A deep-learning-based surrogate model is developed and applied for predicting dynamic subsurface flow in channelized geological models. The surrogate model is based on deep convolutional and recurrent neural network architectures, specifically a residual U-Net and a convolutional long short term memory recurrent network. Training samples entail global pressure and saturation maps, at a series of time steps, generated by simulating oil-water flow in many (1500 in our case) realizations of a 2D channelized system. After training, the `recurrent R-U-Net' surrogate model is shown to be capable of accurately predicting dynamic pressure and saturation maps and well rates (e.g., time-varying oil and water rates at production wells) for new geological realizations. Assessments demonstrating high surrogate-model accuracy are presented for an individual geological realization and for an ensemble of 500 test geomodels. The surrogate model is then used for the challenging problem of data assimilation (history matching) in a channelized system. For this study, posterior reservoir models are generated using the randomized maximum likelihood method, with the permeability field represented using the recently developed CNN-PCA parameterization. The flow responses required during the data assimilation procedure are provided by the recurrent R-U-Net. The overall approach is shown to lead to substantial reduction in prediction uncertainty. High-fidelity numerical simulation results for the posterior geomodels (generated by the surrogate-based data assimilation procedure) are shown to be in essential agreement with the recurrent R-U-Net predictions. The accuracy and dramatic speedup provided by the surrogate model suggest that it may eventually enable the application of more formal posterior sampling methods in realistic problems.

Multitask learning and transfer learning have proven to be useful in the field of machine learning when additional knowledge is available to help a prediction task. We aim at deriving methods following these paradigms for use in autotuning, where the goal is to find the optimal performance parameters of an application treated as a black-box function. We show comparative results with state-of-the-art autotuning techniques. For instance, we observe an average $1.5x$ improvement of the application runtime compared to the OpenTuner and HpBandSter autotuners. We explain how our approaches can be more suitable than some state-of-the-art autotuners for the tuning of any application in general and of expensive exascale applications in particular.

PREPRINT 1 MimickNet, Matching Clinical Post-Processing Under Realistic Black-Box Constraints Ouwen Huang, Student Member, IEEE, Will Long, Student Member, IEEE, Nick Bottenus, Gregg E. Trahey, Senior Member, IEEE, Sina Farsiu, Senior Member, IEEE, and Mark L. Palmeri, Senior Member, IEEE Abstract --Image post-processing is used in clinical-grade ultrasound scanners to improve image quality (e.g., reduce speckle noise and enhance contrast). These post-processing techniques vary across manufacturers and are generally kept proprietary, which presents a challenge for researchers looking to match current clinical-grade workflows. We introduce a deep learning framework, MimickNet, that transforms raw conventional delay-and-summed (DAS) beams into the approximate post-processed images found on clinical-grade scanners. Training MimickNet only requires post-processed image samples from a scanner of interest without the need for explicit pairing to raw DAS data. This flexibility allows it to hypothetically approximate any manufacturer's post-processing without access to the pre-processed data. MimickNet generates images with an average similarity index measurement (SSIM) of 0.930 0.0892 on a 300 cineloop test set, and it generalizes to cardiac cineloops outside of our train-test distribution achieving an SSIM of 0.967 0.002. We also explore the theoretical SSIM achievable by evaluating MimickNet performance when trained under gray-box constraints (i.e., when both pre-processed and post-processed images are available). T o our knowledge, this is the first work to establish deep learning models that closely approximate current clinical-grade ultrasound post-processing under realistic black-box constraints where before and after post-processing data is unavailable. MimickNet serves as a clinical post-processing baseline for future works in ultrasound image formation to compare against.

A team at the US National Renewable Energy Laboratory (NREL) is working on autonomous energy grid (AEG) technology to ensure the electricity grid of the future can manage a growing base of intelligent energy devices, variable renewable energy, and advanced controls. "The future grid will be much more distributed too complex to control with today's techniques and technologies," said Benjamin Kroposki, director of NREL's Power Systems Engineering Center. "We need a path to get there--to reach the potential of all these new technologies integrating into the power system." The AEG effort envisions a self-driving power system - a very "aware" network of technologies and distributed controls that work together to efficiently match bi-directional energy supply to energy demand. This is a hard pivot from today's system, in which centralized control is used to manage one-way electricity flows to consumers along power lines that spoke out from central generators.

In this paper a neural network heuristic dynamic programing (HDP) is used for optimal control of the virtual inertia based control of grid connected three phase inverters. It is shown that the conventional virtual inertia controllers are not suited for non inductive grids. A neural network based controller is proposed to adapt to any impedance angle. Applying an adaptive dynamic programming controller instead of a supervised controlled method enables the system to adjust itself to different conditions. The proposed HDP consists of two subnetworks, critic network and action network. These networks can be trained during the same training cycle to decrease the training time. The simulation results confirm that the proposed neural network HDP controller performs better than the traditional direct fed voltage and reactive power controllers in virtual inertia control schemes.

