EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Crop Classification Using U-Net Integrated with Multimodal Remote Sensing Temporal Features

Zhihui Zhu, Yuling Chen, Chengzhuo Lu, Minglong Yang, Yonghua Xia, Dewu Huang, Jie Lv iD

Sensors · 13.08.2025 · 25 (16) · 5005

DOI: 10.3390/s25165005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.08.2025. Verfasst von Zhihui Zhu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Earth Science and Technology, City College, Kunming University of Science and Technology, Kunming 650093, China. Hauptthemen laut MEDLINE: Remote Sensing Technology, Crops, Agricultural. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Major Project on Deep Earth Exploration: Topic 3 - Prospecting Model and Integrated Exploration Technology for Post-Collisional…, Ministry of Education Industry-University Cooperative Education Program of China, National Science and Technology Major Project for Deep Underground Exploration of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Crop classification plays a vital role in acquiring the spatial distribution of agricultural crops, enhancing agricultural management efficiency, and ensuring food security. With the continuous advancement of remote sensing technologies, achieving efficient and accurate crop classification using remote sensing imagery has become a prominent research focus. Conventional approaches largely rely on empirical rules or single-feature selection (e.g., NDVI or VV) for temporal feature extraction, lacking systematic optimization of multimodal feature combinations from optical and radar data. To address this limitation, this study proposes a crop classification method based on feature-level fusion of multimodal remote sensing data, integrating the complementary advantages of optical and SAR imagery to overcome the temporal and spatial representation constraints of single-sensor observations. The study was conducted in Story County, Iowa, USA, focusing on the growth cycles of corn and soybean. Eight vegetation indices (including NDVI and NDRE) and five polarimetric features (VV and VH) were constructed and analyzed. Using a random forest algorithm to assess feature importance, NDVI+NDRE and VV+VH were identified as the optimal feature combinations. Subsequently, 16 scenes of optical imagery (Sentinel-2) and 30 scenes of radar imagery (Sentinel-1) were fused at the feature level to generate a multimodal temporal feature image with 46 channels. Using Cropland Data Layer (CDL) samples as reference data, a U-Net deep neural network was employed for refined crop classification and compared with single-modal results. Experimental results demonstrated that the fusion model outperforms single-modal approaches in classification accuracy, boundary delineation, and consistency, achieving training, validation, and test accuracies of 95.83%, 91.99%, and 90.81% respectively. Furthermore, consistent improvements were observed across evaluation metrics, including F1-score, precision, and recall.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Remote Sensing TechnologyCrops, AgriculturalAlgorithmsAgricultureNeural Networks, ComputerGlycine maxRadar

Stichwörter der Autor:innen

Sentinel-1Sentinel-2U-Netcrop classificationmultimodal remote sensingrandom foresttemporal feature fusion

Autor:innen und Institutionen

  • Department of Earth Science and Technology, City College, Kunming University of Science and Technology, Kunming 650093, China.
  • School of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430078, China.
  • School of Land and Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China.

ORCID-Profile: Jie Lv

Förderung

  • National Science and Technology Major Project on Deep Earth Exploration: Topic 3 - Prospecting Model and Integrated Exploration Technology for Post-Collisional…
  • Ministry of Education Industry-University Cooperative Education Program of China
  • National Science and Technology Major Project for Deep Underground Exploration of China

Zitieren

APA

Zhu, Z., Chen, Y., Lu, C., Yang, M., Xia, Y., Huang, D., & Lv, J. (2025). Research on Crop Classification Using U-Net Integrated with Multimodal Remote Sensing Temporal Features. Sensors, 25(16), 5005. https://doi.org/10.3390/s25165005

Vancouver

Zhu Z, Chen Y, Lu C, Yang M, Xia Y, Huang D, et al. Research on Crop Classification Using U-Net Integrated with Multimodal Remote Sensing Temporal Features. Sensors. 2025;25(16):5005. doi:10.3390/s25165005

BibTeX
@article{Zhu2025,
  author = {Zhu, Zhihui and Chen, Yuling and Lu, Chengzhuo and Yang, Minglong and Xia, Yonghua and Huang, Dewu and Lv, Jie},
  title = {Research on Crop Classification Using U-Net Integrated with Multimodal Remote Sensing Temporal Features},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5005},
  doi = {10.3390/s25165005}
}
Kostenlos starten →