Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series
This study presents a deep learning-based approach for forecasting Sentinel-1 displacement time series, with particular attention to irregular temporal patterns—an aspect often overlooked in previous works. Displacement data were generated using the Parallel Small BAseline Subset (P-SBAS) technique...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/14/2382 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733939116113920 |
|---|---|
| author | Lama Moualla Alessio Rucci Giampiero Naletto Nantheera Anantrasirichai Vania Da Deppo |
| author_facet | Lama Moualla Alessio Rucci Giampiero Naletto Nantheera Anantrasirichai Vania Da Deppo |
| author_sort | Lama Moualla |
| collection | DOAJ |
| description | This study presents a deep learning-based approach for forecasting Sentinel-1 displacement time series, with particular attention to irregular temporal patterns—an aspect often overlooked in previous works. Displacement data were generated using the Parallel Small BAseline Subset (P-SBAS) technique via the Geohazard Thematic Exploitation Platform (G-TEP). Initial experiments on a regular dataset from Lombardy employed Long Short-Term Memory (LSTM) models to forecast multiple future time steps. Empirical analysis determined that optimal forecasting is achieved with a 50-time-step input sequence, and that predicting 10% of the input sequence length strikes a balance between temporal coverage and accuracy. The investigation then extended to irregular datasets from Lisbon and Washington, comparing two preprocessing strategies: imputation and the inclusion of time intervals as a second feature. While imputation improved one-step predictions, it was inadequate for multi-step forecasting. To address this, a Time-Gated LSTM (TG-LSTM) was implemented. TG-LSTM outperformed standard LSTM for irregular data in one-step prediction but faced limitations in handling heteroscedasticity and computational cost during multi-step forecasting. These issues were effectively resolved using Temporal Fusion Transformers (TFT), which achieved the best performance, with RMSE values of 1.71 mm/year (Lisbon) and 1.26 mm/year (Washington). A key contribution of this work is the development of a GIS-integrated forecasting toolbox that incorporates LSTM models for regular sequences and TG-LSTM/TFT models for irregular ones. The toolbox enables both single- and multi-step displacement predictions, offering a scalable solution for geohazard monitoring and early warning applications. |
| format | Article |
| id | doaj-art-fdac6cbcbaf64a0ea397d67902553d7d |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-fdac6cbcbaf64a0ea397d67902553d7d2025-08-20T03:07:56ZengMDPI AGRemote Sensing2072-42922025-07-011714238210.3390/rs17142382Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time SeriesLama Moualla0Alessio Rucci1Giampiero Naletto2Nantheera Anantrasirichai3Vania Da Deppo4Institute for Photonics and Nanotechnologies, Secondary Office of Padova, 35131 Padova, ItalyTRE-ALTAMIRA S.R.L., 20143 Milan, ItalyInstitute for Photonics and Nanotechnologies, Secondary Office of Padova, 35131 Padova, ItalyVisual Information Laboratory, University of Bristol, Bristol BS1 5DD, UKInstitute for Photonics and Nanotechnologies, Secondary Office of Padova, 35131 Padova, ItalyThis study presents a deep learning-based approach for forecasting Sentinel-1 displacement time series, with particular attention to irregular temporal patterns—an aspect often overlooked in previous works. Displacement data were generated using the Parallel Small BAseline Subset (P-SBAS) technique via the Geohazard Thematic Exploitation Platform (G-TEP). Initial experiments on a regular dataset from Lombardy employed Long Short-Term Memory (LSTM) models to forecast multiple future time steps. Empirical analysis determined that optimal forecasting is achieved with a 50-time-step input sequence, and that predicting 10% of the input sequence length strikes a balance between temporal coverage and accuracy. The investigation then extended to irregular datasets from Lisbon and Washington, comparing two preprocessing strategies: imputation and the inclusion of time intervals as a second feature. While imputation improved one-step predictions, it was inadequate for multi-step forecasting. To address this, a Time-Gated LSTM (TG-LSTM) was implemented. TG-LSTM outperformed standard LSTM for irregular data in one-step prediction but faced limitations in handling heteroscedasticity and computational cost during multi-step forecasting. These issues were effectively resolved using Temporal Fusion Transformers (TFT), which achieved the best performance, with RMSE values of 1.71 mm/year (Lisbon) and 1.26 mm/year (Washington). A key contribution of this work is the development of a GIS-integrated forecasting toolbox that incorporates LSTM models for regular sequences and TG-LSTM/TFT models for irregular ones. The toolbox enables both single- and multi-step displacement predictions, offering a scalable solution for geohazard monitoring and early warning applications.https://www.mdpi.com/2072-4292/17/14/2382Sentinel-1irregular time seriestemporal fusion transformersGeographic Information Systemgeohazard monitoring |
| spellingShingle | Lama Moualla Alessio Rucci Giampiero Naletto Nantheera Anantrasirichai Vania Da Deppo Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series Remote Sensing Sentinel-1 irregular time series temporal fusion transformers Geographic Information System geohazard monitoring |
| title | Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series |
| title_full | Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series |
| title_fullStr | Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series |
| title_full_unstemmed | Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series |
| title_short | Hybrid GIS-Transformer Approach for Forecasting Sentinel-1 Displacement Time Series |
| title_sort | hybrid gis transformer approach for forecasting sentinel 1 displacement time series |
| topic | Sentinel-1 irregular time series temporal fusion transformers Geographic Information System geohazard monitoring |
| url | https://www.mdpi.com/2072-4292/17/14/2382 |
| work_keys_str_mv | AT lamamoualla hybridgistransformerapproachforforecastingsentinel1displacementtimeseries AT alessiorucci hybridgistransformerapproachforforecastingsentinel1displacementtimeseries AT giampieronaletto hybridgistransformerapproachforforecastingsentinel1displacementtimeseries AT nantheeraanantrasirichai hybridgistransformerapproachforforecastingsentinel1displacementtimeseries AT vaniadadeppo hybridgistransformerapproachforforecastingsentinel1displacementtimeseries |