EUVIMEDEUVIMED entdecken
Crossref

LACC: A lightweight attention-conditional convolution network for long-term Wetland classification

Lirong Yin, Lei Wang, Ali Behrangi, Guo-Yue Niu, Siyu Lu, Wenfeng Zheng

Environmental Research · 2026-08 · 302 · 124613

DOI: 10.1016/j.envres.2026.124613 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research, 2026-08. Verfasst von Lirong Yin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Hydrology and Atmospheric Sciences, University of Arizona, Tucson, AZ 85721, USA. Electronic address: lirongy@arizona.edu. Hauptthemen laut MEDLINE: Wetlands, Environmental Monitoring. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wetlands are critical in keeping ecological balance and supporting biodiversity. However, wetland degradation has become more severe. It is crucial to understand the ecological and biological conditions within them to address these threats. Recent advances in artificial intelligence give new tools for wetland monitoring. The study uses Landsat because it is well-suited for long-term and regional-scale analysis for its resolution and continuous data. A novel framework-the Lightweight Attention-Conditional Convolution (LACC) network-is introduced to efficiently process extended time series. By combining lightweight attention with conditional convolution, LACC is designed to better capture temporal variability and complex class patterns while remaining computationally efficient for large-area applications. Using the new model, we generated a 20-year wetland land-cover dataset for the whole state of Louisiana, providing valuable insights into the wetland conditions. The time series could be used to link class transitions and vegetation conditions to changes in biomass/soil carbon stocks, as well as methane-emission proxies, thereby strengthening regional GHG inventories and connecting wetland monitoring to carbon accounting and urban resilience planning across coastal Louisiana.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WetlandsEnvironmental MonitoringLouisiana

Stichwörter der Autor:innen

Attention mechanismConditional convolution networkLACCLightweight attention-conditional convolutionLong-term wetland classificationLouisiana

Autor:innen und Institutionen

  • Hydrology and Atmospheric Sciences, University of Arizona, Tucson, AZ 85721, USA. Electronic address: lirongy@arizona.edu.
  • Department of Geography & Anthropology, Louisiana State University, Baton Rouge, LA 70803, USA.
  • Hydrology and Atmospheric Sciences, University of Arizona, Tucson, AZ 85721, USA.
  • Department of Geography, Texas A&M University, College Station, TX 77843, USA.
  • School of Automation, University of Electronic Science and Technology of China, Chengdu, 611731, China.

Zitieren

APA

Yin, L., Wang, L., Behrangi, A., Niu, G. Y., Lu, S., & Zheng, W. (2026). LACC: A lightweight attention-conditional convolution network for long-term Wetland classification. Environmental Research, 302, 124613. https://doi.org/10.1016/j.envres.2026.124613

Vancouver

Yin L, Wang L, Behrangi A, Niu GY, Lu S, Zheng W. LACC: A lightweight attention-conditional convolution network for long-term Wetland classification. Environmental Research. 2026;302:124613. doi:10.1016/j.envres.2026.124613

BibTeX
@article{Yin2026,
  author = {Yin, Lirong and Wang, Lei and Behrangi, Ali and Niu, Guo-Yue and Lu, Siyu and Zheng, Wenfeng},
  title = {LACC: A lightweight attention-conditional convolution network for long-term Wetland classification},
  journal = {Environmental Research},
  year = {2026},
  volume = {302},
  pages = {124613},
  doi = {10.1016/j.envres.2026.124613}
}
Kostenlos starten →