This study investigates the factors influencing public transport acceptance in Egyptian cities using advanced machine learning techniques, including Optimal Regression Forest (ORF) and Variance-Based Sensitivity Analysis (VBSA). We analyze data from a survey of 2,511 respondents using a stated preference experiment to identify key drivers of acceptance and quantify their impact. VBSA was applied, quantifying both direct and interaction effects of fourteen explanatory variables. The results show that socioeconomic variables, perceived benefits, and service reliability are the most influential factors, with significant implications for policymakers seeking to improve public transport adoption. By integrating ORF and VBSA, our model achieves strong predictive performance, providing actionable insights for enhancing transport policy and service design. These findings contribute to the literature on public transport planning and offer practical recommendations for urban planners and policymakers in Egypt and in other Middle East and North Africa (MENA) cities with comparable socioeconomic and institutional conditions.

The world's growing population, expanding economies, and rapid technological progress have intensified the search for sustainable energy, making green hydrogen produced by renewable-powered water electrolysis a promising alternative to fossil fuels. This research examines the performance and cost of a green hydrogen production system that utilizes dual solar energy conversion methods to power an alkaline water electrolyzer (AWE) using TRNSYS software. Three system design configurations were analyzed under various climatic conditions across Egypt, including Cairo, El-Arish, Mersa-Matruh, Assiut, and Aswan. The first configuration (S.1) integrates a photovoltaic (PV) array with AWE. The second (S.2) adds an evacuated-tube solar collector to harness thermal energy, while the third (S.3) further incorporates a solar thermal storage subsystem to enhance stability and efficiency. The system configurations were evaluated daily, monthly, and annually. Daily and monthly analyses focused on Assiut, while annual assessments covered all five cities. Additionally, the AWE operating temperature, which ranged from 50 °C to 90 °C, was analyzed for its impact on performance metrics. Finally, an economic feasibility study was conducted for the three configurations for the five cities. Model validation showed strong agreement with experimental data from the literature. Results indicate that increasing the AWE temperature enhances hydrogen production efficiency and reduces energy consumption. On a daily scale, S.2 achieved the best performance on a spring day, driven by low PV module temperatures and optimal solar geometry, reaching an AWE operating temperature of 103.62 °C, a hydrogen production rate of 0.547 kg/h, and a total daily yield of 3.876 kg. The summer day showed the most significant relative improvement, with S.2 producing 5.5% more hydrogen than S.1 due to effective solar thermal integration. The monthly analysis revealed that S.3 achieved the highest hydrogen and oxygen productivity, primarily because it can store and reuse thermal energy for continuous water preheating. Annually, S.3 achieved superior performance, increasing hydrogen generation by 7.71%, improving efficiency by 4.68%, and reducing the Levelized Cost of Hydrogen by 4.25%, reaching 2.48 $/kg in Aswan. These findings emphasize that integrating a solar thermal energy storage subsystem improves the overall performance-cost of the solar-to-hydrogen generation system.

This study examines the integration of human behavior into pedestrian path design, adopting a multidimensional approach that encompasses physical, psychological, social, environmental, and economic aspects. Recognizing a significant gap in current literature, particularly the limited consideration of integrated modeling frameworks and machine learning in developing urban contexts, this study aims to identify critical elements influencing pedestrian satisfaction and propose comprehensive, user-centered solutions. Theoretical foundations include behavioral science, urban planning, and architectural insights, while the empirical component involves data collection through direct observations, structured questionnaires, and personal interviews from users of a selected pedestrian path in New Asyut City, Egypt. A key methodological contribution of this research is the innovative application of Deep Residual Neural Networks (DRNNs) and Variance-Based Global Sensitivity Analysis (VBSA), allowing robust quantification and prioritization of design factors. Findings highlight the primary influence of easy access, safety, visual coherence, and climatic comfort, alongside significant interactions among these elements. Moreover, the study underscores critical shortcomings such as inadequate public transportation integration, inconsistent visual aesthetics, limited shading, and lack of economic activities along the pathway. By addressing these deficiencies and interactions comprehensively, this research provides urban planners and policymakers with a replicable analytical model and actionable insights to enhance pedestrian infrastructure. Also, the provided analysis framework is general and can be applied in other urban design contexts.

Light field angular super-resolution (LFASR) aims to reconstruct densely sampled angular views from sparsely captured inputs, enabling high-fidelity rendering, refocusing, and depth estimation. In this paper, we propose a novel LFASR framework that employs a tri-visualization feature extraction strategy, which jointly processes Sub-Aperture Images (SAIs), Epipolar Plane Images (EPIs), and Macro-Pixel Images (MacroPIs) to comprehensively exploit the spatial-angular structure of light fields. These complementary representations are processed in parallel to extract diverse and informative features, which are then refined through a deep spatial aggregation module composed of residual blocks. The proposed pipeline consists of three key stages: Early Feature Extraction (EFE), Advanced Feature Refinement (AFR), and Angular Super-Resolution (ASR). Extensive experiments on both synthetic and real-world …

