Southern Ocean CO2 Machine Learning data products (SOCOML) from 1972-11-20 to 2025-02-23 (NCEI Accession 0309237)

This dataset consists of a comprehensive, quality-controlled reconstruction of key carbonate system parameters in the Southern Ocean interior—including total alkalinity (TA), dissolved inorganic carbon (DIC), pH (total scale), nitrate (NO3), phosphate (PO4), silicate (SiO4), anthropogenic carbon (Cₐₙₜ), and aragonite saturation (Ωₐᵣ)—by leveraging machine learning techniques (ESPER_NN) and integrating all available Argo float profiles with ship-based survey data. The resulting datasets are gridded at 1°×1° horizontal resolution and 84 vertical pressure levels (0-5,600 dbar), and are provided as distinct climatological products: the Float Grid (using all Argo float profiles) and the All-Data Grid (integrating all available Argo and ship-based observations). The Float Grid is further separated into the Non-O₂-Float Grid (limited to Core Argo floats) and O₂-Float Grid (limited to oxygen-measured Biogeochemical Argo floats). Each gridded product is accompanied by uncertainty estimates. The climatological products covers nearly the whole Southern Ocean based on direct measurements instead of applying interpolating mapping methods, thereby providing a more robust result. Model performance is assessed through cross-comparison of Argo and shipboard measurements.

本数据集通过机器学习技术（ESPER_NN）整合所有可用的Argo浮标剖面与船基调查数据，对南大洋内部关键碳酸盐体系参数开展了系统性、经质量管控的重构工作，涵盖总碱度（total alkalinity, TA）、溶解无机碳（dissolved inorganic carbon, DIC）、总尺度pH（pH (total scale)）、硝酸盐（NO3）、磷酸盐（PO4）、硅酸盐（SiO4）、人为碳（anthropogenic carbon, Cₐₙₜ）以及文石饱和度（aragonite saturation, Ωₐᵣ）。生成的数据集以1°×1°的水平分辨率与84个垂直压力层级（0~5600分巴）进行网格化处理，并以两类独立的气候态产品形式提供：浮标网格（Float Grid，仅使用全部Argo浮标剖面）与全数据网格（All-Data Grid，整合所有可用Argo浮标与船基观测数据）。其中浮标网格进一步细分为无氧气浮标网格（Non-O₂-Float Grid，仅限核心Argo浮标）与含氧浮标网格（O₂-Float Grid，仅限搭载氧气传感器的生物地球化学Argo浮标）。每一款网格化产品均附带不确定性估算结果。本气候态产品基于直接测量数据，覆盖范围几乎遍及整个南大洋，且未采用插值制图方法，因此结果更具鲁棒性。模型性能通过Argo浮标与船测数据的交叉比对进行评估。