his study aims to investigate how the electrical-resistivity of different soils and grounding enhancement-materials is influenced by water-content and the dehydration under ambient and high-constant temperatures. The used enhancement-materials were extracted from surrounding wastes in Egyptian desert. First, waste enhancement-materials, their developed-mixture and soil samples were prepared for experimental testing. The contact-resistance between soil and enhancement-material was measured by using a designed soil-box. It was observed that adding a wood-ash as an interface-layer between the soil and enhancement-materials decreased significantly the contact-resistance. The developed-mixture and wood-ash demonstrated highest water-content retention when compared against the other enhancement-materials. This maintains their resistivity values low to serve for grounding purpose. The wood

The Holy City of Mecca is the place where millions of people gather for religious rituals over the year, and despite the enormous administrative efforts directed to the administration of Congestion Management (CM) during the Hajj and the "Al Mashaaer days", there is always the possibility of introducing better services in subsequent years. This study has a practical outcome in this respect, as it aims to develop a methodological framework that can operate as a supportive tool in the administration of the Hajj, thus easing the movement of pilgrims in congested areas. The methodology acknowledges that the major areas of mobility in Mecca seem to be repetitive, with the leading destination being the Al Kaaba area and particular locations (hotels) being targeted at certain times (Prayer times). To support this mobility, the users and the drivers should be connected via a single platform based on an Artificial Intelligence algorithm (Reinforced Learning, for example). Such a strategy would optimize mobility in the area over time by learning from actions/decisions such as ridesharing matching, taxi dispatching, en-route guiding, and the generation of intermodal paths. That would help in providing solutions for real-time interaction. Decisions about departure times, paths to follow, modes of travel, and logistic freight movement would be available for all.

There is no doubt that the travel demand forecasting stage is the most crucial stage in any transportation project, with the aim of improving existing facilities or establishing one from scratch. Although transportation planners agree widely about the four conventional steps of demand forecasting, there are inherent debates about their algorithmic applications. This article gives a thorough review of the demand forecasting stages. In addition, a complete framework is given for the process of travel demand forecasting in multi-modal networks, which considers the interdependence between the forecasting steps and offers the ability to incorporate the advances of machine learning and transportation simulation programs for the sake of accuracy.

Over time, traffic sensors have become recognized as a leading source of traffic flow data. Despite their solid capabilities for measuring various types of traffic flow information, they cannot be implemented at all intersections or mid-blocks within the transportation network. Consequently, the traffic sensor location problem (TSLP) emerged to address the questions of how many sensors are needed and where they should be installed. This study presents a new formulation that combines path covering and differentiation into a single sensor location strategy using vehicle identification sensors. The solution strategy ensures the uniqueness of path flow identification. The problem's complexity has two main dimensions: its mathematical formulation, which is known to be NP-hard, and the inherent combinatorial complexity resulting from the need for complete network path enumeration. Therefore, finding an efficient solution algorithm for large-scale networks is challenging. In this article, the problem is recast as a set-covering problem. The dual formulation is then considered, demonstrating that a shortest path-based column generation strategy can produce as many paths as needed, avoiding existing intractability. This path-building process resolves the problem using a combination of heuristics and exact solution methods. The scalability of the proposed strategies was evaluated using two networks of varying sizes. A benchmark network demonstrated the results' uniqueness compared to those in the literature. Additionally, the method proved highly effective in managing a network with more than 10,000 demand node pairs, producing practical solutions under normal traffic flow circumstances.

Abstract

The effective detection and monitoring of mining tailings’ leachates (MTLs) plays a pivotal role in environmental protection and remediation efforts. Electrical resistivity tomography (ERT) is a non-invasive technique widely employed for mapping subsurface contaminant plumes. However, the efficacy of ERT depends on selecting the optimal electrode array for each specific case. This study addresses this challenge by conducting a comprehensive review of published case studies utilizing ERT to characterize mining tailings. Through numerical simulations, we compare the imaging capabilities of commonly used electrode configurations, six ERT arrays, aiming to identify the optimal array for MTLs’ detection and monitoring. In addition, field surveys employing ERT were conducted at the El Mochito mine tailings site to detect zones saturated with leachates within the tailing storage facilities (TSFs). The findings indicate that the “Wenner-Schlumberger” array exhibits superior data resolution for MTL detection. However, the choice of the optimal electrode array is contingent on factors such as survey location, geological considerations, research objectives, data processing time and cost, and logistical constraints. This study serves as a practical guide for selecting the most effective electrode array in the context of pollutant penetration from mining tailings, employing the ERT technique. Furthermore, it contributes valuable insights into characterizing zones saturated with mining tailing leachates within the TSFs, providing a solid foundation for informed environmental management and remediation strategies.

Abstract

The construction industry’s shift towards sustainable practices has spurred interest in innovative materials, with Recycled Aggregate Concrete (RAC) standing out as a notable candidate. This material leverages recycled aggregates to mitigate waste, conserve resources, and reduce environmental impact. However, the accurate prediction of RAC’s compressive strength (CS) is challenging due to its intricate composition and variable material properties. To address this, artificial intelligence (AI) models are increasingly being used for their ability to uncover complex data patterns. This study offers a detailed comparison of ten advanced AI models for predicting RAC CS, including Artificial Neural Networks, Support Vector Regression, Decision Tree Regression, Random Forest Regression, k-Nearest Neighbors, Lasso, AdaBoost, Bagging, XGBoost, and CatBoost models. Each model is fine-tuned through hyperparameter optimization to enhance predictive accuracy. Additionally, SHAP (SHapley Additive exPlanations) algorithms are employed to interpret the models, providing insights into feature importance. The results demonstrate that all models achieved R² values exceeding 75%, with the CatBoost model attaining the highest R² value of 91% on the testing set. The CatBoost model also recorded the lowest error indices, with an MAE of 2.79 and an RMSE of 4.045, making it the most effective model for predicting RAC strength. SHAP analysis identified cement, water, sand, and RA water absorption as key features influencing RAC strength. This study underscores the potential of AI models in advancing the predictability and performance of sustainable construction materials.

To mitigate the adverse effects of floods, hydrologists are increasingly turning to artificial intelligence methodologies to enhance streamflow forecasting capabilities. Drawing inspiration from the efficacy of the Long Short-Term Memory (LSTM) model in capturing temporal dynamics and dependencies within data set, we have employed LSTM for predicting sequential flow rates utilizing collected data sets. Recognizing that not all data set contribute equally to accurate flood forecasts, it becomes imperative to discern and prioritize the relevant variables. Conventional LSTM models often fall short in effectively identifying and ranking informative factors. To overcome this limitation, we introduce an Attention LSTM (ALSTM) model tailored for streamflow forecasting, adept at identifying and capturing critical factors within the time series dataset. Leveraging data set sourced from the United States Geological Survey (USGS), our proposed model exhibits notable performance enhancements. By integrating an attention mechanism during the pre-processing stage, the ALSTM model showcases its ability to generate precise long-term forecasts across most of the basins. Utilizing a continuous 33-year streamflow data set (1970–2003), our proposed model surpasses conventional time series approaches in streamflow forecasting accuracy.

Streamflow forecasting is vital for managing water resources, such as flood control, agriculture planning, hydropower generation, environmental management, drought management, and water quality management. Motivated by the success of artificial intelligence models for hydrological applications, this study proposes a model that integrates an autoencoder, the Convolutional Neural Networks (CNN), and the Long Short Term Memory (LSTM) networks. Thirty years daily dataset were served to the Autoencoder Convolutional Neural Network Long Short Term Memory (AE-CNN-LSTM) and the baseline models. To evaluate the model's accuracy, 80% of the dataset was used for training and the remaining 20% was used to test the performance of these models. Statistical metrics, for instance, the Root Mean Squared Error (RMSE), the Mean Absolute Error (MAE), the Mean Absolute Percentage Error (MAPE), the Nash–Sutcliffe Efficiency (NSE), and the Coefficient of determination (R²) were employed to evaluate the model’s performance. In terms of train RMSE, test RMSE, train MAE, test MAE, train MAPE, test MAPE, train NSE, test NSE, train R², and test R², the proposed model significantly obtained the best results with values of 2.6299, 2.7971, 0.1676, 0.1881, 16.76, 18.81, 0.98, 0.97, 0.98, and 0.96, respectively.

Abstract

The selection of an optimal dataset is crucial for successful remote sensing analysis. The PRISMA hyperspectral sensor (with 240 spectral bands) and Landsat OLI-2 (boasting high dynamic resolution) offer robust data for various remote sensing applications, anticipating their increased demand in the coming years. However, despite their potential, we have not identified a rigorous evaluation of both datasets in geological applications utilizing Machine Learning Algorithms. Consequently, we conduct a comprehensive analysis using Random Forest, a widely-recommended machine learning algorithm, and employ K-fold cross-validation (with K = 2, 5, 10) with grid-search hyperparameter tuning for enhanced performance. Toward this aim, diverse image-processing approaches, including Principal Component Analysis (PCA), Minimum Noise Fraction (MNF), and Independent Component Analysis (ICA), were applied to enhance feature selection and extraction. Subsequently, to ensure better performance of the RF algorithm, this study utilized well-distributed points instead of polygons to represent each target, thereby mitigating the effects of spatial autocorrelation. Our results reveal dataset-hyperparameter dependencies, with PRISMA mainly influenced by max_depth and Landsat 9 by max_features. Employing grid-search optimally balances dataset characteristics and data splitting (folds), generating accurate lithological maps across all K values. Notably, a significant hyperparameter shift at K = 10 produces the best lithological maps. Fieldwork and petrographic investigations validate the lithological maps, indicating PRISMA’s slight superiority over Landsat OLI-2. Despite this, given the dataset nature and band count difference, we still advocate Landsat 9 as a potent multispectral input for future applications due to its superior radiometric resolution.

Abstract

The construction industry is shifting towards sustainability, emphasizing the need for innovative materials. Recycled Aggregate Concrete (RAC), utilizing recycled aggregates, emerges as a promising eco-friendly solution to minimize waste and resource utilization. However, accurately predicting its compressive strength (CS) is challenging due to varying composition and properties. This study addresses this issue by employing machine learning models, specifically five gradient boosting algorithms: Gradient Boosting Machine (GBM), LightGBM, XGBoost, Categorical Gradient Boost (CGB), and HistGradientBoosting (HGB). A total of 314 mixes from relevant published literature were aggregated to train the models. These models are meticulously fine-tuned through hyperparameter optimization for optimal predictive performance. The study also introduces SHAP (SHapley Additive exPlanations) algorithms for model interpretability, elucidating feature contributions to predictions. The results revealed that among the five gradient boosting models, CGB demonstrated the highest R2 value of 92% on the testing set, while LightGBM exhibited the lowest Coefficient of Determination (R2) value of 88%. Additionally, CGB achieved the lowest Root Mean Square Error (RMSE) of approximately 4.05, whereas XGBoost showed the highest RMSE of around 4.8. Furthermore, for Mean Absolute Error (MAE), LightGBM recorded the lowest value of approximately 3.16, while HGB yielded the highest MAE of about 3.8. The SHAP analyses reveal influential features impacting RAC strength, highlighting the significance of cement, water, sand, and recycled aggregate water absorption in predicting RAC compressive strength.