Journal cover Journal topic
AGILE: GIScience Series Open-access proceedings of the Association of Geographic Information Laboratories in Europe
Journal topic
Articles | Volume 3
AGILE GIScience Ser., 3, 23, 2022
AGILE GIScience Ser., 3, 23, 2022
10 Jun 2022
10 Jun 2022

Machine Learning with UAS LiDAR for Winter Wheat Biomass Estimations

Jordan Bates1, Francois Jonard1,2, Rajina Bajracharya1, Harry Vereecken1, and Carsten Montzka1 Jordan Bates et al.
  • 1Institute of Bio- and Geosciences: Agrosphere (IBG-3), Forschungszentrum Jülich GmbH, 52428 Jülich, Germany
  • 2Earth Observation and Ecosystem Modelling (EOSystM) lab, SPHERES research unit, Université de Liège (ULiège), Allée du Six Août 19, 4000 Liège, Belgium

Keywords: Machine Learning, ANN, LiDAR, UAS, Biomass

Abstract. Biomass is an important indicator in the ecological and management process that can now be estimated at higher temporal and spatial resolutions because of unmanned aircraft systems (UAS). LiDAR sensor technology has advanced enabling more compact sizes that can be integrated with UAS platforms. Its signals are capable of penetrating through vegetation canopies enabling the capture of more information along the plant structure. Separate studies have used LiDAR for crop height, rate of canopy penetrations as related to leaf area index (LAI), and signal intensity as an indicator of plant chlorophyll status or green area index (GAI). These LiDAR products are combined within a machine learning method such as an artificial neural network (ANN) to assess the potential in making accurate biomass estimations for winter wheat.

Publications Copernicus