While current artificial intelligence (AI) technology holds strategic and transformative potential, it isn't always environmentally-friendly due to high energy consumption. To the rescue are researchers from Massachusetts Institute of Technology (MIT), who have devised a solution that not only lowers costs but, more importantly, reduces the AI model training's carbon footprint. Back in June 2019, the University of Massachusetts at Amherst revealed that the amount of energy utilized in AI model training equaled 626,000 pounds of carbon dioxide. Contemporary AI isn't just run on a personal laptop or simple server. Rather, deep neural networks are deployed on diverse arrays of specialized hardware platforms. The level of energy consumption required to power such AI technologies is approximately five times the lifetime carbon emissions from an average American car, including its manufacturing.

Like crystal balls for the universe's deeper mysteries, galaxies and other massive space objects can serve as lenses to more distant objects and phenomena along the same path, bending light in revelatory ways. Gravitational lensing was first theorized by Albert Einstein more than 100 years ago to describe how light bends when it travels past massive objects like galaxies and galaxy clusters. These lensing effects are typically described as weak or strong, and the strength of a lens relates to an object's position and mass and distance from the light source that is lensed. Strong lenses can have 100 billion times more mass than our sun, causing light from more distant objects in the same path to magnify and split, for example, into multiple images, or to appear as dramatic arcs or rings. The major limitation of strong gravitational lenses has been their scarcity, with only several hundred confirmed since the first observation in 1979, but that's changing, and fast.

Rapid development of big data and high-performance computing have encouraged explosive studies of deep learning in geoscience. However, most studies only take single-type data as input, frittering away invaluable multisource, multi-scale information. We develop a general architecture of hybrid deep neural networks (HDNNs) to support mixed inputs. Regarding as a combination of feature learning and target learning, the new proposed networks provide great capacity in high-hierarchy feature extraction and in-depth data mining. Furthermore, the hybrid architecture is an aggregation of multiple networks, demonstrating good flexibility and wide applicability. The configuration of multiple networks depends on application tasks and varies with inputs and targets. Concentrating on reservoir production prediction, a specific HDNN model is configured and applied to an oil development block. Considering their contributions to hydrocarbon production, core photos, logging images and curves, geologic and engineering parameters can all be taken as inputs. After preprocessing, the mixed inputs are prepared as regular-sampled structural and numerical data. For feature learning, convolutional neural networks (CNN) and multilayer perceptron (MLP) network are configured to separately process structural and numerical inputs. Learned features are then concatenated and fed to subsequent networks for target learning. Comparison with typical MLP model and CNN model highlights the superiority of proposed HDNN model with high accuracy and good generalization.

Machine learning (ML) is the field of training machines to achieve high level of cognition and perform human-like analysis. Since ML is a data-driven approach, it seemingly fits into our daily lives and operations as well as complex and interdisciplinary fields. With the rise of commercial, open-source and user-catered ML tools, a key question often arises whenever ML is applied to explore a phenomenon or a scenario: what constitutes a good ML model? Keeping in mind that a proper answer to this question depends on a variety of factors, this work presumes that a good ML model is one that optimally performs and best describes the phenomenon on hand. From this perspective, identifying proper assessment metrics to evaluate performance of ML models is not only necessary but is also warranted. As such, this paper examines a number of the most commonly-used performance fitness and error metrics for regression and classification algorithms, with emphasis on engineering applications.

Solar activity It is vital to accurately predict solar activity, in order to decrease the plausible damage of electronic equipment in the event of a large high-intensity solar eruption. Recently, we have proposed BELFIS (Brain Emotional Learning-based Fuzzy Inference System) as a tool for the forecasting of chaotic systems. The structure of BELFIS is designed based on the neural structure of fear conditioning. The function of BELFIS is implemented by assigning adaptive networks to the components of the BELFIS structure. This paper especially focuses on performance evaluation of BELFIS as a predictor by forecasting solar cycles 16 to 24. The performance of BELFIS is compared with other computational models used for this purpose, and in particular with adaptive neuro-fuzzy inference system (ANFIS).