Accurately estimating the 3D layout of rooms is a crucial task in computer vision, with potential applications in robotics, augmented reality, and interior design. This paper proposes a novel model, PanoTPS-Net, to estimate room layout from a single panorama image. Leveraging a Convolutional Neural Network (CNN) and incorporating a Thin Plate Spline (TPS) spatial transformation, the architecture of PanoTPS-Net is divided into two stages: First, a convolutional neural network extracts the high-level features from the input images, allowing the network to learn the spatial parameters of the TPS transformation. Second, the TPS spatial transformation layer is generated to warp a reference layout to the required layout based on the predicted parameters. This unique combination empowers the model to properly predict room layouts while also generalizing effectively to both cuboid and non-cuboid layouts. Extensive experiments on publicly available datasets and comparisons with state-of-the-art methods demonstrate the effectiveness of the proposed method. The results underscore the model’s accuracy in room layout estimation and emphasize the compatibility between the TPS transformation and panorama images. The robustness of the model in handling both cuboid and non-cuboid room layout estimation is evident with a 3DIoU value of 85.49, 86.16, 81.76, and 91.98 on PanoContext, Stanford-2D3D, Matterport3DLayout, and ZInD datasets, respectively. The source code is available at: https://github.com/HatemHosam/PanoTPS_Net.

Canal rehabilitation improves water management and agricultural productivity but requires balancing immediate benefits with long-term sustainability risks. Unlike previous studies that focused mainly on water seepage and groundwater effects, this research takes a comprehensive approach by integrating environmental, social, and economic factors to create strategic guidelines for sustainable canal projects. This holistic method ensures that water infrastructure improvements optimize performance while maintaining ecological balance, supporting communities, and addressing water security challenges amid climate change and increasing demand. This research introduces a novel approach for conducting quantitative risk assessments of concrete-lined canals by combining Fuzzy logic, the Analytic Hierarchy Process (FAHP), and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). This integrated framework allows for the effective identification and prioritization of key risk factors associated with concrete canal lining projects. To validate the methodology, the study applied it to a case study in Egypt. Risk factors were categorized and analyzed across three primary domains: environmental, economic, and social. Using the FAHP-TOPSIS approach, the study assigned weighted values to individual risk factors within each domain, enabling a comparative evaluation of risk indices and a systematic ranking of environmental, economic, and social considerations. The findings revealed that environmental risk domain had higher index values compared to economic and social domain. Notably, groundwater depletion emerged as a critical factor with a significant impact on the overall risk index. The research employs bow-tie analysis to thoroughly investigate the five most critical risk factors.

This study investigates the impact of transitioning from flood to drip irrigation on sugarcane cultivation in Upper Egypt. It evaluates how planting methods—cane stalks and plantlets—affect sugar quality under both systems. A selected set of crop samples was analyzed for sucrose content in the official laboratory of the Ministry of Irrigation. The results offer insights into the economic benefits of drip irrigation, highlighting its role in enhancing sugar quality and returns. Drip irrigation, particularly with plantlets, achieves a maximum sucrose content of 14.3%, a 21.2% improvement over the 11.8% under flood irrigation. This sugar quality enhancement is accompanied by a substantial yield increase: up to 9,895.6 kg/acre with drip irrigation vs. 5,351.9 kg/acre with flood irrigation—an 84.9% increase. Drip systems also show higher water-use efficiency, generating 1.45 kg of sugar per cubic meter of water, compared to 0.46 kg/m³ for flood. Application efficiencies range from 85% to 90% for drip, versus 45%–50% for flood. The study highlights the potential of drip irrigation in arid regions like Upper Egypt, where water scarcity is a major concern. Integrating modern irrigation with local conditions enhances both production and sustainability. These findings emphasize the dual benefits of higher yield and water savings, maximizing returns and reinforcing agricultural resilience under climate and water stress.

The high uncertainty of distributed renewable energy, coupled with the complex statistical correlations among photovoltaic (PV) output power profiles across different geographical locations, significantly increases the difficulty of power system operation and planning. Efficient extraction of representative PV power generation scenarios is essential for reducing the computational burden of optimization models and improving decision-making efficiency. To address the challenge, a novel graph clustering model based on shared weight and adaptive fusion is proposed, which effectively captures the correlation among multiple PV power stations and extracts representative scenarios. An alternating optimization algorithm based on the Lagrange multiplier method and eigenvalue decomposition is proposed to obtain the global optimal solution with fast convergence, thereby improving computational efficiency. The highlight of this work is the dual validation through systematic theoretical proofs and multiple dimensional simulation experiments. In terms of theoretical proof, the low sensitivity of the model parameters ensures ease of use in real-world settings, while the proven convergence of the algorithm guarantees computational reliability. In terms of simulation experiments, the proposed clustering model is verified to have collaborative optimization capability, feature identification capability, high cohesion, low coupling, noise resistance, and parameter sensitivity, as well as the convergence of the solution algorithm using actual PV data from Australia. The effectiveness of this work in extracting representative scenarios of the PV output is verified through the probabilistic power flow analysis using the IEEE 69-bus network, significantly enhancing the efficiency and credibility of power system planning studies with high renewable penetration.