Drought and excessive groundwater withdrawal in recent years due to increasing population and agricultural sectors have caused numerous problems such as land subsidence in cities across the world. Change in groundwater level, mostly due to over-exploitation of groundwater is one of the most common human-induced processes leading to land subsidence. Taibao City, Chiayi County, Taiwan is an extensive agriculture area sustained by water extraction from groundwater wells. Due to the increase in agricultural activities in this area, water resources become stressful. Surface water can no longer sustain the water demand. As a result, heavy groundwater exploitation occurs in this area. Pumping wells are excavated along the High-Speed Railway (HRS), posing threat to the safety of the railway operation performance, potentially causing adverse effects to the high-speed trains, resulting in a threat to passengers’ safety, lives, and property. This study as a case deals with the harmful effects of groundwater withdrawal in the city of Taibao and make forecasting of land subsidence. The study employs, Symbiotic Search Organism-Neural Network- Long Short Term Memory (SOS-NN-LSTM) model to forecast groundwater level and land subsidence sequentially. The model was applied to forecast groundwater level and land subsidence sequentially on historical cases, where neural network (NN) was used to capture the independent variables, whiles long short-term memory (LSTM) captures the time-dependent variables. Firstly, SOS-NN-LSTM was used to predict groundwater level. Secondly, the predicted groundwater level was used as one of the input variables to predict land subsidence. The role of symbiotic search organism (SOS) in the proposed model is to search for the optimal parameters of the prediction model (NN-LSTM). Sensitivity analysis was also carried out in this study to access the effect of each input variable on the network’s output and the rank was assigned to each individual input variable which determines the relative importance of the variable with respect to the other variables, quantified in terms of an error ratio. The proposed model demonstrates promising and reliable performance in forecasting groundwater level and land subsidence.

Drought and excessive groundwater withdrawal in recent years due to increasing population and agricultural sectors have caused numerous problems such as land subsidence in cities across the world. Change in groundwater level, mostly due to over-exploitation of groundwater is one of the most common human-induced processes leading to land subsidence. Taibao City, Chiayi County, Taiwan is an extensive agriculture area sustained by water extraction from groundwater wells. Due to the increase in agricultural activities in this area, water resources become stressful. Surface water can no longer sustain the water demand. As a result, heavy groundwater exploitation occurs in this area. Pumping wells are excavated along the High-Speed Railway (HRS), posing threat to the safety of the railway operation performance, potentially causing adverse effects to the high-speed trains, resulting in a threat to passengers’ safety, lives, and property. This study as a case deals with the harmful effects of groundwater withdrawal in the city of Taibao and make forecasting of land subsidence. The study employs, Symbiotic Search Organism-Neural Network- Long Short Term Memory (SOS-NN-LSTM) model to forecast groundwater level and land subsidence sequentially. The model was applied to forecast groundwater level and land subsidence sequentially on historical cases, where neural network (NN) was used to capture the independent variables, whiles long short-term memory (LSTM) captures the time-dependent variables. Firstly, SOS-NN-LSTM was used to predict groundwater level. Secondly, the predicted groundwater level was used as one of the input variables to predict land subsidence. The role of symbiotic search organism (SOS) in the proposed model is to search for the optimal parameters of the prediction model (NN-LSTM). Sensitivity analysis was also carried out in this study to access the effect of each input variable on the network’s output and the rank was assigned to each individual input variable which determines the relative importance of the variable with respect to the other variables, quantified in terms of an error ratio. The proposed model demonstrates promising and reliable performance in forecasting groundwater level and land subsidence.

Affandi, A. K. and K. Watanabe (2007). "Daily groundwater level fluctuation forecasting using soft computing technique." Nature and Science 5(2): 1-10.
Balogun, W. O., M. Anifowose, M. Shogo and F. Salaudeen (2011). "Trends and mechanisms of land subsidence of a coastal plain in the delta of Yangtze River-China." Researcher 3: 76-81.
Batelaan, O., F. De Smedt and L. Triest (2003). "Regional groundwater discharge: phreatophyte mapping, groundwater modelling and impact analysis of land-use change." Journal of hydrology 275(1-2): 86-108.
Bierkens, M. F. (1998). "Modeling water table fluctuations by means of a stochastic differential equation." Water Resources Research 34(10): 2485-2499.
Budhu, M. and I. B. Adiyaman (2010). "Mechanics of land subsidence due to groundwater pumping." International Journal for Numerical and Analytical Methods in Geomechanics 34(14): 1459-1478.
Chang, Y.-L., T.-L. Tsai, J.-C. Yang and Y.-K. Tung (2007). "Stochastically optimal groundwater management considering land subsidence." Journal of water resources planning and management 133(6): 486-498
Chen, Z., S. E. Grasby and K. G. Osadetz (2002). "Predicting average annual groundwater levels from climatic variables: an empirical model." Journal of Hydrology 260(1-4): 102-117.
