Bayesian aggregation improves traditional single image crop classification approaches
This work addresses crop classification in cloudy regions where multi-temporal images are unavailable, offering an incremental improvement over existing methods.
The study tackled crop classification from a single satellite image, showing that field-wise classification outperforms pixel-wise methods, with gradient boosting achieving 77.4% accuracy and a macro F1-score of 0.66.
Machine learning (ML) methods and neural networks (NN) are widely implemented for crop types recognition and classification based on satellite images. However, most of these studies use several multi-temporal images which could be inapplicable for cloudy regions. We present a comparison between the classical ML approaches and U-Net NN for classifying crops with a single satellite image. The results show the advantages of using field-wise classification over pixel-wise approach. We first used a Bayesian aggregation for field-wise classification and improved on 1.5% results between majority voting aggregation. The best result for single satellite image crop classification is achieved for gradient boosting with an overall accuracy of 77.4% and macro F1-score 0.66.