The world is not static: This causes real-world time series to change over time through external, and potentially disruptive, events such as macroeconomic cycles or the COVID-19 pandemic. We present an adaptive sampling strategy that selects the part of the time series history that is relevant for forecasting. We achieve this by learning a discrete distribution over relevant time steps by Bayesian optimization. We instantiate this idea with a two-step method that is pre-trained with uniform sampling and then training a lightweight adaptive architecture with adaptive sampling. We show with synthetic and real-world experiments that this method adapts to distribution shift and significantly reduces the forecasting error of the base model for three out of five datasets.

Adaptive mesh refinement (AMR) is necessary for efficient finite element simulations of complex physical phenomenon, as it allocates limited computational budget based on the need for higher or lower resolution, which varies over space and time. We present a novel formulation of AMR as a fully-cooperative Markov game, in which each element is an independent agent who makes refinement and de-refinement choices based on local information. We design a novel deep multi-agent reinforcement learning (MARL) algorithm called Value Decomposition Graph Network (VDGN), which solves the two core challenges that AMR poses for MARL: posthumous credit assignment due to agent creation and deletion, and unstructured observations due to the diversity of mesh geometries. For the first time, we show that MARL enables anticipatory refinement of regions that will encounter complex features at future times, thereby unlocking entirely new regions of the error-cost objective landscape that are inaccessible by traditional methods based on local error estimators. Comprehensive experiments show that VDGN policies significantly outperform error threshold-based policies in global error and cost metrics. We show that learned policies generalize to test problems with physical features, mesh geometries, and longer simulation times that were not seen in training. We also extend VDGN with multi-objective optimization capabilities to find the Pareto front of the tradeoff between cost and error.

The optimal design of many engineering processes can be subject to expensive and time-consuming experimentation. For efficiency, we seek to avoid wasting valuable resources in testing sub-optimal designs. One way to achieve this is by obtaining cheaper approximations of the desired system, which allow us to quickly explore new regimes and avoid areas that are clearly sub-optimal. As an example, consider the case diagrammed in Figure 1 from battery materials research with the goal of designing electrode materials for optimal performance in pouch cells. We can use experiments with cheaper coin cells and shorter test procedures to approximate the behaviour of the material in longer stability tests in pouch cells, which is in turn closer to the expected performance in electric car applications [Chen et al., 2019, Dörfler et al., 2020, Liu et al., 2021]. Similarly, design goals regarding battery life such as discharge capacity retention can be approximated using an early prediction model on the first few charge cycles rather than running aging and stability tests to completion [Attia et al., 2020].

Machine learning models have been employed to perform either physics-free data-driven or hybrid dynamical downscaling of climate data. Most of these implementations operate over relatively small downscaling factors because of the challenge of recovering fine-scale information from coarse data. This limits their compatibility with many global climate model outputs, often available between $\sim$50--100 km resolution, to scales of interest such as cloud resolving or urban scales. This study systematically examines the capability of convolutional neural networks (CNNs) to downscale surface wind speed data over land surface from different coarse resolutions (25 km, 48 km, and 100 km resolution) to 3 km. For each downscaling factor, we consider three CNN configurations that generate super-resolved predictions of fine-scale wind speed, which take between 1 to 3 input fields: coarse wind speed, fine-scale topography, and diurnal cycle. In addition to fine-scale wind speeds, probability density function parameters are generated, through which sample wind speeds can be generated accounting for the intrinsic stochasticity of wind speed. For generalizability assessment, CNN models are tested on regions with different topography and climate that are unseen during training. The evaluation of super-resolved predictions focuses on subgrid-scale variability and the recovery of extremes. Models with coarse wind and fine topography as inputs exhibit the best performance compared with other model configurations, operating across the same downscaling factor. Our diurnal cycle encoding results in lower out-of-sample generalizability compared with other input configurations.

A promising approach for scalable Gaussian processes (GPs) is the Karhunen-Lo\`eve (KL) decomposition, in which the GP kernel is represented by a set of basis functions which are the eigenfunctions of the kernel operator. Such decomposed kernels have the potential to be very fast, and do not depend on the selection of a reduced set of inducing points. However KL decompositions lead to high dimensionality, and variable selection becomes paramount. This paper reports a new method of forward variable selection, enabled by the ordered nature of the basis functions in the KL expansion of the Bayesian Smoothing Spline ANOVA kernel (BSS-ANOVA), coupled with fast Gibbs sampling in a fully Bayesian approach. It quickly and effectively limits the number of terms, yielding a method with competitive accuracies, training and inference times for tabular datasets of low feature set dimensionality. The inference speed and accuracy makes the method especially useful for dynamic systems identification, by modeling the dynamics in the tangent space as a static problem, then integrating the learned dynamics using a high-order scheme. The methods are demonstrated on two dynamic datasets: a `Susceptible, Infected, Recovered' (SIR) toy problem, with the transmissibility used as forcing function, along with the experimental `Cascaded Tanks' benchmark dataset. Comparisons on the static prediction of time derivatives are made with a random forest (RF), a residual neural network (ResNet), and the Orthogonal Additive Kernel (OAK) inducing points scalable GP, while for the timeseries prediction comparisons are made with LSTM and GRU recurrent neural networks (RNNs) along with the SINDy package.

