New CNN model enhances biomass estimation using multi-sensor data

Researchers have developed a novel convolutional neural network (CNN) model for estimating above-ground biomass (AGB) using multi-sensor data, including optical, SAR, and terrain information. This globally trained model can be adapted to specific landscapes with a lightweight empirical field-calibration workflow, improving accuracy without extensive retraining. The framework harmonizes data onto a 10m grid and utilizes a hybrid loss function for skewed biomass distribution. Initial validation shows an R^2 of approximately 0.78 and RMSE of 22 Mg/ha, which is further improved to R^2 of 0.82 and RMSE of 15 Mg/ha after field calibration, outperforming existing products. AI

IMPACT This model could improve the accuracy and efficiency of carbon accounting and climate change mitigation strategies by providing more precise biomass estimations.

RANK_REASON The cluster contains a research paper detailing a new model and methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• ALOS-2 PALSAR-2
• arXiv
• ESA CCI Biomass
• Gedi
• Global Ecosystem Dynamics Investigation
• Sentinel-1
• Sentinel-2
• Subas Chhatkuli PhD

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →