Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 49 min ago
Peer-reviewedCC BY-NC-ND 4.0Scientific Data

A 10-m National Agricultural Parcel Dataset of Ukraine Generated with an Enhanced Multi-Task Network and Sentinel-2 Imagery

  • Junbin Li1,2
  • Hongwei Zeng1,2
  • Hang Zhao1,2,3
  • Miao Zhang1,2
  • Yang Chen4
  • Qiangyi Yu5,6
  • Wenbin Wu5,6
  • Yuanwei Qin7
  • Bingfang Wu1,2
  • Shaohua Wang1,2
7 affiliations
  1. 1State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, 100101 China
  2. 2University of Chinese Academy of Sciences, Beijing, 100049 China
  3. 3Science and Technology Research Institute, China Three Gorges Corporation, Beijing, China
  4. 4Beidou Research Institute, Faculty of Engineering, South China Normal University, Foshan, China
  5. 5State Key Laboratory of Efficient Utilization of Arid and Semi-arid Arable Land in Northern China, Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, 100081 China
  6. 6Key Laboratory of Agricultural Remote Sensing, Ministry of Agriculture and Rural Affairs, Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, 100081 China
  7. 7College of Geography and Remote Sensing, Hohai University, Nanjing, 210098 China
Read full textPDFDOICite

Abstract

Agricultural parcels (APs) are fundamental spatial units for precision agriculture and effective agricultural management. However, large-scale AP mapping remains limited, particularly at national scales. To address this gap, this study proposes a national-scale AP mapping framework based on 10-m resolution Sentinel-2 imagery by enhancing the Hierarchical Boundary-Guided multi-task Network (HBGNet). Specifically, we developed HBGNet 2.0, an upgraded version of HBGNet, which introduces a novel self-adaptive weighting loss function, thereby balancing the learning of different tasks and improving AP delineation. Using HBGNet 2.0, we generated a 10-m resolution national-scale AP dataset for Ukraine in 2023. HBGNet 2.0 demonstrates the best overall performance among all compared models (ResUNet-a, BFINet, BsiNet, SEANet, and HBGNet), achieving the highest OA (92.86%), F1 (91.03%), and IoU (85.70%) metrics. Compared with three publicly available national AP datasets for Ukraine, our dataset exhibits better spatial detail and higher delineation accuracy. This high-precision AP dataset has the potential to serve as a critical resource for Ukrainian agricultural monitoring and for assessing conflict-related crop damage.

Related

  1. Development of an open-access interactive tool for multi-index agricultural and environmental analysis using Landsat and Sentinel-2 on Google Earth Engine
    Almustafa Abd Elkader Ayek, Norah Alshahrani, Mena Elassal +2
    Scientific ReportsPeer-reviewedCC BY 4.0Full textEcologyCrossref
  2. Fine-grained hierarchical crop type classification from integrated hyperspectral EnMAP data and multispectral sentinel-2 time series: A large-scale dataset and dual-stream transformer method
    Wenyuan Li, Shunlin Liang, Yuxiang Zhang +8
    Remote Sensing of EnvironmentPeer-reviewedCC BY13 citedEcologyOpenAlex
  3. RNA3D-Decoy: A Large-Scale Benchmark Dataset of AI-Generated RNA Structure Models for Quality Assessment
    X. Chen, H. Yadi, R. Cao +1
    bioRxivPreprintCC BYFull textBioinformatics & computational biologybioRxiv
  4. Weekly dynamics, subtype replacement and regional heterogeneity of influenza activity in China, 2024–2026: A national sentinel surveillance analysis
    Simin Wang, Zhi Xia, Buyun Shi +3
    PLOS OnePeer-reviewedCC BY 4.0Full textImmunologyGeneral earth sciencePLOSPMC
  5. Patient experience in National digital health platforms: Evidence from patient-generated feedback in Saudi Arabia
    Abdulmohsen Saud Albesher
    PLOS OnePeer-reviewedCC BYFull textEcologyImmunologyPLOSEurope PMC

Cite

BibTeXRIS
BibTeX
@article{li2026national,
  title = {{A 10-m National Agricultural Parcel Dataset of Ukraine Generated with an Enhanced Multi-Task Network and Sentinel-2 Imagery}},
  author = {Junbin Li and Hongwei Zeng and Hang Zhao and Miao Zhang and Yang Chen and Qiangyi Yu and Wenbin Wu and Yuanwei Qin and Bingfang Wu and Shaohua Wang},
  journal = {Scientific Data},
  year = {2026},
  month = jul,
  doi = {10.1038/s41597-026-07837-5},
  url = {https://doi.org/10.1038/s41597-026-07837-5},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - A 10-m National Agricultural Parcel Dataset of Ukraine Generated with an Enhanced Multi-Task Network and Sentinel-2 Imagery
AU  - Junbin Li
AU  - Hongwei Zeng
AU  - Hang Zhao
AU  - Miao Zhang
AU  - Yang Chen
AU  - Qiangyi Yu
AU  - Wenbin Wu
AU  - Yuanwei Qin
AU  - Bingfang Wu
AU  - Shaohua Wang
PY  - 2026
DA  - 2026/07/10
JO  - Scientific Data
DO  - 10.1038/s41597-026-07837-5
UR  - https://doi.org/10.1038/s41597-026-07837-5
AB  - Agricultural parcels (APs) are fundamental spatial units for precision agriculture and effective agricultural management. However, large-scale AP mapping remains limited, particularly at national scales. To address this gap, this study proposes a national-scale AP mapping framework based on 10-m resolution Sentinel-2 imagery by enhancing the Hierarchical Boundary-Guided multi-task Network (HBGNet). Specifically, we developed HBGNet 2.0, an upgraded version of HBGNet, which introduces a novel self-adaptive weighting loss function, thereby balancing the learning of different tasks and improving AP delineation. Using HBGNet 2.0, we generated a 10-m resolution national-scale AP dataset for Ukraine in 2023. HBGNet 2.0 demonstrates the best overall performance among all compared models (ResUNet-a, BFINet, BsiNet, SEANet, and HBGNet), achieving the highest OA (92.86%), F1 (91.03%), and IoU (85.70%) metrics. Compared with three publicly available national AP datasets for Ukraine, our dataset exhibits better spatial detail and higher delineation accuracy. This high-precision AP dataset has the potential to serve as a critical resource for Ukrainian agricultural monitoring and for assessing conflict-related crop damage.
SN  - 2052-4463
ER  -