Tabriz is located in one of the important seismic areas of the world and has witnessed severe earthquakes in the past centuries. Earthquake is associated with multiple risks including geotechnical risks which affected many cities around the world. One of these important risks is the phenomenon of soil liquefaction. Soil liquefaction is the reason for many damages caused by earthquakes which can cause lots of damage to vital arteries of cities, mines, pipe lines and the buried structures in the soil. One of the recent challenges in dealing with liquefaction is utilizing intelligent tools for predicting the effects of this phenomenon in soil layers. For this purpose, a total number of 100 soil samples are collected, while an empirical approach is also developed for achieving Liquefaction Potential Index (LPI) by means of the depth of the soil layers, SPT values, penetration indices, fines content percentages, ground acceleration, and water level of the soil samples. For prediction purpose, the recently developed configuration of the Gradient Boosting (GB) methods is utilized as the main approach while the Artificial Neural Network (ANN) and the Decision Tree (DT) approaches are utilized for comparative investigations. For validation process, 10% of the samples are utilized in a stochastic way to intelligently evaluate the capability of the GB method in contrast to the alternative approaches. The results demonstrate the capability of the GB approach in providing efficient predictive results in dealing with the LPI prediction problem. Regarding the training phase, GB provided the maximum absolute error of 3.44 x 10-8 while the DT's result is partially competitive with maximum absolute of 3.15. Based on the test phase, GB can provide the lowest Mean Squared Error (MSE) of 0.09 while the DT with 0.11 and ANN with 3.25 have the other ranks. The GB is capable of reaching to lowest Mean Absolute Percentage Error (MAPE) of 3.64 in this phase while the DT with 3.07 and DT and ANN with 4.97 and 26.05 have second and third ranks respectively. 0.98 with 2% inaccuracy rate.

The parameters of the soil water characteristic curve (SWCC) play a pivotal role in the examination of unsaturated soil behavior. This study employs three machine learning models-random forest (RF), extreme gradient boosting (XGBoost), and multiexpression programming (MEP)-to predict the SWCC using key soil properties. Among them, the RF model demonstrated the most robust performance in SWCC prediction. The Shapley Additive Explanation (SHAP) analysis further reveals that suction is the most influential factor affecting SWCC predictions, with other input parameters also contributing significantly. Additionally, the MEP model offers a straightforward expression for SWCC estimation and, thus, proved practical for predicting embankment responses and exhibited superior accuracy over traditional methods, such as the Arya and Paris model (ACAP). For a precise assessment of the hydromechanical response of the embankment subjected to infiltration, an increase in pore pressure is observed when employing the MEP model compared to the ACAP model for fine-grained soils. The findings emphasize the potential of RF and MEP in enhancing SWCC prediction and their practical implications for soil engineering applications.

Knowing tractor drawbar pull is crucial to ensure the tractor can handle the required workload efficiently and safely, preventing soil damage and optimising field productivity. The present study proposes a novel approach for tractor drawbar pull prediction by utilising the tractor's geometric parameters and forward speed to develop a cloud-infused, server-less, machine learning-based real-time generalised tractor drawbar pull prediction model for any tractor between the 6-58 kW power range. The drawbar pull prediction models from ANN and six ML algorithms were developed, and the data analysis with hyperparameter tuning concluded that the Extreme Gradient Boosting (XGB) ML model outperformed the other ML models. A reasonable accuracy with R2 = 0.93 and MAPE = 6.77% was achieved using the XGB ML model for a separate validation dataset, which was not used for training. Furthermore, a cloud-based serverless Android App integrated with the XGB ML-based drawbar pull prediction model was developed for real-time tractor drawbar pull prediction and monitoring during tillage operations. The field validation demonstrated the XGB ML model's generalisation ability and effectiveness, with R2 = 0.90 and maximum MAPE of 9.86%. It can be used to simulate and optimize tractor performance, guiding manufacturers in selecting geometric parameters for tractor design.

Droughts cause significant economic damage worldwide. Evaluating their impacts on crop yield and water resources can help mitigate these losses. Using single variables such as precipitation, temperature, the soil moisture condition index (SMCI) and the vegetation condition index (VCI) to estimate drought impacts does not provide sufficient information on these complex conditions. Therefore, this study uses station-based and remote-sensingbased data to develop new composite drought indexes (CDIs), including the principal component analysis drought index (PSDI) and the gradient boosting method drought index (GBMDI). The first dataset includes historical observations of the standardized precipitation index (SPI), standardized precipitation evapotranspiration index (SPEI), and the self-calibrated Palmer drought severity index (SC-PDSI) at the 1-, 3-, 6-, and 12month timescales. The second dataset consists of remote-sensing-based data including the VCI, SMCI, temperature condition index (TCI), and precipitation condition index (PCI). We validated the results of PSDI and GBMDI by comparing them with historical drought events, in-situ drought indices, and annual winter wheat crop yield data from 2003 to 2022 using a regression model. Our temporal analysis revealed extreme to severe drought events during1990s and 2010s. GBMDI typically aligned with actual drought events and exhibited stronger correlations with in-situ drought indices than PSDI. We observed that drought intensity in winter were more severe than in summer. GBMDI was the most effective method, followed by PSDI, for assessing drought impacts on winter wheat yields. Thus, the proposed integrated monitoring framework and indexes offered a valuable and innovative approach to addressing the complexities of agricultural drought, particularly in evaluating its effects.

