Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data
The availability of high-resolution laser scanning data and advanced machine learning algorithms has enabled an accurate potential rockfall source identification. However, the presence of other mass movements, such as landslides within the same region of interest, poses additional challenges to this...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Society of Remote Sensing
2019
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/82041/1/Rockfall%20source%20identification%20using%20a%20hybrid%20Gaussian%20mixture-ensemble%20machine%20learning%20model%20and%20LiDAR%20data.pdf |
| _version_ | 1796980993696989184 |
|---|---|
| author | Fanos, Ali Mutar Pradhan, Biswajeet Mansor, Shattri Md Yusoff, Zainuddin Abdullah, Ahmad Fikri Jung, Hyung Sup |
| author_facet | Fanos, Ali Mutar Pradhan, Biswajeet Mansor, Shattri Md Yusoff, Zainuddin Abdullah, Ahmad Fikri Jung, Hyung Sup |
| author_sort | Fanos, Ali Mutar |
| collection | UPM |
| description | The availability of high-resolution laser scanning data and advanced machine learning algorithms has enabled an accurate potential rockfall source identification. However, the presence of other mass movements, such as landslides within the same region of interest, poses additional challenges to this task. Thus, this research presents a method based on an integration of Gaussian mixture model (GMM) and ensemble artificial neural network (bagging ANN [BANN]) for automatic detection of potential rockfall sources at Kinta Valley area, Malaysia. The GMM was utilised to determine slope angle thresholds of various geomorphological units. Different algorithms (ANN, support vector machine [SVM] and k nearest neighbour [kNN]) were individually tested with various ensemble models (bagging, voting and boosting). Grid search method was adopted to optimise the hyperparameters of the investigated base models. The proposed model achieves excellent results with success and prediction accuracies at 95% and 94%, respectively. In addition, this technique has achieved excellent accuracies (ROC = 95%) over other methods used. Moreover, the proposed model has achieved the optimal prediction accuracies (92%) on the basis of testing data, thereby indicating that the model can be generalised and replicated in different regions, and the proposed method can be applied to various landslide studies. |
| first_indexed | 2024-03-06T10:31:13Z |
| format | Article |
| id | upm.eprints-82041 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T10:31:13Z |
| publishDate | 2019 |
| publisher | The Korean Society of Remote Sensing |
| record_format | dspace |
| spelling | upm.eprints-820412021-09-08T02:17:40Z http://psasir.upm.edu.my/id/eprint/82041/ Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data Fanos, Ali Mutar Pradhan, Biswajeet Mansor, Shattri Md Yusoff, Zainuddin Abdullah, Ahmad Fikri Jung, Hyung Sup The availability of high-resolution laser scanning data and advanced machine learning algorithms has enabled an accurate potential rockfall source identification. However, the presence of other mass movements, such as landslides within the same region of interest, poses additional challenges to this task. Thus, this research presents a method based on an integration of Gaussian mixture model (GMM) and ensemble artificial neural network (bagging ANN [BANN]) for automatic detection of potential rockfall sources at Kinta Valley area, Malaysia. The GMM was utilised to determine slope angle thresholds of various geomorphological units. Different algorithms (ANN, support vector machine [SVM] and k nearest neighbour [kNN]) were individually tested with various ensemble models (bagging, voting and boosting). Grid search method was adopted to optimise the hyperparameters of the investigated base models. The proposed model achieves excellent results with success and prediction accuracies at 95% and 94%, respectively. In addition, this technique has achieved excellent accuracies (ROC = 95%) over other methods used. Moreover, the proposed model has achieved the optimal prediction accuracies (92%) on the basis of testing data, thereby indicating that the model can be generalised and replicated in different regions, and the proposed method can be applied to various landslide studies. The Korean Society of Remote Sensing 2019 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/82041/1/Rockfall%20source%20identification%20using%20a%20hybrid%20Gaussian%20mixture-ensemble%20machine%20learning%20model%20and%20LiDAR%20data.pdf Fanos, Ali Mutar and Pradhan, Biswajeet and Mansor, Shattri and Md Yusoff, Zainuddin and Abdullah, Ahmad Fikri and Jung, Hyung Sup (2019) Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data. Korean Journal of Remote Sensing, 35 (1). pp. 93-115. ISSN 1225-6161; ESSN: 2287-9307 https://www.koreascience.or.kr/article/JAKO201909242559364.page 10.7780/kjrs.2019.35.1.7 |
| spellingShingle | Fanos, Ali Mutar Pradhan, Biswajeet Mansor, Shattri Md Yusoff, Zainuddin Abdullah, Ahmad Fikri Jung, Hyung Sup Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data |
| title | Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data |
| title_full | Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data |
| title_fullStr | Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data |
| title_full_unstemmed | Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data |
| title_short | Rockfall source identification using a hybrid Gaussian mixture-ensemble machine learning model and LiDAR data |
| title_sort | rockfall source identification using a hybrid gaussian mixture ensemble machine learning model and lidar data |
| url | http://psasir.upm.edu.my/id/eprint/82041/1/Rockfall%20source%20identification%20using%20a%20hybrid%20Gaussian%20mixture-ensemble%20machine%20learning%20model%20and%20LiDAR%20data.pdf |
| work_keys_str_mv | AT fanosalimutar rockfallsourceidentificationusingahybridgaussianmixtureensemblemachinelearningmodelandlidardata AT pradhanbiswajeet rockfallsourceidentificationusingahybridgaussianmixtureensemblemachinelearningmodelandlidardata AT mansorshattri rockfallsourceidentificationusingahybridgaussianmixtureensemblemachinelearningmodelandlidardata AT mdyusoffzainuddin rockfallsourceidentificationusingahybridgaussianmixtureensemblemachinelearningmodelandlidardata AT abdullahahmadfikri rockfallsourceidentificationusingahybridgaussianmixtureensemblemachinelearningmodelandlidardata AT junghyungsup rockfallsourceidentificationusingahybridgaussianmixtureensemblemachinelearningmodelandlidardata |