Leveraging Multi-Temporal Sentinel 1 and 2 Satellite Data for Leaf Area Index Estimation With Deep Learning

TL;DR

This paper introduces a deep learning approach combining Sentinel 1 and 2 satellite data at multiple timestamps to accurately estimate Leaf Area Index, enhancing ecosystem monitoring capabilities.

Contribution

The study presents a novel multi-modal, multi-temporal neural network architecture with pre-training modules and seasonality integration for pixel-wise LAI prediction.

Findings

Achieved 0.06 RMSE and 0.93 R2 score on public data.

Developed a multi-modal deep neural network with pre-trained modules.

Incorporated seasonality into the model for improved accuracy.

Abstract

The Leaf Area Index (LAI) is a critical parameter to understand ecosystem health and vegetation dynamics. In this paper, we propose a novel method for pixel-wise LAI prediction by leveraging the complementary information from Sentinel 1 radar data and Sentinel 2 multi-spectral data at multiple timestamps. Our approach uses a deep neural network based on multiple U-nets tailored specifically to this task. To handle the complexity of the different input modalities, it is comprised of several modules that are pre-trained separately to represent all input data in a common latent space. Then, we fine-tune them end-to-end with a common decoder that also takes into account seasonality, which we find to play an important role. Our method achieved 0.06 RMSE and 0.93 R2 score on publicly available data. We make our contributions available at https://github.com/valentingol/LeafNothingBehind for future works to further improve on our current progress.