The degree of mechanical reinforcement provided by plants depends upon its roots distribution in the soil and mechanical properties of the roots. The mechanical properties and distribution of root traits (root diameter and number) in the soil of the standing forest depends on the tree stem diameter. This variation of root traits with tree stem diameter is rarely investigated. Therefore, this research presents the effect of tree stem diameter on the distribution of roots within the standing forest of Cunninghamia in the Longchi forest area, Sichuan province, China. In this area, shallow landslides take place frequently. We investigated the root traits distribution for trees with different stem diameters, i.e., 220 mm, 320 mm, 450 mm, and 468 mm, to show the variation of roots distribution in the soil with stem diameter. The root architecture of the selected trees was studied by step excavation method of the root zone accompanied by measurement of roots physical parameters (roots number and roots diameter) and indices (roots area ratio (RAR), roots biomass (RB), and roots distribution (RD)). We measured the root’s maximum tensile strength by performing root tensile tests in the laboratory. The field and laboratory-measured data were used to estimate the root cohesion by both the commonly used model Wu and Waldron Model (WWM) and Fiber Bundle Model (FBM). The results indicate that the tree stem diameter correlates with both the root distribution and the tensile strength. The roots indices and root cohesion increase with an increase in the diameter of the tree. Further, RAR decreases with depth and lateral distance from the tree stem, while the maximum values were observed in 10 cm depth. The relationship between roots diameter and roots tensile strength is established through power function. The average root cohesion estimated for a tree with stem diameter 220 mm is 23 kPa, 29 kPa for 320 mm, 54 kPa for 450 mm, and 63 kPa for 460 mm. This effect of stem diameter on the increase of soil shear resistance should be considered while evaluating the stability of slopes in standing forests. The comparison between WWM and FBM for investigated species suggests that WWM estimates the cohesion values greater than FBM by 65%.

Accurate estimation of the ultimate bearing capacity (UBC) of shallow foundations is critical for safe and economical geotechnical design. Traditional approaches depend heavily on extensive and costly field and laboratory investigations, while numerical simulations, though effective, are computationally intensive and time-consuming. To address these limitations, this study investigates the application of machine learning (ML) models for efficient and reliable prediction of the ultimate bearing capacity of shallow foundations. Although numerous studies have explored individual ML techniques for this purpose, a comprehensive and consistent comparison of widely used models under identical conditions remains limited. This research evaluates six ML algorithms; k-Nearest Neighbors (kNN), Artificial Neural Network (NN), Random Forest (RF), Extreme Gradient Boosting (xGBoost), Adaptive Boosting (AdaBoost), and Stochastic Gradient Descent (SGD), using a dataset of 169 experimental results collected from literature. The input features include foundation width (B), depth (D), length-to-width ratio (L/B), soil unit weight (γ), and angle of internal friction (φ). Model performance was assessed using multiple evaluation metrics: coefficient of determination (R²), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and objective function (OBJ). To enhance model interpretability, SHapley Additive Explanations (SHAP) and Partial Dependence Plots (PDPs) were employed to analyze feature importance and input-output relationships, highlighting the influence of both soil properties and foundation geometry on predicted bearing capacity. Among the evaluated models, AdaBoost demonstrated the best overall performance, achieving R² values of 0.939 and 0.881 on the training and testing sets, respectively. Based on the cumulative ranking of the models across all evaluation metrics, the models were ranked in the following order of performance: AdaBoost > kNN > RF > xGBoost > NN > SGD. While the results are promising, a key limitation is the use of single-layer soil data, which restricts applicability to more complex, multilayered soil profiles. Future studies should incorporate multilayer datasets and account for spatial variability to enhance the generalizability and robustness of predictive models.

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain.

Flood constitutes one of the world's most serious environmental hazards. Flood bunds are the earthen hydraulic structures which are constructed along the River to control the Flood water to avoid damages to the infrastructures, crops, livestock and loss of human lives. Pakistan which lies in the Indus Basin has been facing severe threats and losses from the floods since histories. About 6807km length of flood embankment has been constructed to safeguard against the floods in the country. Punjab has been worst hit province by heavy floods and rains causing heavy loss. Geotechnical Evaluation is vital for proper functioning of such structures. In this study four flood bunds susceptible to potential embankment breaching during flood have been selected along river Chenab in district Muzaffar Garh Irrigation zone. Suite of analysis using GeoStudio software (SLOPE/W and SEEP/W for stability and seepage analysis respectively) has been performed by considering four different critical scenarios, (1) steady state at highest flood level (2) rapid drawdown from highest flood level (3) steady state at extreme condition with 3 feet free board (4) rapid drawdown from extreme condition with 3 feet free board. The safety of the flood bunds is evaluated in terms of River Embankment Breaching Vulnerability Index (REBVI), safe exit gradient and factor of safety against slope failure. Based on these calculated factors from the numerical analysis it is found that embankment at RD:25,29 are marginally safe, whereas at RD: 147, 157 are susceptible to pipping failure. Therefore, it is recommended to make embankment impervious using cohesive material and to install cut-off walls or berms to lengthen the seepage path.