The application of autonomous UAVs to infrastructure inspection tasks provides benefits in terms of operation time reduction, safety, and cost-effectiveness. This paper presents trajectory planning for three-dimensional autonomous multi-UAV volume coverage and visual inspection of infrastructure based on the Heat Equation Driven Area Coverage (HEDAC) algorithm. The method generates trajectories using a potential field and implements distance fields to prevent collisions and to determine UAVs' camera orientation. It successfully achieves coverage during the visual inspection of complex structures such as a wind turbine and a bridge, outperforming a state-of-the-art method by allowing more surface area to be inspected under the same conditions. The presented trajectory planning method offers flexibility in various setup parameters and is applicable to real-world inspection tasks. Conclusively, the proposed methodology could potentially be applied to different autonomous UAV tasks, or even utilized as a UAV motion control method if its computational efficiency is improved.

Physics-Informed Neural Networks (PINNs) have recently been proposed to solve scientific and engineering problems, where physical laws are introduced into neural networks as prior knowledge. With the embedded physical laws, PINNs enable the estimation of critical parameters, which are unobservable via physical tools, through observable variables. For example, Power Electronic Converters (PECs) are essential building blocks for the green energy transition. PINNs have been applied to estimate the capacitance, which is unobservable during PEC operations, using current and voltage, which can be observed easily during operations. The estimated capacitance facilitates self-diagnostics of PECs. Existing PINNs are often manually designed, which is time-consuming and may lead to suboptimal performance due to a large number of design choices for neural network architectures and hyperparameters. In addition, PINNs are often deployed on different physical devices, e.g., PECs, with limited and varying resources. Therefore, it requires designing different PINN models under different resource constraints, making it an even more challenging task for manual design. To contend with the challenges, we propose Automated Physics-Informed Neural Networks (AutoPINN), a framework that enables the automated design of PINNs by combining AutoML and PINNs. Specifically, we first tailor a search space that allows finding high-accuracy PINNs for PEC internal parameter estimation. We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints. We experimentally demonstrate that AutoPINN is able to find more accurate PINN models than human-designed, state-of-the-art PINN models using fewer resources.

Recently, automated co-design of machine learning (ML) models and accelerator architectures has attracted significant attention from both the industry and academia. However, most co-design frameworks either explore a limited search space or employ suboptimal exploration techniques for simultaneous design decision investigations of the ML model and the accelerator. Furthermore, training the ML model and simulating the accelerator performance is computationally expensive. To address these limitations, this work proposes a novel neural architecture and hardware accelerator co-design framework, called CODEBench. It is composed of two new benchmarking sub-frameworks, CNNBench and AccelBench, which explore expanded design spaces of convolutional neural networks (CNNs) and CNN accelerators. CNNBench leverages an advanced search technique, BOSHNAS, to efficiently train a neural heteroscedastic surrogate model to converge to an optimal CNN architecture by employing second-order gradients. AccelBench performs cycle-accurate simulations for a diverse set of accelerator architectures in a vast design space. With the proposed co-design method, called BOSHCODE, our best CNN-accelerator pair achieves 1.4% higher accuracy on the CIFAR-10 dataset compared to the state-of-the-art pair, while enabling 59.1% lower latency and 60.8% lower energy consumption. On the ImageNet dataset, it achieves 3.7% higher Top1 accuracy at 43.8% lower latency and 11.2% lower energy consumption. CODEBench outperforms the state-of-the-art framework, i.e., Auto-NBA, by achieving 1.5% higher accuracy and 34.7x higher throughput, while enabling 11.0x lower energy-delay product (EDP) and 4.0x lower chip area on CIFAR-10.

In this paper, a hyperparameter tuning based Bayesian optimization of digital twins is carried out to diagnose various faults in grid connected inverters. As fault detection and diagnosis require very high precision, we channelize our efforts towards an online optimization of the digital twins, which, in turn, allows a flexible implementation with limited amount of data. As a result, the proposed framework not only becomes a practical solution for model versioning and deployment of digital twins design with limited data, but also allows integration of deep learning tools to improve the hyperparameter tuning capabilities. For classification performance assessment, we consider different fault cases in virtual synchronous generator (VSG) controlled grid-forming converters and demonstrate the efficacy of our approach. Our research outcomes reveal the increased accuracy and fidelity levels achieved by our digital twin design, overcoming the shortcomings of traditional hyperparameter tuning methods.

