A Deep Transfer Learning Method for Estimating Fractional Vegetation Cover of Sentinel-2 Multispectral Images

Abstract

Fractional vegetation cover (FVC) is an important indicator for exploring hydrosphere, pedosphere, atmosphere, biosphere, and their interactions. Deep learning (DL) is a potential tool to handle large-scale data and approximate the complex nonlinear relationship between variables. It is, therefore, suitable for FVC estimation. However, few DL-based algorithms have been developed to estimate FVC as it is difficult to obtain a large amount of training data. This letter presents a novel method by means of deep transfer learning to address this issue. The proposed technique consists of two steps. In the first step, a large amount of simulated training samples were generated by a physical model (PROSPECT + SAIL radiative transfer model, PROSAIL). In the second step, a long short-term memory (LSTM) network was pretrained with the simulated training dataset obtained in the first step. Then limited real samples from satellite images were used to fine-tune the pretrained network. Experiments were conducted for the Sentinel-2 multispectral satellite images of two areas and the results were compared with those obtained by the traditional the Normalized Difference Vegetation Index (NDVI)-based method and two machine learning approaches. The results demonstrate that the performance of our method outperforms other advanced FVC estimation methods.