EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Source Remote Sensing and Stacking Ensemble Learning for Vineyard Mapping and Inventory Updating in Arid Xinjiang

Leiting Yi, Lei Wang, Zhi Pu, Lei Luo, Siyu Zhou, Shipeng Wang

AgriEngineering · 30.07.2026 · 8 (8) · 318

DOI: 10.3390/agriengineering8080318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AgriEngineering, online erschienen am 30.07.2026. Verfasst von Leiting Yi und 5 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Construction of Forest and Fruit Resource Data System Based on Space-Air-Ground Multi-Source Remote Sensing Monitoring Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate vineyard mapping is important for agricultural resource monitoring, land-use management, and inventory updating in arid regions. However, vineyard identification in Xinjiang, China, is challenged by fragmented parcels, exposed soil backgrounds, irrigation-driven heterogeneity, and strong accumulated-temperature gradients. This study developed a multi-source remote-sensing framework for vineyard mapping and inventory updating by integrating Sentinel-1/2 data, terrain variables, growing-degree-day-derived agrothermal zones (ATZs), and seasonal-difference features. RF, LightGBM, XGBoost, 1D-CNN, and a Stacking ensemble were evaluated using polygon-level in-distribution testing and Leave-One-ATZ-Out cross-zone validation. The in-distribution test was used to assess vineyard separability under similar sample distributions, whereas cross-ATZ validation was used to evaluate model transferability across heterogeneous thermal domains. Tree-based models and Stacking achieved near-ceiling performance under the in-distribution setting, but cross-ATZ validation revealed substantial performance degradation, indicating that conventional local validation can overestimate operational transferability. RF achieved the highest mean cross-zone F1-score, while Stacking achieved the highest cross-zone AP and Recall and provided a flexible probability surface for thresholding, mosaicking, vector post-processing, and patch-level mapping. In Gaochang District, the Stacking-derived result identified 22,998.84 ha of potential vineyard area, achieved an Area Recall of 0.7908 against the historical inventory, and covered 88.03% of existing parcels at ≥30% spatial overlap. The workflow also identified 1356 candidate vineyard patches for inventory updating covering 2502.32 ha for subsequent inventory verification. These results demonstrate that multi-source feature integration and probability-based ensemble mapping can support vineyard mapping and inventory updating in arid regions, while cross-zone validation is essential for assessing operational generalization.

Förderung

  • Construction of Forest and Fruit Resource Data System Based on Space-Air-Ground Multi-Source Remote Sensing Monitoring Technology

Zitieren

APA

Yi, L., Wang, L., Pu, Z., Luo, L., Zhou, S., & Wang, S. (2026). Multi-Source Remote Sensing and Stacking Ensemble Learning for Vineyard Mapping and Inventory Updating in Arid Xinjiang. AgriEngineering, 8(8), 318. https://doi.org/10.3390/agriengineering8080318

Vancouver

Yi L, Wang L, Pu Z, Luo L, Zhou S, Wang S. Multi-Source Remote Sensing and Stacking Ensemble Learning for Vineyard Mapping and Inventory Updating in Arid Xinjiang. AgriEngineering. 2026;8(8):318. doi:10.3390/agriengineering8080318

BibTeX
@article{Yi2026,
  author = {Yi, Leiting and Wang, Lei and Pu, Zhi and Luo, Lei and Zhou, Siyu and Wang, Shipeng},
  title = {Multi-Source Remote Sensing and Stacking Ensemble Learning for Vineyard Mapping and Inventory Updating in Arid Xinjiang},
  journal = {AgriEngineering},
  year = {2026},
  volume = {8},
  number = {8},
  pages = {318},
  doi = {10.3390/agriengineering8080318}
}
Kostenlos starten →