EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Progressive Deep Learning for Accurate Winter Rapeseed Mapping in Complex Terrain: A Case Study of Hanzhong Basin, China

Fang Yin, Xinjie Yu, Yao Wang, Lei Liu

Remote Sensing · 25.05.2026 · 18 (11) · 1706

DOI: 10.3390/rs18111706 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 25.05.2026. Verfasst von Fang Yin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Development and Comprehensive Demonstration of Agricultural Remote Sensing Integrated Ap-plication Service Software, Key Research and Development Program of Shaanxi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate mapping of winter rapeseed cultivation areas is crucial for food security assessment and agricultural resource management, yet remains a persistent challenge in mountainous regions characterized by complex topography and highly fragmented field parcels. To address these challenges, this study develops a progressive deep learning framework using single growing-season data from the Hanzhong Basin. We conducted a structured comparison of remote sensing indices, machine learning, and deep learning approaches for rapeseed identification in heterogeneous landscapes. First, sensitivity analysis of the Flowering Index for Rapeseed was performed to identify the optimal parameterization, yielding high inter-class separability (ND = 0.959) during peak flowering and a threshold-based overall accuracy (OA) of 94.41%. Second, a multidimensional feature space was constructed by integrating Sentinel-2 spectral bands, image texture metrics, and topographic variables; Random Forest-based feature importance selection subsequently enhanced Support Vector Machine classification performance to an OA of 90.70%. Third, we proposed an innovative three-stage progressive UNet++ architecture: Stage1 focuses on binary rapeseed/non-rapeseed classification to establish spatial priors; Stage2 refines discrimination among spectrally similar vegetation classes (rapeseed and other vegetation); and Stage3 achieves comprehensive seven-class semantic segmentation. A weighted focal loss function combined with a weight inheritance mechanism was employed to mitigate class imbalance and facilitate inter-stage knowledge transfer. The final model attained an OA of 98.65% and a mean intersection over union of 95.29%, while effectively suppressing salt-and-pepper noise artifacts in geometrically fragmented parcels. Our findings demonstrate the substantial advantages of progressive deep learning strategies for crop monitoring in topographically constrained environments.

Förderung

  • Development and Comprehensive Demonstration of Agricultural Remote Sensing Integrated Ap-plication Service Software
  • Key Research and Development Program of Shaanxi

Zitieren

APA

Yin, F., Yu, X., Wang, Y., & Liu, L. (2026). Progressive Deep Learning for Accurate Winter Rapeseed Mapping in Complex Terrain: A Case Study of Hanzhong Basin, China. Remote Sensing, 18(11), 1706. https://doi.org/10.3390/rs18111706

Vancouver

Yin F, Yu X, Wang Y, Liu L. Progressive Deep Learning for Accurate Winter Rapeseed Mapping in Complex Terrain: A Case Study of Hanzhong Basin, China. Remote Sensing. 2026;18(11):1706. doi:10.3390/rs18111706

BibTeX
@article{Yin2026,
  author = {Yin, Fang and Yu, Xinjie and Wang, Yao and Liu, Lei},
  title = {Progressive Deep Learning for Accurate Winter Rapeseed Mapping in Complex Terrain: A Case Study of Hanzhong Basin, China},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1706},
  doi = {10.3390/rs18111706}
}
Kostenlos starten →