Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data
An accurate inventory map is a prerequisite for the analysis of landslide susceptibility, hazard, and risk. Field survey, optical remote sensing, and synthetic aperture radar techniques are traditional techniques for landslide detection in tropical regions. However, such techniques are time consuming and costly. In addition, the dense vegetation of tropical forests complicates the generation of an accurate landslide inventory map for these regions. Given its ability to penetrate vegetation
... ate vegetation cover, high-resolution airborne light detection and ranging (LiDAR) has been used to generate accurate landslide maps. This study proposes the use of recurrent neural networks (RNN) and multi-layer perceptron neural networks (MLP-NN) in landscape detection. These efficient neural architectures require little or no prior knowledge compared with traditional classification methods. The proposed methods were tested in the Cameron Highlands, Malaysia. Segmentation parameters and feature selection were respectively optimized using a supervised approach and correlation-based feature selection. The hyper-parameters of network architecture were defined based on a systematic grid search. The accuracies of the RNN and MLP-NN models in the analysis area were 83.33% and 78.38%, respectively. The accuracies of the RNN and MLP-NN models in the test area were 81.11%, and 74.56%, respectively. These results indicated that the proposed models with optimized hyper-parameters produced the most accurate classification results. LiDAR-derived data, orthophotos, and textural features significantly affected the classification results. Therefore, the results indicated that the proposed methods have the potential to produce accurate and appropriate landslide inventory in tropical regions such as Malaysia. risk of earthquakes [1,2], as well as for examining distribution patterns and predicting the landscapes affected by landslide  . Mapping a landslide inventory in tropical areas is challenging because the dense vegetation cover in these regions obscures underlying landforms  . Moreover, the majority of available conventional landslide detection techniques are not rapid and accurate enough for inventory mapping given the rapid vegetation growth in tropical regions. Therefore, inventory mapping requires the use of more rapid and accurate techniques, such as light detection and ranging (LiDAR)  , which uses active laser transmitters and receivers to acquire elevation data. In addition, LiDAR has the unique capability to penetrate densely vegetated areas  and provide detailed information on terrains with high point density. Moreover, it depicts ground surface features and provides useful information on topographical features in areas where landslide locations are obscured by vegetation cover [6, 7] . Numerous studies have applied a multiresolution segmentation algorithm for the remote sensing of land features  . This algorithm requires the identification of three parameters (i.e., scale, shape, and compactness); the values of these parameters can be determined using the traditional trial-and-error method, which is very time consuming and laborious  . Moreover, using the algorithm to delineate the boundary of an object at different scales remains challenging  . Thus, optimal parameters for segmentation should be identified via semiautomatic and automatic approaches    . The automatic selection of segmentation parameters requires the use of the advanced supervised approach presented in  . Processing a large number of irrelevant features causes overfitting  . By contrast, the best classification results are obtained by selecting the most relevant feature  . Landslide identifcation in a particular area can be improved by selecting the most significant feature [15, 16] . As shown in , selecting the most significant feature facilitates the differentiation of landslides from non-landslides. Accuracy can be improved by decreasing the number of features, as recommended in  . The efficiency of feature selection techniques for landslide detection has been proven in    . The neural network (NN) is effective in remote sensing applications  , particularly in solving different image classification problems  specified by nonlinear mathematical fitting for function approximation. NN architectures are classified into the recurrent neural network (RNN), back-propagation neural network, probability neural network, and multilayer perceptron neural network (MLP-NN). NN-based classifiers can adapt to different types of data and inputs, and can overcome the issue of mixed pixels by providing fuzzy output and fit with multiple images [23, 24] . These classifiers include parallel computation, which is superior to statistical classification approaches because it is non-parametric and does not require the prior knowledge of a distribution model for input data  . Moreover, NN-based classifiers can evaluate non-linear relationships between the input data and desired outputs and are distinguished by their fast generalization capability  . NN-based classifiers have been successfully in function approximation, prediction, pattern recognition, landslide detection, image classification, automatic control, and landslide susceptibility       . Authors of  found that MLP-NN can be effectively applied in landslide detection using multi-source data. The RNN model can effectively predict landslide displacement  . The above neural architecture techniques have not been extensively used for landslide detection using only LiDAR data. This research gap urged us to apply the RNN and MLP-NN models in landslide detection based on very high-resolution LiDAR data. To achieve this objective, we optimized multiresolution segmentation parameters via a supervised approach. Using the correlation-based feature selection (CFS) algorithm, we selected the most significant feature from high-resolution airborne laser scanning data. Study Area This study was performed in a small section of the Cameron Highlands, which is notorious for its frequent occurrence of landslides. The study area covers an area of 26.7 km 2 . It is located on northern peninsular Malaysia within the zone comprising latitudes 4 • 26 3 to 4 • 26 18 and longitudes 101 • 23 48 to 101 • 24 4 (Figure 1 ). The annual average rainfall and temperature in this region are Appl. Sci. 2017, 7, 730 3 of 20 approximately 2660 mm and 24/14 • C (daytime/nighttime temperatures), respectively. Approximately 80% of its area is forested with a flat (0 • ) to hilly (80 • ) land form. Appl. Sci. 2017, 7, 730 3 of 20 Two sites were selected to implement and test the proposed models ( Figure 1 ). All the prerequisite considerations were taken in to account during test site selection to avoid missing any land cover classes. To obtain an accurate map of the analysis and test sites, the training sample size was measured via the stratified random sample method.