EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparing UNet configurations for anthropogenic geomorphic feature extraction from land surface parameters

Sarah Farhadpour, Aaron E Maxwell iD

PLOS One · 10.06.2025 · 20 (6) · e0325904

DOI: 10.1371/journal.pone.0325904 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 10.06.2025. Verfasst von Sarah Farhadpour und 1 weiteren Autor:innen. Beteiligte Einrichtung: West Virginia University Department of Geology and Geography, Morgantown, West Virginia, United States of America. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The application of deep learning for semantic segmentation has revolutionized image analysis, particularly in the geospatial and medical fields. UNet, an encoder-decoder architecture, has been suggested to be particularly effective. However, limitations such as small sample sizes and class imbalance in anthropogenic geomorphic feature extraction tasks have necessitated the exploration of advanced modifications to improve model performance. This study investigates a variety of architectural modifications to base UNet including replacing the rectified linear unit (ReLU) activation function with leaky ReLU or swish; incorporating residual connections within the encoder blocks, decoder blocks, and bottleneck; inserting squeeze and excitation modules into the encoder or attention gate modules along the skip connections; replacing the default bottleneck layer with one that incorporates dilated convolution; and using a MobileNetV2 architecture as an encoder backbone. Unique geomorphic datasets derived from high spatial resolution lidar data were used to evaluate the performance of these modified UNet architectures on the tasks of mapping agricultural terraces, mine benches, and valley fill faces. The results were further analyzed across varying training sample sizes (50, 100, 250, 500, and the full training set). Our results suggest that the incorporation of advanced modules can enhance segmentation performance, particularly in scenarios involving limited training data or complex geomorphic landscapes. However, differences were minimal when larger training set sizes were used (e.g., above 500 image chips) and the base UNet architecture was generally adequate. This research contributes valuable insights into the optimization of UNet-based models for anthropogenic geomorphic feature extraction and provides a foundation for future work aimed at improving the accuracy and efficiency of deep learning approaches in geospatial applications. We argue that one of the positive attributes of UNet is that it can be treated as a general framework that can easily be modified.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningImage Processing, Computer-AssistedHumansAlgorithms

Autor:innen und Institutionen

  • West Virginia University Department of Geology and Geography, Morgantown, West Virginia, United States of America.

ORCID-Profile: Aaron E Maxwell

Förderung

  • National Science Foundation

Zitieren

APA

Farhadpour, S., & Maxwell, A. E. (2025). Comparing UNet configurations for anthropogenic geomorphic feature extraction from land surface parameters. PLOS One, 20(6), e0325904. https://doi.org/10.1371/journal.pone.0325904

Vancouver

Farhadpour S, Maxwell AE. Comparing UNet configurations for anthropogenic geomorphic feature extraction from land surface parameters. PLOS One. 2025;20(6):e0325904. doi:10.1371/journal.pone.0325904

BibTeX
@article{Farhadpour2025,
  author = {Farhadpour, Sarah and Maxwell, Aaron E},
  title = {Comparing UNet configurations for anthropogenic geomorphic feature extraction from land surface parameters},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {e0325904},
  doi = {10.1371/journal.pone.0325904}
}
Kostenlos starten →