Estimation of Unconfined Aquifer Transmissivity Using a Comparative Study of Machine Learning Models

Dashti, Zahra; Nakhaei, Mohammad; Vadiati, Meysam; Karami, Gholam Hossein; Kisi, Ozgur

doi:10.1007/s11269-023-03588-9

Cited by 4 publications

(1 citation statement)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the long time and large depth of pit descending has been the main cause of urban ground subsidence in recent years [53]. Therefore, groundwater needs to be controlled, and managing it well is key to achieving sustainable development goals [54].…”

Section: Groundwater Level Changesmentioning

confidence: 99%

Surface Subsidence over a Coastal City Using SBAS-InSAR with Sentinel-1A Data: A Case of Nansha District, China

Yu,

Li,

Xiao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The loss of life and property in economically developed areas due to geological hazards caused by intense ground subsidence is incalculable. As one of the fastest growing areas in the Guangdong-Hong Kong-Macao Greater Bay Area, the study of ground subsidence in Nansha will help to provide a scientific basis for urban planning and improve the capacity of monitoring and prevention of ground subsidence. The combination of coastal soft soil foundation and urbanization conditions creates a certain risk of land subsidence. We chose Nansha District, the geographical center of the Greater Bay Area, as the study area to analyze its surface subsidence characteristics in recent years. The 20-view Sentinel-1A data and SBAS-InSAR technique were used to monitor the ground subsidence in Nansha from 2017 to 2023. The main rate of ground subsidence in Nansha ranges from −19.4 to 7.7 mm/yr and is distributed in the urban area, along the rivers, in the construction area, and in the reclamation area. As of 4 May 2023, the average ground settlement in Nansha is 10.05 mm and the maximum settlement can be up to 142.45 mm. The 6-year total settlement at all four settlement intensities is greater than 60 mm, with the highest value exceeding 110 mm. The cumulative settlement increases with time, but inverse settlement and no settlement also occur at points where settlement is severe. For settlement caused by soft soil consolidation, it is recommended that drainage pipes be installed to accelerate drainage as a means of stabilizing settlement. For settlement caused by groundwater extraction and additional loads on the road surface, it is recommended to rationally extract groundwater and reinforce the foundation of the road surface with severe settlement.

show abstract

Section: Groundwater Level Changesmentioning

confidence: 99%

Surface Subsidence over a Coastal City Using SBAS-InSAR with Sentinel-1A Data: A Case of Nansha District, China

Yu,

Li,

Xiao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

Enhancing Flood Susceptibility Modeling: a Hybrid Deep Neural Network with Statistical Learning Algorithms for Predicting Flood Prone Areas

Ghobadi,

Ahmadipari

2024

Water Resour Manage

View full text Add to dashboard Cite

Uncertainty assessment of aquifer hydraulic parameters from pumping test data

Bashandy,

Bekhit,

Radwan

2024

Appl Water Sci

View full text Add to dashboard Cite

Data from pumping tests is a noisy process, and therefore, performing the pumping test numerous times will not get the same drawdown values. As a consequence, various pumping experiments lead to different values for aquifer parameter estimates. The data of pumping tests are usually analyzed using traditional methods (aquifer tests and AQtesolv software), which depend on trial and error technique. During these methods, non-unique values of hydraulic parameters are selected, which usually have a high level of uncertainty. Uncertainty must be taken into account in determining aquifer parameters, especially when using groundwater models for decision makers. The main goal of this study is to build a comprehensive tool for quantifying uncertainty associated with hydraulic parameter estimation from different pumping test conditions for fully penetrating wells in confined and semi-confined aquifers. To achieve the previous objective, a FORTRAN code was developed to apply the Markov Chain Monte Carlo (MCMC) algorithm using different likelihood functions (exponential, inverse, and log). This developed tool can be used to detect the most probable range of aquifer parameters that are consistent with pumping test data with a high degree of confidence. The tool was successfully used to several hypothetical cases to demonstrate the uncertainty in the quantification of aquifer parameters and compare the findings to the standard method's results. Also, the concept was verified numerically (using Modflow program) with satisfactory results using a hypothetical case with well-known aquifer parameters. Finally, the tool was applied for actual pumping test data with good results.

show abstract

Estimation of Unconfined Aquifer Transmissivity Using a Comparative Study of Machine Learning Models

Cited by 4 publications

References 71 publications

Surface Subsidence over a Coastal City Using SBAS-InSAR with Sentinel-1A Data: A Case of Nansha District, China

Surface Subsidence over a Coastal City Using SBAS-InSAR with Sentinel-1A Data: A Case of Nansha District, China

Enhancing Flood Susceptibility Modeling: a Hybrid Deep Neural Network with Statistical Learning Algorithms for Predicting Flood Prone Areas

Uncertainty assessment of aquifer hydraulic parameters from pumping test data

Contact Info

Product

Resources

About