Integrating image filters and confidence thresholds to improve cropland data layer for deep learning–based cropland segmentation

Accurate cropland segmentation is essential for agricultural monitoring, with deep learning (DL) models relying heavily on training data quality. The USDA’s Cropland Data Layer (CDL) is widely used for this purpose, but it includes classification errors and noise. Although a confidence layer is prov...

Descrición completa

Detalles Bibliográficos

Principais autores:	Reza Maleki, Falin Wu, Guoxin Qu, Yushuang Liu, Amel Oubara, Gongliu Yang
Formato:	Artigo
Idioma:	Inglês
Publicado:	Taylor & Francis Group 2026-12-01
Series:	European Journal of Remote Sensing
Assuntos:	Cropland Data Layer (CDL) confidence layer image filter deep learning Sentinel–2 agricultural monitoring
Acceso en liña:	https://www.tandfonline.com/doi/10.1080/22797254.2026.2631928
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!