Spatial time series forecasting problems arise in a broad range of applications, such as environmental and transportation problems. These problems are challenging because of the existence of specific spatial, short-term and long-term patterns, and the curse of dimensionality. In this paper, we propose a deep neural network framework for large-scale spatial time series forecasting problems. We explicitly designed the neural network architecture for capturing various types of patterns. In preprocessing, a time series decomposition method is applied to separately feed short-term, long-term and spatial patterns into different components of a neural network. A fuzzy clustering method finds cluster of neighboring time series based on similarity of time series residuals; as they can be meaningful short-term patterns for spatial time series. In neural network architecture, each kernel of a multi-kernel convolution layer is applied to a cluster of time series to extract short-term features in neighboring areas. The output of convolution layer is concatenated by trends and followed by convolution-LSTM layer to capture long-term patterns in larger regional areas. To make a robust prediction when faced with missing data, an unsupervised pretrained denoising autoencoder reconstructs the output of the model in a fine-tuning step. The experimental results illustrate the model outperforms baseline and state of the art models in a traffic flow prediction dataset.

Forecasting natural gas demand is a key problem for energy providers, as it allows for efficient pipe reservation and power plant allocation, and enables effective price forecasting. We propose a study of Italian gas demand, with particular focus on industrial and thermoelectric components. To the best of our knowledge, this is the first work about these topics. After a preliminary discussion on the characteristics of gas demand, we apply several statistical learning models to perform day-ahead forecasting, including regularized linear models, random forest, support vector regression and neural networks. Moreover, we introduce four simple ensemble models and we compare their performance with the one of basic forecasters. The out-of-sample Mean Absolute Error (MAE) achieved on 2017 by our best ensemble model is 5.16 Millions of Standard Cubic Meters (MSCM), lower than 9.57 MSCM obtained by the predictions issued by SNAM, the Italian Transmission System Operator (TSO).

Global hydrological and land surface models are increasingly used for tracking terrestrial total water storage (TWS) dynamics, but the utility of existing models is hampered by conceptual and/or data uncertainties related to various underrepresented and unrepresented processes, such as groundwater storage. The gravity recovery and climate experiment (GRACE) satellite mission provided a valuable independent data source for tracking TWS at regional and continental scales. Strong interests exist in fusing GRACE data into global hydrological models to improve their predictive performance. Here we develop and apply deep convolutional neural network (CNN) models to learn the spatiotemporal patterns of mismatch between TWS anomalies (TWSA) derived from GRACE and those simulated by NOAH, a widely used land surface model. Once trained, our CNN models can be used to correct the NOAH simulated TWSA without requiring GRACE data, potentially filling the data gap between GRACE and its follow-on mission, GRACE-FO. Our methodology is demonstrated over India, which has experienced significant groundwater depletion in recent decades that is nevertheless not being captured by the NOAH model. Results show that the CNN models significantly improve the match with GRACE TWSA, achieving a country-average correlation coefficient of 0.94 and Nash-Sutcliff efficient of 0.87, or 14\% and 52\% improvement respectively over the original NOAH TWSA. At the local scale, the learned mismatch pattern correlates well with the observed in situ groundwater storage anomaly data for most parts of India, suggesting that deep learning models effectively compensate for the missing groundwater component in NOAH for this study region.

As home to three top-ranked supercomputers of the last decade, the US Department of Energy's (DOE's) Oak Ridge National Laboratory (ORNL) has become synonymous with scientific computing at the largest scales. Getting the most out of these science machines, however, requires a willingness to experiment with problems and systems of every size and scale. This is especially important as technology vendors introduce new system architectures and as scientists' problem-solving toolkit expands to include artificial intelligence (AI) and advanced data analysis. In that spirit, ORNL recently installed two NVIDIA DGX-2 systems, powerful GPU-accelerated appliances that will provide ORNL researchers with enhanced opportunities to conduct science--machine learning and data-intensive workloads in particular. The appliances will also provide an onramp to ORNL's Summit--the world's most powerful supercomputer--by enabling smaller and more experimental projects to be developed and tested before running on the 200-petaflop machine.

A team of scientists has discovered the ideal wing shape for fast flight - opening up the possibility of harvesting more energy from water. The team, from New York University, conducted a series of tests on 3D-printed wings. Now, they claim their findings could offer improved methods for harvesting renewable energy from sources such as water. Leif Ristroph, an assistant professor at New York University's Courant Institute of Mathematical Sciences, explained how the wing shape was determined using a form of biological evolution. 'We can simulate evolution in the lab by generating a population of wings of different shapes,' he said.

With the click of a mouse and a loud bang, I blasted jets of super-hot, ionized gas called plasma into one another at hundreds of miles per second. I was sitting in the control room of a fusion energy startup called TAE Technologies, and I'd just fired its $150 million plasma collider. That shot was a tiny part of the company's long pursuit of a notoriously elusive power source. I was at the company's headquarters to talk to them about the latest phase of their hunt that involves an algorithm called the Optometrist. Nuclear fusion is the reaction that's behind the Sun's energetic glow.

