The cohesion and internal friction angle of loess are important macro-mechanical parameters for evaluating the safety and stability of engineering construction. Traditional laboratory measurement methods are time-consuming and difficult to conduct on-site. This study aims to compare the effectiveness of five Machine Learning (ML) methods, namely Random Forest (RF), Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), BPNN optimized by Particle Swarm Optimization (PSO-BPNN) and BPNN optimized by Genetic Algorithm (GA-BPNN), in predicting the macro-mechanical properties of loess. To this end, the study collected data from 89 undisturbed loess samples and 229 remolded loess samples to construct training and testing datasets, and used three correlation analysis methods to analyze the influence of physical parameters on mechanical properties. The study found that the water content has the most significant impact on the mechanical properties of loess. In terms of prediction ability, SVM performs the best among the ML methods used, and the determination coefficient for cohesion of undisturbed loess reaches 0.857. Although the training data is limited, the prediction performance of BPNN is significantly improved after being optimized by PSO or GA. The research results show that ML provides an effective way to study the complex mechanical behavior of loess.

To ensure the sustainable development of the surrounding environment and the sustainable operation of landfills, detecting landfill leakage is of great significance. In landfills lacking a leakage monitoring system, the inability to detect and locate damaged High-Density Polyethylene (HDPE) membranes can lead to the contamination of soil and groundwater by landfill leachate. To address this issue, this study proposes a resistivity tomography inversion model based on the external-electrode power supply mode. Utilizing the resistivity difference between the leakage zone and the surrounding soil, electrodes are arranged symmetrically for both power supply and measurement. Upon applying direct current (DC) excitation, potential data are collected, with the finite volume method employed for inversion and the Gauss-Newton method integrated with an adaptive particle swarm optimization algorithm for parameter fitting. Experimental results show that the combined algorithm provides better clarity in edge recognition of low-resistance models compared with single algorithms. The maximum deviation between inferred leakage coordinates and the actual location is 10.1 cm, while the minimum deviation is 6.4 cm, satisfying engineering requirements. This method can effectively locate point sources and line sources, providing an accurate solution for subsequent leakage point filling and improving repair efficiency.

Background and AimsSoil salinization is a major cause of land degradation and ecological damage. Traditional soil salinity monitoring techniques are limited in coverage and scalability, while remote sensing offers broader applicability and efficiency. This study addresses spatiotemporal variations in soil salt content (SSC) inversion across crop types in Tongliao City, Inner Mongolia, China, using an innovative integration of multi-temporal data and crop cover types, improving remote sensing monitoring accuracy.MethodsField sampling data and Sentinel-2 images from June to September in 2021 and 2022 were utilized. The deep learning U-net model classified key crops, including sunflower (33%), beet (12%), and maize (55%), and analyzed the effects of crop coverage on SSC across multiple time series. Six spectral variables were selected using the SVR-RFE model (R2 = 0.994, MAE = 0.016). SSC prediction models were developed using three machine learning methods (DBO-RF, PSO-SVM, BO-BP) and a deep learning method (Transformer).ResultsConsidering crop coverage variations improved the sensitivity of spectral variables to SSC response, enhancing predictive accuracy and model stability. Crop classification showed that the salinity index (SIs) correlated more strongly with SSC than the vegetation index (VIs), with SI6 having the highest correlation coefficient of 0.50. The Transformer model, using multi-time series data, outperformed other algorithms, achieving an average R2 of 0.71. The SSC inversion map from the Transformer model closely matched field survey trends.ConclusionThis research provides a novel approach to soil salinity prediction using satellite remote sensing, offering a scalable solution for monitoring salinization and valuable insights for environmental management and agricultural planning.

