In the context of Industry 4.0, digital transformation is reshaping global energy systems. Among the key enabling technologies, Digital Twin (DT)—a dynamic, virtual replica of physical systems—has emerged as a critical tool for improving the performance, reliability, and safety of clean energy infrastructure. In line with the United Nations Sustainable Development Goals (SDGs)—particularly SDG 7 (Affordable and Clean Energy) and SDG 11 (Sustainable Cities and Communities)—the integration of DTs presents unprecedented opportunities to enhance operational efficiency and support proactive decision making. This state-of-the-art review, focused on studies published in 2020–2025, summarizes applications of DTs across the energy value chain, encompassing a broad spectrum of sectors—including solar, wind, hydropower, hydrogen, geothermal, bioenergy, nuclear, and tidal energy—and their critical role in building-to-grid integration. It synthesizes foundational concepts, assesses the evolution of the DT from a predictive tool to a system-level risk-management platform, and provides a critical analysis of its impact. Furthermore, this review discusses the key challenges hindering widespread adoption, including the critical need for interoperability across systems, ensuring the cybersecurity of socio-technical infrastructure, and addressing the complexities of the human-in-the-loop problem. Key research gaps are identified to guide future innovation. Ultimately, this study underscores the transformative potential of DTs as essential tools for accelerating the digital transformation of the energy sector, offering a robust framework for both methodological development and practical deployment.

Urban flooding has become increasingly frequent due to the rising intensity of rainfall driven by urban development and climate change. Effective prevention measures are crucial to mitigate the significant human and material damages caused by such events. Rapid and accurate pre-detection techniques can help to reduce the impacts of urban flooding. With the advancement of deep learning, deep neural networks (DNNs) have been successfully applied across various domains, including computer vision and speech recognition. In particular, DNNs for computer vision demonstrate high performance with relatively low computational costs. In this paper, we propose a flooding region segmentation model for urban underpasses based on the U-Net architecture. To train and evaluate the model, we collected datasets from the Mannyeon, Oryang, and Daedong underpasses in Daejeon. The proposed method achieved Dice coefficients of 98.8%, 94.03%, and 93.85%, respectively. This model demonstrates high segmentation performance in detecting flooded regions and can be integrated into continuous flood monitoring systems.

As eco-friendly complexes develop, interest in eco-friendly facilities is also growing. Particularly, rainwater harvesting facilities have demonstrated positive effects by reducing runoff to mitigate urban flooding and recycling water for landscaping and cleaning purposes. In this study, we analyzed the quality of stored rainwater, which has improved by excluding initial runoff, and examined the temperature reduction effects of road sprinkling and mist spraying. Road sprinkling decreased the temperature of asphalt and permeable pavements by approximately 15 °C, with permeable pavements maintaining the reduced temperature for a longer time. The indoor experiments with mist spraying showed a temperature reduction effect of 3.4 °C. The quality analysis of the rainwater harvesting facilities revealed that the water quality was suitable for irrigation and landscaping by excluding the initial runoff. This study confirms the effectiveness of rainwater utilization in mitigating urban heat islands and improving water circulation within cities.

Critical cyber–physical infrastructure, such as urban water distribution systems, underpins public health, economic stability, and environmental sustainability, yet faces escalating threats from sophisticated cyber–physical attacks that evade traditional defenses. Deep-learning-based reconstruction models offer the adaptability needed to detect unseen anomalies but impose prohibitive computational and environmental costs, creating an unresolved tension between security and sustainability. While PCA–deep-learning hybrids are widely used, their architectural configurations for anomaly detection have remained naive and unquantified in terms of real-world resource demands. This study demonstrates that among five novel PCA–autoencoder configurations evaluated across two challenging water distribution datasets, architectural synthesis dictates both detection robustness and sustainability, with operational efficiency varying by over an order of magnitude. An integrated model (PCA-D) achieves strong anomaly detection at a cost-effectiveness ratio of 2.62 J per true positive—nearly four times better than the most robust hybrid—while naive wrapper hybrids miss over 77% of threats. The proposed framework converts measured computational loads into annual energy, carbon, and water footprints, revealing that the most detection-robust model is not the most sustainable. These results establish a unifying cost-effectiveness metric and a key design principle: integrated statistical–deep-learning architectures enable genuinely green AI that secures critical infrastructure without incurring excessive environmental burden.

This study conducted a pilot test and field demonstration to analyze the feasibility of using rainwater for road surface sprinkling and its effectiveness in reducing fine dust to create sustainable cities. The pilot test results verified the effectiveness of rainwater sprinkling on road surfaces in reducing fine dust. Subsequently, to ensure field applicability, a test bed with different pavement sections was established along Ojeong-ro in Bucheon, Gyeonggi-do, and a circulatory system for reusing the runoff rainwater was installed and tested for its acceptable dust reduction effectiveness. The results showed that the section with porous pavement exhibited a significant reduction in acceptable dust levels, and a trend of decreasing pollutant levels due to the initial washing effect of rainwater was observed. However, the water quality and quantity analysis revealed that additional purification processes are necessary to reuse the water for road surface sprinkling. Based on these findings, this study suggests that expanding porous pavement and introducing purification systems are essential for installing rainwater utilization facilities to reduce fine dust in urban areas. This research provides critical foundational data that can contribute to urban environmental improvement and establish a sustainable water circulation system.

The uneven spatiotemporal distribution of precipitation, exacerbated by climate change, poses significant challenges to sustainable water resource management and flood forecasting. Deterministic models often fail to address the uncertainties inherent in long-term hydrological predictions. To address this gap, this study introduces a novel probabilistic flood forecasting framework that integrates a distribution head into attention-based architectures (Transformer and Informer) to capture long-range spatiotemporal dependencies. A second contribution is the implementation of a cascaded principal component analysis (PCA)-based data fusion approach that incorporates satellite-derived mesoscale inputs for long-horizon forecasting. The framework was evaluated across forecasting horizons of 7, 30, 60, and 180 d in two hydrologically distinct basins in the USA. Experimental results show that the Transformer achieved the best overall performance, with Continuous Ranked Probability Scores (CRPS) up to 35% lower than those of the baseline Bayesian LSTM in extended forecasting scenarios. In addition, the attention-based models maintained high reliability, with Prediction Interval Coverage Probabilities (PICP) exceeding 90% for the 95% prediction interval even at the 180-d lead time. Although the probabilistic LSTM showed greater error accumulation at longer horizons, the Informer provided a computationally efficient alternative, with accuracy remaining within 5% of the Transformer while reducing computational complexity. These findings highlight the potential of attention-based architectures for stable, uncertainty-aware flood forecasting in hydrologically dynamic basins.