Analysis of cross-validation methods for robust retrieval of biophysical parameters
DOI:
https://doi.org/10.4995/raet.2015.4153Keywords:
Hold-Out, k-fold, Cross-validation, MLRA, Gaussian Process Regression, Kernel Ridge RegressionAbstract
Non-parametric regression methods are powerful statistical methods to retrieve biophysical parameters from remote sensing measurements. However, their performance can be affected by what has been presented during the training phase. To ensure robust retrievals, various cross-validation sub-sampling methods are often used, which allow to evaluate the model with subsets of the field dataset. Here, two types of cross-validation techniques were analyzed in the development of non-parametric regression models: hold-out and k-fold. Selected non-parametric linear regression methods were least squares Linear Regression (LR) and Partial Least Squares Regression (PLSR), and nonlinear methods were Kernel Ridge Regression (KRR) and Gaussian Process Regression (GPR). Cross-validation results showed that LR performed most unstable, while KRR and GPR led to more robust results. This work recommends using a nonlinear regression algorithm (e.g., KRR, GPR) in combination with a k-fold cross-validation technique with k=10 to realize robust retrievals.Downloads
References
Arlot, S., Celisse, A. 2010. A Survey of Cross-validation Procedures for Model Selection. Statistics Surveys, 4, 40-79. http://dx.doi.org/10.1214/09-SS054
Bazi, Y., Alajlan, N., Melgani, F., AlHichri, H., Yager, R.R. 2014. Robust estimation of water chlorophyll concentrations with gaussian process regression and IOWA aggregation operators. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(7), 3019-3028. http://dx.doi. org/10.1109/JSTARS.2014.2327003
Delegido, J., Verrels, J., Rivera, J.P., Ruiz-Verdú, A., Moreno, J. 2015. Brown and green LAI mapping through spectral indices. International Journal of Applied Earth Observation and Geoinformation, 35, 350-358. http://dx.doi.org/10.1016/j. jag.2014.10.001
Guerschman, J.P., Scarth, P.F., McVicar, T.R., Renzullo, L.J., Malthus, T.J., Stewart, J.B., Rickards, J.E., Trevithick, R. 2015. Assessing the effects of site heterogeneity and soil properties when unmixing photosynthetic vegetation, non-photosynthetic vegetation and bare soil fractions from Landsat and MODIS data. Remote Sensing of Environment, 161, 12-26. http://dx.doi.org/10.1016/j.rse.2015.01.021
Hawkins, D.M., Basak, S.C., Mills, D. 2003. Assessing Model Fit by Cross-Validation. Journal of Chemical Information and Computer Sciences, 43(2), 579- 586. http://dx.doi.org/10.1021/ci025626i
Jung, Y., Hu, J. 2015. A k-fold averaging crossvalidation procedure. Journal of Nonparametric Statistics, 27(2), 167-179. http://dx.doi.org/10.1080/1048525 2.2015.1010532
Kozak, A., Kozak, R. 2003. Does cross validation provide additional information in the evaluation of regression models? Canadian Journal of Forest Research, 33(6), 976-987. http://dx.doi.org/10.1139/ x03-022
Lázaro-Gredilla, M., Verrelst, J., Camps-Valls, G. 2014. Retrieval of Biophysical Parameters With Heteroscedastic Gaussian Processes. IEEE Geoscience and Remote Sensing Letters, 11(4), 838- 842. http://dx.doi.org/10.1109/LGRS.2013.2279695
Rasmussen, C.E., Williams, C.K.I. 2006. Gaussian Processes for Machine Learning. The MIT Press, New York, US.
Rivera, J.P., Verrelst, J., Delegido, J., Veroustraete, F., Moreno, J. 2014a. On the Semi-Automatic Retrieval of Biophysical Parameters Based on Spectral Index Optimization. Remote Sensing, 6, 4927-4951. http:// dx.doi.org/10.3390/rs6064927
Rivera, J.P., Verrelst, J., Muñoz-Marí, J., Moreno, J., Camps-Valls, G. 2014b. Toward a Semiautomatic Machine Learning Retrieval of Biophysical Parameters. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7 (4), 1249-1259. http://dx.doi.org/10.1109/ JSTARS.2014.2298752
Shao, J. 1993. Linear Model Selection by CrossValidation. Journal of the American Statistical Association, 88(422), 486-494. http://dx.doi.org/ 10.1080/01621459.1993.10476299
Verrelst, J., Alonso, L., Camps-Valls, G. 2012. Retrieval of Vegetation Biophysical Parameters Using Gaussian Process Techniques. IEEE Transactions on Geoscience and Remote Sensing, 50(5), 1832-1843. http://dx.doi.org/10.1109/TGRS.2011.2168962
Verrelst, J., Rivera, J.P., Leonenko, G., Alonso, L., Moreno, J. 2014a. Optimizing LUT-Based RTM Inversion for Semiautomatic Mapping of Crop Biophysical Parameters from Sentinel-2 and -3 Data: Role of Cost Functions. IEEE Transactions on Geoscience and Remote Sensing, 52(1), 257-269. http://dx.doi.org/10.1109/TGRS.2013.2238242
Verrelst, J., Alonso, L., Rivera, J.P., Moreno, J., Camps-Valls, G. 2014b. Gaussian Process Retrieval of Chlorophyll Content from Imaging Spectroscopy Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2), 867-874. http://dx.doi.org/10.1109/ JSTARS.2012.2222356
Verrelst, J., Rivera, J.P., Moreno, J., Camps-Valls, G., 2014c. Gaussian Processes uncertainty estimates in experimental Sentinel-2 LAI and leaf Chlorofyll content retrieval. ISPRS Journal of Photogrammetry and Remote Sensing, 86, 157-167. http://dx.doi. org/10.1016/j.isprsjprs.2013.09.012
Verrelst, J., Camps-Valls, G., Muñoz-Marí, J., Rivera, J.P., Veroustraete, F., Clevers, J., Moreno, J. 2015. Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical attributes – A review. ISPRS Journal of Photogrammetry and Remote Sensing, 108, 273-290. http://dx.doi.org/10.1016/j. isprsjprs.2015.05.005
Wittenberghe, S.V., Verrelst, V., Rivera, J.P., Alonso, L., Moreno, J., Samson, R. 2014. Gaussian processes retrieval of leaf parameters from a multi-species reflectance, absorbance and fluorescence dataset. Journal of Photochemistry and Photobiology B: Biology, 134, 37-48. http://dx.doi.org/10.1016/j. jphotobiol.2014.03.010
Yang, Y. y Huang, S., 2014. Suitability of five cross validation methods for performance evaluation of nonlinear mixed-effecs forest models – a case study. Forestry, 87, 654-662. http://dx.doi.org/10.1093/ forestry/cpu025
Downloads
Published
Issue
Section
License
This journal is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International