Komparasi Model Deep Learning U-Net dan SAM-LoRA untuk Deteksi Bidang Sawah Citra Resolusi Tinggi Desa Poncosari Kabupaten Bantul Tahun 2023 Menggunakan ArcGIS

Anissa Sephia Wulandari (Departemen Teknologi Kebumian, Universitas Gadjah Mada, Yogyakarta, Indonesia)
Karen Slamet Hardjo (Departemen Teknologi Kebumian, Universitas Gadjah Mada, Yogyakarta, Indonesia)

Spatial : Wahana Komunikasi dan Informasi Geografi
Vol. 25 No. 2 (2025): SPATIAL: Wahana Komunikasi dan Informasi Geografi

The object of paddy field cover in Indonesia in high-resolution images is difficult to identify due to its unique characteristics and similarity to surrounding objects. This study aims to compare the performance of two Deep Learning architectures, UNet with ResNet34 backbone and SAMLoRA with ViT-B backbone, to perform segmentation using high-resolution images with accuracy down to the paddy field unit. Both models were trained using identical hyperparameters, with and without data augmentation, to evaluate accuracy and computational efficiency. The results show that SAMLoRA outperformed UNet across all evaluation metrics, achieving a higher mean Intersection over Union (mIoU) of 0.7909 compared to 0.7568. Although SAMLoRA required a longer training time, it produced clearer and more interpretable segmentations, capturing complex details more effectively. In conclusion, both Deep Learning models offer a much faster and more effective alternative to manual digitization for mapping paddy fields.