Abstract. Over a decade ago, oceanographers began installing oxygen sensors on Argo floats to be deployed throughout the world ocean with the express objective of better constraining trends and variability in the ocean’s inventory of oxygen. Until now, measurements from these Argo-mounted oxygen sensors have been mainly used for localized process studies on air–sea oxygen exchange, biological pump efficiency, upper ocean primary production, and oxygen minimum zone dynamics. Here we present a four-dimensional gridded product of ocean interior oxygen, derived via machine learning algorithms trained on dissolved oxygen observations from Argo-mounted sensors and discrete measurements from ship-based surveys, and applied to temperature and salinity fields constructed from the global Argo array. The data product is called GOBAI-O₂ for Gridded Ocean Biogeochemistry from Artificial Intelligence – Oxygen (Sharp et al., 2022; https://doi.org/10.25921/z72m-yz67; last access: 30 Aug. 2022); it covers 86 % of the global ocean area on a 1° latitude by 1° longitude grid, spans the years 2004–2021 with monthly resolution, and extends from the ocean surface to two kilometers in depth on 58 levels. Two machine learning algorithms — random forest regressions and feed-forward neural networks — are used in the development of GOBAI-O₂, and the performance of those algorithms is assessed using real observations and Earth system model output. GOBAI-O₂ is evaluated through comparisons to the World Ocean Atlas and to direct observations from large-scale hydrographic research cruises. Finally, potential uses for GOBAI-O₂ are demonstrated by presenting average oxygen fields on isobaric and isopycnal surfaces, average oxygen fields across vertical–meridional sections, climatological cycles of oxygen averaged over different pressure intervals, and a globally integrated oxygen inventory time series.

中文翻译：

---

GOBAI-O2：近二十年来海洋内部溶解氧的时空分辨场

摘要。十多年前，海洋学家开始在 Argo 浮标上安装氧气传感器，以便在世界海洋中部署，其明确目标是更好地限制海洋氧气库存的趋势和可变性。到目前为止，这些安装在 Argo 上的氧气传感器的测量结果主要用于气海氧气交换、生物泵效率、上层海洋初级生产和氧气最小区动力学的局部过程研究。在这里，我们展示了海洋内部氧气的四维网格产品，通过机器学习算法获得，该算法通过安装在 Argo 上的传感器的溶解氧观测和船基调查的离散测量进行训练，并应用于由全球 Argo 构建的温度和盐度场大批。数据产品名为GOBAI-O ₂来自人工智能的网格海洋生物地球化学——氧气（Sharp 等人，2022；https://doi.org/10.25921/z72m-yz67；最后访问时间：2022 年 8 月 30 日）；它在 1° 纬度乘 1° 经度的网格上覆盖了全球 86% 的海洋区域，跨越 2004-2021 年，每月分辨率，从海面延伸到 58 个层次的两公里深度。两种机器学习算法——随机森林回归和前馈神经网络——被用于 GOBAI-O ₂的开发，并且这些算法的性能通过实际观测和地球系统模型输出进行评估。GOBAI-O ₂通过与世界海洋地图集的比较和大型水文研究巡航的直接观测进行评估。最后，GOBAI-O 的潜在用途_图2通过显示等压和等密度表面的平均氧场、垂直-经向剖面的平均氧场、不同压力间隔内平均的氧气候循环以及全球综合氧库存时间序列来证明。