Near-surface soil moisture content variation is a major factor in the frequent shallow slope failures observed on Mississippi’s highway slopes built on expansive clay. Soil moisture content variation is monitored generally through borehole sensors in highway embankments and slopes. This point monitoring method lacks spatial resolution, and the sensors are susceptible to premature failure due to wear and tear. In contrast, Unmanned/Uncrewed Aerial Vehicles (UAVs) have higher spatial and temporal resolutions that enable more efficient monitoring of site conditions, including soil moisture variation. The current study focused on developing two methods to predict soil moisture content (θ) using UAV-captured optical and thermal combined with machine learning and statistical modeling. The first method used Red, Green, and Blue (RGB) color values from UAV-captured optical images to predict θ. Support Vector Machine for Regression (SVR), Extreme Gradient Boosting (XGB), and Multiple Linear Regression (MLR) models were trained and evaluated for predicting θ from RGB values. The XGB model and MLR model outperformed the SVR model in predicting soil moisture content from RGB values. The R² values for the XGB and MLR models were >0.9 for predicting soil moisture when compared to SVR (R² = 0.25). The Root Mean Square Error (RMSE) for XGB, SVR, and MLR were 0.009, 0.025, and 0.01, respectively, for the test dataset, affirming that XGB was the best-performing model among the three models evaluated, followed by MLR and SVR. The better-performing XGB and MLR models were further validated by predicting soil moisture using unseen input data, and they provided good prediction results. The second method used Diurnal Land Surface Temperature variation (ΔLST) from UAV-captured Thermal Infrared (TIR) images to predict θ. TIR images of vegetation-covered areas and bare ground areas of the highway embankment side slopes were processed to extract ΔLST amplitudes. The underlying relationship between soil surface thermal inertia and moisture content variation was utilized to develop a predictive model. The resulting single-parameter power curve fit model accurately predicted soil moisture from ΔLST, especially in vegetation-covered areas. The power curve fit model was further validated on previously unseen TIR, and it predicted θ with an accuracy of RMSE = 0.0273, indicating good prediction performance. The study was conducted on a field scale and not in a controlled environment, which aids in the generalizability of the developed predictive models.

Due to cyclic wetting and drying, the hydro-mechanical behavior of unsaturated soil is impacted significantly. In order to assess the soil strength parameters, knowing the unsaturated behavior is important. Soil moisture content is an important parameter that can define the shear strength of the soil. Most of the highway slopes of Mississippi are built on highly expansive clay. During summer, the evaporation of moisture in the soil leads to shrinkage and the formation of desiccation cracks, while during rainfall, the soil swells due to the infiltration of water. In addition to this, the rainwater gets trapped in these cracks and creates perched conditions, leading to the increased moisture content and reduced shear strength of slope soil. The increased precipitation due to climate change is causing failure conditions on many highway slopes of Mississippi. Vetiver, a perennial grass, can be a transformative solution to reduce the highway slope failure challenges of highly plastic clay. The grass has deep and fibrous roots, which provide additional shear strength to the soil. The root can uptake a significant amount of water from the soil, keeping the moisture balance of the slope. The objective of the current study is to assess the changes in moisture contents of a highway slope in Mississippi after the Vetiver plantation. Monitoring equipment, such as rain gauges and moisture sensors, were installed to monitor the rainfall of the area and the moisture content of the soil. The data showed that the moisture content conditions were improved with the aging of the grass. The light detection and ranging (LiDAR) analysis was performed to validate the field data obtained from different sensors, and it was found that there was no significant slope movement after the Vetiver plantation. The study proves the performance of the Vetiver grass in improving the unsaturated soil behavior and stability of highway slopes built on highly expansive clay.

