[ESIP-all] New article in Remote Sensing that may be of interest
DWright at esri.com
Thu Sep 6 15:52:08 EDT 2018
Happy to share this open-access journal article in Remote Sensing that may be of interest
Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.mdpi.com_2072-2D4292_10_9_1419_htm&d=DwIGaQ&c=n6-cguzQvX_tUIrZOS_4Og&r=z_UkiNdaPPnn6f_5YCcwk8pcqAmUKyJq-jppGhCSDi8&m=Itmv7omeEKvunBAhTaphPpu9Ad4Yqyo47HNc-Vvv1AU&s=vghAip6D6jl9ysNWejq5PPJktWjSzOcNf0-ZJ9_3zS4&e=>
Mathias Wessel , Melanie Brandmeier and Dirk Tiede
We use freely available Sentinel-2 data and forest inventory data to evaluate the potential of different machine-learning approaches to classify tree species in two forest regions in Bavaria, Germany. Atmospheric correction was applied to the level 1C data, resulting in true surface reflectance or bottom of atmosphere (BOA) output. We developed a semiautomatic workflow for the classification of deciduous (mainly spruce trees), beech and oak trees by evaluating different classification algorithms (object- and pixel-based) in an architecture optimized for distributed processing. A hierarchical approach was used to evaluate different band combinations and algorithms (Support Vector Machines (SVM) and Random Forest (RF)) for the separation of broad-leaved vs. coniferous trees. The Ebersberger forest was the main project region and the Freisinger forest was used in a transferability study. Accuracy assessment and training of the algorithms was based on inventory data, validation was conducted using an independent dataset. A confusion matrix, with User´s and Producer´s Accuracies, as well as Overall Accuracies, was created for all analyses. In total, we tested 16 different classification setups for coniferous vs. broad-leaved trees, achieving the best performance of 97% for an object-based multitemporal SVM approach using only band 8 from three scenes (May, August and September). For the separation of beech and oak trees we evaluated 54 different setups, the best result achieved an accuracy of 91% for an object-based, SVM, multitemporal approach using bands 8, 2 and 3 of the May scene for segmentation and all principal components of the August scene for classification. The transferability of the model was tested for the Freisinger forest and showed similar results. This project points out that Sentinel-2 had only marginally worse results than comparable commercial high-resolution satellite sensors and is well-suited for forest analysis on a tree-stand level.
Support Vector Machines; Random Forest; forest classification; GIS; remote sensing
Dawn Wright, Ph.D., GISP | Chief Scientist
Esri | 380 New York St | Redlands, CA 92373 | USA
T 909 793 2853 x2182 | M 909 362 6817 | dwright at esri.com | esri.com
esriurl.com/dawn | @deepseadawn
THE SCIENCE OF WHERE ®
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the ESIP-all