Criteria Comparison for Classifying Peatland Vegetation Types Using In Situ Hyperspectral Measurements

Abstract

This study aims to evaluate three classes of methods to discriminate between 13 peatland vegetation types using reflectance data. These vegetation types were empirically defined according to their composition, strata and biodiversity richness. On one hand, it is assumed that the same vegetation type spectral signatures have similarities. Consequently, they can be compared to a reference spectral database. To catch those similarities, several similarities criteria (related to distances (Euclidean distance, Manhattan distance, Canberra distance) or spectral shapes (Spectral Angle Mapper) or probabilistic behaviour (Spectral Information Divergence)) and several mathematical transformations of spectral signatures enhancing absorption features (such as the first derivative or the second derivative, the normalized spectral signature, the continuum removal, the continuum removal derivative reflectance, the log transformation) were investigated. Furthermore, those similarity measures were applied on spectral ranges which characterize specific biophysical properties. On the other hand, we suppose that specific biophysical properties/components may help to discriminate between vegetation types applying supervised classification such as Random Forest (RF), Support Vector Machines (SVM), Regularized Logistic Regression (RLR), Partial Least Squares-Discriminant Analysis (PLS-DA). Biophysical components can be used in a local way considering vegetation spectral indices or in a global way considering spectral ranges and transformed spectral signatures, as explained above. RLR classifier applied on spectral vegetation indices (training size = 25%) was able to achieve 77.21% overall accuracy in discriminating peatland vegetation types. It was also able to discriminate between 83.95% vegetation types considering specific spectral range [350-1350 nm], first derivative of spectral signatures and training size = 25%. Conversely, similarity criterion was able to achieve 81.70% overall accuracy using the Canberra distance computed on the full spectral range [350-2500 nm]. The results of this study suggest that RLR classifier and similarity criteria are promising to map the different vegetation types with high ecological values despite vegetation heterogeneity and mixture.

Detection and discrimination of various oil-contaminated soils using vegetation reflectance

“…The selected VI were finally tested to discriminate among treatments using L 2 -Regularized Logistic Regression (RLR), also known as Ridge regression (Friedman & Popescu 2004, Hoerl & Kennard 1970. RLR has been widely used for classification purposes in various domains including remote sensing (Tuia et al 2016, Zhang et al 2015, and revealed to be efficient when applied on vegetation (Erudel et al 2017). We only trained the RLR classifier at leaf scale to assess the robustness of VI at higher acquisition scales.…”

Application of PROSPECT for estimating total petroleum hydrocarbons in contaminated soils from leaf optical properties

“…In order to assess the accuracy of our approach, the results were compared to those obtained with approaches directly linking TPH concentrations to leaf reflectance in the VIS, including pigmentrelated vegetation indices (listed in [65]) and partial least square regression (PLSR) with reflectance transformation (derivatives, continuum removal, etc.) [12,27].…”

Toward Quantifying Oil Contamination in Vegetated Areas Using Very High Spatial and Spectral Resolution Imagery

“…This provided a 1 m resampled reflectance image with 409 spectral bands covering the reflective domain (400-2500 nm). Because of the low signal-to-noise ratio (SNR), we did not conserve the bands with atmospheric transmission below 80%, as described in [49]. A Savitzky-Golay smoothing filter [50] was applied to improve the SNR at the remaining bands, and the final 1 m georeferenced reflectance image was used for calibrating and validating the methods of detection and quantification described hereafter.…”

“…The RLR classifier was fitted on the training set and applied to the test set. Predictions made on the test set were evaluated using the overall accuracy (OA), Cohen's kappa coefficient, and confusion matrices [49,53,54]. The method was then validated on the other contaminated and control sites (n = 4 and 5 sites, respectively, Table 1).…”