EUVIMEDEUVIMED entdecken
Crossref

Deep Learning-Based Crop Declaration Validation with Noisy Labels: A Comparative Study of Loss Functions and Architectures for Parcel-Level Risk Prioritization

Ali Sinan Adanalı, Gıyasettin Çiçek

ÇOMÜ Ziraat Fakültesi Dergisi · 29.06.2026 · 14 (1) · 128-141

DOI: 10.33202/comuagri.1937201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ÇOMÜ Ziraat Fakültesi Dergisi, online erschienen am 29.06.2026. Verfasst von Ali Sinan Adanalı und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate verification of farmer-declared crop types is essential for the reliable administration of agricultural subsidy programs. In Turkey, parcel-level crop declarations submitted through the Farmer Registration System (FRS/ÇKS) are not subject to systematic field-level verification, introducing structural label noise into deep learning models that rely on these declarations as training supervision. This study presents a deep learning-based crop classification and risk assessment framework applied to 15,000 agricultural parcels in the Biga district of Çanakkale province, Turkey, using Sentinel-2 multi-temporal imagery to validate FRS/ÇKS declarations.The study advances the state of the art along two axes: (i) the first application of Symmetric Cross Entropy (SCE) loss to remote sensing-based parcel classification, and (ii) the integration of classification outputs into a parcel-level risk scoring framework for field verification prioritization. LSTM and 1D CNN-LSTM architectures were comparatively evaluated under both standard Categorical Cross Entropy (CCE) and SCE loss functions. Weekly median composites comprising 14 features — ten Sentinel-2 spectral bands together with NDVI, EVI, NDRE, and LAI vegetation indices — were used as input across 30 temporal steps.The highest performance was achieved by the 1D CNN-LSTM + SCE configuration (Macro F1: 0.741; OA: 86.5%). SCE yielded decisive improvements for minority classes: tomato precision increased from 0.16 to 0.70, and pepper precision from 0.41 to 0.76. The risk scoring mechanism flagged 1,738 of 15,000 parcels (11.6%) as high-risk, enabling an 8.6× more efficient allocation of field inspection resources. Geographic clustering analysis revealed discrepancy rates reaching 48% in certain villages. These findings demonstrate that, in agricultural classification problems with structural label noise, loss function selection can be more determinative than architectural choice.

Zitieren

APA

Adanalı, A. S., & Çiçek, G. (2026). Deep Learning-Based Crop Declaration Validation with Noisy Labels: A Comparative Study of Loss Functions and Architectures for Parcel-Level Risk Prioritization. ÇOMÜ Ziraat Fakültesi Dergisi, 14(1), 128-141. https://doi.org/10.33202/comuagri.1937201

Vancouver

Adanalı AS, Çiçek G. Deep Learning-Based Crop Declaration Validation with Noisy Labels: A Comparative Study of Loss Functions and Architectures for Parcel-Level Risk Prioritization. ÇOMÜ Ziraat Fakültesi Dergisi. 2026;14(1):128-141. doi:10.33202/comuagri.1937201

BibTeX
@article{Adanal2026,
  author = {Adanalı, Ali Sinan and Çiçek, Gıyasettin},
  title = {Deep Learning-Based Crop Declaration Validation with Noisy Labels: A Comparative Study of Loss Functions and Architectures for Parcel-Level Risk Prioritization},
  journal = {ÇOMÜ Ziraat Fakültesi Dergisi},
  year = {2026},
  volume = {14},
  number = {1},
  pages = {128--141},
  doi = {10.33202/comuagri.1937201}
}
Kostenlos starten →