Deep learning-based mapping of land subsidence susceptibility using InSAR and geospatial data
Author affiliations
DOI:
https://doi.org/10.15625/2615-9783/24546Keywords:
Artificial neural networks, InSAR, deep learning, GIS, land subsidence, Hanoi, VietnamAbstract
Land subsidence is one of the geotechnical phenomena that significantly affects infrastructure, construction, and sustainable urban development. Therefore, predicting and identifying areas susceptible to land subsidence has received increasing attention in recent studies. This study examines the application of deep learning models to spatial data analysis for predicting land subsidence susceptibility in the Hanoi area. Land subsidence data were obtained from satellite imagery and processed using a multi-temporal InSAR approach to determine surface deformation. They were then split into two datasets: 70% for training and 30% for validation. A total of 19 conditioning factors were used as input variables for the models, including aspect, slope, curvature, elevation, normalized difference vegetation index (NDVI), groundwater, engineering geology, hydrogeology, Holocene sediment thickness, land use/land cover (LULC), rainfall, topographic wetness index (TWI), and Landsat 8 spectral Bands 1–7. Four deep learning models, including CNN, LSTM, DRDN, and CNN-LSTM, were developed and compared to evaluate their predictive capability. The performance of the models was assessed using AUC, RMSE, MAE, and other evaluation metrics. The results show that all four models achieved good predictive performance, among which the DRDN model provided the best overall results, with AUC = 0.984, MAE = 0.064, and RMSE = 0.254 for the training dataset, while the corresponding values for the validation dataset were AUC = 0.957, MAE = 0.093, and RMSE = 0.305, indicating that the model has high accuracy and strong generalization capability in mapping land subsidence susceptibility in the study area. In addition, SHAP analysis revealed that Holocene sediment thickness and groundwater were the most important factors controlling land subsidence susceptibility in Hanoi.
Downloads
References
Abidin H.Z., Djaja R., Darmawan D., Hadi S., Akbar A., Rajiyowiryono H., Sudibyo Y., Meilano I., Kasuma M.A., Kahar J., Subarya C., 2001. Land subsidence of Jakarta (Indonesia) and its geodetic monitoring system. Natural Hazards, 23(2), 365−387. https://doi.org/10.1023/A:1011144602064.
Ahmed S.F., Alam M.S.B., Hassan M., Rozbu M.R., Ishtiak T., Rafa N., Mofijur M., Shawkat Ali A.B.M., Gandomi A.H., 2023. Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artificial Intelligence Review, 56(11), 13521−13617. https://doi.org/10.1007/s10462-023-10466-8.
Arnhardt R., Novellino A., Hussain E., Bateson L., Newell A., 2023. Land subsidence susceptibility mapping for Hanoi city, Vietnam. Paper presented at the Tenth International Symposium on Land Subsidence. https://nora.nerc.ac.uk/id/eprint/536209.
Bui L.K., Le P.V., Dao P.D., Long N.Q., Pham H.V., Tran H.H., Xie L., 2021. Recent land deformation detected by Sentinel-1A InSAR data (2016–2020) over Hanoi, Vietnam, and the relationship with groundwater level change. GIScience & Remote Sensing, 58(2), 161−179. https://doi.org/10.1080/15481603.2020.1868198.
Cao D.V., Thanh N.P.T., Hong T.T., Van P.T., Van K.M., Van D.H., Indra Prakash, Pham B.T., 2025. Novel Integration of JCHAIDStar with ensemble techniques for comprehensive landslide and flash flood susceptibility mapping. Vietnam Journal of Earth Sciences, 48(2), 219−238. https://doi.org/10.15625/2615-9783/24030.
Chai L., Wei L., Cai P., Liu J., Kang J., Zhang Z., 2024. Risk assessment of land subsidence based on GIS in the Yongqiao area, Suzhou City, China. Scientific Reports, 14(1), 11377, https://doi.org/10.1038/s41598-024-62108-w.
Dang V., Doubre C., Weber C., Gourmelen N., Masson F., 2014. Recent land subsidence caused by the rapid urban development in the Hanoi region (Vietnam) using ALOS InSAR data. Natural Hazards and Earth System Sciences, 14(3), 657−674. https://doi.org/10.5194/nhess-14-657-2014.
