Geotechnical Engineering Commons^™

Machine Learning-Based Upscaling Of Rock Permeability From Pore Scale To Core Scale: Effect Of Training Dataset Size And Sub-Core Volumes, Yaotian Guo, Fei Jiang, Takeshi Tsuji, Yoshitake Kato, Mai Shimokawara, Lionel Esteban, Mojtaba Seyyedi, Marina Pervukhina, Maxim Lebedev, Ryuta Kitamura

Research outputs 2022 to 2026

Permeability characterizes the capacity of porous formations to conduct fluids, thereby governing the performance of carbon capture, utilization, and storage (CCUS), hydrocarbon extraction, and subsurface energy storage. A reliable assessment of rock permeability is therefore essential for these applications. Direct estimation of permeability from low-resolution CT images of large rock samples offers a rapid approach to obtain permeability data. However, the limited resolution fails to capture detailed pore-scale structural features, resulting in low prediction accuracy. To address this limitation, we propose a convolutional neural network (CNN)-based upscaling method that integrates high-precision pore-scale permeability information into core-scale, low-resolution CT images. In …

Geodatabase And Modeling Code Used For Dynamic Landslide Hazard Maps In Eastern Kentucky, Nathaniel O'Leary, L. Sebastian Bryson

Earth and Environmental Sciences Research Data

We developed spatiotemporal landslide hazard maps (LHMs) using soil, hydrologic, and geomorphic parameters from the subaerial infinite slope factor of safety (FS) equation under unsaturated conditions. Soil properties were extracted from the NRCS WSS, while geomorphic variables were derived from a 1.5 m LiDAR-based DEM and ArcGIS Online. Soil moisture from Hydrus-1D, driven by precipitation and evapotranspiration (ET) data from Irrigation Manager, introduced temporal variability. Validation against known landslide sites showed spatial and temporal FS accuracy despite some false positives. We also developed a landslide susceptibility maps (LSM) after comparing three machine learning algorithms, with bagged trees achieving the highest …

Visualizing And Automating Past, Real-Time, And Forecast Dynamic Hazard Maps For Shallow Colluvial Landslides In Eastern Kentucky, Nathaniel O'Leary

Theses and Dissertations--Earth and Environmental Sciences

Landslide hazards are a persistent threat to communities and infrastructure in Eastern Kentucky, where steep slopes, shallow colluvial soils, and variable hydrological conditions make slope failures frequent. This thesis presents an integrated approach to landslide hazard mapping (LHM) through the development of dynamic, spatiotemporal LHMs for shallow colluvial landslides. Two studies within this work investigate and refine the use of the Lu and Godt (2008) factor of safety (FS) equation to improve landslide predictions. The first study establishes a novel LHM workflow using Hydrus-1D to simulate soil moisture infiltration and fluctuations from precipitation and evapotranspiration (ET) data. This study also …

Enhancing Wettability Prediction In The Presence Of Organics For Hydrogen Geo-Storage Through Data-Driven Machine Learning Modeling Of Rock/H2/Brine Systems, Zeeshan Tariq, Muhammad Ali, Nurudeen Yekeen, Auby Baban, Bicheng Yan, Shuyu Sun, Hussein Hoteit

Research outputs 2022 to 2026

The success of geological H2 storage relies significantly on rock–H2–brine interactions and wettability. Experimentally assessing the H2 wettability of storage/caprocks as a function of thermos-physical conditions is arduous because of high H2 reactivity and embrittlement damages. Data-driven machine learning (ML) modeling predictions of rock–H2–brine wettability are less strenuous and more precise. They can be conducted at geo-storage conditions that are impossible or hazardous to attain in the laboratory. Thus, ML models were utilized in this research to accurately model the wettability behavior of a ternary system consisting of H2, rock minerals (quartz and mica), and brine at different operating geological …

Historical And Forecasted Kentucky Specific Slope Stability Analyses Using Remotely Retrieved Hydrologic And Geomorphologic Data, Daniel M. Francis

Theses and Dissertations--Civil Engineering

Hazard analyses of rainfall-induced landslides have typically been observed to experience a lack of inclusion of measurements of soil moisture within a given soil layer at a site of interest. Soil moisture is a hydromechanical variable capable of both strength gains and reductions within soil systems. However, in situ monitoring of soil moisture at every site of interest is an unfeasible goal. Therefore, spatiotemporal estimates of soil moisture that are representative of in-situ conditions are required for use in subsequent landslide hazard analyses.

This study brings together various techniques for the acquisition, modeling, and forecasting of spatiotemporal retrievals of soil …

Soil Moisture And Geomorphologic Data For Use In Dynamic And Forecastable Landslide Hazard Analyses In Eastern Kentucky, Daniel M. Francis, L. Sebastian Bryson

Civil Engineering Research Data

These data are the geomorphologic and land information system-based soil moisture estimates from assimilation of NASA SMAP satellite-based observations and NOAH 3.6 Land Surface Model estimates over known landslides in Eastern Kentucky. Additionally Long Short-Term Memory Recurrent Neural Network and logistic regression machine learning codes, as well as an Application programming interface code are included. Finally, in-situ data from Eastern Kentucky is included.

Spatiotemporal Retrievals Of Soil Moisture And Geomorphologic Data For Landslide Sites In Eastern Kentucky, Lindsey Sebastian Bryson, Daniel M. Francis

Civil Engineering Research Data

These data are the soil texture, land information system-based soil moisture estimates from assimilation of NASA SMAP satellite-based observations and NOAH 3.6 Land Surface Model estimates, artificial neural network machine learning code, and in-situ soil moisture measurements.

Machine Learning Methods To Map Stabilizer Effectiveness Based On Common Soil Properties, Amit Gajurel

Boise State University Theses and Dissertations

Unconfined compressive strength (UCS) has been widely used as one of the primary criteria for the selection of optimum type and amount of chemical stabilizer for subgrade/base stabilization. Guidelines established by various state and federal agencies aid in selecting these optimum values by recommending an initial type and amount based on a wide range of soil index properties. A significant number of laboratory trials have to be done to establish the optimum type and amount of stabilizer for a given target strength. This process takes a copious amount of time, money, and the workforce. In addition to that, the finite …