Precise probabilistic forecasts are fundamental for energy risk management, and there is a wide range of both statistical and machine learning models for this purpose. Inherent to these probabilistic models is some form of uncertainty quantification. However, most models do not capture the full extent of uncertainty, which arises not only from the data itself but also from model and distributional choices. In this study, we examine uncertainty quantification in state-of-the-art statistical and deep learning probabilistic forecasting models for electricity price forecasting in the German market. In particular, we consider distributional deep neural networks (DDNNs) and augment them with an ensemble approach, Monte Carlo (MC) dropout, deep evidential regression (DER), and conformal prediction to account for model uncertainty. Additionally, we consider the extreme gradient boosting (XGBoost) and the LASSO-estimated autoregressive (LEAR) model, each combined with quantile regression averaging (QRA), generalized autoregressive conditional heteroskedasticity (GARCH), and conformal prediction. Across a range of performance metrics, we find that the XGBoost-based models perform well in terms of probabilistic forecasting, irrespective of the uncertainty quantification method. Furthermore, we find that DDNNs benefit from incorporating both data and model uncertainty, improving accuracy of both point and probabilistic forecasts by 7.4% and 7.7% in terms of MAE and CRPS. Uncertainty itself appears to be best captured by the models using conformal prediction. Overall, our extensive study shows that all models under consideration perform competitively. However, their relative performance depends on the choice of metrics for point and probabilistic forecasting.
Paraburkholderia fungorum (P. fungorum) is an environmental bacterium with biotechnological applications, yet clinical isolations raise concerns about opportunistic infection risk. Genetically related pathogens exhibit substantial antibiotic resistance, motivating the investigation of alternative control strategies. This paper investigates P. fungorum photoinactivation across ultraviolet (222 nm, 254 nm, 313 nm, and 365 nm) and visible (400 nm and 464 nm) wavelengths including ROS (reactive oxygen species) quantification via DCFH-DA fluorescence assay. A two-way ANOVA analysis demonstrated that the wavelength is the dominant determinant of photoinactivation efficacy (F = 100.4, p < 0.001) with ROS generation as a more powerful predictor of inactivation than fluence dose alone (F = 60.6, p < 0.001) at 365 nm, 400 nm, and 464 nm. Ultraviolet irradiation at 254 nm achieved the highest efficiency (5.4 log reduction at 24 mJ/cm2), while 365 nm irradiation demonstrated a high efficacy of 5.2 log reduction at 122 J/cm2 with extraordinary ROS production (12,642-fold fluorescence increase). Conversely, inactivation efficiency declined at 400 nm (4.8 log reduction at 378 J/cm2 with 122-fold ROS increase) and 464 nm (3.4 log reduction at 3017 J/cm2 with lesser ROS detection at 27-fold increase). Wavelength-dependent ROS production correlated directly with bacterial inactivation efficacy, explaining the approximately 500-fold ROS differential between 365 nm and 464 nm. The demonstrated photosensitivity of P. fungorum across multiple wavelengths, with the statistical validation of wavelength-dependent mechanisms, provides a foundation for developing practical, mechanism-based phototherapy protocols tailored to specific clinical and environmental decontamination scenarios.
In this paper we investigate a stable space–time formulation for long-time industrial sound emission problems. To this end, we use a well-posed Galerkin formulation in space and time of the acoustic wave equation in ℝ^3 , involving a hypersingular boundary integral operator. Our numerical experiments confirm that the resulting time stepping scheme is stable and accurate for complex acoustic problems in industrial geometries, in contrast to alternative well-known schemes. The proposed method is shown to be efficient for real-world problems, and we obtain very good agreement with physical acoustic measurements.
Automated evaluation of movement quality can enhance physiotherapeutic treatment and sports training by providing objective, real-time feedback. However, deep learning models that assess movements captured by inertial measurement units (IMUs) are often limited by data scarcity, class imbalance, and label ambiguity. We present a data augmentation method for IMU-derived orientation data that generates additional examples by systematically modifying movement trajectories and passing them through a musculoskeletal simulation. The approach enforces the joint-range limits of a musculoskeletal model and enables automatic labeling by combining inverse kinematic parameters with a knowledge-based evaluation strategy. Across four datasets of varying complexity, augmented variants closely resemble real-world data and contribute to gains in classification accuracy, generalization to unseen subjects, and patient-specific fine-tuning from few examples. The magnitude of these gains varies with dataset properties, in particular class balance and label ambiguity. These findings indicate that musculoskeletal simulation-based augmentation can address common challenges faced by deep learning applications in physiotherapeutic exercise evaluation.
Hyperlocal meteorological sensing is essential for accurate solar photovoltaic forecasting, yet professional-grade meteorological stations require investments easily exceeding 1000 USD per node, making distributed deployments economically inaccessible. This work presents a modular internet of things (IoT) device based on the ESP32 microcontroller integrating temperature, humidity, luminosity, and solar irradiance sensors in an IP68-rated enclosure at a total hardware costs of about $65 USD when components are sourced in Germany. A hybrid architecture decouples external model training, performed on a conventional computer using the software Python and the open-source library TensorFlow, from autonomous 24-hour solar voltage forecasting executed on-device via a three-layer feedforward network with 3,011 parameters (11.8 KB). The network is trained offline on site-collected data and deployed on the microcontroller as static weight matrices without cloud connectivity. An on-device incremental gradient descent mechanism enables continuous model adaptation after deployment without external retraining. The system was evaluated through two field deployments: a short period of hardware and firmware validation in Ulm, Germany, and a 115-day deployment in Zapopan, Mexico, comprising 84 days of training and 31 days of autonomous operation with zero missing records. Over a clean 28-day daytime window, the embedded model attained a coefficient of determination of 0.9165 and a mean absolute error of 0.2975 V (4.65% of the operational range), outperforming a climatology baseline (skill score 0.64) while not surpassing a 24-hour persistence baseline. A frozen-weight ablation confirms that the on-device update mechanism yields a small but statistically robust accuracy gain (p = 0.001), demonstrating that autonomous incremental learning is feasible on low-cost hardware without cloud connectivity.
