Object-Based Multigrained Cascade Forest Method for Wetland Classification Using Sentinel-2 and Radarsat-2 Imagery

Abstract

The development of advanced and efficient methods for mapping and monitoring wetland regions is essential for wetland resources conservation, management, and sustainable development. Although remote sensing technology has been widely used for detecting wetlands information, it remains a challenge for wetlands classification due to the extremely complex spatial patterns and fuzzy boundaries. This study aims to implement a comprehensive and effective classification scheme for wetland land covers. To achieve this goal, a novel object-based multigrained cascade forest (OGCF) method with multisensor data (including Sentinel-2 and Radarsat-2 remote sensing imagery) was proposed to classify the wetlands and their adjacent land cover classes in the wetland National Natural Reserve. Moreover, a hybrid selection method (ReliefF-RF) was proposed to optimize the feature set in which the spectral and polarimetric decomposition features are contained. We obtained six spectral features from visible and shortwave infrared bands and 10 polarimetric decomposition features from the H/A/Alpha, Pauli, and Krogager decomposition methods. The experimental results showed that the OGCF method with multisource features for land cover classification in wetland regions achieved the overall accuracy and kappa coefficient of 88.20% and 0.86, respectively, which outperformed the support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and deep neural network (DNN). The accuracy of the wetland classes ranged from 75.00% to 97.53%. The proposed OGCF method exhibits a good application potential for wetland land cover classification. The classification scheme in this study will make a positive contribution to wetland inventory and monitoring and be able to provide technical support for protecting and developing natural resources.

Wet-GC: A Novel Multimodel Graph Convolutional Approach for Wetland Classification Using Sentinel-1 and 2 Imagery With Limited Training Samples

“…Since two different types of satellite datasets are used to investigate the proposed Wet-GC model, in order to maintain the integrity and provide a logical comparison, these datasets are stacked and utilized for the rest of the algorithms employed here. For comparison purposes and to evaluate the efficiency of the Wet-GC, several models, including Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGB), and ResNet50 [64] were selected as efficient classifiers for wetland classification, as reported in [29], [34], [65], [66]. Based on experience reported in [3], [67], and trial and error, the optimum values for the parameters of RF, SVM, and XGB classifiers are defined and presented in Table VΙ.…”

Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer

“…Tian et al [16] used random forest to classify the vegetation of wetlands in arid areas of Xinjiang. L. F. Ruiz et al [17][18][19][20][21] used Sentinel-1 images to classify wetland types.…”

Wetland Mapping in Great Lakes Using Sentinel-1/2 Time-Series Imagery and DEM Data in Google Earth Engine

“…For all three groups of classification approaches, the spatial resolution of the satellite imagery, number of spectral bands, repetition time of the RS datasets, and complexity of the study area have direct effects on the precision of the final classified wetlands [11]. Overall, it has been frequently reported that using object-based classification techniques improves the accuracy of the classified map, particularly when using high-resolution RS datasets [8,12,[17][18][19].…”