Machine Learning and Artificial Intelligence for Digital Twin to Accelerate Sustainability in Positive Energy Districts

The synergistic interplay of artificial intelligence and digital twin in environmentally planning sustainable smart cities: A comprehensive systematic review

“… Shen et al. [ 34 ] ML, AI Positive energy districts (PEDs) Optimization of PEDs Optimization of livability in urban environments for sustainability dimensions. Lv et al.…”

“…By leveraging AI algorithms in UDT, cities can efficiently monitor and allocate resources, such as energy, water, and waste [ 33 ]. Shen, Saini, and Zhang [ 34 ] focused on PEDs in terms of integrating various systems and infrastructures to facilitate optimal interactions among buildings, mobility, energy, and advanced technologies to enhance environmental sustainability. This exploration focuses on both the process of creating a DT for PEDs and its optimization for enhancing livability.…”

“…By leveraging smart IoT sensors, advanced data analytics, powerful AI algorithms, and innovative visualization methods, UDT integrates vast and diverse data from multiple sources to facilitate real-time monitoring and improve predictions and decision-making in urban planning. Indeed, AI and AIoT technologies have recently found their way into the computational functionalities of UDT [ 29 , 30 ], enriching data-driven environmental planning initiatives [ [31] , [32] , [33] , [34] , [35] , [36] ] in sustainable smart cities. By integrating AI models, such as machine learning (ML), deep learning (DL), computer vision (CV), and natural language processing (NLP), planners can effectively manage vast datasets, identify patterns, and discern trends via UDT systems, thereby facilitating more informed decision-making across various domains through automation, optimization, and prediction.…”

Greencoin as an AI-Based Solution Shaping Climate Awareness

“…It is a combined approach to new forms of modeling and analysis based on big data and machine learning/artificial intelligence that combines the capabilities of a virtual model, data management, analytics, simulation, system control, visualization, and information sharing. Such an approach is considered a potential solution for positive energy districts (PED) optimization, for example, because it requires the integration of various systems and infrastructures to obtain optimal interactions between buildings, stakeholders, mobility, energy systems, and ICT systems [ 98 ].…”

“…An overview of AI applications in cities provides valuable information for optimizing living conditions in the urban environment following sustainable social, economic, and environmental development [ 23 , 54 , 98 ]. The number of case studies found proved the increasing interest in the use of AI for urban processes [ 25 ], but our SLR search [ 9 , 10 , 11 ] showed that despite the recognized need to develop digital solutions to achieve urban climate neutrality [ 5 ], there is still limited evidence on tools that moved outside the theoretical or pilot phase.…”