Abstract
In this paper a neural network is used to perform a mapping between Synthetic Aperture Radar (SAR) backscatter information and LiDAR measurements, and the performance of the neural network model is evaluated against that of a multiple linear regression model. Our aim is to find a relationship between SAR backscatter information and the LiDAR tree volume measurements on a number of land uses in South Africa's Kruger National Park, using a linear as well as a non-linear model. We also seek to find the optimal grid cell size as well as the best combination of SAR polarisation- and decomposition parameters. Our findings suggest that there exists a linear or at least a near-linear relationship between the SAR backscatter information and the LiDAR measurements in South African savannas and that the addition of polarisation- and decomposition parameters to the input of the models aid in improving the Root Mean Squared Error (RMSE) performance.
| Original language | English (US) |
|---|---|
| Title of host publication | 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings |
| Pages | 1934-1937 |
| Number of pages | 4 |
| DOIs | |
| State | Published - Nov 16 2011 |
| Externally published | Yes |
| Event | 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Vancouver, BC, Canada Duration: Jul 24 2011 → Jul 29 2011 |
Publication series
| Name | International Geoscience and Remote Sensing Symposium (IGARSS) |
|---|
Other
| Other | 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 |
|---|---|
| Country | Canada |
| City | Vancouver, BC |
| Period | 7/24/11 → 7/29/11 |
Fingerprint
Keywords
- LiDAR
- Linear regression
- mapping
- Neural network
- RMSE
- Synthetic Aperture Radar
ASJC Scopus subject areas
- Computer Science Applications
- Earth and Planetary Sciences(all)
Cite this
SAR-to-LiDAR mapping for tree volume prediction in the Kruger National Park. / Myburgh, H. C.; Olivier, J. C.; Mathieu, R.; Wessels, K.; Leblon, B.; Asner, G.; Buckley, J.
2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings. 2011. p. 1934-1937 6049504 (International Geoscience and Remote Sensing Symposium (IGARSS)).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - SAR-to-LiDAR mapping for tree volume prediction in the Kruger National Park
AU - Myburgh, H. C.
AU - Olivier, J. C.
AU - Mathieu, R.
AU - Wessels, K.
AU - Leblon, B.
AU - Asner, G.
AU - Buckley, J.
PY - 2011/11/16
Y1 - 2011/11/16
N2 - In this paper a neural network is used to perform a mapping between Synthetic Aperture Radar (SAR) backscatter information and LiDAR measurements, and the performance of the neural network model is evaluated against that of a multiple linear regression model. Our aim is to find a relationship between SAR backscatter information and the LiDAR tree volume measurements on a number of land uses in South Africa's Kruger National Park, using a linear as well as a non-linear model. We also seek to find the optimal grid cell size as well as the best combination of SAR polarisation- and decomposition parameters. Our findings suggest that there exists a linear or at least a near-linear relationship between the SAR backscatter information and the LiDAR measurements in South African savannas and that the addition of polarisation- and decomposition parameters to the input of the models aid in improving the Root Mean Squared Error (RMSE) performance.
AB - In this paper a neural network is used to perform a mapping between Synthetic Aperture Radar (SAR) backscatter information and LiDAR measurements, and the performance of the neural network model is evaluated against that of a multiple linear regression model. Our aim is to find a relationship between SAR backscatter information and the LiDAR tree volume measurements on a number of land uses in South Africa's Kruger National Park, using a linear as well as a non-linear model. We also seek to find the optimal grid cell size as well as the best combination of SAR polarisation- and decomposition parameters. Our findings suggest that there exists a linear or at least a near-linear relationship between the SAR backscatter information and the LiDAR measurements in South African savannas and that the addition of polarisation- and decomposition parameters to the input of the models aid in improving the Root Mean Squared Error (RMSE) performance.
KW - LiDAR
KW - Linear regression
KW - mapping
KW - Neural network
KW - RMSE
KW - Synthetic Aperture Radar
UR - http://www.scopus.com/inward/record.url?scp=80955122653&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80955122653&partnerID=8YFLogxK
U2 - 10.1109/IGARSS.2011.6049504
DO - 10.1109/IGARSS.2011.6049504
M3 - Conference contribution
AN - SCOPUS:80955122653
SN - 9781457710056
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 1934
EP - 1937
BT - 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings
ER -