Training strategy over architecture: A systematic ablation study for Spartina detection from aerial imagery with small geospatial datasets

Adrien Le Guillou, Manon Brehier, Jérôme Ammann, Xavier Dauvergne and Pierre Stéphan

PLOS ONE, 2026, vol. 21, issue 9, 1-33

Abstract: In operational coastal monitoring of spatially fragmented intertidal habitats, labelled datasets are structurally constrained by the limited spatial extent of target species, yet the relative influence of training strategy versus architecture on segmentation performance remains poorly characterised. We present a systematic ablation study disentangling these contributions for automated detection of the invasive cordgrass Spartina from very high resolution aerial imagery. Three segmentation architectures, U-Net, DeepLabV3 + , and SegFormer-B2, were trained under twelve configurations spanning four training-strategy axes, each evaluated by five-fold cross-validation on 810 patches derived from aerial colour-infrared imagery and elevation data, yielding 180 training runs. Training strategy dominates architectural design: the gap between the best and worst strategy (~10 pts of overlap accuracy) exceeds the inter-architecture spread (

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0358464 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 58464&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0358464

DOI: 10.1371/journal.pone.0358464

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().