The field of remote sensing is rapidly advancing, with a focus on developing innovative methods for land cover analysis and biomass estimation. Recent studies have highlighted the importance of integrating hyperspectral imagery, depth information, and graph-based frameworks to improve the accuracy and scalability of remote sensing applications. Researchers are also exploring the use of large-scale datasets, such as the MajorTOM dataset, to pretrain earth observation foundation models and fine-tune them for specific downstream tasks. Noteworthy papers include the introduction of the HyBiomass dataset, which provides a globally distributed benchmark for forest aboveground biomass estimation, and the development of the DepthSeg framework, which incorporates depth prompting to mitigate spectral confusion and shadow occlusion in remote sensing semantic segmentation. Additionally, the proposed unified graph-based framework for 3D tree reconstruction and non-destructive biomass estimation has shown strong performance under challenging conditions, making it a promising solution for large-scale applications.