{"slug": "biomazon-a-multimodal-dataset-for-3d-forest-structure-and-biomass-modeling-in", "title": "Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin", "summary": "Researchers released Biomazon, a 20-meter multimodal benchmark dataset covering the Amazon Basin that pairs GEDI relative height (RH) profiles and aboveground biomass density (AGBD) targets with satellite and land cover predictors. The dataset addresses the lack of a machine learning-ready benchmark for predicting the entire forest vertical structure as an ordered profile, rather than separate scalar targets. Biomazon establishes a standardized evaluation framework for structurally consistent RH-profile prediction and structure-biomass modeling in tropical forests.", "body_md": "arXiv:2606.05368v1 Announce Type: new\nAbstract: Accurate, spatially explicit characterization of tropical forest structure is essential for carbon accounting and ecosystem monitoring, yet most ML pipelines predict canopy-top height proxies (e.g., RH95/RH98) or AGBD as separate scalar targets, rather than learning the forest vertical structure as an ordered profile. The community lacks a ML-ready multimodal benchmark for predicting the entire GEDI RH profile jointly with AGBD, or for evaluating methods that enforce physically consistent ordering across RH percentiles. We address this with Biomazon, a 20 m multimodal benchmark dataset over the Amazon Basin that pairs GEDI RH and AGBD targets with multi-sensor predictors (Sentinel-1/2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World LULC, and AlphaEarth embeddings) under standardized spatial splits and evaluation protocols. Using a shared encoder-decoder with task-specific heads as a baseline framework, we conduct a comprehensive ablation study of (i) backbone/model scale, (ii) modality contributions, and (iii) the use of auxiliary embeddings under standalone and fusion settings, and we report both single-target and joint-target results to quantify tradeoffs under a unified training protocol. Finally, we contextualize baseline performance through regionally aligned comparisons against existing gridded products, including GEDI L4D RH10-RH98 and AGBD, at matching temporal scale. Biomazon, together with the accompanying protocols and baseline results, establishes a reference benchmark for future work on structurally consistent RH-profile prediction and structure-biomass modeling in tropical forests.", "url": "https://wpnews.pro/news/biomazon-a-multimodal-dataset-for-3d-forest-structure-and-biomass-modeling-in", "canonical_source": "https://arxiv.org/abs/2606.05368", "published_at": "2026-06-05 04:00:00+00:00", "updated_at": "2026-06-05 04:17:39.482705+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "ai-research"], "entities": ["GEDI", "Sentinel-1", "Sentinel-2", "ALOS-2 PALSAR-2", "Copernicus DEM", "Dynamic World", "AlphaEarth", "Amazon Basin"], "alternates": {"html": "https://wpnews.pro/news/biomazon-a-multimodal-dataset-for-3d-forest-structure-and-biomass-modeling-in", "markdown": "https://wpnews.pro/news/biomazon-a-multimodal-dataset-for-3d-forest-structure-and-biomass-modeling-in.md", "text": "https://wpnews.pro/news/biomazon-a-multimodal-dataset-for-3d-forest-structure-and-biomass-modeling-in.txt", "jsonld": "https://wpnews.pro/news/biomazon-a-multimodal-dataset-for-3d-forest-structure-and-biomass-modeling-in.jsonld"}}