In this study, we present a hyperspectral image classification method by combining spectral, spatial, and semantic information. The main steps of the proposed method are summarized as follows: First, principal component analysis transform is conducted on an original image to produce its extended morphological profile, Gabor features, and superpixel-based segmentation map. To model spatial information, the extended morphological profile and Gabor features are used to represent structure and texture features, respectively. Moreover, the mean filtering is performed within each superpixel to maintain the homogeneity of the spatial features. Then, the k-means clustering and the entropy rate superpixel segmentation are combined to produce semantic feature vectors by using a bag of visual-words model for each superpixel. Next, three kernel functions are constructed to describe the spectral, spatial, and semantic information, respectively. Finally, the composite kernel technique is used to fuse all the features into a multiple kernel function that is fed into a support vector machine classifier to produce a final classification map. Experiments demonstrate that the proposed method is superior to the most popular kernel-based classification methods in terms of both visual inspection and quantitative analysis, even if only very limited training samples are available.
4 August 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Ensemble learning methods have been widely used due to their remarkable generalized performance, but their potential in landslide spatial prediction application is not fully studied. To take full advantage of ensemble learning techniques, the classification and regression tree classifier and four tree-based ensemble classifiers of random forest, extremely randomized tree, gradient boosting decision trees and extreme gradient boosting decision trees are used in this study for landslide susceptibility assessment. Specifically, a stacking ensemble learning framework coupled with embedded feature selection is presented, consisting of multiple tree-based classifiers mentioned previously as base learners and logistic regression as a meta-learner in a two-layer structure. In the study area of Yongxin, China, 364 historical landslide locations were first randomly partitioned into a ratio of 7/3 for training and testing the model. Then, a spatial database of sixteen landslide causative factors were constructed for landslide prediction. Meanwhile, the relative importance of these factors were quantified by using the total number of feature splits and the average Gini index during the training process, and a novel embedded feature selection method was used in the base learner of the proposed framework to further improve computational efficiency and predictive performance by allowing each base learner to obtain its own optimal sub-feature space. Finally, different methods were assessed by using several evaluation criteria. Experimental results demonstrated that the proposed ensemble learning framework had the highest area under the curve value of 0.864, and it is more effective than the conventional tree-based classifiers and other ensemble learning methods.
8 November 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Many studies consider landslide susceptibility prediction as a binary classification problem when using machine learning methods, which requires both landslide and nonlandslide samples for modeling. Nevertheless, there are only landslide and unlabeled areas in the real world, and directly considering unlabeled areas as nonlandslide areas may cause bias and incorrect label assignment. In this article, we present a positive unlabeled learning method coupled with adaptive sampling and random forest (AdaPU-RF) to predict landslide susceptibility in the Three Gorges Reservoir area, China. This method can make full use of the landslide and nonlandslide information contained in unlabeled areas. Experimental results show that the AdaPU-RF method achieves desirable predication outcomes in terms of accuracy analysis, sensitivity analysis, and uncertainty analysis. Overall, the application of AdaPU-RF provides a new perspective for landslide susceptibility prediction, and can be recommended for other areas with similar geo-environmental conditions.
21 December 2023 in International Journal of Applied Earth Observation and Geoinformation