Despite the increasing importance of AI and ML in smart cities, there are obstacles and factors to take into account for their effective execution and responsible use. These challenges include technical limitations, ethical concerns, privacy issues, and the need for robust policy frameworks. Additionally, the scope and potential applications of AI and ML in smart cities need to be explored to understand the extent to which these technologies can revolutionize urban environments.

This research aims to address the opportunities and difficulties of integrating AI and ML in smart cities. The scope of this study encompasses the following areas:

Understanding the AI and ML’s function in optimizing urban infrastructure, including transportation systems, energy distribution, and waste management.

AI and ML are playing an essential part in the development and advancement of smart cities. The integration of AI and ML technologies with relation to smart cities offers transformative solutions and opportunities for urban environments. AI and ML are enabling examination of large volumes of information collected from various sources in smart cities, leading to data-driven decision-making and improved urban management. According to a study by [2], AI and ML techniques are essential for energy management and optimization in smart cities, resulting in significant energy savings and environmental benefits. These technologies allow for the processing of real-time data from transportation networks, optimizing traffic flow, reducing congestion, and enhancing overall transportation efficiency [3]. Predictive analytics and anomaly detection powered by ML algorithms play a crucial role in smart cities. ML models can analyze patterns and historical data to identify trends, make accurate predictions, and optimize resource allocation in areas such as garbage management, energy use, and safety for people [4]. For example, predictive analytics can be used to predict traffic jams and adjust the timing of the traffic signals accordingly [5]. Furthermore, AI and ML technologies facilitate citizen engagement and personalized services in smart cities. Chatbots and virtual assistants powered by AI provide interactive interfaces for citizens to access information, report issues, and receive personalized recommendations, enhancing the overall citizen experience [6]. These technologies enable smart cities to provide efficient and customized services to their residents.

AI and ML technologies hold tremendous potential to revolutionize urban environments, enabling transformative advancements in various aspects of city life as given below:

Enhancing Urban Infrastructure: AI and ML technologies have the capacity to optimize urban infrastructure through enhancing effectiveness, sustainability, and resource management. ML algorithms can analyze data from diverse sources to optimize energy consumption in smart grids, reducing costs and environmental impact [2]. Furthermore, AI techniques can be applied to intelligent transportation systems, optimizing traffic flow, reducing congestion, and enhancing overall mobility [5].

The research begins with an introduction to smart cities, providing an overview of their defining features and the pivotal role of AI and ML in their development. It then delves into the ways AI and ML can enhance urban infrastructure, optimizing transportation systems, energy grids, waste management, and urban planning. The discussion also encompasses how AI and ML contribute to public safety and security, through intelligent surveillance, predictive analytics, and cybersecurity measures. Furthermore, the research explores the uses for AI and ML in smart governance and citizen services, enabling citizen engagement, virtual assistance, and decision-making based on data. The blending of AI and ML in smart healthcare is also examined, focusing on remote patient monitoring, disease outbreak detection, and improved healthcare access. Ethical and privacy considerations are highlighted, emphasizing the responsible application of ML and AI in smart cities while safeguarding citizen privacy and addressing biases. The research concludes with a discussion on the challenges and future directions of AI and ML in smart cities, including technical limitations, policy frameworks, and emerging trends.

Researchers and organisations have used numerous definitions to describe smart cities. Reference [11] defined smart cities as “innovative cities that use information and communication technologies (ICT) and other means to improve the quality of life, efficiency of urban operations and services, and competitiveness while ensuring that it meets the needs of present and future generations.” This concept emphasizes the use of ICT as a fundamental element in making cities smarter. The following are the characteristics of smart cities as indicated by Fig. 1.

(a) ICT Infrastructure: Smart cities are characterized by robust and interconnected information and communication technology (ICT) infrastructure that enables data gathering, analysis, and sharing to improve urban operations and services [12].

(b) Data-Driven Decision-Making: To enable data-driven decision-making, smart cities rely on the gathering and analysis of enormous volumes of data from numerous sources. This information consists of data from sensors, devices, and systems deployed throughout the city [13].

(c) Sustainability and Efficiency: Smart cities prioritize sustainable practices, aiming to optimize resource utilization, reduce environmental impact, and enhance energy efficiency [14].

