Random Forest Outperformed Convolutional Neural Networks for Shrub Willow Above Ground Biomass Estimation Using Multi-Spectral UAS Imagery

• Published in: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS pp. 8269 - 8272
• Main Authors: Tamiminia, Haifa, Salehi, Bahram, Mahdianpari, Masoud, Beier, Colin M., Klimkowski, Daniel J., Volk, Timothy A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 11.07.2021
• Subjects: Above-ground biomass; Biological system modeling; Deep learning; Estimation; machine learning; multi-spectral imagery; Radio frequency; Training; Training data; UAS; Vegetation mapping
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS47720.2021.9553515

Shrub willow is a valuable source of hardwood biomass feedstock which is used for the production of bioenergy, biofuels, and renewable bio-based products. The biomass produced from this short-rotation woody plant can be used for heat and electricity generation. Thus, an accurate estimation of shrub willow above-ground biomass (AGB) is of paramount importance. This paper aimed to estimate shrub willow AGB using multi-spectral unmanned aerial system (UAS) imagery and machine learning techniques. To accomplish this goal, a machine learning model (i.e., random forest (RF)) and a deep learning method (i.e., convolutional neural network (CNN)) were applied to the spectral bands and some vegetation indices over a site in Camillus, NY, US in July 2019. The results demonstrated the superiority of the RF model (RMSE of 1.73 Mg/ha and R2 of 0.95) compared to the CNN (RMSE of 2.69 Mg/ha and R2 of 0.89) technique. Adding vegetation indices to spectral bands and using a convolutional approach for training purposes could significantly improve the modeling efficiency.