Equation-based and data-driven modeling: Open-source software current state and future directions

Gunnell, LaGrande; Nicholson, Bethany; Hedengren, John D.

doi:10.1016/j.compchemeng.2023.108521

Cited by 4 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In relation to this problem, Bradley et al [116] state that hybrid first-principles, data-driven methods generally outperform purely data-driven models, but the interpretation and extrapolation of modelling results require particular attention. Gunnell et al [117] present the current state and future directions for open-source software for equation-based and data-driven modelling and highlight an emerging trend of integration of data-driven and principles-based (i.e., physics-informed) tools.…”

Section: Physics-informed ML and Grey-box Modelling In Buildingsmentioning

confidence: 99%

Interpretable Data-Driven Methods for Building Energy Modelling—A Review of Critical Connections and Gaps

Manfren,

Gonzalez-Carreon,

James

2024

Energies

View full text Add to dashboard Cite

Technological improvements are crucial for achieving decarbonisation targets and addressing the impacts of climate change in the built environment via mitigation and adaptation measures. Data-driven methods for building performance prediction are particularly important in this regard. Nevertheless, the deployment of these technologies faces challenges, particularly in the domains of artificial intelligence (AI) ethics, interpretability and explainability of machine learning (ML) algorithms. The challenges encountered in applications for the built environment are amplified, particularly when data-driven solutions need to be applied throughout all the stages of the building life cycle and to address problems from a socio-technical perspective, where human behaviour needs to be considered. This requires a consistent use of analytics to assess the performance of a building, ideally by employing a digital twin (DT) approach, which involves the creation of a digital counterpart of the building for continuous analysis and improvement. This paper presents an in-depth review of the critical connections between data-driven methods, AI ethics, interpretability and their implementation in the built environment, acknowledging the complex and interconnected nature of these topics. The review is organised into three distinct analytical levels: The first level explores key issues of the current research on the interpretability of machine learning methods. The second level considers the adoption of interpretable data-driven methods for building energy modelling and the problem of establishing a link with the third level, which examines physics-driven grey-box modelling techniques, in order to provide integrated modelling solutions. The review’s findings highlight how the interpretability concept is relevant in multiple contexts pertaining to energy and the built environment and how some of the current knowledge gaps can be addressed by further research in the broad area of data-driven methods.

show abstract

Section: Physics-informed ML and Grey-box Modelling In Buildingsmentioning

confidence: 99%

Interpretable Data-Driven Methods for Building Energy Modelling—A Review of Critical Connections and Gaps

Manfren,

Gonzalez-Carreon,

James

2024

Energies

View full text Add to dashboard Cite

show abstract

Practical exercises of computer-aided process synthesis for chemical engineering undergraduates

Suthar,

Mehta,

Panda

et al. 2024

Education for Chemical Engineers

View full text Add to dashboard Cite

Advancing Wine Fermentation: Extended Kalman Filter for Early Fault Detection

Lima,

Luna,

Lima

et al. 2024

Preprint

View full text Add to dashboard Cite

This work proposes an Extended Kalman Filter (EKF) state estimation approach for early detection of stuck and sluggish wine fermentations. The goal is to provide accurate information to enologists during fermentation to facilitate timely intervention and decision making. The study investigates the sensitivity of the fermentation process to various factors such as model parameters and initial conditions, especially for unmeasured nitrogen. It also shows how the estimation depends on meaningful sugar measurements, which are not available during the lag phase of fermentation. According to Monte Carlo simulations, the estimation algorithm was able to predict 95% of the problematic fermentations within the first few days. When initial nitrogen measurements are taken into account, a reliable prediction is available on the first day in 80% of the cases, justifying the additional cost. These results support the use of advanced control and monitoring methods in wine production and other alcoholic fermentation processes.

show abstract

Equation-based and data-driven modeling: Open-source software current state and future directions

Cited by 4 publications

References 45 publications

Interpretable Data-Driven Methods for Building Energy Modelling—A Review of Critical Connections and Gaps

Interpretable Data-Driven Methods for Building Energy Modelling—A Review of Critical Connections and Gaps

Practical exercises of computer-aided process synthesis for chemical engineering undergraduates

Advancing Wine Fermentation: Extended Kalman Filter for Early Fault Detection

Contact Info

Product

Resources

About