The growing demand for renewable energy positions it as a cornerstone for climate change mitigation and greenhouse gas emissions reduction. Although renewable energy sources generate around 30% of global electricity, their production and deployment involve significant environmental challenges. This review analyzes renewable energy projects from a life cycle perspective, focusing on environmental impacts throughout the supply chain. Particular emphasis is placed on the energy-intensive nature of manufacturing phases, which account for 60% to 80% of total emissions. The extraction of critical raw materials such as neodymium, dysprosium, indium, tellurium, and silicon is associated with emission levels ranging from 0.02 to 0.09 kg of carbon dioxide equivalent per kilowatt-hour for rare earth elements, along with an estimated average land degradation of 0.2 hectares per megawatt installed. Furthermore, the production of solar-grade silicon for photovoltaic panels consumes approximately 293 kilowatt-hours of electricity per kilogram, significantly contributing to the overall environmental footprint. Through a comprehensive review of the existing literature, this study integrates life cycle assessment and sustainable supply chain management approaches to identify environmental hotspots, quantify emissions, and propose strategic improvements. The analysis provides a structured, systematized, and data-driven evaluation, highlighting the relevance of circular economy principles, advanced recycling technologies, and digital innovations to enhance sustainability, traceability, and resilience in renewable energy supply chains. This work offers actionable insights for decision-makers and policymakers to guide the low-carbon transition.

K-Nearest Neighbors Regression (kNN regression) is a non-parametric, instance-based learning algorithm widely employed for predicting continuous target variables. In contrast to conventional regression methods assuming specific functional forms, kNN regression operates by averaging the target values of the k nearest data points, determined by a chosen distance metric such as Euclidean or Manhattan distance. This method exhibits high adaptability to diverse data distributions, rendering it a versatile tool for modeling in finance, healthcare, and environmental contexts. The selection of k, representing the number of neighbors considered, significantly influences the model's performance by striking a balance between bias and variance. The simplicity and effectiveness of kNN regression are counterbalanced by challenges such as computational complexity with large datasets and susceptibility to noise. This chapter delves into the mathematical foundations and fundamentals of kNN regression, offering a comprehensive guide for leveraging this algorithm in predictive modeling endeavors.

This article presents a 3-D anthropometric vision system, free of ionizing radiation for measuring the medial longitudinal arch (MLA) and longitudinal arch angle (LAA) of the foot, essential for evaluating foot arch disorders that can affect a person’s lifestyle. Existing 2-D techniques for determining MLA based on anthropometric tests have limitations because they exclude important information about foot such as pronation, dorsiflexion, and rotation. To overcome these limitations, the proposed system uses stereo vision and a landmark detection algorithm to measure the 3-D MLA and LAA, considering the $z$ -axis perpendicular to the sagittal plane. The proposed system is compared with a commercial LIDAR using a tridimensional grid (ground truth), obtaining a root mean square error (RMSE) of 1.2° for the proposed system and an RMSE of 4.8° for LIDAR. The proposed system offers several advantages over traditional techniques, including low error, 3-D measurement capabilities, and free of ionizing radiation. In addition, the system’s application in human subjects showed a variability range between 3-D and 2-D measurements for MLA, which is consistent with previous research. Overall, the proposed system has the potential to improve the evaluation and treatment of foot arch disorders, thereby enhancing a person’s quality of life.

The accelerated growth in demands for natural resources such as water and energy has generated a potential energy and water crisis, while the requirements have been hastily driven by the development of emerging technologies that have spanned the various sectors, so the intersection of these technologies, such as Artificial Intelligence (AI), in sustainability, governance and public policies, offers transformative opportunities to combat climate change and promote sustainable development. This study explores the integration of AI in public administration to promote climate resilience, equity and innovation, highlights the applications of AI in resource management, disaster prediction, renewable energy optimization and planning. sustainable, highlighting the priority role of public policies, ethical frameworks and public-private collaborations to ensure the equitable and transparent deployment of AI. Challenges such as data accessibility, resource allocation and adjacent regulatory balance are analyzed with strategies to overcome them, including capacity development and infrastructure investment. The innovative findings suggest that AI as a tool for efficiently managed climate action helps to address environmental challenges, highlighting key elements such as sustainable development through AI that requires collaborative integration between stakeholders, such as those across sectors, integrating equity and ethical principles into climate action and resource management policies. This integrated approach positions AI as a fundamental tool for a more sustainable and equitable future.