Next Article in Journal
High Chlorophyll-a Areas along the Western Coast of South Sulawesi-Indonesia during the Rainy Season Revealed by Satellite Data
Next Article in Special Issue
Potential of Airborne LiDAR Derived Vegetation Structure for the Prediction of Animal Species Richness at Mount Kilimanjaro
Previous Article in Journal
Random Forest-Based Reconstruction and Application of the GRACE Terrestrial Water Storage Estimates for the Lancang-Mekong River Basin
Previous Article in Special Issue
Semi-Automatic Generation of Training Samples for Detecting Renewable Energy Plants in High-Resolution Aerial Images
Article

Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques?

1
GIScience Group, Department of Geography, Friedrich Schiller University Jena, Loebdergraben 32, 07743 Jena, Germany
2
NEIKER Tecnalia, 48160 Tecnalia, Spain
3
Department of Statistics, Ludwig-Maximilians-Universität München, Akademiestrasse 1/I, 80799 Munich, Germany
*
Author to whom correspondence should be addressed.
Academic Editor: Hanna Meyer
Remote Sens. 2021, 13(23), 4832; https://doi.org/10.3390/rs13234832
Received: 12 September 2021 / Revised: 15 November 2021 / Accepted: 23 November 2021 / Published: 28 November 2021
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
This study analyzed highly correlated, feature-rich datasets from hyperspectral remote sensing data using multiple statistical and machine-learning methods. The effect of filter-based feature selection methods on predictive performance was compared. In addition, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated. Defoliation of trees (%), derived from in situ measurements from fall 2016, was modeled as a function of reflectance. Variable importance was assessed using permutation-based feature importance. Overall, the support vector machine (SVM) outperformed other algorithms, such as random forest (RF), extreme gradient boosting (XGBoost), and lasso (L1) and ridge (L2) regressions by at least three percentage points. The combination of certain feature sets showed small increases in predictive performance, while no substantial differences between individual feature sets were observed. For some combinations of learners and feature sets, filter methods achieved better predictive performances than using no feature selection. Ensemble filters did not have a substantial impact on performance. The most important features were located around the red edge. Additional features in the near-infrared region (800–1000 nm) were also essential to achieve the overall best performances. Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies. Nevertheless, more training data and replication in similar benchmarking studies are needed to be able to generalize the results. View Full-Text
Keywords: hyperspectral imagery; forest health monitoring; machine learning; feature selection; model comparison hyperspectral imagery; forest health monitoring; machine learning; feature selection; model comparison
Show Figures

Graphical abstract

MDPI and ACS Style

Schratz, P.; Muenchow, J.; Iturritxa, E.; Cortés, J.; Bischl, B.; Brenning, A. Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques? Remote Sens. 2021, 13, 4832. https://doi.org/10.3390/rs13234832

AMA Style

Schratz P, Muenchow J, Iturritxa E, Cortés J, Bischl B, Brenning A. Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques? Remote Sensing. 2021; 13(23):4832. https://doi.org/10.3390/rs13234832

Chicago/Turabian Style

Schratz, Patrick, Jannes Muenchow, Eugenia Iturritxa, José Cortés, Bernd Bischl, and Alexander Brenning. 2021. "Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques?" Remote Sensing 13, no. 23: 4832. https://doi.org/10.3390/rs13234832

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop