Universiti Teknologi Malaysia Institutional Repository

Shallow landslide prediction using a novel hybrid functional machine learning algorithm

Dieu, Tien Bui and Shahabi, Himan and Omidvar, Ebrahim and Shirzadi, Ataollah and Geertsema, Marten and Clague, John J. and Khosravi, Khabat and Pradhan, Biswajeet and Pham, Binh Thai and Chapi, Kamran and Barati, Zahra and Ahmad, Baharin and Rahmani, Hosein and Gróf, Gyula and Lee, Saro (2019) Shallow landslide prediction using a novel hybrid functional machine learning algorithm. Remote Sensing, 11 (8). pp. 1-22.


Official URL: http://dx.doi.org/10.3390/rs11080952


Coastal wetland mapping plays an essential role in monitoring climate change, the hydrological cycle, and water resources. In this study, a novel classification framework based on the gravitational optimized multilayer perceptron classifier and extended multi-attribute profiles (EMAPs) is presented for coastal wetland mapping using Sentinel-2 multispectral instrument (MSI) imagery. In the proposed method, the morphological attribute profiles (APs) are firstly extracted using four attribute filters based on the characteristics of wetlands in each band from Sentinel-2 imagery. These APs form a set of EMAPs which comprehensively represent the irregular wetland objects in multiscale and multilevel. The EMAPs and original spectral features are then classified with a new multilayer perceptron (MLP) classifier whose parameters are optimized by a stability-constrained adaptive alpha for a gravitational search algorithm. The performance of the proposed method was investigated using Sentinel-2 MSI images of two coastal wetlands, i.e., the Jiaozhou Bay and the Yellow River Delta in Shandong province of eastern China. Comparisons with four other classifiers through visual inspection and quantitative evaluation verified the superiority of the proposed method. Furthermore, the effectiveness of different APs in EMAPs were also validated. By combining the developed EMAPs features and novel MLP classifier, complicated wetland types with high within-class variability and low between-class disparity were effectively discriminated. The superior performance of the proposed framework makes it available and preferable for the mapping of complicated coastal wetlands using Sentinel-2 data and other similar optical imagery.

Item Type:Article
Uncontrolled Keywords:morphological attribute profiles, multilayer perceptron, gravitational search algorithm
Subjects:T Technology > TH Building construction > TH434-437 Quantity surveying
Divisions:Built Environment
ID Code:88649
Deposited By: Yanti Mohd Shah
Deposited On:22 Feb 2021 14:00
Last Modified:22 Feb 2021 14:00

Repository Staff Only: item control page