In highway slopes (HWS) constructed on high expansive clay soil (HECS), in situ moisture variation is an environmentally driven variable that can significantly impact the safety of the constructed soil. Electrical resistivity imaging (ERI) is a non-destructive method with a considerable potential for subsurface soil moisture mapping, which can be correlated with volumetric soil moisture content (VSMC) and soil matric suction (SMS) of HECS to remarkably enhance the evaluation of the performance of the HWS. However, limited datasets are available to evaluate the accuracy and feasibility of the available correlative field-based models for the HECS under various field conditions. The objective of the current study is to develop a field-based model of VSMC and SMS using real-time field monitoring and ERI data. Six HWS located in the Jackson metro area in Mississippi (MS), USA were considered as reference slopes in this study. Comprehensive field instrumentation was executed at the six HWS to monitor the VSMC, SMS and rainfall intensity. The sensors were installed at the crest, middle and toe of the slope. The 2D ERI test was conducted using a dipole–dipole array with multiple electrodes at 5 ft (1.5 m) spacing. The ERI survey was conducted at the crest and middle of the six HWS to image the continuous soil subsurface profile in terms of moisture variation. The developed models indicated a good agreement between instrumented and ERI data. The developed models will facilitate the estimation of VSMC and SMS variations and aid in performance monitoring of the HWS built on HECS such as Yazoo clay.

Geotechnical assets such as highway embankments and slopes (HWS) are critical to the integrity of transportation infrastructure. However, they are largely overlooked by Transportation Asset Management programs in the United States. The HWS are vulnerable to landslides induced by several factors including frequent occurrences of extreme rainfall events. Therefore, mapping vulnerable HWS and developing an inventory will significantly help with infrastructure asset management. To this end, this research adopted proven geographical information systems based on landslide susceptibility mapping methods typically applied to hillside slopes, and a method for mapping at-risk HWS assets was developed. Several supervised machine learning (ML) classification models were developed and evaluated to accurately map at-risk HWS in the study area of central Mississippi. Digital Elevation Models (DEMs) created from remote sensing data obtained from satellites, drone sensors, and terrestrial LiDAR were utilized to develop rasterized causative factors. The causative factors used included: Geotechnical and geomorphological attributes, such as slope, aspect, curvature, elevation, normalized difference vegetation index (NDVI), soil composition, and terrain from DEM; and hydrological factors, including precipitation, distance from the stream, groundwater depth, and topographic wetness index. Known locations of failed and not-failed HWS were selected and rasterized, and the pixels were extracted as ground truth data. The rasterized causative factors were utilized as independent features to train the classification ML models for predicting HWS failure susceptibility. Models were evaluated by developing confusion matrices and using probabilistic metrics such as area under curve (AUC) score, F-1score, and Accuracy scores. Random forest outperformed the other models (AUC, F1, and Accuracy scores of 1.0). Probability threshold tuning was performed on the random forest model, and susceptibility maps with different thresholds were evaluated. An optimal threshold of 0.75 was used to balance false negatives and false positives in the predicted results, ensuring more reliable identification of hazard-prone slopes. The trained RF model revealed that the elevation, distance from streams, the NDVI, and precipitation were the top four factors influencing HWS failures in this study. The method allows for easy identification of vulnerable HWS across vast geographic areas. This method helps in effective fund utilization by doing targeted interventions and preventative maintenance efforts. Transportation agencies can implement this methodology on HWS at any location to strategize geotechnical asset management efforts.

This study characterizes a sinkhole-impacted railroad embankment site through a comprehensive geophysical investigation encompassing eight electrical resistivity imaging (ERI) lines, four multichannel analysis of surface waves (MASW) lines, and three LiDAR datasets. Geophysical data from the coupled ERI and MASW at the south embankment mid-slope and toe revealed low resistivity (<50 Ω·m) and low shear-wave velocity (Vs) to depths of 25 to 30 ft, indicating moisture-weakened or void-prone zones. Increased Vs values beyond a 30 ft depth indicated stiffer soil or bedrock. Confined moisture pockets were highlighted along the sinkhole parallel to the slope’s toe. Widespread low-resistivity zones and low Vs were found at the mid-slope and toe to 30 ft, suggesting saturated, softened zones in those areas. Low resistivity and low Vs were found at several locations in the crest, railway track, and subgrade zones between 10 and 40 ft and at ∼240 ft lateral distances along the investigation lines at the crest of the railroad embankment, mostly within 15- to 30-ft depths. Low-resistivity and low-Vs zones beneath and adjacent to known sinkholes at the north slope toe indicated saturated voids and potential zones of instability. Resistivity and Vs variations indicated active seepage, hydraulically active zones, and potential sinkhole depths on both sides of the embankment. The coupled MASW and ERI investigation method revealed subsurface anomalies associated with sinkhole formation, narrowing down the critical areas for potential interventions. This noninvasive approach enabled rapid and cost-effective screening of railroad assets for prioritized proactive maintenance, particularly following extreme weather events.