Schweiger Anna Katharina
Tree Species Classification from AVIRIS-NG Hyperspectral Imagery using Convolutional Neural Networks
Project Number: Parcs Data Center: 53850, 4D: CH-7524
Project Type: |
Master |
Project Duration: |
01/12/2022 - 01/05/2022 project completed |
Funding Source: |
other , |
Leading Institution: |
Universität Zürich |
Project Leader: |
Dr. Anna Katharina Schweiger Postdoc Remote Sensing Geographisches Institut - Remote Sensing Lab. Universität Zürich Winterthurerstr. 190 - Irchel 8057 Zürich Phone: ; +41 (0) 44 635 51 61 FAX: +41 (0) 44 635 68 48 e-Mail: anna.k.schweiger(at)gmail.com http://www.geo.uzh.ch/rsl/ |
Research Areas:
Disciplines:
Abstract:
This study focuses on the automatic classification of tree species using a three-dimensional
convolutional neural network (CNN) based on field-sampled ground reference data, a LiDAR point
cloud and AVIRIS-NG airborne hyperspectral remote sensing imagery with 2 m spatial resolution
acquired on 14 June 2021. I created a tree species map for my 10.4 km2 study area which is located
in the Jurapark Aargau, a Swiss regional park of national interest. I collected ground reference data
for six major tree species present in the study area (Quercus robur, Fagus sylvatica, Fraxinus
excelsior, Pinus sylvestris, Tilia platyphyllos, total n = 331). To match the sampled ground reference
to the AVIRIS-NG 425 band hyperspectral imagery, I delineated individual tree crowns (ITCs) from
a canopy height model (CHM) based on LiDAR point cloud data. After matching the ground
reference data to the hyperspectral imagery, I split the extracted image patches to training,
validation, and testing subsets. The amount of training, validation and testing data was increased by
applying image augmentation through rotating, flipping, and changing the brightness of the original
input data. The classifier is a CNN trained on the first 32 principal components (PC’s) extracted
from AVIRIS-NG data. The CNN uses image patches of 5 ? 5 pixels and consists of two
convolutional layers and two fully connected layers. The latter of which is responsible for the final
classification using the softmax activation function. The results show that the CNN classifier
outperforms comparable conventional classification methods. The CNN model is able to predict the
correct tree species with an overall accuracy of 70% and an average F1-score of 0.67. A random
forest classifier reached an overall accuracy of 67% and an average F1-score of 0.61 while a
support-vector machine classified the tree species with an overall accuracy of 66% and an average
F1-score of 0.62. This work highlights that CNNs based on imaging spectroscopy data can produce
highly accurate high resolution tree species distribution maps based on a relatively small set of
training data thanks to the high dimensionality of hyperspectral images and the ability of CNNs to
utilize spatial and spectral features of the data. These maps provide valuable input for modelling
the distributions of other plant and animal species and ecosystem services. In addition, this work
illustrates the importance of direct collaboration with environmental practitioners to ensure user
needs are met. This aspect will be evaluated further in future work by assessing how these products
are used by environmental practitioners and as input for modelling purposes.
Publications:
Zehnder, B. 2022. Tree Species Classification from AVIRIS-NG Hyperspectral Imagery using Convolutional Neural Networks. Master Thesis. Universität Zürich.
pdf Masterorarbeit
Last update: 1/23/24
Source of data: ProClim- Research InfoSystem (1993-2024)
Update the data of project: CH-7524
Go Back