Dang V.K.K., Nguyen H.T., Au T.A., Pham T.H., 2022. Deep based learning: ebin sorting system development. Vietnam Journal of Marine Science and Technology, 22(1), 85–93. https://doi.org/10.15625/1859-3097/16928.
Eghbali M., Azarakhshi M., Khalaj M.R., 2024. Determining land subsidence potential using the evidential belief function model: A case study for the Bardaskan Aquifer, Iran. Natural Resource Modeling, 37(3), e12397. https://doi.org/10.1111/nrm.12397.
Faryabi M., 2023. A fuzzy logic approach for land subsidence susceptibility mapping: the use of hydrogeological data. Environmental Earth Sciences, 82(9), 209. https://doi.org/10.1007/s12665-023-10909-z.
Galloway D.L., Burbey T.J., 2011. Regional land subsidence accompanying groundwater extraction. Hydrogeology Journal, 19(8), 1459−1486. https://doi.org/10.1007/s10040-011-0775-5.
Hieu T.T., Cham D.D., Van Tien P., Quan N.C., Hai P.T., Anh N.D., Thao P.B., Van T.T.T, Trinh Q.N., Thanh N.T., Cuong T.Q., 2026. Landslide detection and susceptibility analysis: A case study in Pieng stream catchment, Son La province. Journal of Science and Transport Technology, 6(1), 282−299. https://doi.org/10.58845/jstt.utt.2026.en.6.1.282-299.
Holzer T.L., Galloway D.L., 2005. Impacts of land subsidence caused by withdrawal of underground fluids in the United States. https://doi.org/10.1130/2005.4016(08).
Hong S.-H., 2024. Monitoring Time-Series Subsidence Observation in Incheon Using X-Band COSMO-SkyMed Synthetic Aperture Radar. Korean Journal of Remote Sensing, 40(2), 141−150. https://doi.org/10.7780/kjrs.2024.40.2.2.
Hosseinzadeh E., Anamaghi S., Behboudian M., Kalantari Z., 2024. Evaluating Machine Learning-Based Approaches in Land Subsidence Susceptibility Mapping. Land, 13(3), 322, https://doi.org/10.3390/land13030322.
Ikehara M.E., Phillips S.P., 1994. Determination of land subsidence related to ground-water-level declines using global positioning system and leveling surveys in Antelope Valley, Los Angeles and Kern Counties, California, 1992 (vol. 94): US Department of the Interior, US Geological Survey.
Karimiasl S., Hessari B., Zeinalzadeh K., Erfanian M., 2024. Assessment of land subsidence susceptibility in the Salmas Plain Aquifer Northwestern Lake Urmia, utilizing fuzzy logic. Watershed Engineering and Management, 16(3), 331−353.
Kariminejad N., Mohammadifar A., Sepehr A., Garajeh M.K., Rezaei M., Desir G., Román Q.A., Gholami H., 2024. Detection of land subsidence using hybrid and ensemble deep learning models. Applied Geomatics, 16(3), 593−610. https://doi.org/10.1007/s12518-024-00572-9.
Ku C.-Y., Liu C.-Y., 2023. Modeling of land subsidence using GIS-based artificial neural network in Yunlin County, Taiwan. Scientific Reports, 13(1), 4090. https://doi.org/10.1038/s41598-023-31390-5.
Kumar R., Ha H., Son N.D., Nguyen L.H., 2025. Optimizing CNN, SVM, and MLP for Prediction of Compressive Strength of Concrete using Grid Search Optimization. Journal of Science and Transport Technology, 198−217. https://doi.org/10.58845/jstt.utt.2025.en.5.4.198-217.
Le T.S., Chang C.-P., Nguyen X.T., Yhokha A., 2016. TerraSAR-X data for high-precision land subsidence monitoring: A case study in the historical centre of Hanoi, Vietnam. Remote Sensing, 8(4), 338. https://doi.org/10.3390/rs8040338.
Lenardón Sánchez M., Farías C.A., Cigna F., 2024. Multi-Decadal Land Subsidence Risk Assessment at Major Italian Cities by Integrating PSInSAR with Urban Vulnerability. Land, 13(12), 2103. https://doi.org/10.3390/land13122103.
Li F., Liu G., Tao Q., Zhai M., 2023. Land subsidence prediction model based on its influencing factors and machine learning methods. Natural Hazards, 116(3), 3015−3041. https://doi.org/10.1007/s11069-022-05796-9.
