In constructing models for predicting soil organic matter (SOM) by using visible and near-infrared (vis–NIR) spectroscopy, the selection of representative calibration samples is decisive. Few researchers have studied the inclusion of spectral pretreatments in the sample selection strategy. We collected 108 soil samples and applied six commonly used spectral pretreatments to preprocess soil spectra, namely, Savitzky–Golay (SG) smoothing, first derivative (FD), logarithmic function log(1/R), mean centering (MC), standard normal variate (SNV), and multiplicative scatter correction (MSC). Then, the Kennard–Stone (KS) strategy was used to select calibration samples based on the pretreated spectra, and the size of the calibration set varied from 10 samples to 86 samples (80% of the total samples). These calibration sets were employed to construct partial least squares regression models (PLSR) to predict SOM, and the built models were validated by a set of 21 samples (20% of the total samples). The results showed that 64−78% of the calibration sets selected by the inclusion of pretreatment demonstrated significantly better performance of SOM estimation. The average improved residual predictive deviations (ΔRPD) were 0.06, 0.13, 0.19, and 0.13 for FD, log(1/R), MSC, and SNV, respectively. Thus, we concluded that spectral pretreatment improves the sample selection strategy, and the degree of its influence varies with the size of the calibration set and the type of pretreatment.

This study, with Yixing (Jiangsu Province, China) and Honghu (Hubei Province, China) as study areas, aimed to compare the successive projection algorithm (SPA) and the genetic algorithm (GA) in spectral feature selection for estimating soil organic carbon (SOC) contents with visible-near-infrared (Vis-NIR) reflectance spectroscopy and further to assess whether the spectral features selected from one site could be applied to another site. The SOC content and Vis-NIR reflectance spectra of soil samples were measured in the laboratory. Savitzky–Golay smoothing and log₁₀(1/R) (R is reflectance) were used for spectral preprocessing. The reflectance spectra were resampled using different spacing intervals ranging from 2 to 10 nm. Then, SPA and GA were conducted for selecting the spectral features of SOC. Partial least square regression (PLSR) with full-spectrum PLSR and the spectral features selected by SPA (SPA-PLSR) and GA (GA-PLSR) were calibrated and validated using independent datasets, respectively. Moreover, the spectral features selected from one study area were applied to another area. Study results showed that, for the two study areas, the SPA-PLSR and GA-PLSR improved estimation accuracies and reduced spectral variables compared with the full spectrum PLSR in estimating SOC contents; GA-PLSR obtained better estimation results than SPA-PLSR, whereas SPA was simpler than GA, and the spectral features selected from Yixing could be well applied to Honghu, but not the reverse. These results indicated that the SPA and GA could reduce the spectral variables and improve the performance of PLSR model and that GA performed better than SPA in estimating SOC contents. However, SPA is simpler and time-saving compared with GA in selecting the spectral features of SOC. The spectral features selected from one dataset could be applied to a target dataset when the dataset contains sufficient information adequately describing the variability of samples of the target dataset.

Accurately and timely monitoring the spatial distribution and composition of mangrove species is critical for assessing mangroves’ health, dynamics, and biodiversity, as well as mangroves’ degradation and restoration. Recent advances in machine learning algorithms, coupled with spaceborne remote sensing technique, offer an unprecedented opportunity to map mangroves at species level with high resolution over large extents. However, a single data source or data type is insufficient to capture the complex features of mangrove species and cannot satisfy the need for fine species classification. Moreover, identifying and selecting effective features derived from integrated multisource data are essential for integrating high-dimensional features for mangrove species discrimination. In this study, we developed a novel framework for mangrove species classification using spectral, texture, and polarization information derived from 3-source spaceborne imagery: WorldView-2 (WV-2), OrbitaHyperSpectral (OHS), and Advanced Land Observing Satellite-2 (ALOS-2). A total of 151 remote sensing features were first extracted, and 18 schemes were designed. Then, a wrapper method by combining extreme gradient boosting with recursive feature elimination (XGBoost-RFE) was conducted to select the sensitive variables and determine the optical subset size of all features. Finally, an ensemble learning algorithm of XGBoost was applied to classify 6 mangrove species in the Zhanjiang Mangrove National Nature Reserve, China. Our results showed that combining multispectral, hyperspectral, and L-band synthetic aperture radar features yielded the best mangrove species classification results, with an overall accuracy of 94.02%, a quantity disagreement of 4.44%, and an allocation disagreement of 1.54%. In addition, this study demonstrated important application potential of the XGBoost classifier. The proposed framework could provide fine-scale data and conduce to mangroves’ conservation and restoration.