Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data
The increasing availability of Synthetic Aperture Radar (SAR) images facilitates the generation of rich Differential Interferometric SAR (DInSAR) data. Temporal analysis of DInSAR products, and in particular deformation Time Series (TS), enables advanced investigations for ground deformation identif...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3821 |
| _version_ | 1797412395949228032 |
|---|---|
| author | S. Mohammad Mirmazloumi Angel Fernandez Gambin Riccardo Palamà Michele Crosetto Yismaw Wassie José A. Navarro Anna Barra Oriol Monserrat |
| author_facet | S. Mohammad Mirmazloumi Angel Fernandez Gambin Riccardo Palamà Michele Crosetto Yismaw Wassie José A. Navarro Anna Barra Oriol Monserrat |
| author_sort | S. Mohammad Mirmazloumi |
| collection | DOAJ |
| description | The increasing availability of Synthetic Aperture Radar (SAR) images facilitates the generation of rich Differential Interferometric SAR (DInSAR) data. Temporal analysis of DInSAR products, and in particular deformation Time Series (TS), enables advanced investigations for ground deformation identification. Machine Learning algorithms offer efficient tools for classifying large volumes of data. In this study, we train supervised Machine Learning models using 5000 reference samples of three datasets to classify DInSAR TS in five deformation trends: Stable, Linear, Quadratic, Bilinear, and Phase Unwrapping Error. General statistics and advanced features are also computed from TS to assess the classification performance. The proposed methods reported accuracy values greater than 0.90, whereas the customized features significantly increased the performance. Besides, the importance of customized features was analysed in order to identify the most effective features in TS classification. The proposed models were also tested on 15000 unlabelled data and compared to a model-based method to validate their reliability. Random Forest and Extreme Gradient Boosting could accurately classify reference samples and positively assign correct labels to random samples. This study indicates the efficiency of Machine Learning models in the classification and management of DInSAR TSs, along with shortcomings of the proposed models in classification of nonmoving targets (i.e., false alarm rate) and a decreasing accuracy for shorter TS. |
| first_indexed | 2024-03-09T05:02:26Z |
| format | Article |
| id | doaj.art-c956768ce99d49b7822f130f0f3001be |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:02:26Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c956768ce99d49b7822f130f0f3001be2023-12-03T12:59:17ZengMDPI AGRemote Sensing2072-42922022-08-011415382110.3390/rs14153821Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR DataS. Mohammad Mirmazloumi0Angel Fernandez Gambin1Riccardo Palamà2Michele Crosetto3Yismaw Wassie4José A. Navarro5Anna Barra6Oriol Monserrat7Geomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainArtificial Intelligence Lab, Oslo Metropolitan University, 0130 Oslo, NorwayGeomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainGeomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainGeomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainGeomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainGeomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainGeomatics Research Unit, Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Av. Gauss 7, 08860 Castelldefels, Barcelona, SpainThe increasing availability of Synthetic Aperture Radar (SAR) images facilitates the generation of rich Differential Interferometric SAR (DInSAR) data. Temporal analysis of DInSAR products, and in particular deformation Time Series (TS), enables advanced investigations for ground deformation identification. Machine Learning algorithms offer efficient tools for classifying large volumes of data. In this study, we train supervised Machine Learning models using 5000 reference samples of three datasets to classify DInSAR TS in five deformation trends: Stable, Linear, Quadratic, Bilinear, and Phase Unwrapping Error. General statistics and advanced features are also computed from TS to assess the classification performance. The proposed methods reported accuracy values greater than 0.90, whereas the customized features significantly increased the performance. Besides, the importance of customized features was analysed in order to identify the most effective features in TS classification. The proposed models were also tested on 15000 unlabelled data and compared to a model-based method to validate their reliability. Random Forest and Extreme Gradient Boosting could accurately classify reference samples and positively assign correct labels to random samples. This study indicates the efficiency of Machine Learning models in the classification and management of DInSAR TSs, along with shortcomings of the proposed models in classification of nonmoving targets (i.e., false alarm rate) and a decreasing accuracy for shorter TS.https://www.mdpi.com/2072-4292/14/15/3821ground deformationDInSARclassificationMachine LearningTime Series |
| spellingShingle | S. Mohammad Mirmazloumi Angel Fernandez Gambin Riccardo Palamà Michele Crosetto Yismaw Wassie José A. Navarro Anna Barra Oriol Monserrat Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data Remote Sensing ground deformation DInSAR classification Machine Learning Time Series |
| title | Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data |
| title_full | Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data |
| title_fullStr | Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data |
| title_full_unstemmed | Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data |
| title_short | Supervised Machine Learning Algorithms for Ground Motion Time Series Classification from InSAR Data |
| title_sort | supervised machine learning algorithms for ground motion time series classification from insar data |
| topic | ground deformation DInSAR classification Machine Learning Time Series |
| url | https://www.mdpi.com/2072-4292/14/15/3821 |
| work_keys_str_mv | AT smohammadmirmazloumi supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT angelfernandezgambin supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT riccardopalama supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT michelecrosetto supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT yismawwassie supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT joseanavarro supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT annabarra supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata AT oriolmonserrat supervisedmachinelearningalgorithmsforgroundmotiontimeseriesclassificationfrominsardata |