(d) Citizen-Centric Approach: Smart cities focus on enhancing the standard of living for residents by offering them with improved facilities, increased citizen engagement, and a better overall urban experience [15].

(e) Collaborative Governance: Smart cities promote collaboration and partnerships between several parties, including government agencies and businesses, academic institutions, and residents, to co-create and implement innovative solutions [16].

Smart city initiatives are driven by various key components and technologies that enable the transformation of urban environments as follows:

Smart cities are undergoing an IoT revolution by facilitating connectivity and real-time data exchange among various physical devices and sensors [17]. IoT is significantly contributing to several key aspects of smart cities, including transportation systems, energy grids, and waste management. IoT is playing a vital role in optimizing transportation systems in smart cities. By deploying IoT-enabled sensors and devices, cities may collect statistics on traffic movement in real-time, congestion levels, and availability of parking [17]. Such information enables the implementation of data-driven traffic management strategies, resulting in less traffic and more efficient transit. In energy management, IoT is enabling development of smart grids that optimize energy distribution and consumption. IoT sensors deployed in energy grids give current information on energy use trends, granting utilities to identify inefficiencies & allocate energy more efficiently [17]. This results in improved demand response management and reduced energy wastage. Waste management is another area benefiting from IoT in smart cities. IoT sensors in garbage bins track the level of fill and transmit data to waste management systems [17]. This data enables optimized waste collection routes and schedules, leading to enhanced resource utilization and cost reduction. By leveraging IoT technologies, smart cities are adopting a citizen-centric approach, focusing on improving the standard of living for locals. IoT-enabled devices and applications empower citizens to actively engage with urban services and provide real-time feedback [15]. This citizen engagement contributes to the overall success of smart city initiatives. Moreover, IoT fosters collaboration between different stakeholders in smart cities. Government agencies, private sector entities, academic institutions, and citizens come together to co-create innovative solutions [16]. This collaborative governance approach ensures that initiatives related to smart cities meet community needs and ambitions.

A key role is played by AI and ML in driving smart city development, offering transformative solutions to enhance urban environments as follows:

Data Analytics and Decision-Making: AI and ML techniques enable advanced analytics of data and decision-making processes in smart city development. These technologies can analyze vast amounts of data collected from a variety of sources, including sensors and tools, to extract valuable insights and patterns [12]. Algorithms using ML and AI can process real-time data and generate actionable recommendations to optimize resource allocation, improve services, and enhance urban planning [23].

In order to improve the effectiveness, safety, and sustainability of transportation systems, intelligent transportation systems (ITS) refers to the integration of cutting-edge technology, such as sensors, communication networks, and data analytics, into the transportation infrastructure [34]. ITS aims to provide intelligent solutions for traffic management, traveler information, vehicle operations, and transportation infrastructure. Intelligent transportation systems utilize various sensors and technologies to monitor traffic conditions and collect real-time data. These sensors can include loop detectors, video cameras, and GPS devices [35]. Data collected from these sensors, such as traffic volume, speed, and congestion patterns, are crucial for effective traffic management and decision-making. In order to forecast traffic patterns and congestion, advanced traffic management approaches use AI and ML algorithms to analyse historical and real-time traffic data. These predictions help in proactive congestion management and enable authorities to implement effective traffic control strategies, such as adaptive signal control systems [36]. ML models can also optimize traffic signal timings to minimize delays and improve traffic flow [37]. AI and optimisation algorithms are used by intelligent traffic signal control systems to dynamically change signal timings based on current traffic circumstances as indicated by Table 1. These programmes enhance travel times, optimise traffic flow, and lessen congestion [38]. ML techniques can be applied to learn traffic patterns and adapt signal control strategies to changing traffic demands [36]. Communication between automobiles, infrastructure, and traffic management systems is made possible through the incorporation of connected vehicle technology. This connectivity allows for cooperative systems that exchange real-time data, such as vehicle speed, location, and traffic conditions [39]. Cooperative systems facilitate enhanced traffic management, collision avoidance, and improved traveler information.