Liu K., Zhang J., Liu J., Wang M., Yue Q., 2024. Projection of land susceptibility to subsidence hazard in China using an interpretable CNN deep learning model. Science of the Total Environment, 913, 169502. https://doi.org/10.1016/j.scitotenv.2023.169502.
Liu X., Chen H., Gong B., Jiang G., Wang J., 2024. Formation process of cover collapse sinkholes related to groundwater level decline in karst areas. Journal of Mountain Science, 21(11), 3832−3846. https://doi.org/10.1007/s11629-024-8944-x.
Massonnet D., Feigl K.L., 1995. Discrimination of geophysical phenomena in satellite radar interferograms. Geophysical Research Letters, 22(12), 1537−1540. https://doi.org/10.1029/95GL00711.
Massonnet D., Feigl K.L., 1998. Radar interferometry and its application to changes in the Earth's surface. Reviews of geophysics, 36(4), 441−500. https://doi.org/10.1029/97RG03139.
Mazziotta M., Pareto A., 2022. Normalization methods for spatio‐temporal analysis of environmental performance: Revisiting the Min-Max method. Environmetrics, 33(5), e2730. https://doi.org/10.1002/env.2730.
Mehrnoor S., Robati M., Kheirkhah Zarkesh M.M., Farsad F., Baikpour S., 2023. Land subsidence hazard assessment based on novel hybrid approach: BWM, weighted overlay index (WOI), and support vector machine (SVM). Natural Hazards, 115(3), 1997−2030. https://doi.org/10.1007/s11069-022-05624-0.
Musunuri Y.R., Kwon O.-S., 2021. Deep residual dense network for single image super-resolution. Electronics, 10(5), 555. https://doi.org/10.3390/electronics10050555.
Nguyen T.G., Tran T.D., Nguyen C.T., 2023. A Optimizing the Long Short-Term Memory (LSTM) model by Bayesian method for salinity intrusion forecasting: a study at Dai Ngai station, Soc Trang province, Vietnam. Vietnam Journal of Marine Science and Technology, 23(3), 223−232. https://doi.org/10.15625/1859-3097/18174.
Nguyen T.D., Ha Q.M., Truong K.H., Cu M.H., Nguyen V.H., 2024. Applying machine learning for hydraulic flow unit classification and permeability prediction: case study from carbonate reservoir in the Southern part, Song Hong basin. Vietnam Journal of Marine Science and Technology, 24(3), 219−234. https://doi.org/10.15625/1859-3097/18654.
Nguyen H.D., Dinh K.D., Truong H.Q., Bui Q.-T., Nguyen T.N.U., Petrisor A.-I., 2025. Flood susceptibility assessment using deep neural networks and open-source spatial datasets in transboundary river basin. Vietnam Journal of Earth Sciences, 47(3), 315−336. https://doi.org/10.15625/2615-9783/22711.
Nguyen T.-H., Le V.-H., 2026. Cross-Branch CNN-MLP Integration for Improving Landslide Spatial Probability on Mt. Umyeon, Korea. Journal of Science and Transport Technology, 183−198. https://doi.org/10.58845/jstt.utt.2026.en.6.1.183-198.
Nozadkhalil T., Cakir Z., Ergintav S., Doğan U., Walter T.R., 2023. Land subsidence due to natural gas extraction in the Thrace basin (NW Turkey) and its influence on the North Anatolian fault under the Marmara Sea. Turkish Journal of Earth Sciences, 32(3), 421−430. https://doi.org/10.55730/1300-0985.1852.
Pan Z., Chen X., Yang X., Song Y., Ban R., Zhang M., 2022. Formation mechanism analysis of cover collapse sinkholes in Wugaishan Town, Chenzhou City, Hunan province, China. Environmental Earth Sciences, 81(2), 48. https://doi.org/10.1007/s12665-022-10171-9.
Pham G.H., Pham B.T.T., Hoang K.O.T., Tran T.T., Chi H.N.D., 2026. GIS Based Soil Erosion Susceptibility Assessment Using Deep Learning Models: A Case Study in the Mountainous Region of Nghe An, Vietnam. Journal of Science and Transport Technology, 67−86. https://doi.org/10.58845/jstt.utt.2026.en.6.1.67-86.
