Research map / Time series / Foundation models for time series
BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series
Andrea Nascetti, RITU YADAV, Kirill Brodt, Qixun Qu, Hongwei Fan, Yuri Shendryk, Isha Shah, Christine Chung
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| U-TAE instead of U-Net++ ensemble | baseline DL models · BioMassters test overall | RMSE: 27.92 -> 27.49 | Improved |
| U-TAE instead of Swin UNETR | baseline DL models · BioMassters test overall | RMSE: 27.53 -> 27.49 | No clear effect |
| Higher biomass density (low to high) | U-TAE · BioMassters test | RMSE: 15.24 -> 37.59 | Hurt |
| Higher biomass density (low to high) | Swin UNETR · BioMassters test | RMSE: 15.25 -> 37.64 | Hurt |
| Higher biomass density (low to high) | U-Net++ Ensembled · BioMassters test | RMSE: 15.60 -> 38.04 | Hurt |
| U-TAE instead of U-Net++ ensemble on bias in high density | baseline DL models · BioMassters test high density | average bias: 1.76 -> 0.49 | Mixed |
| U-TAE instead of Swin UNETR on bias overall | baseline DL models · BioMassters test overall | average bias: 1.16 -> 0.64 | Improved |
| Deep learning on Sentinel-1/2 time series instead of existing global biomass products | top DL models · low biomass density | RMSE: 30 t/px -> 15.24 | Improved |
| Deep learning on Sentinel-1/2 time series instead of existing global biomass products | top DL models · high biomass density | RMSE: 50 t/px -> 37.59 | Improved |
Closest papers by meaning
- FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring (AAAI 2025 · similarity 0.86)
- Multi-modal Learning for Geospatial Vegetation Forecasting (CVPR 2024 · similarity 0.85)
- ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images (CVPR 2025 · similarity 0.84)
- Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation (ICML 2025 · similarity 0.83)
- Open-Canopy: Towards Very High Resolution Forest Monitoring (CVPR 2025 · similarity 0.83)
- CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
