The detection of drones or unmanned aerial vehicles is a crucial component in protecting safety-critical infrastructures and maintaining privacy for individuals and organizations. The widespread use of optical sensors for perimeter surveillance has made optical sensors a popular choice for data collection in the context of drone detection. However, efficiently processing the obtained sensor data poses a significant challenge. Even though deep learning-based object detection models have shown promising results, their effectiveness depends on large amounts of annotated training data, which is time consuming and resource intensive to acquire. Therefore, this work investigates the applicability of synthetically generated data obtained through physically realistic simulations based on three-dimensional environments for deep learning-based drone detection. Specifically, we introduce a novel three-dimensional simulation approach built on Unreal Engine and Microsoft AirSim for generating synthetic drone data. Furthermore, we quantify the respective simulation–reality gap and evaluate established techniques for mitigating this gap by systematically exploring different compositions of real and synthetic data. Additionally, we analyze the adaptation of the simulation setup as part of a feedback loop-based training strategy and highlight the benefits of a simulation-based training setup for image-based drone detection, compared to a training strategy relying exclusively on real-world data.

Drone detection is an important yet challenging task in the context of object detection. The development of robust and reliable drone detection systems requires

Disruptive events and the rapid evolution of urban energy systems highlight the need for robust methods to reconstruct critical infrastructure networks. Comprehensive, up-to-date power grid representations are essential for both researchers developing methods for analysing and optimising power systems and first responders requiring approximate data for urgent decisions. However, traditional grid reconstruction approaches often rely on incomplete data, expert knowledge, or closed datasets, limiting their utility during emergencies. This study proposes a novel automated method for reconstructing medium-voltage (MV) power grids. The novelty of the proposed method lies in combining OpenStreetMap energy and land-use data in a unified and automated framework, thereby reducing the need for expert input. The proposed method employs a systematic aggregation of data, an estimation of energy demand, and the application of algorithmic techniques to generate synthetic MV grid models that functionally represent real networks, capturing key topological features. The resulting outputs include visual representations to support decision-makers in simulating "what-if” scenarios and ensuring rapid operational awareness. In a step toward eliminating reliance on proprietary data, our approach broadens access to critical infrastructure insights across diverse urban contexts, contributing to critical infrastructure resilience and potentially supporting both energy system research and crisis management. A case study demonstrates that a medium-sized city’s MV grid can be reconstructed in minutes without expert knowledge or geographically constrained datasets, underscoring the method’s deployment potential and practical value for emergency scenarios.

Disruptive events and the rapid evolution of urban energy systems highlight the need for robust methods to reconstruct critical infrastructure. Comprehensive, up-to-date power grid representations are essential for researchers developing methods for analysing and optimising power systems and first responders requiring approximate data for urgent decisions. However, traditional grid-reconstruction approaches often rely on incomplete data, expert knowledge, or closed datasets, limiting their utility during emergencies. This study introduces a novel automated method for reconstructing medium-voltage (MV) power grids by leveraging and augmenting publicly available energy and land-use data from OpenStreetMap to reduce the need for expert input. By systematically aggregating the data, estimating energy demand, and applying algorithmic techniques, our method can generate synthetic MV grid models that functionally represent real networks, capturing key topological features. The resulting outputs include visual representations to support decision-makers in simulating "what-if" scenarios and ensuring rapid operational awareness. In a step toward eliminating reliance on proprietary data, our approach broadens access to critical infrastructure insights across diverse urban contexts, contributing to the reacting phase of critical infrastructure resilience and potentially supporting both energy system research and crisis management. A case study demonstrates that a medium-sized city’s MV grid can be reconstructed in minutes without expert knowledge or geographically constrained datasets, underscoring the method’s deployment potential and practical value for emergency scenarios.

Knowledge of Water Distribution System (WDS) pipe topology is a prerequisite for hydraulic simulation, interdependency analysis, and crisis-response planning, yet network records are withheld as security-sensitive critical-infrastructure information and rarely accessible to external researchers or emergency responders. Existing reconstruction methods require operator-provided inputs, and none exploits fire hydrant locations, despite hydrants being physical components of the pipe network. We formulate the placement of a tree-based WDS skeleton as a Constraint Programming (CP) optimisation over the OpenStreetMap (OSM) road network, with hard constraints enforcing connectivity and tree structure, and soft objectives for demand coverage, topographic-head plausibility, and hydrant-proximity guidance. The method requires only open data from OSM and a freely available digital elevation model (DEM). A spatially stratified k-fold cross-validation protocol using held-out hydrants enables quantitative evaluation without ground-truth pipe data. We evaluate the method on Darmstadt, Germany, comparing a literature Answer Set Programming (ASP) baseline, a CP formulation without hydrant guidance, and the hydrant-guided variant. On a city-wide instance with 554 hydrants, the hydrant-guided method reduces the mean distance from held-out hydrants to the nearest reconstructed pipe by 10.2% relative to the ASP baseline (a reduction of 2.76 m, 95% CI over folds 0.94–4.59 m; p < 0.001) and by 8.2–10.2% across three independent solver runs, while preserving full demand coverage and a comparable pipe count. Because utility pipe records are unavailable, this measures agreement with hydrant positions unseen by the optimiser, not with the actual pipe network. The results show that publicly mapped hydrant locations carry spatial information that generalises to hydrants withheld from the optimisation.