MHMeg Van Horn

Meg Van Horn

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Meg Van Horn has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hierarchical YOLO-SAM: A Scalable Pipeline for Automated Segmentation and Morphometric Tracking of Coral Recruits in Time-Series Microscopy

    by Richard S. Zhao, Cuixian Chen, Meg Van Horn, Nicole D. Fogarty

    Coral reef ecosystems are declining rapidly due to climate change, disease, and anthropogenic stressors, driving the expansion of land-based coral propagation for reef restoration. A major bottleneck in these efforts is the manual measurement of coral recruit tissue area from microscopy images, which requires 2–7 min per image and limits scalability. We present a hierarchical deep learning pipeline that automates this measurement by integrating YOLO-based detection with Segment Anything Model (SAM) segmentation. YOLO localizes recruits and classifies them by developmental stage; stage-specific fine-tuned SAM models then segment live tissue using bounding box and background point prompts to suppress segmentation leakage and improve boundary precision. Surface area is computed directly from the segmented masks using pixel size extracted from image metadata. The pipeline reduces processing time to approximately 3–5 s per image—a 24–140× speedup over manual tracing. Evaluated on 3668 microscopy images from two national coral research facilities, the system achieves a mean IoU exceeding 95% and an auto-acceptance rate (AAR) of 71.51%, where predicted-to-ground-truth area ratios fall within a ±5% tolerance of expert annotation, substantially reducing manual workload while maintaining measurement reliability across species, developmental stages, and imaging conditions. This workflow addresses a critical bottleneck in restoration research and demonstrates the broader applicability of AI-based image analysis in marine ecology.

  • Open Access

    Optimization of light spectra for the grow-out of Caribbean reef-building corals

    by Liam A. Abrams, Nicole D. Fogarty, Hanna R. Koch, Celia Leto, Keri L. O’nEil, Keri Martin, Tyler A. Pratt, Louis-Pierre Rich, Samantha F. Tanguay, Meg Van Horn, et al.

    The land-based sexual propagation of reef-building corals for restoration remains to be fully optimized, particularly the grow-out phase. This study attempted to optimize the post-settlement survival and growth (up to 7 months old) of the Caribbean reef building corals Colpophyllia natans, Pseudodiploria strigosa and Montastraea cavernosa under three light spectra: (1) near-surface sunlight, typical in outdoor grow-out tanks; (2) reef-mimic (using Radion lights to replicate wavelengths at 10m depth); (3) blue-shifted (using Radion lights peaking between 400-450 nm). The study was conducted concurrently at four ex situ nurseries using the same larval cohorts. All treatments started at 25 µmol photons m-2s-1 and experienced equal gradual increases until reaching 200 µmol photons m-2s-1 on day 133. The light spectra tested yielded comparable survival, but artificial lighting promoted higher growth than the near-surface sunlight spectrum. There were species-specific differences in optimal light spectrum: C. natans grew up to two times larger under the reef-mimic spectrum, M. cavernosa grew up to five times larger under the blue-shifted spectrum, and P. strigosa performed equally well under both the blue-shifted and reef-mimic spectra, being up to 0.3-0.4 times larger than the ones reared under the near-surface light spectrum. For all species, corals reared under the near-surface spectrum had a slight delay of pigmentation. The majority of corals sampled at the end of the experiment were dominated by algal symbionts of the genus Durusdinium. This study suggests that the optimal light spectrum is species-specific and can be manipulated to maximize growth.