European Beech Spring Phenological Phase Prediction with UAV-derived Multispectral Indices and Machine Learning Regression

The acquisition of phenological events play an integral part in investigating the effects of climate change on forest dynamics and assessing the potential risk involved with the early onset of young leaves. Large scale mapping of forest phenological timing using earth observation data, could facilitate a better understanding of phenological processes due to an added spatial component. The translation of traditional phenological ground observation data into reliable ground truthing for the purpose of the training and validation of Earth Observation (EO) mapping applications is a challenge. In this study, we explored the possibility of predicting high resolution phenological phase data for European beech (Fagus sylvatica) with the use of Unmanned Aerial Vehicle (UAV)-based multispectral indices and machine learning. Using a comprehensive feature selection process, we were able to identify the most effective sensors, vegetations indices, training data partitions, and machine learning models for phenological phase prediction. The best performing model that generalised well over various sites was the model utilising the Green Chromatic Coordinate (GCC) and Generalized Addictive Model (GAM) boosting. The GCC training data was derived from the radiometrically calibrated visual bands from a multispectral sensor and predicted using uncalibrated RGB sensor data. The final GCC/GAM boosting model was capable in predicting phenological phases on unseen datasets within a RMSE threshold of 0.5. This research shows the potential of the interoperability among common UAV-mounted sensors in particular the utility of readily available low cost RGB sensors. Considerable limitations were however discovered with indices implementing the near-infrared (NIR) band due to oversaturation. Future work involves adapting models to facilitate the ICP Forests phenological flushing stages.