Amazon's 2023 Drought: Sentinel-1 Reveals Extreme Rio Negro River Contraction

no code implementations • 29 Jan 2024 • Fabien H Wagner, Samuel Favrichon, Ricardo Dalagnol, Mayumi CM Hirye, Adugna Mullissa, Sassan Saatchi

Here, we used a U-net deep learning model to map water surfaces in the Rio Negro River basin every 12 days in 2022 and 2023 using 10 m spatial resolution Sentinel-1 satellite radar images.

Sub-Meter Tree Height Mapping of California using Aerial Images and LiDAR-Informed U-Net Model

no code implementations • 2 Jun 2023 • Fabien H Wagner, Sophia Roberts, Alison L Ritz, Griffin Carter, Ricardo Dalagnol, Samuel Favrichon, Mayumi CM Hirye, Martin Brandt, Philipe Ciais, Sassan Saatchi

Tree canopy height is one of the most important indicators of forest biomass, productivity, and species diversity, but it is challenging to measure accurately from the ground and from space.

K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation

no code implementations • 18 May 2022 • Fabien H. Wagner, Ricardo Dalagnol, Alber H. Sánchez, Mayumi C. M. Hirye, Samuel Favrichon, Jake H. Lee, Steffen Mauceri, Yan Yang, Sassan Saatchi

The model detects $k$ hard clustering classes represented in the model as $k$ discrete binary masks and their associated $k$ independently generated textures, that combined are a simulation of the original image.

Clustering Image Segmentation +1