Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran
InSAR processing is vastly used for land deformation monitoring from the space. Machine learning methods are known as strong tools for data modeling as well as predicting. In this study, we are going to model and predict the future behavior of land subsidence by InSAR processing and leveraging deep...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-11-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/15481603.2021.1991689 |
| _version_ | 1797679030003040256 |
|---|---|
| author | Ali Radman Mehdi Akhoondzadeh Benyamin Hosseiny |
| author_facet | Ali Radman Mehdi Akhoondzadeh Benyamin Hosseiny |
| author_sort | Ali Radman |
| collection | DOAJ |
| description | InSAR processing is vastly used for land deformation monitoring from the space. Machine learning methods are known as strong tools for data modeling as well as predicting. In this study, we are going to model and predict the future behavior of land subsidence by InSAR processing and leveraging deep learning methods over the lands in the vicinity of Lake Urmia (located in the northwest of Iran). Accordingly, Sentinel-1 data over 56 months from November 2014 to June 2019 and small baseline subsets (SBAS) InSAR methods were utilized. Several regions with a high rate of subsidence were identified (maximum monthly subsidence of 13.3 mm). Furthermore, environmental factors affecting subsidence were considered. Therefore, parameters such as rainfall, groundwater, and lake area variations were measured using TRMM, GRACE, and MODIS satellite data, respectively. In order to determine and assess the relation between land deformations and environmental variations, several machine learning methods were implemented. The environmental parameters were used as the input of models and ground deformations as the target to be predicted. Eventually, ground deformations were estimated using multi-layer perceptron (MLP), convolutional neural network (CNN), and long short-term memory (LSTM) networks, in which each network had strengths and weaknesses on different occasions. Thus, by blending the forecast of the three models, a weighted ensemble was constructed, which outperformed the single models and reached the root mean square error (RMSE), mean absolute error (MAE), and standard deviation (SD) of 8.2 mm, 6.4 mm, and ±5.2 mm, respectively. The result indicated that although each single model had proper accuracy, an ensemble model can improve land deformation anticipation using the strength of networks in various conditions. |
| first_indexed | 2024-03-11T23:08:28Z |
| format | Article |
| id | doaj.art-7b411387168940398ad980fba9c0947c |
| institution | Directory Open Access Journal |
| issn | 1548-1603 1943-7226 |
| language | English |
| last_indexed | 2024-03-11T23:08:28Z |
| publishDate | 2021-11-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj.art-7b411387168940398ad980fba9c0947c2023-09-21T12:43:07ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262021-11-015881413143310.1080/15481603.2021.19916891991689Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, IranAli Radman0Mehdi Akhoondzadeh1Benyamin Hosseiny2School of Surveying and Geospatial Engineering, College of Engineering, University of TehranSchool of Surveying and Geospatial Engineering, College of Engineering, University of TehranSchool of Surveying and Geospatial Engineering, College of Engineering, University of TehranInSAR processing is vastly used for land deformation monitoring from the space. Machine learning methods are known as strong tools for data modeling as well as predicting. In this study, we are going to model and predict the future behavior of land subsidence by InSAR processing and leveraging deep learning methods over the lands in the vicinity of Lake Urmia (located in the northwest of Iran). Accordingly, Sentinel-1 data over 56 months from November 2014 to June 2019 and small baseline subsets (SBAS) InSAR methods were utilized. Several regions with a high rate of subsidence were identified (maximum monthly subsidence of 13.3 mm). Furthermore, environmental factors affecting subsidence were considered. Therefore, parameters such as rainfall, groundwater, and lake area variations were measured using TRMM, GRACE, and MODIS satellite data, respectively. In order to determine and assess the relation between land deformations and environmental variations, several machine learning methods were implemented. The environmental parameters were used as the input of models and ground deformations as the target to be predicted. Eventually, ground deformations were estimated using multi-layer perceptron (MLP), convolutional neural network (CNN), and long short-term memory (LSTM) networks, in which each network had strengths and weaknesses on different occasions. Thus, by blending the forecast of the three models, a weighted ensemble was constructed, which outperformed the single models and reached the root mean square error (RMSE), mean absolute error (MAE), and standard deviation (SD) of 8.2 mm, 6.4 mm, and ±5.2 mm, respectively. The result indicated that although each single model had proper accuracy, an ensemble model can improve land deformation anticipation using the strength of networks in various conditions.http://dx.doi.org/10.1080/15481603.2021.1991689insarmachine learningpredictionensemblesubsidence |
| spellingShingle | Ali Radman Mehdi Akhoondzadeh Benyamin Hosseiny Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran GIScience & Remote Sensing insar machine learning prediction ensemble subsidence |
| title | Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran |
| title_full | Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran |
| title_fullStr | Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran |
| title_full_unstemmed | Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran |
| title_short | Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran |
| title_sort | integrating insar and deep learning for modeling and predicting subsidence over the adjacent area of lake urmia iran |
| topic | insar machine learning prediction ensemble subsidence |
| url | http://dx.doi.org/10.1080/15481603.2021.1991689 |
| work_keys_str_mv | AT aliradman integratinginsaranddeeplearningformodelingandpredictingsubsidenceovertheadjacentareaoflakeurmiairan AT mehdiakhoondzadeh integratinginsaranddeeplearningformodelingandpredictingsubsidenceovertheadjacentareaoflakeurmiairan AT benyaminhosseiny integratinginsaranddeeplearningformodelingandpredictingsubsidenceovertheadjacentareaoflakeurmiairan |