Heavy rainfall events can cause major disruption to human activities. It is desirable to predict these events ahead of time so that decision makers can take action to protect life, property and prosperity. Nowcasting, or short-term forecasting from observations, remains an important tool in predicting these events. The essential goals of nowcasting are identical to those of all weather forecasting, with the only difference being the spatial and temporal scales involved. The World Meteorological Organization (WMO, 2016) distinguishes among the various forecasting time horizons as: "Usually forecasts for the next 0-2 hours are called nowcasting, from 2-12 hours very short-range forecasting (VSRF), and short-range forecasting beyond that; but the capabilities of the different ranges can vary upon variables and weather situations." Radar-based nowcasting emerged in an era of mainly synoptic and mesoscale weather prediction. Predicting rainfall during that time was a challenge for numerical weather prediction (NWP) models, since computational restrictions limited the resolution at which NWP models could operate. As a result, NWP models were able to capture mesoscale weather patterns such as fronts, but not the smaller-scale convective patterns that occur within mesoscale systems. Thus, these models had limited utility in predicting rainfall in the early hours of the forecast because of its dependence on the unrepresented small scales.

Gravitational Search Algorithm (GSA) and Particle Swarm Optimization (PSO) are nature-inspired, swarm-based optimization algorithms respectively. Though they have been widely used for single-objective optimization since their inception, they suffer from premature convergence. Even though the hybrids of GSA and PSO perform much better, the problem remains. Hence, to solve this issue we have proposed a fuzzy mutation model for two hybrid versions of PSO and GSA - Gravitational Particle Swarm (GPS) and PSOGSA. The developed algorithms are called Mutation based GPS (MGPS) and Mutation based PSOGSA (MPSOGSA). The mutation operator is based on a fuzzy model where the probability of mutation has been calculated based on the closeness of particle to population centroid and improvement in the particle value. We have evaluated these two new algorithms on 23 benchmark functions of three categories (unimodal, multi-modal and multi-modal with fixed dimension). The experimental outcome shows that our proposed model outperforms their corresponding ancestors, MGPS outperforms GPS 13 out of 23 times (56.52%) and MPSOGSA outperforms PSOGSA 17 times out of 23 (73.91 %). We have also compared our results against those of recent optimization algorithms such as Sine Cosine Algorithm (SCA), Opposition-Based SCA, and Volleyball Premier League Algorithm (VPL). In addition, we have applied our proposed algorithms on some classic engineering design problems and the outcomes are satisfactory. The related codes of the proposed algorithms can be found in this link: Fuzzy-Mutation-Embedded-Hybrids-of-GSA-and-PSO.

Water demand is a highly important variable for operational control and decision making. Hence, the development of accurate forecasts is a valuable field of research to further improve the efficiency of water utilities. Focusing on probabilistic multi-step-ahead forecasting, a time series model is introduced, to capture typical autoregressive, calendar and seasonal effects, to account for time-varying variance, and to quantify the uncertainty and path-dependency of the water demand process. To deal with the high complexity of the water demand process a high-dimensional feature space is applied, which is efficiently tuned by an automatic shrinkage and selection operator (lasso). It allows to obtain an accurate, simple interpretable and fast computable forecasting model, which is well suited for real-time applications. The complete probabilistic forecasting framework allows not only for simulating the mean and the marginal properties, but also the correlation structure between hours within the forecasting horizon. For practitioners, complete probabilistic multi-step-ahead forecasts are of considerable relevance as they provide additional information about the expected aggregated or cumulative water demand, so that a statement can be made about the probability with which a water storage capacity can guarantee the supply over a certain period of time. This information allows to better control storage capacities and to better ensure the smooth operation of pumps. To appropriately evaluate the forecasting performance of the considered models, the energy score (ES) as a strictly proper multidimensional evaluation criterion, is introduced. The methodology is applied to the hourly water demand data of a German water supplier.

The aim of the project is to investigate and assess opportunities for applying reinforcement learning (RL) for power system control. As a proof of concept (PoC), voltage control of thermostatically controlled loads (TCLs) for power consumption regulation was developed using Modelica-based pipeline. The Q-learning RL algorithm has been validated for deterministic and stochastic initialization of TCLs. The latter modelling is closer to real grid behaviour, which challenges the control development, considering the stochastic nature of load switching. In addition, the paper shows the influence of Q-learning parameters, including discretization of state-action space, on the controller performance.