Cheng, M.-Y. and D. Prayogo (2014). "Symbiotic organisms search: a new metaheuristic optimization algorithm." Computers & Structures 139: 98-112.
Coppola Jr, E. A., A. J. Rana, M. M. Poulton, F. Szidarovszky and V. W. Uhl (2005). "A neural network model for predicting aquifer water level elevations." Groundwater 43(2): 231-241.
Coulibaly, P., F. Anctil, R. Aravena and B. Bobée (2001). "Artificial neural network modeling of water table depth fluctuations." Water resources research 37(4): 885-896.
D. C. Korir, "Novel deep learning approach for schedule estimate to completion in construction project using NN-LSTM," Thesis Civil and Construction Engineering, National Taiwan University of Science and Technology, 2017.
Daliakopoulos, I. N., P. Coulibaly and I. K. Tsanis (2005). "Groundwater level forecasting using artificial neural networks." Journal of hydrology 309(1-4): 229-240.
Dash, N. B., S. N. Panda, R. Remesan and N. Sahoo (2010). "Hybrid neural modeling for groundwater level prediction." Neural Computing and Applications 19(8): 1251-1263.
Dehghani, M., M. J. V. Zoej and I. Entezam (2013). "Neural network modelling of Tehran land subsidence measured by persistent scatterer interferometry." Photogrammetrie-Fernerkundung-Geoinformation 2013(1): 5-17.
Dogan, A., H. Demirpence and M. Cobaner (2008). "Prediction of groundwater levels from lake levels and climate data using ANN approach." Water Sa 34(2): 199-208.
Ezugwu, A. E., O. J. Adeleke and S. Viriri (2018). "Symbiotic organisms search algorithm for the unrelated parallel machines scheduling with sequence-dependent setup times." PloS one 13(7): e0200030.
Figueroa-Miranda, S., J. T. Vargas, J. A. Ramos-Leal, V. M. Hernández-Madrigal and C. I. Villaseñor-Reyes (2018). "Land subsidence by groundwater over-exploitation from aquifers in tectonic valleys of Central Mexico: A review." Engineering geology.
Ghorbanzadeh, O., T. Blaschke, J. Aryal and K. Gholaminia (2018). "A new GIS-based technique using an adaptive neuro-fuzzy inference system for land subsidence susceptibility mapping." Journal of Spatial Science: 1-17.
Graves, A. (2012). Supervised sequence labelling. Supervised sequence labelling with recurrent neural networks, Springer: 5-13.
Hochreiter, S. (1998). "The vanishing gradient problem during learning recurrent neural nets and problem solutions." International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 6(02): 107-116.
Hochreiter, S. and J. Schmidhuber (1997). "Long short-term memory." Neural computation 9(8): 1735-1780.
Hosseini, Z. and M. Nakhaie (2015). "Estimation of groundwater level using a hybrid genetic algorithm-neural network." Pollution 1(1): 9-21.
Hung, N. Q., M. S. Babel, S. Weesakul and N. Tripathi (2009). "An artificial neural network model for rainfall forecasting in Bangkok, Thailand." Hydrology and Earth System Sciences 13(8): 1413-1425.
Hung, W.-C., C. Hwang, Y.-A. Chen, L. Zhang, K.-H. Chen, S.-H. Wei, D.-R. Huang and S.-H. Lin (2017). "Land subsidence in Chiayi, Taiwan, from compaction well, leveling and alos/palsar: Aquaculture-induced relative sea level rise." Remote Sensing 10(1): 40.
Hwang, C., W.-C. Hung and C.-H. Liu (2008). "Results of geodetic and geotechnical monitoring of subsidence for Taiwan High Speed Rail operation." Natural Hazards 47(1): 1-16.

Jalalkamali, A., H. Sedghi and M. Manshouri (2011). "Monthly groundwater level prediction using ANN and neuro-fuzzy models: a case study on Kerman plain, Iran." Journal of hydroinformatics 13(4): 867-876.
Jozefowicz, R., W. Zaremba and I. Sutskever (2015). An empirical exploration of recurrent network architectures. International Conference on Machine Learning.
Khalil, B., S. Broda, J. Adamowski, B. Ozga-Zielinski and A. Donohoe (2015). "Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models." Hydrogeology Journal 23(1): 121-141.
Larson, K., H. Başaǧaoǧlu and M. Marino (2001). "Prediction of optimal safe ground water yield and land subsidence in the Los Banos-Kettleman City area, California, using a calibrated numerical simulation model." Journal of hydrology 242(1-2): 79-102.
Lee, S., I. Park and J.-K. Choi (2012). "Spatial prediction of ground subsidence susceptibility using an artificial neural network." Environmental management 49(2): 347-358.
Mahmoudpour, M., M. Khamehchiyan, M. Nikudel and M. Gassemi (2013). "Characterization of regional land subsidence induced by groundwater withdrawals in Tehran, Iran." Geopersia 3(2): 49-62.
