A Novel Deep Learning Framework combining optical-SAR Data to Generate Gap-Free 20 M LAI Time Series for Crop Monitoring

The Leaf Area Index (LAI) is a critical indicator of crop growth, making high-resolution, gap-free LAI data of paramount importance for crop monitoring. However, the availability of optical data is significantly reduced due to cloud contamination. Conversely, SAR data can be acquired under all weather conditions. Additionally, both Sentinel-2 optical data and Sentinel-1 SAR data provide high spatial resolution and high temporal frequency. Therefore, with the aim of generating gap-free LAI time series at both high spatial and temporal resolutions, we propose a novel deep learning framework that combines Sentinel-2 optical and Sentinel-1 SAR data. This framework employs a Convolutional Neural Network (CNN) backbone to incorporate spatial context into LAI estimation. It implements a year-to-acquisition-date training strategy to enhance estimation accuracy. First, the model is pre-trained on data collected over a one-year time series. Then, it is progressively fine-tuned for each specific acquisition date on which LAI estimation is required. These components are integrated into an operational workflow for automated generation of gap-free LAI time series data. We validate the proposed framework through a comprehensive evaluation across diverse climate types, crop percentages, and gap length scenarios. Results demonstrate the superior performance of the proposed framework (<tex-math notation="LaTeX">R²</tex-math>: 0.86, RMSE: 0.26, <tex-math notation="LaTeX">|Bias|</tex-math>: 0.07, SSIM: 0.85) compared to seven standard optical-based gap-filling approaches and two deep learning–based methods that integrate optical and SAR data, with gap length being the primary factor affecting performance. Furthermore, the framework shows robust LAI reconstruction under undetected residual clouds, ensuring accurate temporal and spatial information over croplands.