Super resolution of historic Landsat imagery using a dual generative adversarial network (GAN) model with CubeSat constellation imagery for spatially enhanced long-term vegetation monitoring

Abstract

Detailed spatial representations of terrestrial vegetation are essential for precision agricultural applications and the monitoring of land cover changes in heterogeneous landscapes. The advent of satellite-based remote sensing has facilitated daily observations of the Earth’s surface with high spatial resolution. In particular, a data fusion product such as Planet Fusion has realized the delivery of daily, gap-free surface reflectance data with 3-m pixel resolution through full utilization of relatively recent (i.e., 2018-) CubeSat constellation data. However, the spatial resolution of past satellite sensors (i.e., 30–60 m for Landsat) has restricted the detailed spatial analysis of past changes in vegetation. In order to overcome the spatial resolution constraint of Landsat data for long-term vegetation monitoring, we propose a dual remote-sensing super-resolution generative adversarial network (dual RSS-GAN) approach combining Planet Fusion and Landsat 8 data to simulate spatially enhanced long-term time-series of the normalized difference vegetation index (NDVI) and near-infrared reflectance from vegetation (NIRv). We evaluated the performance of the dual RSS-GAN against in situ tower-based continuous measurements (up to 8 years) and remotely piloted aerial system-based maps of cropland and deciduous forest in the Republic of Korea. The dual RSS-GAN enhanced spatial representations in Landsat 8 images and captured seasonal variation in vegetation indices (R2 > 0.90, for the dual RSS-GAN maps vs in situ data from all sites). Overall, the dual RSS-GAN reduced Landsat 8 vegetation index underestimations compared with in situ measurements; relative bias values of NDVI ranged from − 5.8 % to 0.3 % and − 12.4 % to − 3.7 % for the dual RSS-GAN and Landsat 8, respectively. This improvement was caused by spatial enhancement through the dual RSS-GAN, which reflects fine-scale information from Planet Fusion. Finally, the dual RSS-GAN maps showed both spatial enhancement and reducing the underestimation of vegetation index in historic Landsat dataset from 1984. This study presents a new approach for resolving sub-pixel spatial information in Landsat images.