The Pan-STARRS1 (PS1) $3\pi$ survey is a comprehensive optical imaging survey of three quarters of the sky in the $grizy$ broad-band photometric filters. We present the methodology used in assembling the source classification and photometric redshift (photo-z) catalogue for PS1 $3\pi$ Data Release 1, titled Pan-STARRS1 Source Types and Redshifts with Machine learning (PS1-STRM). For both main data products, we use neural network architectures, trained on a compilation of public spectroscopic measurements that has been cross-matched with PS1 sources. We quantify the parameter space coverage of our training data set, and flag extrapolation using self-organizing maps. We perform a Monte-Carlo sampling of the photometry to estimate photo-z uncertainty. The final catalogue contains $2,902,054,648$ objects. On our validation data set, for non-extrapolated sources, we achieve an overall classification accuracy of $98.1\%$ for galaxies, $97.8\%$ for stars, and $96.6\%$ for quasars. Regarding the galaxy photo-z estimation, we attain an overall bias of $\left =0.0005$, a standard deviation of $\sigma(\Delta z_{\mathrm{norm}})=0.0322$, a median absolute deviation of $\mathrm{MAD}(\Delta z_{\mathrm{norm}})=0.0161$, and an outlier fraction of $O=1.89\%$. The catalogue will be made available as a high-level science product via the Mikulski Archive for Space Telescopes at this https URL.

中文翻译：

---

PS1-STRM：PS1 3π DR1 的神经网络源分类和光度红移目录

Pan-STARRS1 (PS1) $3\pi$ 调查是在 $grizy$ 宽带光度过滤器中对四分之三天空进行的综合光学成像调查。我们介绍了用于组装 PS1 $3\pi$ 数据版本 1 的源分类和光度红移 (photo-z) 目录的方法，标题为 Pan-STARRS1 Source Types and Redshifts with Machine learning (PS1-STRM)。对于这两种主要数据产品，我们使用神经网络架构，并在与 PS1 源交叉匹配的公共光谱测量汇编上进行训练。我们量化了训练数据集的参数空间覆盖率，并使用自组织映射标记外推。我们执行光度测量的蒙特卡洛采样来估计 photo-z 的不确定性。最终目录包含 2,902,054,648 美元的物品。在我们的验证数据集上，对于非外推源，我们实现了星系的 98.1\%$、恒星的 97.8\%$ 和类星体的 96.6\%$ 的总体分类准确度。关于星系 photo-z 估计，我们获得了 $\left =0.0005$ 的总体偏差，标准偏差为 $\sigma(\Delta z_{\mathrm{norm}})=0.0322$，中值绝对偏差为 $ \mathrm{MAD}(\Delta z_{\mathrm{norm}})=0.0161$，以及 $O=1.89\%$ 的异常值部分。该目录将作为高级科学产品通过此 https URL 的 Mikulski Archive for Space Telescopes 提供。$\mathrm{MAD}(\Delta z_{\mathrm{norm}})=0.0161$ 的中值绝对偏差，以及 $O=1.89\%$ 的异常值分数。该目录将作为高级科学产品通过此 https URL 的 Mikulski Archive for Space Telescopes 提供。$\mathrm{MAD}(\Delta z_{\mathrm{norm}})=0.0161$ 的中值绝对偏差，以及 $O=1.89\%$ 的异常值分数。该目录将作为高级科学产品通过此 https URL 的 Mikulski Archive for Space Telescopes 提供。