Engineers widely use Gaussian process regression framework to construct surrogate models aimed to replace computationally expensive physical models while exploring design space. Thanks to Gaussian process properties we can use both samples generated by a high fidelity function (an expensive and accurate representation of a physical phenomenon) and a low fidelity function (a cheap and coarse approximation of the same physical phenomenon) while constructing a surrogate model. However, if samples sizes are more than few thousands of points, computational costs of the Gaussian process regression become prohibitive both in case of learning and in case of prediction calculation. We propose two approaches to circumvent this computational burden: one approach is based on the Nystr\"om approximation of sample covariance matrices and another is based on an intelligent usage of a blackbox that can evaluate a~low fidelity function on the fly at any point of a design space. We examine performance of the proposed approaches using a number of artificial and real problems, including engineering optimization of a rotating disk shape.

Subsurface applications including geothermal, geological carbon sequestration, oil and gas, etc., typically involve maximizing either the extraction of energy or the storage of fluids. Characterizing the subsurface is extremely complex due to heterogeneity and anisotropy. Due to this complexity, there are uncertainties in the subsurface parameters, which need to be estimated from multiple diverse as well as fragmented data streams. In this paper, we present a non-intrusive sequential inversion framework, for integrating data from geophysical and flow sources to constraint subsurface Discrete Fracture Networks (DFN). In this approach, we first estimate bounds on the statistics for the DFN fracture orientations using microseismic data. These bounds are estimated through a combination of a focal mechanism (physics-based approach) and clustering analysis (statistical approach) of seismic data. Then, the fracture lengths are constrained based on the flow data. The efficacy of this multi-physics based sequential inversion is demonstrated through a representative synthetic example.

The goal of this paper is to assess the utility of Reduced-Order Models (ROMs) developed from 3D physics-based models for predicting transient thermal power output for an enhanced geothermal reservoir while explicitly accounting for uncertainties in the subsurface system and site-specific details. Numerical simulations are performed based on Latin Hypercube Sampling (LHS) of model inputs drawn from uniform probability distributions. Key sensitive parameters are identified from these simulations, which are fracture zone permeability, well/skin factor, bottom hole pressure, and injection flow rate. The inputs for ROMs are based on these key sensitive parameters. The ROMs are then used to evaluate the influence of subsurface attributes on thermal power production curves. The resulting ROMs are compared with field-data and the detailed physics-based numerical simulations. We propose three different ROMs with different levels of model parsimony, each describing key and essential features of the power production curves. ROM-1 is able to accurately reproduce the power output of numerical simulations for low values of permeabilities and certain features of the field-scale data, and is relatively parsimonious. ROM-2 is a more complex model than ROM-1 but it accurately describes the field-data. At higher permeabilities, ROM-2 reproduces numerical results better than ROM-1, however, there is a considerable deviation at low fracture zone permeabilities. ROM-3 is developed by taking the best aspects of ROM-1 and ROM-2 and provides a middle ground for model parsimony. It is able to describe various features of numerical simulations and field-data. From the proposed workflow, we demonstrate that the proposed simple ROMs are able to capture various complex features of the power production curves of Fenton Hill HDR system. For typical EGS applications, ROM-2 and ROM-3 outperform ROM-1.

Many traditional methods for identifying changepoints can struggle in the presence of outliers, or when the noise is heavy-tailed. Often they will infer additional changepoints in order to fit the outliers. To overcome this problem, data often needs to be pre-processed to remove outliers, though this is difficult for applications where the data needs to be analysed online. We present an approach to changepoint detection that is robust to the presence of outliers. The idea is to adapt existing penalised cost approaches for detecting changes so that they use loss functions that are less sensitive to outliers. We argue that loss functions that are bounded, such as the classical biweight loss, are particularly suitable -- as we show that only bounded loss functions are robust to arbitrarily extreme outliers. We present an efficient dynamic programming algorithm that can find the optimal segmentation under our penalised cost criteria. Importantly, this algorithm can be used in settings where the data needs to be analysed online. We show that we can consistently estimate the number of changepoints, and accurately estimate their locations, using the biweight loss function. We demonstrate the usefulness of our approach for applications such as analysing well-log data, detecting copy number variation, and detecting tampering of wireless devices.

Reducing waste and responsible energy management has become a necessity for corporations looking to shore up their image in the eye of the public. However, while going green is certainly a commendable, ethical goal, it's also a fiscally responsible one. Companies that implement green strategies – such as waste reduction, energy efficiency and predictive maintenance – invariably save money in the long run. An effective energy management strategy requires the latest technology. Today, that's a combination of the internet of things (IoT) and machine-learning algorithms, more commonly known as artificial intelligence (AI).

Drone companies saw a record number of deals last year. On a quarterly basis, Q1'17 was the most active quarter historically for deals, reaching 32 investments worth $113M. Within the space, terrestrial imagery, infrastructure inspection, and delivery have emerged as some of the primary use cases for drone technology. Using CB Insights data, we identified over 70 leading private companies in the drones space and categorized them into the twelve main categories in which they operate. We define drones broadly to include software and hardware companies developing technologies related to unmanned aerial, marine, and/or land vehicles designed for unstructured environments.

Data is the foundation of success, from fueling scientific research and creating new medical treatments, to delivering a personalized shopping experience and optimizing business operations. Today's organizations are utilizing cutting-edge technologies to harness the full power of their data. However, legacy IT lacks the management and analytics capabilities required to handle growing datasets. High performance computing (HPC) is key to extracting real-time insights, and enabling IT departments to achieve new levels of performance. Among these advancements, machine learning is a powerful tool that allows organizations to ingest continuous streams of information and glean actionable intelligence.

It should come as no surprise that the Internet of Things (IoT) is one of the most eagerly anticipated trends in heavy industry. Powered by a host of technologies, including low-cost sensors, IP and wireless networks, private and public clouds, and powerful edge infrastructure, industrial IoT promises to transform the way companies provide products and services and interact with customers and partners. Simultaneously, another revolution is taking place in artificial intelligence (AI). For years, programmed intelligence based on simple rules and limited data inputs have powered various industrial applications. A robot arm that extracts a molded part from a chemical wash after certain conditions are met is an example of a narrow, "weak" AI.

As the Industrial Internet of Things (IIoT) picks up steam, attention is pivoting from connectivity to analytics, flooding manufacturers with a wave of new offerings that all promise to facilitate real business change. Startups as well as familiar automation providers are pulling together new platforms and tools designed to spin the treasure trove of data collected from plant floor equipment and industrial assets into nuggets of actionable insights that can help optimize decision-making. Much of this data has existed in some form for decades, but it's primarily been locked away in siloed and incompatible plant floor systems. As a result, the data has never been fully utilized as part of a broader analytics effort to foster predictive maintenance, optimize energy usage of plant floor assets, or to initiate a response to critical events like a water leak or pump failure to minimize lost production. "It's really easy to capture data, but to then make that data actionable is where companies are really struggling," notes Ryan Lester, director of IoT strategy for Xively, an IoT platform provider.

Binary, or one-bit, representations of data arise naturally in many applications, and are appealing in both hardware implementations and algorithm design. In this work, we study the problem of data classification from binary data and propose a framework with low computation and resource costs. We illustrate the utility of the proposed approach through stylized and realistic numerical experiments, and provide a theoretical analysis for a simple case. We hope that our framework and analysis will serve as a foundation for studying similar types of approaches.