The loss of nitrogen in soil damages the environment. Clarifying the mechanism of ammonium nitrogen (NH4+-N) transport in soil and increasing the fixation of NH4+-N after N application are effective methods for improving N use efficiency. However, the main factors are not easily identified because of the complicated transport and retardation factors in different soils. This study employed machine learning (ML) to identify the main influencing factors that contribute to the retardation factor (Rf) of NH4+-N in soil. First, NH4+-N transport in the soil was investigated using column experiments and a transport model. The Rf (1.29 - 17.42) was calculated and used as a proxy for the efficacy of NH4+-N transport. Second, the physicochemical parameters of the soil were determined and screened using lasso and ridge regressions as inputs for the ML model. Third, six machine learning models were evaluated: Adaptive Boosting, Extreme Gradient Boosting (XGB), Random Forest, Gradient Boosting Regression, Multilayer Perceptron, and Support Vector Regression. The optimal ML model of the XGB model with a low mean absolute error (0.81), mean squared error (0.50), and high test r(2) (0.97) was obtained by random sampling and five-fold cross-validation. Finally, SHapely Additive exPlanations, entropy-based feature importance, and permutation characteristic importance were used for global interpretation. The cation exchange capacity (CEC), total organic carbon (TOC), and Kaolin had the greatest effects on NH4+-N transport in the soil. The accumulated local effect offered a fundamental insight: When CEC > 6 cmol(+) kg(-1), and TOC > 40 g kg(-1), the maximum resistance to NH4+-N transport within the soil was observed. This study provides a novel approach for predicting the impact of the soil environment on NH4+-N transport and guiding the establishment of an early-warning system of nutrient loss.

In soil mechanics, liquefaction is the phenomenon that occurs when saturated, cohesionless soils temporarily lose their strength and stiffness under cyclic loading shaking or earthquake. The present work introduces an optimal performance model by comparing two baselines, thirty tree-based, thirty support vector classifier-based, and fifteen neural network-based models in assessing the liquefaction potential. One hundred and seventy cone penetration test results (liquefied and non-liquefied) have been compiled from the literature for this aim. Earthquake magnitude, vertical-effective stress, mean grain size, cone tip resistance, and peak ground acceleration parameters have been used as input parameters to predict the soil liquefaction potential for the first time. Performance metrics, accuracy, an area under the curve (AUC), precision, recall, and F1 score have measured the training and testing performances. The comparison of performance metrics reveals that the model Runge-Kutta optimized extreme gradient boosting (RUN_XGB) has assessed the liquefaction potential with an overall accuracy of 99%, AUC of 0.99, precision of 0.99, recall value of 1, and F1 score of 1. Moreover, model RUN_XGB has a true negative rate of 0.98, negative predictive value of 1, Matthews correlation coefficient of 0.98, and average classification accuracy of 0.99, close to the ideal values and presents the robustness of the RUN_XGB model. Finally, the RUN_XGB model has been recognized as an optimal performance model for predicting the liquefaction potential. It has been noted that a low multicollinearity level affects the prediction accuracy of models based on conventional soft computing techniques, i.e., logistic regression. This research will help researchers choose suitable hybrid algorithms and enhance the accuracy of seismic soil liquefaction potential models.

The epicentral region of earthquakes is typically where liquefaction -related damage takes place. To determine the maximum distance, such as maximum epicentral distance (Re), maximum fault distance (Rf), or maximum hypocentral distance (Rh), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (Re, Rf, or Rh) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short -Term Memory), BiLSTM (Bidirectional Long Short -Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

The undrained shear strength is widely acknowledged as a fundamental mechanical property of soil and is considered a critical engineering parameter. In recent years, researchers have employed various methodologies to evaluate the shear strength of soil under undrained conditions. These methods encompass both numerical analyses and empirical techniques, such as the cone penetration test (CPT), to gain insights into the properties and behavior of soil. However, several of these methods rely on correlation assumptions, which can lead to inconsistent accuracy and precision. The study involved the development of innovative methods using extreme gradient boosting (XGB) to predict the pile set-up component A based on two distinct data sets. The first data set includes average modified cone point bearing capacity (q(t)), average wall friction (f(s)), and effective vertical stress (sigma(vo)), while the second data set comprises plasticity index (PI), soil undrained shear cohesion (S-u), and the over consolidation ratio (OCR). These data sets were utilized to develop XGBoost-based methods for predicting the pile set-up component A. To optimize the internal hyperparameters of the XGBoost model, four optimization algorithms were employed: Particle Swarm Optimization (PSO), Social Spider Optimization (SSO), Arithmetic Optimization Algorithm (AOA), and Sine Cosine Optimization Algorithm (SCOA). The results from the first data set indicate that the XGBoost model optimized using the Arithmetic Optimization Algorithm (XGB - AOA) achieved the highest accuracy, with R2 values of 0.9962 for the training part and 0.9807 for the testing part. The performance of the developed models was further evaluated using the RMSE, MAE, and VAF indices. The results revealed that the XGBoost model optimized using XGBoost - AOA outperformed other models in terms of accuracy, with RMSE, MAE, and VAF values of 0.0078, 0.0015, and 99.6189 for the training part and 0.0141, 0.0112, and 98.0394 for the testing part, respectively. These findings suggest that XGBoost - AOA is the most accurate model for predicting the pile set-up component.