The integration of machine learning methods and Model Predictive Control (MPC) has received increasing attention in recent years. In general, learning-based predictive control (LPC) is promising to build data-driven models and solve the online optimization problem with lower computational costs. However, the robustness of LPC is difficult to be guaranteed since there will be uncertainties due to function approximation used in machine learning algorithms. In this paper, a novel robust learning-based predictive control (r-LPC) scheme is proposed for constrained nonlinear systems with unknown dynamics. In r-LPC, the Koopman operator is used to form a global linear representation of the unknown dynamics, and an incremental actor-critic algorithm is presented for receding horizon optimization. To realize the satisfaction of system constraints, soft logarithmic barrier functions are designed within the learning predictive framework. The recursive feasibility and stability of the closed-loop system are discussed under the convergence arguments of the approximation algorithms adopted. Also, the robustness property of r-LPC is analyzed theoretically by taking into consideration the existence of perturbations on the controller due to possible approximation errors. Simulation results with the proposed learning control approach for the data-driven regulation of a Van der Pol oscillator system have been reported, including the comparisons with a classic MPC and an infinite-horizon Dual Heuristic Programming (DHP) algorithm. The results show that the r-LPC significantly outperforms the DHP algorithm in terms of control performance and can be comparative to the MPC in terms of regulating control as well as energy consumption. Moreover, its average computational cost is much smaller than that with the MPC in the adopted environment.

We present an algorithm for marginalising changepoints in time-series models that assume a fixed number of unknown changepoints. Our algorithm is differentiable with respect to its inputs, which are the values of latent random variables other than changepoints. Also, it runs in time O(mn) where n is the number of time steps and m the number of changepoints, an improvement over a naive marginalisation method with O(n^m) time complexity. We derive the algorithm by identifying quantities related to this marginalisation problem, showing that these quantities satisfy recursive relationships, and transforming the relationships to an algorithm via dynamic programming. Since our algorithm is differentiable, it can be applied to convert a model non-differentiable due to changepoints to a differentiable one, so that the resulting models can be analysed using gradient-based inference or learning techniques. We empirically show the effectiveness of our algorithm in this application by tackling the posterior inference problem on synthetic and real-world data.

Information theory provides a mathematical foundation to measure uncertainty in belief. Belief is represented by a probability distribution that captures our understanding of an outcome's plausibility. Information measures based on Shannon's concept of entropy include realization information, Kullback-Leibler divergence, Lindley's information in experiment, cross entropy, and mutual information. We derive a general theory of information from first principles that accounts for evolving belief and recovers all of these measures. Rather than simply gauging uncertainty, information is understood in this theory to measure change in belief. We may then regard entropy as the information we expect to gain upon realization of a discrete latent random variable. This theory of information is compatible with the Bayesian paradigm in which rational belief is updated as evidence becomes available. Furthermore, this theory admits novel measures of information with well-defined properties, which we explore in both analysis and experiment. This view of information illuminates the study of machine learning by allowing us to quantify information captured by a predictive model and distinguish it from residual information contained in training data. We gain related insights regarding feature selection, anomaly detection, and novel Bayesian approaches.

Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices R.M. Churchill Theory Department Princeton Plasma Physics Laboratory 100 Stellarator Road, Princeton, NJ 08540, USA rchurchi@pppl.gov and the DIII-D team General Atomics P .O. Box 85608, San Diego, California 92186, USA Abstract The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series generated by diagnostic instruments observing fusion plasmas. Here we apply this neural network architecture to the popular problem of disruption prediction in fusion tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. ECEi measures a fundamental plasma quantity (electron temperature) with high temporal resolution over the entire plasma discharge, making it sensitive to a number of potential pre-disruptions markers with different temporal and spatial scales. Promising, initial disruption prediction results are obtained training a deep CNN with large receptive field ( 30k), achieving an F 1-score of 91% on individual time-slices using only the ECEi data. 1 Introduction Plasma phenomena contain a wide range of temporal and spatial scales, often exhibiting multi-scale characteristics (see Figure 1).

The trick is the use of computer vision (aka a form of AI) to align a large array of mirrors as they reflect sunlight on a solitary target. That allows for the kind of accuracy that hasn't been possible until now. There's still a lot of work to go before the technology enters real-world use. Heliogen achieved the record heat levels the first day of its plant's operation, company founder Bill Gross told CNN. While impressive, it won't immediately translate to a practical solution.