Recovering a globally accurate complex physics field from limited sensor is critical to the measurement and control in the aerospace engineering. General reconstruction methods for recovering the field, especially the deep learning with more parameters and better representational ability, usually require large amounts of labeled data which is unaffordable. To solve the problem, this paper proposes Uncertainty Guided Ensemble Self-Training (UGE-ST), using plentiful unlabeled data to improve reconstruction performance. A novel self-training framework with the ensemble teacher and pretraining student designed to improve the accuracy of the pseudo-label and remedy the impact of noise is first proposed. On the other hand, uncertainty-guided learning is proposed to encourage the model to focus on the highly confident regions of pseudo-labels and mitigate the effects of wrong pseudo-labeling in self-training, improving the performance of the reconstruction model. Experiments include the pressure velocity field reconstruction of airfoil and the temperature field reconstruction of aircraft system indicate that our UGE-ST can save up to 90% of the data with the same accuracy as supervised learning.

Reconfigurable morphing surfaces provide new opportunities for advanced human-machine interfaces and bio-inspired robotics. Morphing into arbitrary surfaces on demand requires a device with a sufficiently large number of actuators and an inverse control strategy that can calculate the actuator stimulation necessary to achieve a target surface. The programmability of a morphing surface can be improved by increasing the number of independent actuators, but this increases the complexity of the control system. Thus, developing compact and efficient control interfaces and control algorithms is a crucial knowledge gap for the adoption of morphing surfaces in broad applications. In this work, we describe a passively addressed robotic morphing surface (PARMS) composed of matrix-arranged ionic actuators. To reduce the complexity of the physical control interface, we introduce passive matrix addressing. Matrix addressing allows the control of independent actuators using only 2N control inputs, which is significantly lower than control inputs required for traditional direct addressing. Our control algorithm is based on machine learning using finite element simulations as the training data. This machine learning approach allows both forward and inverse control with high precision in real time. Inverse control demonstrations show that the PARMS can dynamically morph into arbitrary pre-defined surfaces on demand. These innovations in actuator matrix control may enable future implementation of PARMS in wearables, haptics, and augmented reality/virtual reality (AR/VR).

"Prevention is the daughter of intelligence," said the famous English poet and navigator Walter Raleigh four centuries ago. But the explorer couldn't predict that the intelligence he was talking about would one day be artificial intelligence. Indeed, AI has become a reliable ally in preventing unwanted outcomes, thanks to the anomaly detection and forecasting capabilities of its sub-branch known as machine learning. But what are these powers based on, and how can they be leveraged in various scenarios and AI use cases? When detecting anomalies, the typical way to go in many business areas was traditionally based on predetermined rules.

Proteins are complex and dynamic molecules, encoded by our genes, that are responsible for many of the varied and fundamental processes of life. They have an astounding range of roles in biology. The rods and cones in our eyes that sense light and make it possible for us to see, the molecular sensors that underlie hearing and our sense of touch, the complex molecular machines that convert sunlight into chemical energy in plants, the motors that drive motion in microbes and our muscles, enzymes that break down plastic, antibodies that protect us from disease, and molecular circuits that cause disease when they fail -- are all proteins. Metagenomics, one of the new frontiers in the natural sciences, uses gene sequencing to discover proteins in samples from environments across the earth, from microbes living in the soil, deep in the ocean, in extreme environments like hydrothermal vents, and even in our guts and on our skin. The natural world contains a vast number of proteins beyond the ones that have been cataloged and annotated in well-studied organisms.

A logged forest in the Amazon. A collaboration led by Ekena Rangel Pinagé (Oregon State University) has used very-high-resolution satellite imagery to develop a machine learning model that aims to improve climate scientists' ability to estimate aboveground carbon stocks in the Amazon. Findings of the study were published in the journal Carbon Balance and Management. Covering more than 2.5 million square miles in South America, the Amazon is the largest of the world's tropical forests, which play huge ecological roles for the planet despite covering less than 10% of the Earth's land area. More than half of all carbon stored in aboveground biomass is sequestered in tropical rain forests, which are also home to greater than 60% of all terrestrial species.