Prakash I., Nguyen D.D., Tuan N.T., Van Phong T., Van Hiep L., 2024. Landslide susceptibility zoning: integrating multiple Intelligent models with SHAP Analysis. Journal of Science and Transport Technology, 23−41. https://doi.org/10.58845/jstt.utt.2024.en.4.1.23-41.
Sainath T.N., Vinyals O., Senior A., Sak H., 2015. Convolutional, long short-term memory, fully connected deep neural networks. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP). Ieee, 4580−4584. Doi: 10.1109/ICASSP.2015.7178838.
Sekkeravani M.A., Bazrafshan O., Pourghasemi H.R., Holisaz A., 2022. Spatial modeling of land subsidence using machine learning models and statistical methods. Environmental Science and Pollution Research, 29(19), 28866−28883. https://doi.org/10.1007/s11356-021-18037-6.
Sun H., Peng H., Zeng M., Wang S., Pan Y., Pi P., Xue Z., Zhao X., Zhang A., Liu F., 2023. Land subsidence in a coastal city based on SBAS-InSAR monitoring: a case study of Zhuhai, China. Remote sensing, 15(9), 2424. https://doi.org/10.3390/rs15092424.
Teatini P., Tosi L., Strozzi T., Carbognin L., Wegmüller U., Rizzetto F., 2005. Mapping regional land displacements in the Venice coastland by an integrated monitoring system. Remote sensing of environment, 98(4), 403−413. https://doi.org/10.1016/j.rse.2005.08.002.
Tuan T., Hong P., Tam T., Nguyet N., Dung N., Huy P., Phong T., 2024. Landslide susceptibility in Phuoc Son, Quang Nam: A deep learning approach. Vietnam Journal of Earth Sciences, 47(1), 39−57. https://doi.org/10.15625/2615-9783/21658.
Vrigazova B., 2021. The proportion for splitting data into training and test set for the bootstrap in classification problems. Business Systems Research: International Journal of the Society for Advancing Innovation and Research in Economy, 12(1), 228−242. https://doi.org/10.2478/bsrj-2021-0015.
Wei W., Yongbin J., Yanhong L., Ji L., Xin W., Tong Z., 2019. An advanced deep residual dense network (DRDN) approach for image super-resolution. International Journal of Computational Intelligence Systems, 12(2), 1592−1601. https://doi.org/10.2991/ijcis.d.191209.001.
Wu J., Shi X., Ye S., Xue Y., Zhang Y., Wei Z., Fang Z., 2010. Numerical simulation of viscoelastoplastic land subsidence due to groundwater overdrafting in Shanghai, China. Journal of Hydrologic Engineering, 15(3), 223−236. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000172.
Xuan B.T., Thuy D.L., Van P.T., Hong N.V., Van Le H., Nguyen D.D., Prakash I., Thanh T.P., Thai B.P., 2024. Groundwater potential zoning using Logistics Model Trees based novel ensemble machine learning model. Vietnam Journal of Earth Sciences, 46(2), 272−281. https://doi.org/10.15625/2615-9783/20316.
Younas M., Khan S.D., Tirmizi O., Hamed Y., 2023. Geospatial analytics of driving mechanism of land subsidence in Gulf Coast of Texas, United States. Science of the Total Environment, 902, 166102. https://doi.org/10.1016/j.scitotenv.2023.166102.
Yu H., Arabameri A., Costache R., Crăciun A., Arora A., 2022. Land subsidence susceptibility assessment using advanced artificial intelligence models. Geocarto International, 37(27), 18067−18093. https://doi.org/10.1080/10106049.2022.2136265.
Zebker H., Villasenor J., 1992. Decorrelation in interferometric radar echoes. IEEE Transactions on geoscience and remote sensing, 30(5), 950−959.
Zhao Q., Zhang Y., Pepe A., Mastro P., Zheng T., Yang T., 2025. Coupled ground subsidence and rapid urbanization of the Red River delta region and the city of Hanoi, Vietnam, revealed through a Multi-Track InSAR analysis. International Journal of Applied Earth Observation and Geoinformation, 144, 104886. https://doi.org/10.1016/j.jag.2025.104886.
Zhao R., Arabameri A., Santosh M., 2024. Land subsidence susceptibility mapping: a new approach to improve decision stump classification (DSC) performance and combine it with four machine learning algorithms. Environmental Science and Pollution Research, 31(10), 15443−15466. https://doi.org/10.1007/s11356-024-32075-w.
Downloads
Published
How to Cite
Issue
Section