The oil and natural gas industry is turning to artificial intelligence technology to save billions of dollars in maintenance and production costs. Houston oilfield services company Baker Hughes, tech giant Microsoft and Silicon Valley artificial intelligence company C3.ai have signed an agreement to develop and deploy the technology for industry customers around the globe, the companies said Tuesday. In the oil field, artificial intelligence technology is being used to compile massive amounts of data transmitted by sensors and so-called smart equipment, look for patterns, make predictions and inform decisions by operators. "Companies that adopt this technology will be the next Amazon, and those that don't adopt will be the next Sears," Tom Siebel, C3.ai founder and CEO, said in an interview. Baker Hughes and C3.ai launched a joint venture in June to deploy artificial intelligence in the oil patch.

WASHINGTON, D.C. – Today, the U.S. Department of Energy's (DOE's) Advanced Research Projects Agency-Energy (ARPA-E) announced $15 million in funding for 23 projects to accelerate the incorporation of machine learning and artificial intelligence into the energy technology and product design processes as part of the Design Intelligence Fostering Formidable Energy Reduction (and) Enabling Novel Totally Impactful Advanced Technology Enhancements (DIFFERENTIATE) program. Launched in April of this year, the DIFFERENTIATE program aims to develop streamlined solutions to next-generation energy challenges. The program identified three general mathematical optimization problems that are common to many design processes. The selected projects then conceptualized machine learning and artificial intelligence-based solutions to help engineers execute and solve these problems in a manner that dramatically accelerates the pace of energy innovation. "The incorporation of AI and Machine Learning into our energy technology design and engineering processes has great potential to increase the productivity of our nation's engineers and scientists," said Secretary of Energy Rick Perry.

A startup backed by billionaire Microsoft founder, Bill Gates, says a breakthrough in solar technology may revolutionize the way materials like steel and glass are created. The company, called Heliogen, says it uses artificial intelligence to help operate an array of mirrors capable of reflecting and focusing the sun's light and creating a type of solar oven. The system works so well that they report being able to create temperatures of 1,000 degrees Fahrenheit - about a quarter of the temperature found on the Sun's surface. That extreme heat is a first for solar-powered systems like Heliogens and, according to the company, could be used as an environmentally friendly way of creating crucial materials like cement, glass, and steel. As noted by CNN, Heliogen's system could drastically impact global emissions - roughly 7 percent of of C02 released into Earth's environment are from manufacturing cement alone according to the International Energy Agency.

Reconstruction of seismic data with missing traces is a long-standing issue in seismic data processing. In recent years, rank reduction operations are being commonly utilized to overcome this problem, which require the rank of seismic data to be a prior. However, the rank of field data is unknown; usually it requires much time to manually adjust the rank and just obtain an approximated rank. Methods based on deep learning require very large datasets for training; however acquiring large datasets is difficult owing to physical or financial constraints in practice. Therefore, in this work, we developed a novel method based on unsupervised learning using the intrinsic properties of a convolutional neural network known as U-net, without training datasets. Only one undersampled seismic data was needed, and the deep seismic prior of input data could be exploited by the network itself, thus making the reconstruction convenient. Furthermore, this method can handle both irregular and regular seismic data. Synthetic and field data were tested to assess the performance of the proposed algorithm (DSPRecon algorithm); the advantages of using our method were evaluated by comparing it with the singular spectrum analysis (SSA) method for irregular data reconstruction and de-aliased Cadzow method for regular data reconstruction. Experimental results showed that our method provided better reconstruction performance than the SSA or Cadzow methods. The recovered signal-to-noise ratios (SNRs) were 32.68 dB and 19.11 dB for the DSPRecon and SSA algorithms, respectively. Those for the DSPRecon and Cadzow methods were 35.91 dB and 15.32 dB, respectively.

This paper introduces EQShapelets (EarthQuake Shapelets) a time-series shape-based approach embedded in machine learning to autonomously detect earthquakes. It promises to overcome the challenges in the field of seismology related to automated detection and cataloging of earthquakes. EQShapelets are amplitude and phase-independent, i.e., their detection sensitivity is irrespective of the magnitude of the earthquake and the time of occurrence. They are also robust to noise and other spurious signals. The detection capability of EQShapelets is tested on one week of continuous seismic data provided by the Northern California Seismic Network (NCSN) obtained from a station in central California near the Calaveras Fault. EQShapelets combined with a Random Forest classifier, detected all of the cataloged earthquakes and 281 uncataloged events with lower false detection rate thus offering a better performance than autocorrelation and FAST algorithms. The primary advantage of EQShapelets over competing methods is the interpretability and insight it offers. Shape-based approaches are intuitive, visually meaningful and offers immediate insight into the problem domain that goes beyond their use in accurate detection. EQShapelets, if implemented at a large scale, can significantly reduce catalog completeness magnitudes and can serve as an effective tool for near real-time earthquake monitoring and cataloging.