Assessing the Subsidence Potential of Tasuj Plain Using Sentinel-1 Satellite Imagery Interferometry, the DIFA Framework, and Artificial Intelligence

Nouri-Sangarab, Soraya; Asghari Moghaddam, Asghar

doi:10.22111/jneh.2026.54780.2156

Assessing the Subsidence Potential of Tasuj Plain Using Sentinel-1 Satellite Imagery Interferometry, the DIFA Framework, and Artificial Intelligence

Articles in Press

Document Type : Research Article

Authors

¹ PhD. student in Hydrogeology, Department of Earth Sciences, University of Tabriz, Tabriz, Iran

² Professor, Department of Earth Sciences, University of Tabriz, Tabriz, Iran

10.22111/jneh.2026.54780.2156

Abstract

Given the increasing demand for groundwater resources due to population growth and agricultural and industrial activities, declining water levels in aquifers have heightened concerns about land subsidence. Consequently, the Tasuj Plain, as one of the plains in the Urmia Lake basin, is experiencing a gradual decline in groundwater levels, making it essential to assess subsidence and evaluate its potential to mitigate future hazards. To this end, the ALPRIFT framework -comprising seven layers of parameters influencing subsidence- was used to map the aquifer's subsidence potential. The subsidence potential index was classified into three categories: low, moderate, and high. To adapt ALPRIFT to the study area, some parameters were modified (removed or added), resulting in a revised subsidence potential index termed DIFA. The DIFA index was categorized into two classes: low and moderate. Subsequently, using Sentinel-1 satellite imagery, the average annual subsidence rate from 2016 to 2022 was estimated at 3.4 cm, showing a significant correlation with groundwater levels during the 2016–2022 water year and the revised subsidence potential (DIFA). To further refine the DIFA method and address its uncertainties, artificial intelligence techniques—fuzzy logic (Sugeno and Mamdani) and artificial neural networks (ANN)—were employed. The correlation coefficients between the results from ALPRIFT, DIFA, DIFA-SL (Sugeno Logic), DIFA-ML (Mamdani Logic), DIFA-ANN, and radar-derived subsidence data were 0.17, 0.32, 0.86, 0.84, and 0.86, respectively.

Keywords

Main Subjects

Environmental Hazards

References

References [in Persian]

Amighpey, M., Arabi, S. (2024). Studying Land Subsidence in Iran Caused by Groundwater Over-Extraction by Preparing the Comprehensive Subsidence Map of the Country. Iran-Water Resources Research, 19(5):145-156. [In Persian]

Habibi, M.H.G. (2013). Application of Artificial Intelligence Methods for Predicting Groundwater Levels in Hadishahr Plain, M.Sc. Thesis, University of Tabriz. [In Persian]

Khodabandeh, A.A., Amini-Fazl, A. (1993). Geological Map of Tasuj Quadrangle (1:100,000), Geological Survey of Iran. [In Persian]

Salehi, R., Ghafouri, M., Lashkaripour, G.H., Dehghani, M. (2013). Evaluation of Land Subsidence in South Mahyar Plain Using Radar Interferometry, Iranian Journal of Irrigation and Water Engineering, 3(11). [In Persian]

Zandi, R., Farzinkia, R., Shafiei, N. (2019). Land Subsidence and Radar Interferometry, Satellite Publications. [In Persian]

References [in English]

Hu, B., Zhou, J., Wang, J., Chen, Z., Dongqi, Wang. (2009). Risk assessment of land subsidence at Tianjin coaltal erea in China. Environmental Earth Sciences, 59(2):269-276.

Poland, J.F. (1984). Guidebook to Studies of Land Subsidence Due to Groundwater Withdrawal, United Nations Educational, Scientific and Cultural Organization, UNESCO.

Aller, L., Bennett, T., Lehr, J., Petty, R. (1987). DRASTIC: a standardized system for evaluating groundwater pollution using hydrogeologic settings. US EPA, Robert S. Kerr Environmental Research Laboratory, 85(2).

Nadiri, A.A., Gharekhan, M., Khatib, R., Sadeghfam, S., Asghari Moghaddam, A. (2017). Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine (SICM). Science of the Total Environment, 574, 691–706.

Nadiri, A.A., Gharekhani, M., Khatibi, R., Asghari Moghaddam, A. (2017)b. Assessment of groundwater vulnerability using a supervised committee to combine fuzzy logic and models. Environmental Science and Pollution Research, 24(9), 8562-8577.

Nadiri, A.A., Sedghi, Z., Khatibi, R., Gharekhani, M. (2017) c. Mapping vulnerability of multiple aquifers using multiple models and fuzzy logic to objectively derive model structures. Science of the Total Environment, 593-594, 75-90.

Nadiri, A.A., Taheri, Z., Khatibi, R., Barzegari, G., Dideban, K. (2018). Introducing a new framework for mapping subsidence vulnerability indices (SVIs). Sci Total Environ. 628:1043–1057.