An ocean front detection and tracking algorithm
Yishuo Wang, Feng Zhou, Qicheng Meng, Muping Zhou, Zhijun Hu, Chengqing Zhang, Tianhao Zhao
TL;DR
This work tackles the challenge of robust ocean front detection and tracking by reframing fronts as probabilistic regions and integrating gradient information with physics-guided operators. The BFDT-MSA framework combines a Bayesian decision mechanism, morphological refinement (including skeletonization and ring deletion), and a metric-space definition of temporal front distance to achieve continuous, coherent fronts and reliable tracking. Key contributions include the Bayesian fusion of gradient priors and field operators, morphology-driven coherence enforcement, and the first formalization of front tracking in metric space, all released as open-source. Quantitative results on global SST data (2022–2024) show substantially reduced over-detection, sharper intensity, and more realistic front dimensions compared to baseline methods, with strong implications for climate modeling and marine resource management.
Abstract
Existing ocean front detection methods--including histogram-based variance analysis, Lyapunov exponent, gradient thresholding, and machine learning--suffer from critical limitations: discontinuous outputs, over-detection, reliance on single-threshold decisions, and lack of open-source implementations. To address these challenges, this paper proposes the Bayesian Front Detection and Tracking framework with Metric Space Analysis (BFDT-MSA). The framework introduces three innovations: (1) a Bayesian decision mechanism that integrates gradient priors and field operators to eliminate manual threshold sensitivity; (2) morphological refinement algorithms for merging fragmented fronts, deleting spurious rings, and thinning frontal zones to pixel-level accuracy; and (3) a novel metric space definition for temporal front tracking, enabling systematic analysis of front evolution. Validated on global SST data (2022--2024), BFDT-MSA reduces over-detection by $73\%$ compared to histogram-based methods while achieving superior intensity ($0.16^\circ$C/km), continuity, and spatiotemporal coherence. The open-source release bridges a critical gap in reproducible oceanographic research.