Artificial Intelligence (AI) and machine learning will not replace humans in the oil industry anytime soon, according to speakers at the Thursday edition of International Petroleum Week in London. Kallanish Energy was in attendance. People may find it difficult to embrace new technologies for fear of change, but the human workforce has a role to play even with robots in abundance, explained Tullow Oil Digital Transformation Program leader Chris Rivinus. "The maturity level of these tools does not match the hype and concern of replacing people, especially in high risk situations," he said. There is a need for people to control the machines and ensure they follow safety procedures.

Alphabet subsidiary DeepMind (it was acquired by Alphabet in 2014) has been developing artificial-intelligence programs since 2010 to solve complex problems. One of DeepMind's latest projects, according to a recent Google post, has centered around the predictability of wind power. That's not to say that wind-farm owners don't try to predict output. The industry has been using AI techniques for years to try to come closer and closer to real wind predictions. But wind is still very difficult to predict.

From smart factories and smart cities to virtual personal assistants and self-driving cars, artificial intelligence (AI) and the Internet of Things (IoT) are transforming how people around the world live, work, and play. But fundamentally changing the ways people, devices, and data interact is not simple or easy work. Microsoft's AI & IoT Insider Labs was created to help all types of organizations accelerate their digital transformation. Member organizations around the world get access to support both technology development and product commercialization, for everything from hardware design to manufacturing to building applications and turning data into insights using machine learning. Here's how AI & IoT Insider Labs is helping one partner, SunCulture, leverage new technology to provide solar-powered water pumping and irrigation systems for smallholder farmers in Kenya.

Whetstone, a software tool that sharpens the output of artificial neurons, has enabled neural computer networks to process information up to a hundred times more efficiently than the current industry standard, say the Sandia National Laboratories researchers who developed it. The aptly named software, which greatly reduces the amount of circuitry needed to perform autonomous tasks, is expected to increase the penetration of artificial intelligence into markets for mobile phones, self-driving cars and automated interpretation of images. "Instead of sending out endless energy dribbles of information," Sandia neuroscientist Brad Aimone said, "artificial neurons trained by Whetstone release energy in spikes, much like human neurons do." The largest artificial intelligence companies have produced spiking tools for their own products, but none are as fast or efficient as Whetstone, says Sandia mathematician William Severa. "Large companies are aware of this process and have built similar systems, but often theirs work only for their own designs. Whetstone will work on many neural platforms."

Technological shifts in the industry are needed to continue to meet demand and deliver profits. Traditionally information technology (IT) and operational technology (OT) staff have worked on opposite sides, siloed from each other – not overlapping on projects or deployments. However, in the world of industrial IoT (IIoT) that approach has been flipped, demanding that these departments be entirely in sync and aligned. With Gartner's prediction of 60% of IIoT analytics coming from IIoT platforms coupled with edge computing, OT/IT convergence is necessary to prepare for this influx of IIoT analytics for continued, if not improved, performance and output from refineries and drilling operations, along with individual machines involved in those operations. One concern for aligning teams on IIoT investments and deployments is the differences in languages used.

Google's subsidiary DeepMind has created a machine-learning model to boost the use of wind power by predicting its likely output 36 hours ahead. Drawbacks: Although the adoption of wind power has grown thanks to cheaper turbine costs, it will always suffer from unpredictability. That limits it compared with other energy sources that can reliably deliver power at a set time. An experiment: To help solve this problem, last year DeepMind started building algorithms to boost the efficacy of Google's wind farms in the US, according to a blog post. Researchers trained a neural network on weather forecasts and past turbine data, so it could predict power output 36 hours ahead.

I was honored when MIT Technology Review invited me to be the first guest curator of its 10 Breakthrough Technologies. Narrowing down the list was difficult. I wanted to choose things that not only will create headlines in 2019 but captured this moment in technological history--which got me thinking about how innovation has evolved over time. My mind went to--of all things--the plow. Plows are an excellent embodiment of the history of innovation. Humans have been using them since 4000 BCE, when Mesopotamian farmers aerated soil with sharpened sticks. We've been slowly tinkering with and improving them ever since, and today's plows are technological marvels.

Alphabet's DeepMind, an artificial intelligence (AI) firm, has used machine learning to boost the productivity of wind energy. In a blogpost Tuesday, DeepMind's Carl Elkin and Sims Witherspoon, together with Google's Will Fadrhonc, described how in 2018 DeepMind and Google had started to apply "machine learning algorithms to 700 megawatts of wind power capacity in the central United States." The post explained how a neural network was trained on weather forecasts and historical turbine data. The DeepMind system was configured in order to "predict wind power output 36 hours ahead of actual generation." This essentially means that the technology deployed by DeepMind can predict how much energy wind turbines and farms can produce.

Google announced today that it has made energy produced by wind farms more viable using the artificial intelligence software of its London-based subsidiary DeepMind. By using DeepMind's machine learning algorithms to predict the wind output from the farms Google uses for its green energy initiatives, the company says it can now schedule set deliveries of energy output, which are more valuable to the grid than standard, non-time-based deliveries. According to Google, this software has improved the "value" of the wind energy these farms are providing by 20 percent over a baseline where no such time-based predictions are being performed. We don't know exactly what that value is in monetary terms or in terms of energy output. We also don't know where exactly this is being deployed, although Google works with wind farms largely in the Midwest, where some of its US data centers are located.

A problem of considerable importance within the field of uncertainty quantification (UQ) is the development of efficient methods for the construction of accurate surrogate models. Such efforts are particularly important to applications constrained by high-dimensional uncertain parameter spaces. The difficulty of accurate surrogate modeling in such systems, is further compounded by data scarcity brought about by the large cost of forward model evaluations. Traditional response surface techniques, such as Gaussian process regression (or Kriging) and polynomial chaos are difficult to scale to high dimensions. To make surrogate modeling tractable in expensive high-dimensional systems, one must resort to dimensionality reduction of the stochastic parameter space. A recent dimensionality reduction technique that has shown great promise is the method of `active subspaces'. The classical formulation of active subspaces, unfortunately, requires gradient information from the forward model - often impossible to obtain. In this work, we present a simple, scalable method for recovering active subspaces in high-dimensional stochastic systems, without gradient-information that relies on a reparameterization of the orthogonal active subspace projection matrix, and couple this formulation with deep neural networks. We demonstrate our approach on synthetic and real world datasets and show favorable predictive comparison to classical active subspaces.