Rapid urbanization challenges urban micro-climates, strains resources and affects public health. Understanding micro-climate dynamics is key to effective mitigation and sustainable development. Local Climate Zone (LCZ) classification supports climate-resilient planning but is complicated by the diversity and complexity of diverse urban landscapes and the coexistence of varying land uses and materials within small areas. While LCZ classification typically uses multispectral imagery, LiDAR, and land-use data, these sources often miss temporal thermal dynamic patterns. Thermal satellite imagery improves LCZ classification by distinguishing zones with similar structures but differing thermal behavior. This research proposes using deep learning-based multitemporal semantic segmentation to classify urban LCZs based solely on temporal thermal patterns from ECOSTRESS satellite imagery. The methodology is applied in a in a case study around the near coastal cities of Rotterdam and The Hague in The Netherlands and demonstrates how spatial and temporal factors (both diurnal and seasonal) influence the performance of the semantic segmentation model on different LCZ classes. The study shows that a U-Net architecture applied on spatio-temporal thermal imagery effectively classifies urban LCZs, achieving a test accuracy of 0.75. Temporal factors significantly impact model performance, with higher accuracies observed for daytime (0.8) and Spring/Summer imagery (0.78), as these conditions provide clearer thermal separability for distinguishing LCZs. The model achieved its highest test accuracy (0.83) when trained and tested on thermal images with the highest LST values. This suggests that focusing on high-value LST images with sufficient variability enhances classification performance compared to a generalized approach using the full dataset.

Centralized energy systems are often limited by their dependence on large, centralized power plants and extensive transmission networks, making them vulnerable to single points of failure and less resilient to disruptions. Microgrids offer resilience, enhanced energy efficiency, and improved integration of renewable resources compared to centralized energy systems, enabling localized energy management and reduced reliance on fossil fuels. Deep Reinforcement Learning (DRL) has shown its potential for microgrid energy optimization by enabling intelligent, adaptive control over energy resources and energy exchange. By learning from interactions with the environment, the DRL agent dynamically adjusts the power outputs of distributed energy resources, manages energy storage systems, and balances energy exchange between microgrid elements and with the main grid, aiming to minimize costs and ensure reliable power availability. However, incorporating spatial relationships into DRL action space significantly increases computational demands. In line with this, we have introduced a novel method that integrates DRL, Graph Neural Network (GNN) and dynamic clustering to optimize microgrid operations. GNNs are specialized deep learning models that adapt to graphs of varying sizes and structures. This adaptability enables GNN-equipped DRL agents to effectively learn from and apply knowledge to a wide range of network topologies. The agent can be used for subsets, or sub-microgrids, taking into account the scalability and efficiency of the optimization process, enabling distance and routing optimization without an aggregated model. This approach addresses the computational challenges associated with large action spaces and varying topologies in microgrid management.

Transforming the global energy sector from fossil-fuel based to renewable energy sources is crucial to limiting global warming and achieving climate neutrality. The decentralized nature of the renewable energy system allows private households to deploy photovoltaic systems on their rooftops. However, inconsistent data on installed photovoltaic (PV) systems complicate planning for an efficient grid expansion. To address this issue, deep-learning techniques, can support collecting data about PV systems from aerial and satellite imagery. Previous research, however, lacks the consideration for ground truth data-specific characteristics of PV panels. This study aims to implement a semantic segmentation model that detects PV systems in aerial imagery to explore the impact of area-specific characteristics in the training data and CNN hyperparameters on the performance of a CNN. Hence, a U-Net architecture is employed to analyze land use types, rooftop colors, and lower-resolution images. Additionally, the impact of near-infrared data on the detection rate of PV panels is analyzed. The results indicate that a U-Net is suitable for classifying PV panels in high-resolution aerial imagery (10 cm) by reaching F1 scores of up to 91.75% while demonstrating the importance of adapting the training data to area-specific ground truth data concerning urban and architectural properties.