In this paper we propose an energy-efficient learning framework which exploits structural and functional similarities between a machine learning network and a general electrical network satisfying the Tellegen's theorem. The proposed formulation ensures that the network's active-power is dissipated only during the process of learning, whereas the network's reactive-power is maintained to be zero at all times. As a result, in steady-state, the learned parameters are stored and self-sustained by electrical resonance determined by the network's nodal inductances and capacitances. Based on this approach, this paper introduces three novel concepts: (a) A learning framework where the network's active-power dissipation is used as a regularization for a learning objective function that is subjected to zero total reactive-power constraint; (b) A dynamical system based on complex-domain, continuous-time growth transforms which optimizes the learning objective function and drives the network towards electrical resonance under steady-state operation; and (c) An annealing procedure that controls the trade-off between active-power dissipation and the speed of convergence. As a representative example, we show how the proposed framework can be used for designing resonant support vector machines (SVMs), where we show that the support-vectors correspond to an LC network with self-sustained oscillations. We also show that this resonant network dissipates less active-power compared to its non-resonant counterpart.

HPCwire: Walk us through the program, give us a sense of what these AI and science town halls are all about and what they are trying to accomplish? RS: If you remember back in 2007, we had three town hall meetings – at Argonne, Berkeley and Oak Ridge – that launched the whole DOE Exascale project and so forth. At that time the idea was to get people together and ask them, for exascale, what if we could build these faster machines, what would you do with them. It was a way to get people thinking about the possibility of that and of course it took long time to get the exascale computing program going. With these town halls we are kind of asking a variation on that question. Now we're asking the question of what's the opportunity for AI in science or the application of science, particularly in the context of DOE, but more broadly because DOE's got a lot of collaborations with NIH and other agencies. So really asking the fundamental question of what do we have to do in the AI space to make it relevant for science. The point of the town halls – three in the labs and one in Washington in October – is go get people thinking about what opportunities there are in different scientific domains for breakthrough science that can be accomplished by leveraging AI and working AI into simulation, and bringing AI into big data, bringing AI to the facility and so forth. So that's the concept; it's really to get the community moving.

Utilities and energy retailers from across the globe will gather at the exclusive Bidgely Engage 2019 conference under the banner of'Unlock the Power of UtilityAI ' this September 11-13 in Napa, Calif. Engage 2019 is utility artificial intelligence (AI) leader Bidgely's third annual event that brings together utilities, AI experts and tech leaders to discuss trends, best practices and lessons learned in applied AI for the energy industry, as well as to enjoy networking in California's legendary wine country. This press release features multimedia. "For Engage, we pull in industry luminaries and tech leaders from outside the energy space to learn from their AI journeys and to explore how AI and machine learning advancements specifically for energy is delivering compounding benefits to utilities around the world," said Bidgely CMO Gautam Aggarwal. The shift of AI becoming mainstream in the energy industry was recently cited in a report by Navigant Research, covering how the future of utilities will be driven by the emerging disciplines of machine learning and artificial intelligence.

This paper presents a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process. The method combines the perspectives of model reduction and machine learning. Model reduction brings in the physics of the problem, constraining the ROM predictions to lie on a subspace defined by the governing equations. This is achieved by defining the ROM in proper orthogonal decomposition (POD) coordinates, which embed the rich physics information contained in solution snapshots of a high-fidelity computational fluid dynamics (CFD) model. The machine learning perspective brings the flexibility to use transformed physical variables to define the POD basis. This is in contrast to traditional model reduction approaches that are constrained to use the physical variables of the high-fidelity code. Combining the two perspectives, the approach identifies a set of transformed physical variables that expose quadratic structure in the combustion governing equations and learns a quadratic ROM from transformed snapshot data. This learning does not require access to the high-fidelity model implementation. Numerical experiments show that the ROM accurately predicts temperature, pressure, velocity, species concentrations, and the limit-cycle amplitude, with speedups of more than five orders of magnitude over high-fidelity models. Moreover, ROM-predicted pressure traces accurately match the phase of the pressure signal and yield good approximations of the limit-cycle amplitude.

Linear Logic and Defeasible Logic have been adopted to formalise different features of knowledge representation: consumption of resources, and non monotonic reasoning in particular to represent exceptions. Recently, a framework to combine sub-structural features, corresponding to the consumption of resources, with defeasibility aspects to handle potentially conflicting information, has been discussed in literature, by some of the authors. Two applications emerged that are very relevant: energy management and business process management. We illustrate a set of guide lines to determine how to apply linear defeasible logic to those contexts.