For Wärtsilä, a Finnish headquartered firm that employs around 18,000 workers and which manufactures and services power sources and other equipment in the marine and energy markets, digital business transformation is a very practical thing. In fact, back in December 2016, Marco claimed that Wärtsilä was "embarking on one of the boldest, innovative and most exciting digital transformation programmes in the industrial, marine and energy sectors." The company is not the most famous of firms, unless you work in the marine or renewable energy business, you may have never heard of it, but in fact, roughly one in two marine vessels in the world are either serviced, powered, navigated or propelled by Wartsila's technology. But what about today, how is the digital business transformation programme performing? "One of the things we've now decided to do is create a sort of digital boot camp, a digital academy, with a leadership programme on what it means to lead in a digitally-enabled business. Marco Ryan, a veteran in digital business transformation, likens this process to a digital onion, and compares the old way of doing things to the Parthenon. "At Wärtsilä, we had over 300 ideas submitted by colleagues in the last 18 months, of which about 50 or 60 have actually come into our incubation centres.

Simulator imperfection, often known as model error, is ubiquitous in practical data assimilation problems. Despite the enormous efforts dedicated to addressing this problem, properly handling simulator imperfection in data assimilation remains to be a challenging task. In this work, we propose an approach to dealing with simulator imperfection from a point of view of functional approximation that can be implemented through a certain machine learning method, such as kernel-based learning adopted in the current work. To this end, we start from considering a class of supervised learning problems, and then identify similarities between supervised learning and variational data assimilation. These similarities found the basis for us to develop an ensemble-based learning framework to tackle supervised learning problems, while achieving various advantages of ensemble-based methods over the variational ones. After establishing the ensemble-based learning framework, we proceed to investigate the integration of ensemble-based learning into an ensemble-based data assimilation framework to handle simulator imperfection. In the course of our investigations, we also develop a strategy to tackle the issue of multi-modality in supervised-learning problems, and transfer this strategy to data assimilation problems to help improve assimilation performance. For demonstration, we apply the ensemble-based learning framework and the integrated, ensemble-based data assimilation framework to a supervised learning problem and a data assimilation problem with an imperfect forward simulator, respectively. The experiment results indicate that both frameworks achieve good performance in relevant case studies, and that functional approximation through machine learning may serve as a viable way to account for simulator imperfection in data assimilation problems.

Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradientdescent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neuron's dependence on the weights and errors located deeper in the network require exhaustive data movement which presents a key problem in enhancing the performance and energy-efficiency of machine-learning hardware. In this work, we propose a bio-plausible alternative to backpropagation drawing from advances in feedback alignment algorithms in which the error computation at a single synapse reduces to the product of three scalar values, satisfying the three factor rule. Using a sparse feedback matrix, we show that a neuron needs only a fraction of the information previously used by the feedback alignment algorithms to yield results which are competitive with backpropagation. Consequently, memory and compute can be partitioned and distributed whichever way produces the most efficient forward pass so long as a single error can be delivered to each neuron. We evaluate our algorithm using standard data sets, including ImageNet, to address the concern of scaling to challenging problems. Our results show orders of magnitude improvement in data movement and 2 improvement in multiply-and-accumulate operations over backpropagation. All the code and results are available under https://github.com/bcrafton/ssdfa. I. INTRODUCTION The demise of Dennard scaling [11] and decline of Moores Law [27] have exposed the fundamental scaling limitations of the von Neumann models of computing. This transition is accompanied by the realization that in a fast evolving, socially interconnected world, we are observing a seismic shift in the amount of unstructured data that need to be processed in real-time [25] which has heralded the third wave of Artificial Intelligence and the exponential growth of Machine Learning in data-analytics, real-time control, computer vision, robotics and so on. We expect that intelligent systems of the future will be limited by the energy growth of data movement rather than compute.

"Deep Archetypal Analysis" generates latent representations of high-dimensional datasets in terms of fractions of intuitively understandable basic entities called archetypes. The proposed method is an extension of linear "Archetypal Analysis" (AA), an unsupervised method to represent multivariate data points as sparse convex combinations of extremal elements of the dataset. Unlike the original formulation of AA, "Deep AA" can also handle side information and provides the ability for data-driven representation learning which reduces the dependence on expert knowledge. Our method is motivated by studies of evolutionary trade-offs in biology where archetypes are species highly adapted to a single task. Along these lines, we demonstrate that "Deep AA" also lends itself to the supervised exploration of chemical space, marking a distinct starting point for de novo molecular design. In the unsupervised setting we show how "Deep AA" is used on CelebA to identify archetypal faces. These can then be superimposed in order to generate new faces which inherit dominant traits of the archetypes they are based on.