To achieve effective and sustainable energy management, it is essential to optimise energy distribution and consumption in smart networks. Bidirectional energy flow and real-time monitoring are made possible by smart grids, which incorporate renewable energy sources, energy storage systems, and demand-side management. The implementation of smart meters as part of the Advanced Metering Infrastructure (AMI) allows for detailed energy consumption monitoring [40]. Demand response initiatives further encourage customers to modify their energy use habits during periods of high demand, which results in load shifting and lessens grid stress [41]. Incorporating DERs, such as solar panels and wind turbines, into the energy grid enables the generation of renewable energy and supports local energy production. AI and ML algorithms contribute a vital funtion in optimizing energy management and distribution, enabling load forecasting, energy scheduling, and power flow optimization [42]. ML models can analyze real-time data, predict energy demand, and dynamically adjust energy distribution and generation to optimize efficiency [43]. By incorporating these technologies, smart grids contribute to reduced energy waste, improved grid stability, and increased utilization of renewable energy sources, ultimately promoting sustainable energy management.

Smart waste management systems are instrumental in promoting environmental sustainability by optimizing waste collection, reducing pollution, and maximizing resource utilization as indicated by Table 1. These systems leverage advanced technologies such as Internet of Things (IoT), sensors, and data analytics to enhance waste management processes. Smart bins with sensors that are IoT-enabled can track garbage levels, enabling effective collection routes and reducing needless visits [44]. Data gathering and analysis in real-time enable waste management authorities to identify high-volume areas, optimize collection schedules, and allocate resources more effectively. Furthermore, ML algorithms may examine both historical and current data to predict waste generation designs, facilitating proactive forecasting and resource allocation [45]. Smart waste management systems also promote recycling and waste segregation through the implementation of intelligent sorting techniques. For instance, different sorts of garbage may be recognised using AI-powered picture recognition systems, which can then be categorised [46]. This enables more efficient recycling processes and reduces the environmental impact of waste disposal. By implementing smart waste management systems, cities can achieve significant improvements in environmental sustainability, waste reduction, and resource conservation, leading to a cleaner and greener future.

Improving urban planning and infrastructure development is essential for creating sustainable and livable cities. Technologically sophisticated tools like geographic information systems (GIS), remote sensing, and data analytics, play a crucial role in enhancing urban planning processes. GIS enables the integration and analysis of geospatial data, facilitating informed decision-making for urban development [47]. Remote sensing technologies, such as satellite imagery and aerial photography, provide valuable information for monitoring land use, vegetation, and changes in urban environments [30]. These technologies contribute to effective urban planning by identifying areas for development, assessing environmental impacts, and supporting infrastructure design. Additionally, data analytics and ML algorithms enable the analysis and processing of large-scale urban data, supporting evidence-based decision-making [23]. For instance, ML models can predict population growth patterns, traffic flows, and energy demands, aiding in infrastructure planning and resource allocation [25]. By leveraging these technologies, cities can optimize land use, transportation networks, and environmental management, resulting in urban landscapes that are more resilient and sustainable.

AI and ML algorithms enable the development of intelligent surveillance and monitoring systems. These systems can analyze video feeds, detect anomalies, and identify potential security threats in real-time [31]. For example, AI-based video analytics can detect abnormal behavior, unauthorized access, or suspicious activities, enhancing situational awareness and enabling proactive security measures [31].

AI and ML techniques are utilized in predictive analytics for crime prevention and emergency response. These technologies analyze large volumes of historical crime data, social media feeds, and other relevant sources to identify patterns and predict potential crime hotspots [9]. ML models can assist law enforcement agencies in allocating resources, optimizing patrol routes, and developing proactive crime prevention strategies [9].

AI and ML play a significant role in enhancing cybersecurity in smart city environments. ML algorithms can analyze network traffic, detect anomalies, and identify potential cyber threats [48]. These technologies enable early detection and mitigation of cyberattacks, protecting critical infrastructure and sensitive data in smart city systems [48]. AI-powered systems can also adaptively learn and evolve to counter emerging cyber threats, improving the resilience and robustness of cybersecurity defenses [49].

AI technologies make it easier for citizens to participate and engage by enabling personalized interactions and gathering valuable insights. For instance, AI-powered chatbots and virtual assistants can provide citizens with instant access to information, services, and support [50]. These intelligent systems can handle citizen queries, provide recommendations, and guide users through various government processes. AI algorithms can also analyze citizen sentiment from social media and other sources, providing policymakers with real-time feedback and understanding of public opinion [51]. This enhances citizen-government interaction and promotes inclusive governance.

