Machine Learning Techniques for Tree Species Classification Using Co-Registered LiDAR and Hyperspectral Data

Abstract

The use of light detection and ranging (LiDAR) techniques for recording and analyzing tree and forest structural variables shows strong promise for improving established hyperspectral-based tree species classifications; however, previous multi-sensoral projects were often limited by error resulting from seasonal or flight path differences. The National Aeronautics and Space Administration (NASA) Goddard's LiDAR, hyperspectral, and thermal imager (G-LiHT) is now providing co-registered data on experimental forests in the United States, which are associated with established ground truths from existing forest plots. Free, user-friendly machine learning applications like the Orange Data Mining Extension for Python recently simplified the process of combining datasets, handling variable redundancy and noise, and reducing dimensionality in remotely sensed datasets. Neural networks, CN2 rules, and support vector machine methods are used here to achieve a final classification accuracy of 67% for dominant tree species in experimental plots of Howland Experimental Forest, a mixed coniferous-deciduous forest with ten dominant tree species, and 59% for plots in Penobscot Experimental Forest, a mixed coniferous-deciduous forest with 15 dominant tree species. These accuracies are higher than those produced using LiDAR or hyperspectral datasets separately, suggesting that combined spectral and structural data have a greater richness of complementary information than either dataset alone. Using greatly simplified datasets created by our dimensionality reduction methodology, machine learner performance remains comparable or higher to that using the full dataset. Across forests, the identification of shared structural and spectral variables suggests that this methodology can successfully identify parameters with high explanatory power for differentiating among tree species, and opens the possibility of addressing large-scale forestry questions using optimized remote sensing workflows.

Remotely sensing the species of individual trees

“…Machine learning, a family of statistical techniques with origins in the field of artificial intelligence, is recognized as holding great promise for efficient processing of remote sensing data and modeling ecological systems (Olden et al 2008). For remotely sensing the species of individual trees, machine learning has the capacity of handling datasets with high dimensionality, reduce variable redundancy and noise, and simplify the process of combining datasets (Marrs and Ni-Meister 2019). Many previous studies have attempted to identify and map individual tree species based on the developments in remote sensing technology coupled with machine learning techniques (e.g.…”

“…Many previous studies have attempted to identify and map individual tree species based on the developments in remote sensing technology coupled with machine learning techniques (e.g. Dalponte et al 2019;Kamal and Phinn 2011;Lim et al 2019;Marrs and Ni-Meister 2019;Maxwell et al 2018). It is also increasingly easy to implement such techniques: free, user-friendly data mining and machine learning applications have already been made available in software such as Matlab, R, and Python.…”

“…A sample workflow for comparing machine learning methods for tree species classification is shown in Fig. 6.3 (Marrs and Ni-Meister 2019). This thesis tested several machine learning algorithms for tree species classification.…”

“…Traditionally, the occurrence of tree species was measured by field sampling, which is accurate but time-consuming and not feasible across large areas. Over the last four decades, advances in remote sensing technologies and machine learning methods have enabled the mapping of tree species from various sensor types (Marrs and Ni-Meister 2019). Hyperspectral sensors and Light Detection and Ranging (LiDAR) system are the most common sources of remotely sensed data used for the classification of tree species (Fassnacht et al 2016).…”

“…Sample workflow for comparing machine learning methods for tree species classification(Marrs and Ni-Meister 2019).…”