A third Russian airfield is ablaze from a drone attack, a day after Ukraine demonstrated an apparent new ability to penetrate hundreds of kilometres deep into Russian airspace with attacks on two Russian air bases. A drone struck an airfield in the Russian region of Kursk bordering Ukraine, setting fire to an oil storage tank. Russia said three of its military personnel were killed in what it said were Ukrainian drone attacks on two Russian air bases hundreds of kilometres from the frontlines in Ukraine. Kyiv did not directly claim responsibility. Ukraine's military intelligence chief said Russia had enough high-precision missiles to conduct several more big air raids on Ukraine before it runs out of stock.

Saudi Space Commission announces the launch of its Saudi Space Accelerator Program in line with the Kingdom's vision of becoming a global hub of innovation by 2030. The program seeks to enhance the national Space sector through the development of its infrastructure and enabling local entrepreneurs and businesses to advance innovative Space solutions. The Program addresses the current state in the Kingdom's Space sector and proposes proactive Space solutions. Through the implementation of this program, the commission will ignite the local ecosystem and determine its maturity level, and to ensure that the sector remains viable for years to come, by providing an established business environment for growth and innovation for entrepreneurs to thrive in – overall improving the effectiveness of the commission's future programs and initiatives over the long-run. The Saudi Space Accelerator Program is being supported by a greater initiative; The future Office for Entrepreneurship Development, that seeks to establish a new business unit within the commission dedicated to enabling the entrepreneurial space scene in the Kingdom.

The new Thales multimodal biometric pod is an efficient enrolment and identification solution that helps smoothly manage travelers' border and immigration processes. The combination of'iris & face' capture and recognition capacities enables a fast and secure enrolment and ID verification at borders. The pod features a modern design that perfectly suits the authority's needs in highly secure environments. The travel industry and border security agencies have recognized the need to improve efficiency and overall traveler experience at border entry and exit points. For years, biometrics has been used by authorities to simplify traveler experiences at borders, speeding up people enrolment and ID checks such as the eGates or Entry-Exit Systems.

NuScale Power, LLC (NuScale) announced it has awarded two new contracts to Framatome to design fuel handling equipment and fuel storage racks for NuScale's VOYGR SMR power plant. This marks a critical supply chain and manufacturing development step, as NuScale fulfills customers' project timelines to deploy its groundbreaking technology by the end of the decade. "NuScale is proud to strengthen our relationship with Framatome, a renowned and widely respected international leader in nuclear energy," said Dale Atkinson, NuScale Chief Operating Officer and Chief Nuclear Officer. "This agreement showcases how NuScale's technology is meticulously developed with a premier international nuclear design and fabrication organization." Framatome will be partnering with American Crane and Orano to design and adapt its existing fuel handling equipment and high-density spent fuel storage rack designs to meet the needs of a NuScale VOYGR power plant.

The past three months alone has seen the UK announce three major milestones – covering carbon storage, offshore wind and hybrid energy projects – to propel it further down the road towards net zero. But that journey is no longer only about creating a sustainable, green future. World events have brought security of supply sharply into focus, placing new impetus on governments to accelerate alternative energy projects. While moving at pace is critical for the planet, the old proverb of more haste, less speed – warning against making errors by acting too quickly and without due diligence – should be weighing on the minds of developers. Nicola Blanshard, CEO of Geoteric, a world-leading AI-driven seismic interpretation software provider, believes the balance of speed and success can be achieved through appropriate application of technology.

A promising approach to improve cloud parameterizations within climate models and thus climate projections is to use deep learning in combination with training data from storm-resolving model (SRM) simulations. The ICOsahedral Non-hydrostatic (ICON) modeling framework permits simulations ranging from numerical weather prediction to climate projections, making it an ideal target to develop neural network (NN) based parameterizations for sub-grid scale processes. Within the ICON framework, we train NN based cloud cover parameterizations with coarse-grained data based on realistic regional and global ICON SRM simulations. We set up three different types of NNs that differ in the degree of vertical locality they assume for diagnosing cloud cover from coarse-grained atmospheric state variables. The NNs accurately estimate sub-grid scale cloud cover from coarse-grained data that has similar geographical characteristics as their training data. Additionally, globally trained NNs can reproduce sub-grid scale cloud cover of the regional SRM simulation. Using the game-theory based interpretability library SHapley Additive exPlanations, we identify an overemphasis on specific humidity and cloud ice as the reason why our column-based NN cannot perfectly generalize from the global to the regional coarse-grained SRM data. The interpretability tool also helps visualize similarities and differences in feature importance between regionally and globally trained column-based NNs, and reveals a local relationship between their cloud cover predictions and the thermodynamic environment. Our results show the potential of deep learning to derive accurate yet interpretable cloud cover parameterizations from global SRMs, and suggest that neighborhood-based models may be a good compromise between accuracy and generalizability.