Chatbots and virtual assistants powered by AI offer efficient and streamlined government services. These intelligent systems automate routine processes, such as filling forms, making appointments, and accessing public records, reducing administrative burden [52]. Chatbots can guide citizens through service applications, provide personalized recommendations, and offer 24/7 assistance [52]. By automating these tasks, government agencies can improve service delivery, enhance accessibility, and save time and resources.

AI and data analytics allow urban officials to make data-driven decisions. Using extensive data analysis from a variety of sources, including user feedback, IoT devices, and social media, AI algorithms can extract valuable insights and patterns [23]. These insights inform evidence-based policy formulation, urban planning, and service improvements [15]. AI technologies can assist in predicting future scenarios, simulating policy impacts, and optimizing resource allocation for improved governance outcomes [23]. Data-driven decision-making enhances the effectiveness and efficiency of government services, ensuring that policies and initiatives align with citizen needs.

In order for healthcare practitioners to monitor patients’ health problems remotely and give care at a distance, AI and ML are essential to remote patient monitoring and telemedicine. ML algorithms can analyze patient data collected from wearables, sensors, and electronic health records, detecting anomalies and providing early warning signs for deteriorating health [53]. Telemedicine platforms powered by AI facilitate virtual consultations, remote diagnosis, and personalized treatment recommendations, improving accessibility and convenience for patients [54].

Predictive analytics is used to identify disease outbreaks and take appropriate action. ML models can spot patterns and forecast disease outbreaks by examining a variety of data sources, including social media, electronic health records, and environmental data [55]. AI algorithms can support real-time monitoring of disease spread, identify high-risk areas, and assist in resource allocation and response planning [56]. Early detection and prompt response are crucial for effective disease control and prevention.

Healthcare access and service delivery are improved by AI and ML technologies in smart cities. In order to improve clinical decision-making, these technologies can analyse vast amounts of healthcare data, including patient records, medical literature, and therapy recommendations [57]. ML algorithms can assist in diagnosing diseases, predicting treatment outcomes, and recommending personalized treatment plans [58]. AI-powered chatbots and virtual assistants provide timely and accurate information to patients, reducing wait times and improving healthcare access [59]. Additionally, AI and ML can increase operational efficiency in healthcare institutions by streamlining operations and allocating resources more efficiently [60].

To prevent possible harm and advance social well-being, smart cities must employ AI and ML technologies responsibly and ethically. To regulate the use of AI systems, policies and frameworks that prioritise openness, responsibility, and justice should be created [61]. Design and implementation procedures should incorporate ethical issues, ensuring that AI systems align with societal values and respect human rights [62]. Responsible use of AI also requires ongoing monitoring, auditing, and evaluation of AI algorithms and systems to address potential biases and unintended consequences [61].

As smart cities rely on extensive data collection and analysis, safeguarding citizen privacy and data protection becomes paramount. To specify how data is gathered, rules for data governance must be developed that are visible and clear, stored, accessed, and shared [63]. To safeguard personal information, strong data anonymization methods, encryption, and secure data storage should be used [64]. Citizens’ consent and control over their data should be respected, and mechanisms for data access, correction, and deletion should be provided [63].

AI algorithms have the potential to perpetuate biases and discrimination if not carefully designed and monitored. Bias mitigation techniques, such as varied and unbiased training data, algorithmic auditing, and continuous evaluation, should be employed to minimize biases in AI algorithms [65]. Fairness metrics and guidelines can help in promoting fairness and equal treatment across different demographic groups [66]. Ensuring transparency in AI decision-making processes can enhance accountability and enable individuals to challenge and understand algorithmic outcomes [62].

