An improved algorithm for detecting mesoscale ocean fronts from satellite observations: Detailed mapping of persistent fronts around the China Seas and their long-term trends

Mesoscale fronts are highly energetic ocean processes that dominate local biogeochemical processes and air-sea interactions and exert significant effects on ocean dynamics, ecology, and climate. An automatic front detection algorithm applied to satellite-based observations is a fundamental approach to acquiring frontal occurrence information. Histogram-based algorithms have been widely used in previous studies, and, despite being the most popular front detection algorithm, continuous improvements have been needed to address imperfect detection issues (undetected coastal fronts, discontinuities of fronts and repeated detection of fronts). In this study, a new algorithm is proposed to address the issues by coupling inverse distance weighting and mathematical morphology operators. Using 14,610 images acquired from 1982 to 2021, a series of comparisons between the new and existing algorithms have been implemented to validate the improvements. Statistical results suggest that the number of frontal pixels detected by our algorithm increased by 58.45% in the coastal domain when compared to previous methods. Statistical analysis also shows most of these increased fronts can be supported by a classic gradient-based method which is superior in detecting coastal fronts, which demonstrates the improvement of new algorithm in detecting coastal fronts. Furthermore, visual analyses suggest that our algorithm can better connect discontinuous fronts and reduce repeated detections, and statistical comparisons in the open seas present a 34.50% improvement in the average length of frontal segments. Moreover, based on an automated objective delineation method, an analysis of 40 years of seasonal frontal occurrences (as detected by our algorithm) produced a dataset that shows a detailed map of 59 persistent fronts around the China Seas. This map updates previously hand-delineated frontal positions and identifies some previously unreported persistent fronts. Further analyses show that the frontal occurrence or intensity of a majority of persistent fronts around the China Seas presents significant (P < 0.05) long-term variability over the last 40 years. The improved algorithm, together with its application in identifying persistent fronts around the China Seas, is expected to be extended to other waters to better investigate the response of marine ecosystems to front dynamics and predict the distribution of marine organisms within a changing climate.