Seeing Through the Clouds: Cloud Gap Imputation with Prithvi Foundation Model

TL;DR

This paper compares Vision Transformer and CGAN models for imputing cloud-covered pixels in multispectral satellite imagery, aiming to improve data quality for time series analysis.

Contribution

It introduces a novel comparison between ViT and CGAN models for cloud gap imputation in satellite imagery, highlighting the effectiveness of pretrained ViT models.

Findings

ViT outperforms CGAN in imputation accuracy

Pretrained ViT achieves better structural similarity scores

Models effectively reconstruct missing cloud-covered pixels

Abstract

Filling cloudy pixels in multispectral satellite imagery is essential for accurate data analysis and downstream applications, especially for tasks which require time series data. To address this issue, we compare the performance of a foundational Vision Transformer (ViT) model with a baseline Conditional Generative Adversarial Network (CGAN) model for missing value imputation in time series of multispectral satellite imagery. We randomly mask time series of satellite images using real-world cloud masks and train each model to reconstruct the missing pixels. The ViT model is fine-tuned from a pretrained model, while the CGAN is trained from scratch. Using quantitative evaluation metrics such as structural similarity index and mean absolute error as well as qualitative visual analysis, we assess imputation accuracy and contextual preservation.