Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning

Dudeni-Tlhone, NontembekoMutanga, ODebba, PraveshCho, Moses A2023-10-242023-10-242023-08Dudeni-Tlhone, N., Mutanga, O., Debba, P. & Cho, M.A. 2023. Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning. Remote Sensing, 15(17). http://hdl.handle.net/10204/131712072-4292https://doi.org/10.3390/rs15174117http://hdl.handle.net/10204/13171Hyperspectral sensors capture and compute spectral reflectance of objects over many wavelength bands, resulting in a high-dimensional space with enough information to differentiate between spectrally similar objects. Due to the curse of dimensionality, high spectral dimensionality can also be difficult to handle and analyse, demanding complex processing and the use of advanced analytical techniques. Moreover, when hyperspectral measurements are taken at different temporal frequencies, separation is likely to improve; however, additional complexities in modelling time variability concurrently with this high spectral dimensionality may be created. As a result, the applicability of ensemble-based techniques suitable for high-dimensional data is examined in this research, together with the statistical evaluation of time-induced variability, since spectral measurements of tree species were taken at different time periods. Classification errors for the stochastic gradient boosting (SGB) and random forest (RF) methods ranged between 5.6% and 13.5%, respectively. Differences in classification accuracy or errors were also accounted for in the assessment of the models, with up to 46% of variation in classification error due to the effect of time in the RF model, indicating that measurement time is important in improving discrimination between tree species. This is because optical leaf characteristics can vary during the course of the year due to seasonal effects, health status, or the developmental stage of a tree. Different spectral properties (assumed from relevant wavelength bands) were found to be key factors impacting the models’ discrimination performance at various measurement times.FulltextenClassification errorsGradient boostingMeasurement timeOptical leaf reflectance characteristicsRandom forestTemporal-hyperspectral data and seasonal variabilityTree-based classificationDistinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learningArticleDudeni-Tlhone, N., Mutanga, O., Debba, P., & Cho, M. A. (2023). Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning. Remote Sensing, 15(17), http://hdl.handle.net/10204/13171Dudeni-Tlhone, Nontembeko, O Mutanga, Pravesh Debba, and Moses A Cho "Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning." Remote Sensing, 15(17) (2023) http://hdl.handle.net/10204/13171Dudeni-Tlhone N, Mutanga O, Debba P, Cho MA. Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning. Remote Sensing, 15(17). 2023; http://hdl.handle.net/10204/13171.TY - Article AU - Dudeni-Tlhone, Nontembeko AU - Mutanga, O AU - Debba, Pravesh AU - Cho, Moses A AB - Hyperspectral sensors capture and compute spectral reflectance of objects over many wavelength bands, resulting in a high-dimensional space with enough information to differentiate between spectrally similar objects. Due to the curse of dimensionality, high spectral dimensionality can also be difficult to handle and analyse, demanding complex processing and the use of advanced analytical techniques. Moreover, when hyperspectral measurements are taken at different temporal frequencies, separation is likely to improve; however, additional complexities in modelling time variability concurrently with this high spectral dimensionality may be created. As a result, the applicability of ensemble-based techniques suitable for high-dimensional data is examined in this research, together with the statistical evaluation of time-induced variability, since spectral measurements of tree species were taken at different time periods. Classification errors for the stochastic gradient boosting (SGB) and random forest (RF) methods ranged between 5.6% and 13.5%, respectively. Differences in classification accuracy or errors were also accounted for in the assessment of the models, with up to 46% of variation in classification error due to the effect of time in the RF model, indicating that measurement time is important in improving discrimination between tree species. This is because optical leaf characteristics can vary during the course of the year due to seasonal effects, health status, or the developmental stage of a tree. Different spectral properties (assumed from relevant wavelength bands) were found to be key factors impacting the models’ discrimination performance at various measurement times. DA - 2023-08 DB - ResearchSpace DP - CSIR J1 - Remote Sensing, 15(17) KW - Classification errors KW - Gradient boosting KW - Measurement time KW - Optical leaf reflectance characteristics KW - Random forest KW - Temporal-hyperspectral data and seasonal variability KW - Tree-based classification LK - https://researchspace.csir.co.za PY - 2023 SM - 2072-4292 T1 - Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning TI - Distinguishing tree species from in situ hyperspectral and temporal measurements through ensemble statistical learning UR - http://hdl.handle.net/10204/13171 ER -27062