UAV-Based Multispectral Time-Series Imagery of Biomass Sorghum — 2019

 

CABBI Theme: Feedstock Production

Keyword: Biomass Analytics

 

Citation

Varela Quintela, S., Leakey, A.D.B. May 10, 2021. “UAV-Based Multispectral Time-Series Imagery of Biomass Sorghum — 2019.” University of Illinois Urbana-Champaign. DOI: 10.13012/B2IDB-0353090_V1.

 

Spatial extraction of geometric and spectral feature at each plot, temporal integration and smoothing via splines, extraction of time-point and dynamics features from spline continuous solution from each feature. Random Forest implementation for determination of variable importance and above-ground biomass (AGB) prediction. This last step is implemented for time-point and dynamic features at each of the predefined date as predictors of end-of-season AGB.

Overview

UAV-based high-resolution multispectral time-series orthophotos utilized to understand the relation between growth dynamics, imagery temporal resolution, and end-of-season biomass productivity of biomass sorghum as bioenergy crop. Sensor utilized is a RedEdge Micasense flown at 40 meters above ground level at the Energy Farm at University of Illinois Urbana-Champaign in 2019.

 

Data

3D Reconstructed Orthophotos (234 MB)

Spectral Orthophotos (6.38 GB)

 

Related Publications

Varela, S.Pederson, T.Bernacchi, C.J.Leakey, A.D.B. May 1, 2021. “Understanding growth Dynamics and Yield Prediction of Sorghum Using High Temporal Resolution UAV Imagery Time Series and Machine Learning.” Remote Sensing 13 (9), 1763. DOI: 10.3390/rs13091763.

Varela, S.Pederson, T.Bernacchi, C.J., Leakey, A.D.B. Feb. 4, 2022. “Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum.” Remote Sensing 14(3): 733. DOI: 10.3390/rs14030733.