In our previous study (Heim et al., 2018), leaf spectral data was collected on a lemon myrtle (Backhousia citriodora) plantation in northern New South Wales, Australia 28.6911090 S, 124 153.295480 E, and were organized in a single csv
file.
Column 1: Type is a categorical variables referring to the spectral classes (“Healthy”, “Treated” and “Untreated”).
Column 2 and follwoing: X505-X2500 are the wavebands along the electromagnetic spectrum and have been recorded, using a field spectrometer, in spectral reflectance [%].
## Type X505 X515 X525 X535 X545 X555 X565
## 1 Healthy 6.24695 7.47541 8.76196 9.60083 10.41397 11.52191 12.96581
## 2 Healthy 6.02445 7.13753 8.42296 9.31252 10.17494 11.21573 12.56159
## 3 Healthy 3.74299 4.63272 6.33524 8.56322 10.76416 12.29122 12.07371
## 4 Healthy 5.18315 6.23946 8.53988 11.24664 13.43128 14.70756 14.08224
## 5 Healthy 4.32373 5.43988 6.51496 7.16402 7.80067 8.78375 10.21582
## 6 Healthy 6.27764 7.34788 8.36860 8.99552 9.74910 10.76764 12.21082
## X575
## 1 14.42017
## 2 13.84469
## 3 10.57803
## 4 12.16332
## 5 11.78936
## 6 13.92898
Please refer to our previous article (Heim et al., 2018a) for more information:
Heim, R. H., Wright, I. J., Chang, H. , Carnegie, A. J., Pegg, G. S., Lancaster, E. K., Falster, D. S. and Oldeland, J. (2018), Detecting myrtle rust (Austropuccinia psidii) on lemon myrtle trees using spectral signatures and machine learning. Plant Pathol, 67: 1114-1121. doi:10.1111/ppa.12830
Data can be downloaded from project GitHub repository
Copyright © 2018 René Hans-Jürgen Heim
contact: rene.heim@hdr.mq.edu.au