An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan
Abstract Background Landslide-affecting factors are uncorrelated or non-linearly correlated, limiting the predictive performance of traditional machine learning methods for landslide susceptibility assessment. Deep learning methods can take advantage of the high-level representation and reconstructi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-01-01
|
| Series: | Geoenvironmental Disasters |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40677-020-0143-7 |
| _version_ | 1818731924738277376 |
|---|---|
| author | Kounghoon Nam Fawu Wang |
| author_facet | Kounghoon Nam Fawu Wang |
| author_sort | Kounghoon Nam |
| collection | DOAJ |
| description | Abstract Background Landslide-affecting factors are uncorrelated or non-linearly correlated, limiting the predictive performance of traditional machine learning methods for landslide susceptibility assessment. Deep learning methods can take advantage of the high-level representation and reconstruction of information from landslide-affecting factors. In this paper, a novel deep learning-based algorithm that combine classifiers of both deep learning and machine learning is proposed for landslide susceptibility assessment. A stacked autoencoder (StAE) and a sparse autoencoder (SpAE) both consist of an input layer for raw data, hidden layer for feature extraction, and output layer for classification and prediction. As a study case, Oda City and Gotsu City in Shimane Prefecture, southwestern Japan, were used for susceptibility assessment and prediction of landslides triggered by extreme rainfall. Results The prediction performance was compared by analyzing real landslide and non-landslide data. The prediction performance of random forest (RF) was evaluated as better than that of a support vector machine (SVM) in traditional machine learning, so RF was combined with both StAE and SpAE. The results show that the prediction ratio of the combined classifiers was 93.2% for StAE combined with RF model and 92.5% for SpAE combined with RF model, which were higher than those of the SVM (87.4%), RF (89.7%), StAE (84.2%), and SpAE (88.2%). Conclusions This study provides an example of combined classifiers giving a better predictive ratio than a single classifier. The asymmetric and unsupervised autoencoder combined with RF can exploit optimal non-linear features from landslide-affecting factors successfully, outperforms some conventional machine learning methods, and is promising for landslide susceptibility assessment. |
| first_indexed | 2024-12-17T23:25:25Z |
| format | Article |
| id | doaj.art-87ae8b521da74432b7704408d4b4a9b4 |
| institution | Directory Open Access Journal |
| issn | 2197-8670 |
| language | English |
| last_indexed | 2024-12-17T23:25:25Z |
| publishDate | 2020-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Geoenvironmental Disasters |
| spelling | doaj.art-87ae8b521da74432b7704408d4b4a9b42022-12-21T21:28:47ZengSpringerOpenGeoenvironmental Disasters2197-86702020-01-017111610.1186/s40677-020-0143-7An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, JapanKounghoon Nam0Fawu Wang1Department of Earth Science, Shimane UniversityDepartment of Earth Science, Shimane UniversityAbstract Background Landslide-affecting factors are uncorrelated or non-linearly correlated, limiting the predictive performance of traditional machine learning methods for landslide susceptibility assessment. Deep learning methods can take advantage of the high-level representation and reconstruction of information from landslide-affecting factors. In this paper, a novel deep learning-based algorithm that combine classifiers of both deep learning and machine learning is proposed for landslide susceptibility assessment. A stacked autoencoder (StAE) and a sparse autoencoder (SpAE) both consist of an input layer for raw data, hidden layer for feature extraction, and output layer for classification and prediction. As a study case, Oda City and Gotsu City in Shimane Prefecture, southwestern Japan, were used for susceptibility assessment and prediction of landslides triggered by extreme rainfall. Results The prediction performance was compared by analyzing real landslide and non-landslide data. The prediction performance of random forest (RF) was evaluated as better than that of a support vector machine (SVM) in traditional machine learning, so RF was combined with both StAE and SpAE. The results show that the prediction ratio of the combined classifiers was 93.2% for StAE combined with RF model and 92.5% for SpAE combined with RF model, which were higher than those of the SVM (87.4%), RF (89.7%), StAE (84.2%), and SpAE (88.2%). Conclusions This study provides an example of combined classifiers giving a better predictive ratio than a single classifier. The asymmetric and unsupervised autoencoder combined with RF can exploit optimal non-linear features from landslide-affecting factors successfully, outperforms some conventional machine learning methods, and is promising for landslide susceptibility assessment.https://doi.org/10.1186/s40677-020-0143-7Stacked autoencoderSparse autoencoderSupport vector machineRandom forestLandslide susceptibility |
| spellingShingle | Kounghoon Nam Fawu Wang An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan Geoenvironmental Disasters Stacked autoencoder Sparse autoencoder Support vector machine Random forest Landslide susceptibility |
| title | An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan |
| title_full | An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan |
| title_fullStr | An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan |
| title_full_unstemmed | An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan |
| title_short | An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan |
| title_sort | extreme rainfall induced landslide susceptibility assessment using autoencoder combined with random forest in shimane prefecture japan |
| topic | Stacked autoencoder Sparse autoencoder Support vector machine Random forest Landslide susceptibility |
| url | https://doi.org/10.1186/s40677-020-0143-7 |
| work_keys_str_mv | AT kounghoonnam anextremerainfallinducedlandslidesusceptibilityassessmentusingautoencodercombinedwithrandomforestinshimaneprefecturejapan AT fawuwang anextremerainfallinducedlandslidesusceptibilityassessmentusingautoencodercombinedwithrandomforestinshimaneprefecturejapan AT kounghoonnam extremerainfallinducedlandslidesusceptibilityassessmentusingautoencodercombinedwithrandomforestinshimaneprefecturejapan AT fawuwang extremerainfallinducedlandslidesusceptibilityassessmentusingautoencodercombinedwithrandomforestinshimaneprefecturejapan |