AI and ML in smart cities face several technical issues that need to be resolved. These challenges contain the lack of standardized data formats, interoperability issues among different systems, and the need for robust and scalable algorithms [67]. Further research is required to enhance the accuracy and reliability of AI models, improve the interpretability of ML algorithms, and handle dynamic and complex urban data [68]. Additionally, the deployment of AI and ML systems in resource-constrained environments and the integration of edge computing and technical obstacles must be removed while using cloud technology [69]. The execution of AI and ML in smart cities requires careful policy and regulatory considerations. Privacy, security, and ethical concerns must be addressed to protect citizen rights and ensure responsible use of these technologies [70]. Governments need to establish comprehensive frameworks and rules to control the gathering, using, and sharing of data, and to mitigate potential biases and discriminatory practices [71]. Policymakers working together, technology developers, and citizens are essential to establish trust, transparency, and accountability in the deployment of AI and ML in smart cities. The future of AI and ML in smart cities holds tremendous potential. Integrating AI with Internet of Things (IoT) devices to enable real-time data processing and edge decision-making is one of the emerging trends [69]. Federated learning approaches, which allow multiple entities to collaboratively train ML models without sharing sensitive data, hold promise for privacy-preserving AI in smart cities [72]. Continued advancements in AI algorithms, such as deep learning and reinforcement learning, will enhance the capabilities of smart city systems. Furthermore, the application of AI and ML in sustainability, resilience, and social equity domains of smart cities will contribute to more inclusive and environmentally-friendly urban environments.

The research highlights the significant role of AI and ML in smart city development across various domains. The findings emphasize how these technologies can drive transformative solutions, enhance urban environments, and enhance inhabitants’ quality of life. One key area where AI and ML can make a substantial impact is data analytics and selecting the best alternative. By examining the massive volumes of information gathered from sensors and devices, these technologies can extract valuable insights and patterns, leading to optimized resource allocation, improved services, and enhanced urban planning. This capability has the potential to revolutionize how cities operate and rely on current facts to make wise judgements. Predictive analytics and optimization are another crucial aspect where AI and ML can drive smart city development. By examining both past and present data, ML algorithms can forecast inclinations and configurations, enabling cities to proactively address challenges. This capability can be applied to various areas such as traffic management, energy consumption, and waste management, leading to optimized resource allocation and improved operational efficiency. Intelligent transportation systems stand out as a key domain where AI and ML can substantially enhance smart cities. AI algorithms can offer real-time traffic monitoring by using real-time data, congestion prediction, and adaptive traffic signal control. These technologies contribute to improved traffic flow, reduced congestion, and enhanced mobility services. The integration of connected vehicle technologies further enhances traffic management and traveler information. In order to improve public safety and security in smart cities, AI and ML are also essential. Intelligent surveillance systems powered by AI algorithms can analyze video feeds and detect anomalies, improving situational awareness and enabling proactive security measures. Large volumes of data may be processed by ML models to find patterns associated with crime, supporting law enforcement agencies in preventing and responding to incidents effectively. Smart energy management is another domain where AI and ML can drive sustainability in smart cities. ML algorithms can optimize energy consumption and distribution by analyzing usage of energy patterns and incorporating renewable sources of electricity into the grid. These technologies contribute to more efficient resource utilization and reduced environmental impact. The research also highlights the importance of AI and ML in improving urban planning and infrastructure development. By integrating GIS, remote sensing, and data analytics, these technologies enhance decision-making processes and enable evidence-based urban planning. ML models can predict population growth, traffic flows, and energy demands, aiding in infrastructure planning and resource allocation. However, the implementation of AI and ML in smart cities comes with ethical and privacy considerations. Ensuring responsible and ethical use of these technologies is crucial to avoid potential harm and promote societal well-being. Safeguarding citizen privacy and data protection is also essential in the era of extensive data collection. To guarantee equality across all demographic groups, it is vital to address biases and promote fairness in AI systems. While AI and ML offer immense potential for smart city development, several challenges need to be addressed. Technical challenges include standardizing data formats, addressing interoperability issues, and developing robust and scalable algorithms. Policy and regulatory considerations are crucial to establish frameworks that protect citizen rights and ensure responsible use of AI and ML. Building trust, transparency, and accountability in the use of these technologies requires cooperation amongst stakeholders, including decision-makers, technology developers, and people. Looking ahead, emerging trends such as the integration of AI with IoT devices and federated learning approaches hold promise for further advancements in smart city development. Continued advancements in AI algorithms, such as deep learning and reinforcement learning, will expand the capabilities of smart city systems. Additionally, applying AI and ML in sustainability, resilience, and social equity domains will contribute to more inclusive and environmentally-friendly urban environments.