Deriving Non-Cloud Contaminated Sentinel-2 Images with RGB and Near-Infrared Bands from Sentinel-1 Images Based on a Conditional Generative Adversarial Network

Abstract

Sentinel-2 images have been widely used in studying land surface phenomena and processes, but they inevitably suffer from cloud contamination. To solve this critical optical data availability issue, it is ideal to fuse Sentinel-1 and Sentinel-2 images to create fused, cloud-free Sentinel-2-like images for facilitating land surface applications. In this paper, we propose a new data fusion model, the Multi-channels Conditional Generative Adversarial Network (MCcGAN), based on the conditional generative adversarial network, which is able to convert images from Domain A to Domain B. With the model, we were able to generate fused, cloud-free Sentinel-2-like images for a target date by using a pair of reference Sentinel-1/Sentinel-2 images and target-date Sentinel-1 images as inputs. In order to demonstrate the superiority of our method, we also compared it with other state-of-the-art methods using the same data. To make the evaluation more objective and reliable, we calculated the root-mean-square-error (RSME), R2, Kling–Gupta efficiency (KGE), structural similarity index (SSIM), spectral angle mapper (SAM), and peak signal-to-noise ratio (PSNR) of the simulated Sentinel-2 images generated by different methods. The results show that the simulated Sentinel-2 images generated by the MCcGAN have a higher quality and accuracy than those produced via the previous methods.

Cross-Year Reuse of Historical Samples for Crop Mapping Based on Environmental Similarity

“…The growing season of the main crops is from April to October, but indoor seedlings are mostly used for rice in April, so observable spectral changes mostly occur from May to October. As there are a lot of clouds in remote sensing images generally, it will affect the results of crop classification (Xiong et al, 2021). Therefore, GF-1 WFV data with cloud < 10% in the main growing season (May-October) of maize, rice, and soybean from 2013 to 2018 were used as a remote sensing data source (300-400 scenes/year).…”

“…The data came from the L1 product of China Center for Resources Satellite Data and Application, which refers to remote sensing products that have a radiometric correction and have not undergone geometric correction. Moreover, a Multilevel Raster Data Cleaning and Reconstitution Multigrid (RDCRMG) system developed by our team was used for image preprocessing, segmentation, and storage to a 10-km grid (Xiong et al, 2021).…”