Preprints
https://doi.org/10.5194/gmd-2024-15
https://doi.org/10.5194/gmd-2024-15
Submitted as: development and technical paper
 | 
04 Jun 2024
Submitted as: development and technical paper |  | 04 Jun 2024
Status: this preprint is currently under review for the journal GMD.

Enhanced Land Subsidence Interpolation through a Hybrid Deep Convolutional Neural Network and InSAR Time Series

Zahra Azarm, Hamid Mehrabi, and Saeed Nadi

Abstract. Land subsidence, the gradual or sudden sinking of the land, poses a global threat to infrastructure and the environment. This paper introduced a hybrid method based on deep convolutional neural networks (CNN) and persistent scattered interferometric synthetic aperture radar (PSInSAR) to estimate land subsidence in areas where PSInSAR cannot provide reliable measurements. This approach involves training a deep CNN with subsidence driving forces and PSInSAR data to learn patterns and estimate subsidence values. Our evaluation of the model shows its efficiency in overcoming the discontinuities observed in the PSInSAR results, producing a continuous subsidence surface. The deep CNN was evaluated on training, validation, and testing data, resulting in mean squared errors of 5 mm, 9 mm, and 11 mm, respectively. In contrast, the kriging interpolation method showed a mean square error of 37.19 mm in the experimental data set. subsidence prediction using the deep CNN method showed a 70 % improvement compared to the Kriging interpolation method.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Zahra Azarm, Hamid Mehrabi, and Saeed Nadi

Status: open (until 30 Jul 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Zahra Azarm, Hamid Mehrabi, and Saeed Nadi
Zahra Azarm, Hamid Mehrabi, and Saeed Nadi

Viewed

Total article views: 95 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
69 19 7 95 3 3
  • HTML: 69
  • PDF: 19
  • XML: 7
  • Total: 95
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 04 Jun 2024)
Cumulative views and downloads (calculated since 04 Jun 2024)

Viewed (geographical distribution)

Total article views: 95 (including HTML, PDF, and XML) Thereof 95 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 12 Jun 2024
Download
Short summary
The article introduces a new method using deep CNN and PSInSAR to estimate land subsidence, addressing the limitations of traditional methods. It focuses on Isfahan province, demonstrating substantial improvement over traditional techniques. The deep CNN method showed a 70 % enhancement in subsidence prediction, with the study area experiencing over 38 cm of subsidence between 2014 and 2020.