Non-Intrusive Load Monitoring (NILM) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's power demand. The resulting model is called Prior Flow Variational Autoencoder or, for simplicity PFVAE. Thus, instead of having one model per appliance, the resulting model is responsible for estimating the power demand, appliance-by-appliance, at once. We train and evaluate our proposed model in a publicly available dataset composed of power demand measures from a poultry feed factory located in Brazil. The proposed model's quality is evaluated by comparing the obtained normalized disaggregation error (NDE) and signal aggregated error (SAE) with the previous work values on the same dataset. Our proposal achieves highly competitive results, and for six of the eight machines belonging to the dataset, we observe consistent improvements that go from 28% up to 81% in NDE and from 27% up to 86% in SAE.

Load forecasting is crucial for multiple energy management tasks such as scheduling generation capacity, planning supply and demand, and minimizing energy trade costs. Such relevance has increased even more in recent years due to the integration of renewable energies, electric cars, and microgrids. Conventional load forecasting techniques obtain single-value load forecasts by exploiting consumption patterns of past load demand. However, such techniques cannot assess intrinsic uncertainties in load demand, and cannot capture dynamic changes in consumption patterns. To address these problems, this paper presents a method for probabilistic load forecasting based on the adaptive online learning of hidden Markov models. We propose learning and forecasting techniques with theoretical guarantees, and experimentally assess their performance in multiple scenarios. In particular, we develop adaptive online learning techniques that update model parameters recursively, and sequential prediction techniques that obtain probabilistic forecasts using the most recent parameters. The performance of the method is evaluated using multiple datasets corresponding with regions that have different sizes and display assorted time-varying consumption patterns. The results show that the proposed method can significantly improve the performance of existing techniques for a wide range of scenarios.

AI applications are transforming business operations and processes in the power sector as well as the broader economy, leading to greater cost savings, increased efficiency and new services for consumers. But further developments rely on the ability to foster and support innovation, addressing outstanding matters related to investments, data access and governance, as well as ethics. By 2025, 81% of the energy companies will have adopted artificial intelligence, reaping the numerous benefits of accelerated developments in this field and fast tracking the clean energy transition. This is according to an assessment released by Eurelectric, AI Insights: The Power Sector in a Post-Digital Age. First, AI can enable a faster decarbonisation of the power sector.

Going Green sits down with Dr. Austin Sendek, Founder & CEO of Aionics, Inc. to discuss his path to building an artificial intelligence platform to help with R&D in decarbonizing materials. I am the CEO and Founder at Aionics, Inc. I am the CEO/Founder at Aionics, a company commercializing A.I. software for accelerating the pace of R&D in decarbonization materials. I founded Aionics after graduating with my Ph.D. in Applied Physics from Stanford in 2018. At the time, I had offers to join several materials companies at the executive or VP-level, but ultimately decided I could have a broader impact on global carbon emissions if I built an R&D platform that could be licensed across multiple companies in multiple industries.

Chemical kinetics consists of the phenomenological framework for the disentanglement of reaction mechanisms, optimization of reaction performance and the rational design of chemical processes. Here, we utilize feed-forward artificial neural networks as basis functions for the construction of surrogate models to solve ordinary differential equations (ODEs) that describe microkinetic models (MKMs). We present an algebraic framework for the mathematical description and classification of reaction networks, types of elementary reaction, and chemical species. Under this framework, we demonstrate that the simultaneous training of neural nets and kinetic model parameters in a regularized multiobjective optimization setting leads to the solution of the inverse problem through the estimation of kinetic parameters from synthetic experimental data. We probe the limits at which kinetic parameters can be retrieved as a function of knowledge about the chemical system states over time, and assess the robustness of the methodology with respect to statistical noise. This surrogate approach to inverse kinetic ODEs can assist in the elucidation of reaction mechanisms based on transient data.

Uncertainty is ubiquitous with flow in subsurface rocks because of their inherent heterogeneity and lack of in-situ measurements. To complete uncertainty analysis in a multi-scale manner, it is a prerequisite to provide sufficient rock samples. Even though the advent of digital rock technology offers opportunities to reproduce rocks, it still cannot be utilized to provide massive samples due to its high cost, thus leading to the development of diversified mathematical methods. Among them, two-point statistics (TPS) and multi-point statistics (MPS) are commonly utilized, which feature incorporating low-order and high-order statistical information, respectively. Recently, generative adversarial networks (GANs) are becoming increasingly popular since they can reproduce training images with excellent visual and consequent geologic realism. However, standard GANs can only incorporate information from data, while leaving no interface for user-defined properties, and thus may limit the diversity of reconstructed samples. In this study, we propose conditional GANs for digital rock reconstruction, aiming to reproduce samples not only similar to the real training data, but also satisfying user-specified properties. In fact, the proposed framework can realize the targets of MPS and TPS simultaneously by incorporating high-order information directly from rock images with the GANs scheme, while preserving low-order counterparts through conditioning. We conduct three reconstruction experiments, and the results demonstrate that rock type, rock porosity, and correlation length can be successfully conditioned to affect the reconstructed rock images. Furthermore, in contrast to existing GANs, the proposed conditioning enables learning of multiple rock types simultaneously, and thus invisibly saves the computational cost.

Climate change is far and away the greatest threat of the modern human era -- a crisis that will only get worse the longer we dither -- with American car culture as a major contributor to the nation's greenhouse emissions. But carbon-neutralizing energy and solutions are already on the horizon and, in some more developed countries like Sweden, are already being deployed. In his latest book, Our Livable World, science and technology analyst Marc Shaus, takes readers on a fascinating tour of the emerging tools -- from "smart highways" to jet fuel made from trash -- that will not only help curb climate change but perhaps even usher in a new, more sustainable, livable world. The following excerpt is reprinted from Our Livable World: How Scientists Today Are Creating the Clean Earth of Tomorrow by Marc Shaus. Reprinted with permission of Diversion Books.

… the findings from the photo mosaic maps will be extrapolated to the regions covered by the echo-sounder mapping by means of machine learning.”.

Electricity load forecasting enables the grid operators to optimally implement the smart grid's most essential features such as demand response and energy efficiency. Electricity demand profiles can vary drastically from one region to another on diurnal, seasonal and yearly scale. Hence to devise a load forecasting technique that can yield the best estimates on diverse datasets, specially when the training data is limited, is a big challenge. This paper presents a deep learning architecture for short-term load forecasting based on bidirectional sequential models in conjunction with feature engineering that extracts the hand-crafted derived features in order to aid the model for better learning and predictions. In the proposed architecture, named as Deep Derived Feature Fusion (DeepDeFF), the raw input and hand-crafted features are trained at separate levels and then their respective outputs are combined to make the final prediction. The efficacy of the proposed methodology is evaluated on datasets from five countries with completely different patterns. The results demonstrate that the proposed technique is superior to the existing state of the art.

Last week the Canadian government tabled legislation as part of its climate action plan to meet and exceed Canada's emissions reduction targets. This followed comments made two days earlier by the Bank of Canada's Governor in which he cautioned that climate change will have a profound impact on our economy. A survey conducted by IBM last month shows that the majority Canadians agree – 73% believe the advancement of clean technologies and artificial intelligence are important in ensuring economic growth. The survey also reveals that most people are keen to integrate more technology into their personal lives if it would support planetary health – 74% of Canadians said they are willing to adopt technology solutions to help live a more environmentally friendly lifestyle. So, while countries around the world – including ours – work towards the 2050 net zero emission goal and implement other innovative'good tech' measures to combat climate change, how can we do our part with the technology we use every single day?