The oil and gas industry's technological innovation over the last 150 years is truly astonishing, which is why its lackadaisical adoption of artificial intelligence is so surprising. Geologists have figured out how to vibrate the earth and use seismic imaging to describe rocks thousands of feet below the surface. Mechanical engineers have designed tools that can steer a drill bit through a narrow band of oil for more than a mile. Likewise, petroleum engineers have collected billions of data points from hundreds of devices to design the most productive wells. But when it comes to using that data to train an artificial intelligence to generate insights, the industry is still dabbling.

It's no secret - oil and gas industry leaders acknowledge they have been slow to embrace digital technologies. A recent Boston Consulting Group report sums it up well: "The oil and gas industry is not an easy place to go digital." Digitisation brings with it the promise of improved safety and efficiency, yet many companies still have a long way to go. It may be surprising to learn that some businesses even lack the technology to locate their workers ‒ which has clear and potentially dire implications for emergency situations. This is partly because most of the industry is still deeply rooted in 20th-century methodologies, systems and processes.

CGG's integrated geoscience services enable you to build the most comprehensive earth models that support the exploration and production of natural resources. Learn more about our broad range of leading products and expert services that help unlock the secrets of the earth through a variety of geoscience disciplines.

Washington D.C.: With the help of machine learning and artificial intelligence researchers are accelerating the power of batteries. Researchers at the U.S. Department of Energy's (DOE) Argonne National Laboratory have turned to the power of machine learning and artificial intelligence to dramatically accelerate the process of battery discovery, according to the study published in -- Chemical Science. As described in two new papers, Argonne researchers first created a highly accurate database of roughly 133,000 small organic molecules that could form the basis of battery electrolytes. To do so, they used a computationally intensive model called G4MP2. This collection of molecules, however, represented only a small subset of 166 billion larger molecules that scientists wanted to probe for electrolyte candidates.

A universal interatomic potential applicable to arbitrary elements and structures is urgently needed in computational materials science. Graph convolution-based neural network is a promising approach by virtue of its ability to express complex relations. Thus far, it has been thought to represent a completely different approach from physics-based interatomic potentials. In this paper, we show that these two methods can be regarded as different representations of the same tight-binding electronic relaxation framework, where atom-based and overlap integral or "bond"-based Hamiltonian information are propagated in a directional fashion. Based on this unified view, we propose a new model, named the tensor embedded atom network (TeaNet), where the stacked network model is associated with the electronic total energy relaxation calculation. Furthermore, Tersoff-style angular interaction is translated into graph convolution architecture through the incorporation of Euclidean tensor values. Our model can represent and transfer spatial information. TeaNet shows great performance in both the robustness of interatomic potentials and the expressive power of neural networks. We demonstrate that arbitrary chemistry involving the first 18 elements on the periodic table (H to Ar) can be realized by our model, including C-H molecular structures, metals, amorphous SiO${}_2$, and water.

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of losses into prior hidden states and inputs held in memory. This allows gradients to flow from present to past and effectively learn with perfect hindsight, but at a significant memory cost. In this paper we show that it is possible to train high performance recurrent networks using information that is local in time, and thereby achieve a significantly reduced memory footprint. We describe a predictive autoencoder called bRSM featuring recurrent connections, sparse activations, and a boosting rule for improved cell utilization. The architecture demonstrates near optimal performance on a non-deterministic (stochastic) partially-observable sequence learning task consisting of high-Markov-order sequences of MNIST digits. We find that this model learns these sequences faster and more completely than an LSTM, and offer several possible explanations why the LSTM architecture might struggle with the partially observable sequence structure in this task. We also apply our model to a next word prediction task on the Penn Treebank (PTB) dataset. We show that a 'flattened' RSM network, when paired with a modern semantic word embedding and the addition of boosting, achieves 103.5 PPL (a 20-point improvement over the best N-gram models), beating ordinary RNNs trained with BPTT and approaching the scores of early LSTM implementations. This work provides encouraging evidence that strong results on challenging tasks such as language modelling may be possible using less memory intensive, biologically-plausible training regimes.

We present a novel algorithm that predicts the probability that time derivative of the horizontal component of the ground magnetic field $dB/dt$ exceeds a specified threshold at a given location. This quantity provides important information that is physically relevant to Geomagnetically Induced Currents (GIC), which are electric currents induced by sudden changes of the Earth's magnetic field due to Space Weather events. The model follows a 'gray-box' approach by combining the output of a physics-based model with a machine learning approach. Specifically, we use the University of Michigan's Geospace model, that is operational at the NOAA Space Weather Prediction Center, with a boosted ensemble of classification trees. We discuss in detail the issue of combining a large dataset of ground-based measurements ($\sim$ 20 years) with a limited set of simulation runs ($\sim$ 2 years) by developing a surrogate model for the years in which simulation runs are not available. We also discuss the problem of re-calibrating the output of the decision tree to obtain reliable probabilities. The performance of the model is assessed by typical metrics for probabilistic forecasts: Probability of Detection and False Detection, True Skill Score, Heidke Skill Score, and Receiver Operating Characteristic curve.

Recent advances in Capsule Networks (CapsNets) have shown their superior learning capability, compared to the traditional Convolutional Neural Networks (CNNs). However, the extremely high complexity of CapsNets limits their fast deployment in real-world applications. Moreover, while the resilience of CNNs have been extensively investigated to enable their energy-efficient implementations, the analysis of CapsNets' resilience is a largely unexplored area, that can provide a strong foundation to investigate techniques to overcome the CapsNets' complexity challenge. Following the trend of Approximate Computing to enable energy-efficient designs, we perform an extensive resilience analysis of the CapsNets inference subjected to the approximation errors. Our methodology models the errors arising from the approximate components (like multipliers), and analyze their impact on the classification accuracy of CapsNets. This enables the selection of approximate components based on the resilience of each operation of the CapsNet inference. We modify the TensorFlow framework to simulate the injection of approximation noise (based on the models of the approximate components) at different computational operations of the CapsNet inference. Our results show that the CapsNets are more resilient to the errors injected in the computations that occur during the dynamic routing (the softmax and the update of the coefficients), rather than other stages like convolutions and activation functions. Our analysis is extremely useful towards designing efficient CapsNet hardware accelerators with approximate components. To the best of our knowledge, this is the first proof-of-concept for employing approximations on the specialized CapsNet hardware.

Our cities are growing at an uncontrollable rate. The UN estimates that there are now 33 megacities with a population of over 10 million, (five in India and six--or more--in China), and the largest city in the world, Tokyo, has close to 37.5 million people. As cities sprawl into green space and their inhabitants endure increasingly cramped and polluted conditions, accurate planning about how urban spaces function is more important than ever. With the climate crisis looming, data and new technology could be our best option to create more livable and sustainable cities. Part one of this series will focus on visualizing how cities are growing, how to plan them more accurately and sustainably, and explore how smart technologies can make cities more efficient now and in the future.

In 2018, OpenAI found that the amount of computational power used to train the largest AI models had doubled every 3.4 months since 2012. The San Francisco-based for-profit AI research lab has now added new data to its analysis. This shows how the post-2012 doubling compares with the historic doubling time since the beginning of the field. From 1959 to 2012, the amount of power used doubled every two years, tracking Moore's Law. This means the resources used today are doubling at a rate seven times faster than before.