An ocean front detection and tracking algorithm

TL;DR

This paper introduces BFDT-MSA, a Bayesian framework for ocean front detection and tracking that overcomes limitations of existing methods, providing more accurate, continuous, and reproducible results validated on global SST data.

Contribution

The paper presents a novel Bayesian detection and tracking framework with morphological refinement and metric space analysis, improving accuracy and reproducibility in ocean front detection.

Findings

Reduces over-detection by 73% compared to traditional methods.

Achieves pixel-level accuracy in front delineation.

Demonstrates superior spatiotemporal coherence and intensity measurement.

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.