Maier, H. R. and G. C. Dandy (2000). "Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications." Environmental modelling & software 15(1): 101-124.
Mohanty, S., M. K. Jha, A. Kumar and K. Sudheer (2010). "Artificial neural network modeling for groundwater level forecasting in a river island of eastern India." Water resources management 24(9): 1845-1865.
Nayak, P. C., Y. S. Rao and K. Sudheer (2006). "Groundwater level forecasting in a shallow aquifer using artificial neural network approach." Water resources management 20(1): 77-90.
Oh, H.-J. and S. Lee (2010). "Assessment of ground subsidence using GIS and the weights-of-evidence model." Engineering Geology 115(1-2): 36-48.
Pang, L., M. E. Close, J. P. Watt and K. W. Vincent (2000). "Simulation of picloram, atrazine, and simazine leaching through two New Zealand soils and into groundwater using HYDRUS-2D." Journal of Contaminant Hydrology 44(1): 19-46.
Park, I., J. Choi, M. J. Lee and S. Lee (2012). "Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping." Computers & geosciences 48: 228-238.
Phi, T. H., and L. A. Strokova. 2015. Prediction maps of land subsidence caused by groundwater exploitation in Hanoi, Vietnam. Resource-Efficient Technologies 1 (2):80-89.
Pishro, M., S. Khosravi, S. Tehrani and S. Mousavi (2016). "Modeling and zoning of land subsidence in the southwest of Tehran using artificial neural networks." International Journal of Human Capital in Urban Management 1(3): 159-168.
Rahmati, O., A. Golkarian, T. Biggs, S. Keesstra, F. Mohammadi and I. N. Daliakopoulos (2019). "Land subsidence hazard modeling: Machine learning to identify predictors and the role of human activities." Journal of environmental management 236: 466-480.
Ren, G., J. Buckeridge and J. Li (2014). "Estimating land subsidence induced by groundwater extraction in unconfined aquifers using an influence function method." Journal of Water Resources Planning and Management 141(7): 04014084.
Rumelhart, D. E., G. E. Hinton and R. J. Williams (1988). "Learning representations by back-propagating errors." Cognitive modeling 5(3): 1.
Shrestha, P. K., N. M. Shakya, V. P. Pandey, S. J. Birkinshaw and S. Shrestha (2017). "Model-based estimation of land subsidence in Kathmandu Valley, Nepal." Geomatics, Natural Hazards and Risk 8(2): 974-996.
Sujay Raghavendra, N. and P. C. Deka (2015). "Forecasting monthly groundwater level fluctuations in coastal aquifers using hybrid Wavelet packet–Support vector regression." Cogent Engineering 2(1): 999414.
Suryanarayana, C., C. Sudheer, V. Mahammood and B. K. Panigrahi (2014). "An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam, India." Neurocomputing 145: 324-335.
Taormina, R., K.-W. Chau and R. Sethi (2012). "Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon." Engineering Applications of Artificial Intelligence 25(8): 1670-1676.
Taravatrooy, N., M. R. Nikoo, M. Sadegh and M. Parvinnia (2018). "A hybrid clustering-fusion methodology for land subsidence estimation." Natural Hazards 94(2): 905-926.
VaeziNejad, S. M., M. M. Tofigh and S. M. Marandi (2011). "Zonation and prediction of land subsidence (case study-Kerman, Iran)." International Journal of Geosciences 2(02): 102.
Wei, Y. and C. Yang (2018). "Predictive Modeling of Mining Induced Ground Subsidence with Survival Analysis and Online Sequential Extreme Learning Machine." Geotechnical and Geological Engineering 36: 3573-3581.
Werbos, P. J. (1990). "Backpropagation through time: what it does and how to do it." Proceedings of the IEEE 78(10): 1550-1560.
Xu, X., G. Huang, H. Zhan, Z. Qu and Q. Huang (2012). "Integration of SWAP and MODFLOW-2000 for modeling groundwater dynamics in shallow water table areas." Journal of Hydrology 412: 170-181.
Yadav, B., S. Ch, S. Mathur and J. Adamowski (2017). "Assessing the suitability of extreme learning machines (ELM) for groundwater level prediction." Journal of water and land development 32(1): 103-112.
Zhang, J., Y. Zhu, X. Zhang, M. Ye and J. Yang (2018). "Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas." Journal of hydrology 561: 918-929.
Zhao, Y., Y. Li, L. Zhang and Q. Wang (2016). "Groundwater level prediction of landslide based on classification and regression tree." Geodesy and Geodynamics 7(5): 348-355.
Zhu, L., H. Gong, X. Li, Y. Li, X. Su and G. Guo (2013). "Comprehensive analysis and artificial intelligent simulation of land subsidence of Beijing, China." Chinese geographical science 23(2): 237-248.
Zume, J. and A. Tarhule (2008). "Simulating the impacts of groundwater pumping on stream–aquifer dynamics in semiarid northwestern Oklahoma, USA." Hydrogeology Journal 16(4): 797-810.