Their study, published today in Science Advances, is the first to apply an experimentally validated machine learning method to rapidly design and develop advanced gas separation membranes. "Our work points to a new way of materials design and we expect it to revolutionize the field," says the study's PI Sanat Kumar, Bykhovsky Professor of Chemical Engineering and a pioneer in developing polymer nanocomposites with improved properties. Plastic films or membranes are often used to separate mixtures of simple gases, like carbon dioxide (CO2), nitrogen (N2), and methane (CH4). Scientists have proposed using membrane technology to separate CO2 from other gases for natural gas purification and carbon capture, but there are potentially hundreds of thousands of plastics that can be produced with our current synthetic toolbox, all of which vary in their chemical structure. Manufacturing and testing all of these materials is an expensive and time-consuming process, and to date, only about 1,000 have been evaluated as gas separation membranes.

Around the world, the lockdown measures to contain the pandemic have led to economic contraction and a significant drop in energy consumption including electricity, gas, and oil. CEOs, experts, and policymakers are still taking stock of the impact of COVID-19 on the energy landscape and what it means for the ongoing transition to sustainable energy. In India, the renewable sector, including large hydro, accounted for 15.6 percent of the generation in January, which is a lean season for hydro. Solar, wind, small hydro, biomass i.e officially referred to as Renewable Energy in India ― contributed 9.11 percent, up from 8.55 percent in the same period last year. Renewable energy provides an opportunity for building back better' as many people all over the world believe that the coronavirus pandemic is a result of us not being responsible for the environment.

Data-driven methods have recently made great progress in the discovery of partial differential equations (PDEs) from spatial-temporal data. However, several challenges remain to be solved, including sparse noisy data, incomplete candidate library, and spatially- or temporally-varying coefficients. In this work, a new framework, which combines neural network, genetic algorithm and adaptive methods, is put forward to address all of these challenges simultaneously. In the framework, a trained neural network is utilized to calculate derivatives and generate a large amount of meta-data, which solves the problem of sparse noisy data. Next, genetic algorithm is utilized to discover the form of PDEs and corresponding coefficients with an incomplete candidate library. Finally, a two-step adaptive method is introduced to discover parametric PDEs with spatially- or temporally-varying coefficients. In this method, the structure of a parametric PDE is first discovered, and then the general form of varying coefficients is identified. The proposed algorithm is tested on the Burgers equation, the convection-diffusion equation, the wave equation, and the KdV equation. The results demonstrate that this method is robust to sparse and noisy data, and is able to discover parametric PDEs with an incomplete candidate library.

Paradigmatic problems in supervised machine learning (ML) involve predicting an output response from an input, based on patterns extracted from a (training) dataset. In classification, the output response is (finitely) discrete and we need to classify input data into one of these discrete categories. In regression, the output is continuous, typically a real number or a vector. Owing to this important distinction in output response, the two tasks are typically treated differently. The differences in treatment manifest in two phases of modern ML: optimization (training), which consists of an algorithmic procedure to extract a predictor from the training data, typically by minimizing the training loss (also called empirical risk); and generalization (testing), which consists of an evaluation of the obtained predictor on a separate test, or validation, dataset. Traditionally, the choice of loss functions for both phases is starkly different across classification and regression tasks. The squared-loss function is typically used both for the training and the testing phases in regression. In contrast, the hinge or logistic (cross-entropy for multi-class problems) loss functions are typically used in the training phase of classification, while the very different 0-1 loss function is used for testing.

The lifelong control problem of an off-grid microgrid is composed of two tasks, namely estimation of the condition of the microgrid devices and operational planning accounting for the uncertainties by forecasting the future consumption and the renewable production. The main challenge for the effective control arises from the various changes that take place over time. In this paper, we present an open-source reinforcement framework for the modeling of an off-grid microgrid for rural electrification. The lifelong control problem of an isolated microgrid is formulated as a Markov Decision Process (MDP). We categorize the set of changes that can occur in progressive and abrupt changes. We propose a novel model based reinforcement learning algorithm that is able to address both types of changes. In particular the proposed algorithm demonstrates generalisation properties, transfer capabilities and better robustness in case of fast-changing system dynamics. The proposed algorithm is compared against a rule-based policy and a model predictive controller with look-ahead. The results show that the trained agent is able to outperform both benchmarks in the lifelong setting where the system dynamics are changing over time.