Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin
Quick Answer
Biomazon introduces a 20 m multimodal dataset for predicting 3D forest structure and biomass in the Amazon Basin, integrating GEDI RH profiles and AGBD with multi-sensor data.
Quick Take
This benchmark facilitates machine learning evaluations of forest vertical structure and biomass modeling, establishing a reference for future research.
Key Points
- Biomazon dataset pairs GEDI RH profiles with AGBD using multi-sensor predictors.
- Standardized spatial splits and evaluation protocols enhance machine learning benchmarking.
- Comprehensive ablation study evaluates model scale, modality contributions, and embeddings.
- Baseline performance compared with existing products like GEDI L4D RH10-RH98.
- Establishes a reference for structurally consistent RH-profile prediction in tropical forests.
Paper Resources
Source Excerpt
arXiv:2606. 05368v1 Announce Type: new Abstract: 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. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.