Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms

Abstract

Surveying canopy attributes while conducting fieldwork in the rain forest is time-consuming. Low-cost imagery such as digital cover photography is a potential source of information to speed up the process of vegetation assessments and reduce costs during expeditions. This study presents an image-based non-destructive method to estimate canopy attributes of wild cacao trees in two regions of the rain forest in Colombia, using digital cover photography and machine learning algorithms. Upward-looking photography at the base of each cacao tree and machine learning algorithms were used to estimate gap fraction (GF), foliage cover (FC), crown cover (CC), crown porosity (CP), clumping index (Ω), and leaf area index (LAI) of the canopy cover. Here we used the cacao wild trees found on forestry plots as a case study to test the application of low-cost imagery on the extraction and analysis of canopy attributes. Canopy attributes were successfully extracted from the canopy cover imagery and provided 92% of classification accuracy for the structural attributes of the canopy. Canopy cover attributes allowed us to differentiate between canopy structures of the Amazon and Pacific rainforests sites suggesting that wild cacao trees are associated with different vegetation types. We also compare classification results for the computer extraction of canopy attributes with a digital canopy cover benchmark. We conclude that our approach was effective to quickly survey canopy features of vegetation associated with and of crop wild relatives of cacao. This study allows highly reproducible estimates of canopy attributes using cover photography and state-of-the-art machine learning algorithms such as deep learning Convolutional Neural Networks.