Integration of convolutional neural networks with parcel-based image analysis for crop type mapping from time-series images

Timely and accurate crop mapping is crucial for yield prediction, food security assessment and agricultural management. Convolutional neural networks (CNNs) have become powerful state-of-the-art methods in many fields, including crop type detection from satellite imagery. However, existing CNNs generally have large number of layers and filters that increase the computational cost and the number of parameters to be learned, which may not be convenient for the processing of time-series images. To that end, we propose a light CNN model in combination with parcel-based image analysis for crop classification from time-series images. The model was applied on two areas (Manisa and K & imath;rklareli) in T & uuml;rkiye using Sentinel-2 data. Classification results based on all bands of the time-series data had overall accuracies (OA) of 89.3% and 88.3%, respectively for Manisa and K & imath;rklareli. The results based on the optimal bands selected through the Support Vector Machine-Recursive Feature Elimination (SVM-RFE) method had OA of 86.6% and 86.5%, respectively. The proposed model outperformed the VGG-16, ResNet-50, and U-Net models used for comparison. For Manisa and K & imath;rklareli respectively, VGG-16 achieved OA of 86.0% and 86.5%, ResNet-50 achieved OA of 84.1% and 84.8%, and U-Net achieved OA of 82.2% and 81.9% based on all bands. Based on the optimal bands, VGG-16 achieved OA of 84.2% and 84.7%, ResNet-50 achieved OA of 82.4% and 83.1%, and U-Net achieved OA of 80.5% and 80.2%. The results suggest that the proposed model is promising for accurate and cost-effective crop classification from Sentinel-2 time-series imagery.