With increased urbanization and the impacts of climate change, cities around the world are making resilience-building a priority. Simultaneously, advances in technology have enabled the creation of City Digital Twins (CDTs). Informed by a literature review and interviews with resilience and Digital Twin experts, this paper explores how CDTs might support the development of more resilient urban communities. First, the various definitions of urban resilience, smart cities and CDTs are described. Second, the paper explores how characteristics of CDTs make them uniquely equipped to facilitate (1) a better understanding of complex phenomena, (2) the imagination of possible futures and (3) collaboration between stakeholders. Finally, the technical requirements and challenges of CDT implementation are discussed, including (1) identifying priority hazards and users, (2) collecting and managing data, (3) integrating different models and (4) ensuring usability. The paper concludes by emphasizing the important role of stakeholders in shaping CDTs that can be successfully integrated by the communities they serve.

Applying any sustainable intervention in the urban energy system requires fundamental knowledge of the energy demand dynamics. Only when we can predict the users' energy demand at any given time with accuracy, we can redesign the urban energy system. Accordingly, the main objective of this paper is to determine the annual electricity usage of the building connections in the urban built environment. In this paper firstly through a literature review, the important electricity usage explanatory variables of the built environment are recognized. For each building, besides the annual electricity usage, three major categories of explanatory variables, including physical, socioeconomic, and geospatial characteristics are determined. Based on the available data sources, a building electricity usage database is created. The database is categorized based on the two most frequently used building sectors including residential and non-residential. Ordinary Least Squares (OLS) technique is applied to the constructed database to estimate the predicting model parameters establishing a relationship between the annual electricity usage as a dependent variable and physical, socioeconomic, and geospatial variables as independent variables. In this research, to determine the contribution of geospatial characteristics in the annual electricity usage variability, regression analysis is performed in two consecutive steps. In the first step only, the geospatial characteristics were implemented in the multiple linear regression analysis. Following that, in the second step, the other categories including physical and socioeconomic characteristics are added to the model. The result revealed that in both building sectors most of the predictors are statistically significant at the 0.05 level. While for the residential buildings the geospatial characteristics account for 9.7% of the electricity usage variation, these values for the service and industry sub-sectors are 9.9% and 8.7% respectively. In total, all variables explain 28.1%, 39.4%, and 42.9% of the electricity usage variability of residential, service, and industrial buildings respectively.

Wind turbine site planning is a multidisciplinary task comprising of several stakeholder groups from different domains and with different priorities. An information system capable of integrating the knowledge on the multiple aspects of a wind turbine plays a crucial role on providing a common picture to the involved groups. In this study, we have developed an interactive and intuitive 3D system (Falcon) for planning wind turbine locations. This system supports iterative design loops (wind turbine configurations), based on the emerging field of geodesign. The integration of GIS, game engine and the analytical models has resulted in an interactive platform with real-time feedback on the multiple wind turbine aspects which performs efficiently for different use cases and different environmental settings. The implementation of tiling techniques and open standard web services support flexible and on-the-fly loading and querying of different (massive) geospatial elements from different resources. This boosts data accessibility and interoperability that are of high importance in a multidisciplinary process. The incorporation of the analytical models in Falcon makes this system independent from external tools for different environmental impacts estimations and results in a unified platform for performing different environmental analysis in every stage of the scenario design. Game engine techniques, such as collision detection, are applied in Falcon for the real-time implementation of different environmental models (e.g. noise and visibility). The interactivity and real-time performance of Falcon in any location in the whole country assist the stakeholders in the seamless exploration of various scenarios and their resulting environmental effects and provides a scope for an interwoven discussion process. The flexible architecture of the system enables the effortless application of Falcon in other countries, conditional to input data availability. The embedded open web standards in Falcon results in a smooth integration of different input data which are increasingly available online and through standardized access mechanisms.

In this study, we propose an interactive information system for wind turbine siting, considering its visual and sound externalities. This system is an integration of game engine, GIS and analytical sound propagation model in a unified 3D web environment. The game engine–GIS integration provides a 3D virtual environment where users can navigate through the existing geospatial data of the whole country and place different wind turbine types to explore their visual impact on the landscape. The integration of a sound propagation model in the game engine–GIS supports the real-time calculation and feedback regarding wind turbine sound at the surrounding buildings. The platform's GIS component enables massive (on-the-fly) georeferenced data utilization through tiling techniques as well as data accessibility and interoperability via cloud-based architecture and open geospatial standard protocols. The game engine, on the other hand, supports performance optimization for both data display and sound model calculations.