Pipes and tunnels are prone to longitudinal deformation under normal faulting. Predicting the active length, defined as the major deformed length, is crucial for the seismic design of pipes and tunnels. However, an accurate prediction method is hard to develop due to a limited number of experimental data. In this study, a large number of numerical simulations are conducted based on a three-dimensional beam-spring model validated by centrifuge tests. The results are fed to XGBoost models to develop a robust prediction method. For ease of application, only the friction angle of soil, burial depth, diameter, and thickness of pipes or tunnels are incorporated as features. A hyperparameter tuning approach integrating grid search and Bayesian optimization was employed in the training process to establish optimal models with comparatively low complexity and high accuracy. A comparison of predictions from the XGBoost models and curves fitted on relative structure-soil stiffness demonstrates that XGBoost models are much superior. The effects of each feature on the predictions were analyzed by employing the SHAP method. The proposed XGBoost models can effectively and efficiently predict the active length of pipes and tunnels with minimal inputs.

Erosion causes significant damage to life and nature every year; therefore, controlling erosion is of great importance. Therefore, maintaining the balance between soil, plants, and water plays a vital role in controlling erosion. Aim of this study was to estimate some erodability parameters (structural stability index-SSI, aggregate stability-AS, and erosion ratio-ER) with indices and reflectance obtained via TripleSat satellite imagery using machine learning algorithms (support vector regression-SVR, artificial neural network-ANN, and K-nearest neighbors-KNN) in Samsun Province, Vezirkopru, Turkiye. Various interpolation methods (inverse distance weighting-IDW, radial basis function-RBF, and kriging) were also used to create spatial distribution maps of the study area for observed and predicted values. Estimates were made using NDVI, SAVI, and ASVI indices obtained from satellite images and NIR reflectance. Accordingly, the ANN algorithm yielded the lowest MAE (2.86%), MAPE (9.46%), and highest R2 (0.82) for SSI estimation. For AS and ER estimation, SVR had the highest predictive accuracy. Given the RMSE values in spatial distribution maps for observed and estimated values (SSI 7.861-7.248%, AS 14.485-14.536%, and ER 4.919-3.742%), the highest predictive accuracy was obtained with kriging. Thus, it was concluded that erosion parameters can be successfully estimated with reflectance and index values obtained from satellite images using SVR and ANN algorithms, and low-error distribution maps can be created using the kriging method.

Vehicle -emitted fine particulate matter (PM 2.5 ) has been associated with significant health outcomes and environmental risks. This study estimates the contribution of traffic -related exhaust emissions (TREE) to observed PM 2.5 using a novel factorization framework. Specifically, co -measured nitrogen oxides (NO x ) concentrations served as a marker of vehicle -tailpipe emissions and were integrated into the optimization of a Non -negative Matrix Factorization (NMF) analysis to guide the factor extraction. The novel TREE-NMF approach was applied to long-term (2012 - 2019) PM 2.5 observations from air quality monitoring (AQM) stations in two urban areas. The extracted TREE factor was evaluated against co -measured black carbon (BC) and PM 2.5 species to which the TREE-NMF optimization was blind. The contribution of the TREE factor to the observed PM 2.5 concentrations at an AQM station from the first location showed close agreement ( R 2 = 0 .79) with monitored BC data. In the second location, a comparison of the extracted TREE factor with measurements at a nearby Surface PARTiculate mAtter Network (SPARTAN) station revealed moderate correlations with PM 2.5 species commonly associated with fuel combustion, and a good linear regression fit with measured equivalent BC concentrations. The estimated concentrations of the TREE factor at the second location accounted for 7 - 11 % of the observed PM 2.5 in the AQM stations. Moreover, analysis of specific days known to be characterized by little traffic emissions suggested that approximately 60 - 78 % of the traffic -related PM 2.5 concentrations could be attributed to particulate traffic -exhaust emissions. The methodology applied in this study holds great potential in areas with limited monitoring of PM 2.5 speciation, in particular BC, and its results could be valuable for both future environmental health research, regional radiative forcing estimates, and promulgation of tailored regulations for traffic -related air pollution abatement.

This research presents an efficient computational method for retrofitting of buildings by employing an active learning-based ensemble machine learning (AL-Ensemble ML) approach developed in OpenSees, Python and MATLAB. The results of the study shows that the AL-Ensemble ML model provides the most accurate estimations of interstory drift (ID) and residual interstory drift (RID) for steel structures using a dataset of 2-, to 9-story steel structures considering four soil type effects. To prepare the dataset, 3584 incremental dynamic analysis (IDA) were performed on 64 structures. The research employs 6-, and 8-story structures to validate the AL-Ensemble ML model's effectiveness, showing it achieves the highest accuracy among conventional ML models, with an R-2 of 98.4%. Specifically, it accurately predicts the RID of floor levels in a 6-story structure with an accuracy exceeding 96.6%. Additionally, the programming code identifies the specific damaged floor level in a building, facilitating targeted local retrofitting instead of retrofitting the entire structure promising a reduction in retrofitting costs while enhancing prediction accuracy.