Search for: All records

Recent research has highlighted the effectiveness of advanced building controls in reducing the energy consumption of heating, ventilation, and air-conditioning (HVAC) systems. Among advanced building control strategies, deep reinforcement learning control (DRL) shows the potential to achieve energy savings for HVAC systems and has emerged as a promising strategy. However, training DRL requires an interactive environment for the agent, which is challenging to achieve with real buildings due to time and response speed constraints. To address this challenge, a simulation environment serving as a training environment is needed, even though the DRL algorithm does not necessarily need a model. The error between the model and the real building is inevitable in this process, which may influence the efficiency of the DRL controller. To investigate the impact of model error, a virtual testbed was established. A high- fidelity Modelica-based model is developed serving as the virtual building. Three reduced-order models (ROMs) (i.e., 3R2C, Light Gradient Boosting Machine (LightGBM) and artificial neural network (ANN) models) were trained with the historical data generated from the virtual building and were embedded in the training environments of DRL. The sensitivity of ROMs and the Modelica model to random and periodical actions were tested and compared. Deploying the policy trained based on a ROM-based environment, which stands for a surrogate model in reality, into the Modelica-based virtual building testing environment, which stands for real-building, is a practical approach to implementing the DRL control. The performance of the practical DRL controller is compared with rule-based control (RBC) and an ideal DRL controller which was trained and deployed both in the virtual building environment. In the final episode with best rewards of the case study, the 3R2C, LightGBM, and ANN-based DRL outperform the RBC by 7.4%, 14.4%, and 11.4%, respectively in terms of the reward, comprising the weighted sum of energy cost, temperature violations, and the slew rate of the control signal, but falls short of the ideal Modelica-based DRL controller which outperforms RBC by 29.5%. The DRL controllers based on data-driven models are highly unstable with higher maximum rewards but much lower average rewards which might be caused by the significant prediction defect in certain action regions of the data-driven model. 

Resource limitations make it challenging to provide all students with one of the most effec- tive educational interventions: personalized instruction. Reinforcement learning could be a pivotal tool to decrease the development costs and enhance the effectiveness of intelligent tutoring software, that aims to provide the right support, at the right time, to a student. Here we illustrate that deep reinforcement learning can be used to provide adaptive peda- gogical support to students learning about the concept of volume in a narrative storyline software. Using explainable artificial intelligence tools, we extracted interpretable insights about the pedagogical policy learned and demonstrated that the resulting policy had simi- lar performance in a different student population. Most importantly, in both studies, the reinforcement-learning narrative system had the largest benefit for those students with the lowest initial pretest scores, suggesting the opportunity for AI to adapt and provide support for those most in need. 

Machine learning (ML) has shown to be an effective alternative to physical models for quality prediction and process optimization of metal additive manufacturing (AM). However, the inherent “black box” nature of ML techniques such as those represented by artificial neural networks has often presented a challenge to interpret ML outcomes in the framework of the complex thermodynamics that govern AM. While the practical benefits of ML provide an adequate justification, its utility as a reliable modeling tool is ultimately reliant on assured consistency with physical principles and model transparency. To facilitate the fundamental needs, physics-informed machine learning (PIML) has emerged as a hybrid machine learning paradigm that imbues ML models with physical domain knowledge such as thermomechanical laws and constraints. The distinguishing feature of PIML is the synergistic integration of data-driven methods that reflect system dynamics in real-time with the governing physics underlying AM. In this paper, the current state-of-the-art in metal AM is reviewed and opportunities for a paradigm shift to PIML are discussed, thereby identifying relevant future research directions. 

Key challenges to regionalization of methane fluxes in the Amazon basin are the large seasonal variation in inundated areas and habitats, the wide variety of aquatic ecosystems throughout the Amazon basin, and the variability in methane fluxes in time and space. Based on available measurements of methane emission and areal extent, seven types of aquatic systems are considered: streams and rivers, lakes, seasonally flooded forests, seasonally flooded savannas and other interfluvial wetlands, herbaceous plants on riverine floodplains, peatlands, and hydroelectric reservoirs. We evaluate the adequacy of sampling and of field methods plus atmospheric measurements, as applied to the Amazon basin, summarize published fluxes and regional estimates using bottom-up and top-down approaches, and discuss current understanding of biogeochemical and physical processes in Amazon aquatic environments and their incorporation into mechanistic and statistical models. Recommendations for further study in the Amazon basin and elsewhere include application of new remote sensing techniques, increased sampling frequency and duration, experimental studies to improve understanding of biogeochemical and physical processes, and development of models appropriate for hydrological and ecological conditions. 

In this article the recent developments of the open-source OpenMolcas chemistry software environment, since spring 2020, are described, with the main focus on novel functionalities that are accessible in the stable branch of the package and/or via interfaces with other packages. These community developments span a wide range of topics in computational chemistry, and are presented in thematic sections associated with electronic structure theory, electronic spectroscopy simulations, analytic gradients and molecular structure optimizations, ab initio molecular dynamics, and other new features. This report represents a useful summary of these developments, and it offers a solid overview of the chemical phenomena and processes that OpenMolcas can address, while showing that OpenMolcas is an attractive platform for state-of-the-art atomistic computer simulations. 

We define big data as large amounts of information, collected about many people, over multiple devices. We define critical big data research as efforts to demonstrate how flaws — ethical or methodological — in the collection and use and of big have implications for social inequality. There are many critical and creative big data research endeavors around the world. Here we present an annotated catalog of projects that: are both critical and creative in their analysis of big data; have a distinct Principal Investigator (PI) or clear team; and, are producing an identifiable body of public essays, original research, or civic engagement projects. We have catalogued these endeavors with as much descriptive information as possible, and organized projects by the domains of big data critique and creativity in which they are having an impact. We identify some 35 distinct projects, and several dozen individual researchers, artists and civic leaders, operating in 16 domains of inquiry. We recommend expanding critical and creative work in several domains: expanding work in China; supporting policy initiatives in Latin America’s young democracies; expanding work on algorithmic manipulation originating in authoritarian countries; identifying best practices for how public agencies in the United States should develop big data initiatives. We recommend that the next stage of support for these lines of inquiry is to help publicize the output of these projects, many of which are of interest to a handful of specialists but should be made accessible to policy makers, journalists, and the interested public.