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 consumin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/7/7/730 |
| _version_ | 1819208288307249152 |
|---|---|
| author | Mustafa Ridha Mezaal Biswajeet Pradhan Maher Ibrahim Sameen Helmi Zulhaidi Mohd Shafri Zainuddin Md Yusoff |
| author_facet | Mustafa Ridha Mezaal Biswajeet Pradhan Maher Ibrahim Sameen Helmi Zulhaidi Mohd Shafri Zainuddin Md Yusoff |
| author_sort | Mustafa Ridha Mezaal |
| collection | DOAJ |
| description | 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 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. |
| first_indexed | 2024-12-23T05:37:00Z |
| format | Article |
| id | doaj.art-16c951c2bd4e41ac98e0c5a9d44baae5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-23T05:37:00Z |
| publishDate | 2017-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-16c951c2bd4e41ac98e0c5a9d44baae52022-12-21T17:58:18ZengMDPI AGApplied Sciences2076-34172017-07-017773010.3390/app7070730app7070730Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning DataMustafa Ridha Mezaal0Biswajeet Pradhan1Maher Ibrahim Sameen2Helmi Zulhaidi Mohd Shafri3Zainuddin Md Yusoff4Department of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaAn 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 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.https://www.mdpi.com/2076-3417/7/7/730landslide detectionLiDARrecurrent neural networks (RNN)multi‐layer perceptron neural networks (MLP‐NN)GISremote sensing |
| spellingShingle | Mustafa Ridha Mezaal Biswajeet Pradhan Maher Ibrahim Sameen Helmi Zulhaidi Mohd Shafri Zainuddin Md Yusoff Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data Applied Sciences landslide detection LiDAR recurrent neural networks (RNN) multi‐layer perceptron neural networks (MLP‐NN) GIS remote sensing |
| title | Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data |
| title_full | Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data |
| title_fullStr | Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data |
| title_full_unstemmed | Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data |
| title_short | Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data |
| title_sort | optimized neural architecture for automatic landslide detection from high resolution airborne laser scanning data |
| topic | landslide detection LiDAR recurrent neural networks (RNN) multi‐layer perceptron neural networks (MLP‐NN) GIS remote sensing |
| url | https://www.mdpi.com/2076-3417/7/7/730 |
| work_keys_str_mv | AT mustafaridhamezaal optimizedneuralarchitectureforautomaticlandslidedetectionfromhighresolutionairbornelaserscanningdata AT biswajeetpradhan optimizedneuralarchitectureforautomaticlandslidedetectionfromhighresolutionairbornelaserscanningdata AT maheribrahimsameen optimizedneuralarchitectureforautomaticlandslidedetectionfromhighresolutionairbornelaserscanningdata AT helmizulhaidimohdshafri optimizedneuralarchitectureforautomaticlandslidedetectionfromhighresolutionairbornelaserscanningdata AT zainuddinmdyusoff optimizedneuralarchitectureforautomaticlandslidedetectionfromhighresolutionairbornelaserscanningdata |