Performance evaluation of transfer learning based deep convolutional neural network with limited fused spectro-temporal data for land cover classification

Abstract

Deep learning (DL) techniques are effective in various applications, such as parameter estimation, image classification, recognition, and anomaly detection. They excel with abundant training data but struggle with limited data. To overcome this, transfer learning is commonly used, leveraging complex learning abilities, saving time, and handling limited labeled data. This study assesses a transfer learning (TL)-based pre-trained “deep convolutional neural network (DCNN)” for classifying land use land cover using a limited and imbalanced dataset of fused spectro-temporal data. It compares the performance of shallow artificial neural networks (ANNs) and deep convolutional neural networks, utilizing multi-spectral sentinel-2 and high-resolution planet scope data. Both machine learning and deep learning algorithms successfully classified the fused data, but the transfer learning-based deep convolutional neural network outperformed the artificial neural network. The evaluation considered a weighted average of F1-score and overall classification accuracy. The transfer learning-based convolutional neural network achieved a weighted average F1-score of 0.92 and a classification accuracy of 0.93, while the artificial neural network achieved a weighted average F1-score of 0.87 and a classification accuracy of 0.89. These results highlight the superior performance of the transfer learned convolutional neural network on a limited and imbalanced dataset compared to the traditional artificial neural network algorithm.