Agriculture is one of the prime economical sources of India and most of the people directly or indirectly depend on farming. The researchers are focusing on plant ailment detection and managing the imbalanced nutrition in plants. Automation is introduced in agricultural fields and most of these automation strategies use the Internet of Things (IoT) for enhance productivity and automate processes. With the help of several deep and machine learning approaches the endless decision-making performance is performed. Here, the endless decision performance shows appropriate outcomes which helps to solve the unstructured problems in smart farming. It is monitored that the traditional analysis doesn't have enough decision-making ability in the selection of fertilizer quantity that is to be used in farming. This inability leads to crop ailments and that affects the lifestyle of humans too. So, the prior detection of ailments in crops is essential. Enforcing Smart Agriculture is a hot topic in research nowadays to overcome crop damage in the future. Therefore, a new IoT-based smart farming model using deep learning is proposed to increase crop yield. By detecting disease, pests, smart irrigation, and yield, the smart farming model can reduce the amount of water and chemicals used in agriculture. This smart farming model consists of four phases a) disease prediction, b) pest detection c) smart irrigation, and d) yield prediction. In the first phase, the crop images are gathered from online datasets. The diseases in crops are predicted using Multiscale Adaptive CNN with LSTM layer (MA-CNN-LSTM), where the parameters in MA-CNN-LSTM are optimized using Advanced Mountaineering Team-Based Optimization Algorithm (AMTBO). In the second phase, the input images are given to MA-CNN-LSTM to detect crop pests. Here, the AMTBO is utilized for tuning parameters. In the third phase, the soil quality and environment data are fed into the Multi-scale Adaptive 1DCNN with LSTM layer (MA-1D CNN-LSTM) to predict the smart irrigation, where the parameter optimization is done using the AMTBO. Smart irrigation enhances the growth of crops and minimizes water usage. In the final phase, the input data such as crop quality, soil quality, and environment data are given to the MA-1D CNN-LSTM to check the overall yield prediction in an agricultural region. Here, the parameters in MA-1D CNN-LSTM are optimized via the AMTBO. The simulation results are compared with other algorithms and classification techniques to check the performance of the developed model.

The characterization of soil resistance properties is of paramount importance in the realm of pavement design. Indices such as dynamic modulus, resilient modulus, and California Bearing Ratio (CBR) are commonly employed to ascertain these properties. The CBR test is an experimental methodology implemented in laboratory or field settings to assess the subgrade's shear strength and stiffness modulus. Due to the exorbitant expenses linked with these assessments, it is deemed essential to implement distinct methodologies to predict their results. The advancement of artificial intelligence (AI) methodologies has enabled the production of innovative models and algorithms. Implementing these techniques enables research professionals to choose predictive methodologies over empirical ones. This study employs an AI methodology to assess the mechanical properties of the CBR index. The radial basis function (RBF) technique was used as a problem-solving methodology to create a machine-learning model. The methodology entails the utilization of sampling experiments to tackle a precisely defined problem. Three different meta-heuristic optimisation techniques were used in this study, namely, the Archimedes optimization algorithm (AOA), bald eagle search optimization (BESO), and Ebola optimization search (EOS), to achieve optimal outcomes. Furthermore, the entire procedure is subjected to evaluation by employing evaluators. According to the results, RBEO obtained the most suitable values in presented metrics, such as R2 and RMSE, equal to 0.9969 and 0.629, respectively. In general, EOS indicated the most desirable accuracy when coupled with RBF compared to BESO and AOA.

In modern times, various empirical and theoretical methodologies have been proposed for the determination of undrained shear strength (USS) via the application of field tests, with particular emphasis on the evaluation of pertinent soil properties. Several techniques utilized in this area incorporate correlation assumptions that yield imprecise results. Moreover, conventional methodologies display a dearth of efficacy with respect to both temporal and financial resources. Through novel machine learning strategies that utilize the Random Forest model, this study aims to rectify the deficiencies of current approaches and achieve more accurate assessments of the undrained shear strength of fragile soils. Three meta-heuristic optimization techniques, including Manta Ray Foraging Optimization (MRFO), Weevil Damage Optimization Algorithm (WDOA), and School-Based Optimization (SBO), were used in this research to accomplish optimization goals. The models were trained using four designated intake parameters, which included liquid limit (LL), plastic limit (PL), overburden weight (OBW), and sleeve friction (SF). To evaluate the models, the last phase of the study utilized a set of five statistical metrics, which included R2, RMSE, MSE, U95, and WAPE. In general, it can be concluded that machine learning in the hybrid method has been shown to be an effective technique for predicting the USS.

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.