The contribution of this paper is a framework for training and evaluation of Model Predictive Control (MPC) implemented using constrained neural networks. Recent studies have proposed to use neural networks with differentiable convex optimization layers to implement model predictive controllers. The motivation is to replace real-time optimization in safety critical feedback control systems with learnt mappings in the form of neural networks with optimization layers. Such mappings take as the input the state vector and predict the control law as the output. The learning takes place using training data generated from off-line MPC simulations. However, a general framework for characterization of learning approaches in terms of both model validation and efficient training data generation is lacking in literature. In this paper, we take the first steps towards developing such a coherent framework. We discuss how the learning problem has similarities with system identification, in particular input design, model structure selection and model validation. We consider the study of neural network architectures in PyTorch with the explicit MPC constraints implemented as a differentiable optimization layer using CVXPY. We propose an efficient approach of generating MPC input samples subject to the MPC model constraints using a hit-and-run sampler. The corresponding true outputs are generated by solving the MPC offline using OSOP. We propose different metrics to validate the resulting approaches. Our study further aims to explore the advantages of incorporating domain knowledge into the network structure from a training and evaluation perspective. Different model structures are numerically tested using the proposed framework in order to obtain more insights in the properties of constrained neural networks based MPC.

Ensemble smoothers are among the most successful and efficient techniques currently available for history matching. However, because these methods rely on Gaussian assumptions, their performance is severely degraded when the prior geology is described in terms of complex facies distributions. Inspired by the impressive results obtained by deep generative networks in areas such as image and video generation, we started an investigation focused on the use of autoencoders networks to construct a continuous parameterization for facies models. In our previous publication, we combined a convolutional variational autoencoder (VAE) with the ensemble smoother with multiple data assimilation (ES-MDA) for history matching production data in models generated with multiple-point geostatistics. Despite the good results reported in our previous publication, a major limitation of the designed parameterization is the fact that it does not allow applying distance-based localization during the ensemble smoother update, which limits its application in large-scale problems. The present work is a continuation of this research project focusing in two aspects: firstly, we benchmark seven different formulations, including VAE, generative adversarial network (GAN), Wasserstein GAN, variational auto-encoding GAN, principal component analysis (PCA) with cycle GAN, PCA with transfer style network and VAE with style loss. These formulations are tested in a synthetic history matching problem with channelized facies. Secondly, we propose two strategies to allow the use of distance-based localization with the deep learning parameterizations.

Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks. With Sherpa, scientists can quickly optimize hyperparameters using a variety of powerful and interchangeable algorithms. Sherpa can be run on either a single machine or in parallel on a cluster. Finally, an interactive dashboard enables users to view the progress of models as they are trained, cancel trials, and explore which hyperparameter combinations are working best. Sherpa empowers machine learning practitioners by automating the more tedious aspects of model tuning. Its source code and documentation are available at https://github.com/sherpa-ai/sherpa.

Bayesian method is capable of capturing real world uncertainties/incompleteness and properly addressing the over-fitting issue faced by deep neural networks. In recent years, Bayesian Neural Networks (BNNs) have drawn tremendous attentions of AI researchers and proved to be successful in many applications. However, the required high computation complexity makes BNNs difficult to be deployed in computing systems with limited power budget. In this paper, an efficient BNN inference flow is proposed to reduce the computation cost then is evaluated by means of both software and hardware implementations. A feature decomposition and memorization (\texttt{DM}) strategy is utilized to reform the BNN inference flow in a reduced manner. About half of the computations could be eliminated compared to the traditional approach that has been proved by theoretical analysis and software validations. Subsequently, in order to resolve the hardware resource limitations, a memory-friendly computing framework is further deployed to reduce the memory overhead introduced by \texttt{DM} strategy. Finally, we implement our approach in Verilog and synthesise it with 45 $nm$ FreePDK technology. Hardware simulation results on multi-layer BNNs demonstrate that, when compared with the traditional BNN inference method, it provides an energy consumption reduction of 73\% and a 4$\times$ speedup at the expense of 14\% area overhead.

Amazon-owned Ring has unleashed a few upgraded versions of the six-year-old Ring Video Doorbell over the years, including the $230 Video Doorbell 3 Plus that went on sale in April, yet the original $100 Ring Video Doorbell has remained on sale as a budget option. Now comes word that the $100 model is finally getting its own update. Available for pre-order now and slated to ship on June 3, the second-generation Ring Video DoorbellRemove non-product link will keep the original's $100 price tag while adding new features such as improved video resolution, privacy zones, an additional "near" motion zone, and more. Starting with the basics, the revamped Ring Video Doorbell boosts its video resolution to 1080p, versus 720p for the first-generation model, along with "crisper" night vision and "improved" two-way audio quality. The new Video Doorbell features "privacy zones" that let you specify areas in the camera's 155-degree field of view that you don't want recorded or displayed in the Ring App's live view, while an additional "near zone" allows for motion detection in areas that are between five and 15 feet in front of your home.

Researchers have designed a machine learning method that can predict battery health with 10x higher accuracy than current industry standard, which could aid in the development of safer and more reliable batteries for electric vehicles and consumer electronics. The researchers, from Cambridge and Newcastle Universities, have designed a new way to monitor batteries by sending electrical pulses into them and measuring the response. The measurements are then processed by a machine learning algorithm to predict the battery's health and useful lifespan. Their method is non-invasive and is a simple add-on to any existing battery system. The results are reported in the journal Nature Communications.