SE-ResUNet Using Feature Combinations: A Deep Learning Framework for Accurate Mountainous Cropland Extraction Using Multi-Source Remote Sensing Data

Ling Xiao, Jiasheng Wang (), Kun Yang, Hui Zhou, Qianwen Meng, Yue He and Siyi Shen
Additional contact information
Ling Xiao: Faculty of Geography, Yunnan Normal University, Kunming 650500, China
Jiasheng Wang: Faculty of Geography, Yunnan Normal University, Kunming 650500, China
Kun Yang: Faculty of Geography, Yunnan Normal University, Kunming 650500, China
Hui Zhou: Faculty of Geography, Yunnan Normal University, Kunming 650500, China
Qianwen Meng: Faculty of Geography, Yunnan Normal University, Kunming 650500, China
Yue He: Faculty of Geography, Yunnan Normal University, Kunming 650500, China
Siyi Shen: Faculty of Geography, Yunnan Normal University, Kunming 650500, China

Land, 2025, vol. 14, issue 5, 1-23

Abstract: The accurate extraction of mountainous cropland from remote sensing images remains challenging due to its fragmented plots, irregular shapes, and the terrain-induced shadows. To address this, we propose a deep learning framework, SE-ResUNet, that integrates Squeeze-and-Excitation (SE) modules into ResUNet to enhance feature representation. Leveraging Sentinel-1/2 imagery and DEM data, we fuse vegetation indices (NDVI/EVI), terrain features (Slope/TRI), and SAR polarization characteristics into 3-channel inputs, optimizing the network’s discriminative capacity. Comparative experiments on network architectures, feature combinations, and terrain conditions demonstrated the superiority of our approach. The results showed the following: (1) feature fusion (NDVI + TerrainIndex + SAR) had the best performance (OA: 97.11%; F1-score: 96.41%; IoU: 93.06%), significantly reducing shadow/cloud interference. (2) SE-ResUNet outperformed ResUNet by 3.53% for OA and 8.09% for IoU, emphasizing its ability to recalibrate channel-wise features and refine edge details. (3) The model exhibited robustness across diverse slopes/aspects (OA > 93.5%), mitigating terrain-induced misclassifications. This study provides a scalable solution for mountainous cropland mapping, supporting precision agriculture and sustainable land management.

Keywords: feature combination; SE module; ResUNet network; mountain cropland; remote sensing (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/14/5/937/pdf (application/pdf)
https://www.mdpi.com/2073-445X/14/5/937/ (text/html)

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:gam:jlands:v:14:y:2025:i:5:p:937-:d:1642552

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().