Review of studies on tree species classification from remotely sensed data

By Fabian Ewald Fassnacht, Hooman Latifi, K. Stereńczak, A. Modzelewska, Michael Andrew Lefsky, Lars T. Waser, Christoph Straub, Aniruddha Ghosh. 2016

957 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/d349c5e2ea9fe157821805809d1044d414402c06

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecological Modeling

1. Lars T. Waser
2. Achilleas Psomas
3. Yadvinder S. Malhi

In Ecology

1. Mohammadreza Sheykhmousa
2. Misganu Debella-Gilo
3. Mathias I. Disney
4. Saeid Homayouni
5. Bogdan Zagajewski
6. Masoud MahdianPari
7. Pedram Ghamisi
8. Lars T. Waser

In Environmental Engineering

1. Achilleas Psomas
2. Nataliia Rehush
3. Marius Rüetschi
4. Lars T. Waser
5. Kim Calders
6. Mathias I. Disney
7. Mohammadreza Sheykhmousa
8. Saeid Homayouni

Citations in the corpus

• Tree species classification using structural features derived from terrestrial laser scanning (2020, background): “(2014), systematically describe and examine the traits that drive the observed variance in the remote sensing signal and thereby enable or hamper species classification (Fassnacht et al., 2016).”
• Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, background): “[53] summarized the significant trends in RS techniques for the classification of tree species and discussed the effectiveness of different sensors and algorithms for this application.”
• Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images (2017, background): “Moreover, such MNF datasets can and will be different from each other (both in terms of quality and features present in each MNF band) requiring additional preprocessing before the classification process (Fassnacht et al., 2016).”
• Mapping dominant leaf type based on combined Sentinel-1/-2 data – Challenges for mountainous countries (2021, methodology): “Based on a previous countrywide mapping approach (Waser et al., 2017) and tree species classification studies (Waser et al., 2014; Fassnacht et al., 2016), we applied the three vegetation indices GEMI, NDVI and MSAVI2, which substantially contributed (>50% besides the NIR and Red-Edge bands) to the…”
• National mapping and estimation of forest area by dominant tree species using Sentinel-2 data (2020, methodology): “Mapping tree species at a national level can nonetheless be a daunting task and most studies have been carried out under optimized conditions, i.e. case studies, rather than countrywide (Fassnacht et al. 2016, Waser et al. 2017).”