The injected signals and simulated data were created using CSIRO's open source simulateSearch software.\nThe real data from the multibeam survey were acquired from the CSIRO Data Access Portal.

本研究介绍了用于发现意外信号的单碟帕克斯数据集（Single-dish PARKES data sets for finding the uneXpected，缩写SPARKESX），该数据集汇集了真实与模拟的高时间分辨率观测数据。SPARKESX包含来自帕克斯“穆里扬”（Murriyang）射电望远镜的三次模拟巡天。针对每次巡天，我们生成了多类模拟与注入的预期信号（如脉冲星、快速射电暴）、认知有限的信号（如耀星预期产生的特征）以及完全未知的信号。本研究通过展示基于标准脉冲星搜索软件PRESTO的典型处理流程在识别注入信号方面的表现，提供了基准性能指标。

本数据集旨在助力新型搜索算法的研发，涵盖图像处理、机器学习与深度学习方向。数据集包含原始数据、真值标签以及基准性能指标。

本数据集共分为4个部分，相关链接中可查看各分卷详情：
1. 第一部分：真值标签、注入图像与多波束数据集
2. 第二部分：PAF数据集
3. 第三部分：PAF数据集
4. 第四部分：PAF数据集

发表信息：《SPARKESX：用于发现意外信号的单碟帕克斯数据集——一项数据挑战赛》（Yong等，2022，已投稿）

数据溯源：注入信号与模拟数据均通过CSIRO开源的simulateSearch软件生成。

本次多波束巡天的真实数据源自CSIRO数据访问门户（CSIRO Data Access Portal）。