Global Monthly Ocean Dissolved Oxygen (1960–2023) Reconstructed to 5,902 m with BLENDR, a Bayesian-Optimized Ensemble Learning Framework

Abstract. Oceanic oxygen levels, crucial for marine ecosystems and biogeochemical cycles, have declined significantly over the past few decades due to climate change, posing severe environmental risks. However, historical dissolved oxygen (DO) measurements, especially below 2,000 m, remain sparse, limiting comprehensive annual and seasonal analyses. Here, we introduce the BLENDR framework (Bayesian-optimized Learning and ENsemble modeling for Data Reconstruction), a Bayesian-optimized ensemble of six machine-learning models (Random Forest, XGBoost, LightGBM, CatBoost, Extremely Randomized Trees and Histogram-based Gradient Boosting) fused via dynamic weighting, to reconstruct global monthly DO distributions at a 1° × 1° resolution from the surface to 5,902 m from 1960 to 2023. Validation against an independent dataset demonstrated that BLENDR achieves lower errors than any individual model. Our dataset captures depth-dependent deoxygenation, with the most pronounced decline occurring between 150 and 200 m, and reveals severely accelerated oxygen loss in the Arctic Ocean and North Atlantic over the past decade. This work provides the first long-term, global monthly DO product from the ocean surface to 5,902 m. The bathypelagic DO data provided in this work is a significant contribution to deep ocean oxygen dynamics and global biogeochemical cycles.