Machine learning-based maize (Zea mays L.) extraction at parcel level using Sentinel 2A-derived spectral indices

Creative Commons License

Bantchina B. B., Gündoğdu K. S.

JOURNAL OF APPLIED REMOTE SENSING, cilt.18, sa.3, ss.1-16, 2024 (SCI-Expanded)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 18 Sayı: 3
  • Basım Tarihi: 2024
  • Doi Numarası: 10.1117/1.jrs.18.034515
  • Dergi Adı: JOURNAL OF APPLIED REMOTE SENSING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Aquatic Science & Fisheries Abstracts (ASFA), CAB Abstracts, Communication Abstracts, Compendex, INSPEC, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1-16
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

Crop type classification is crucial for policymaking and precision agriculture applications. This study aimed to develop a parcel-based maize (Zea mays L.) extraction approach using Sentinel 2A-derived spectral indices and machine learning (ML) in two distinct study sites: Ye ¸silova and Ormankadı villages in Bursa Province, Turkey. Employing 13 widely recognized spectral indices, the investigation implemented 4 ML classifiers: support vector machines, random forest, K-nearest neighbors, and bootstrap aggregating. The training-test methodology was explored using two scenarios: Ye ¸silova as the training set and Ormankadı as the test set, and vice versa. The models calibrated on Ye ¸silova and validated on Ormankadı maintained the accuracy of the model, with an overall accuracy (OA) ranging from 79.3% to 89.9%, precision between 72.8% and 80.1%, recall between 82.1% and 84.9%, F1-score between 77.4% and 82.2%, and a Matthews correlation coefficient (MCC) ranging from 58.9% to 68.3%. Furthermore, the models consistently demonstrated good performance when Ormankadı served as the training set and Ye ¸silova as the test set, with commendable OA (78.7% to 84.8%), precision (85.5% to 88.0%), recall (88.0% to 91.1%), F1-score (86.2% to 89.5%), and MCC (68.2% to 76.0%). This study demonstrated the potential of using high-resolution remote sensing and ML for effective maize crop extraction using diverse datasets.