Machine Learning for Sustainable Energy Systems

Donti, Priya L.; Kolter, J. Zico

doi:10.1146/annurev-environ-020220-061831

Cited by 53 publications

(60 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, with the current Machine Learning models, it is possible to carry out predictive analytics on any type of data, especially in its application to Sustainable Energy Systems, as extensively explained by Donti et al 34 using algorithms that imitate human cognitive functions through ANN because they stand out in the analysis and optimization processes. Therefore, there is a great potential in using these tools to optimize the methodology applied in the modelling and simulation of the thermal behaviour, as well as the energy consumption of a building, as indicated by Santos-Herrero et al 35 in its overview of MPC in building climatization.…”

Section: Methodsmentioning

confidence: 99%

Energy and thermal modelling of an office building to develop an artificial neural networks model

Santos-Herrero

López-Guede

Flores-Abascal

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Nowadays everyone should be aware of the importance of reducing CO2 emissions which produce the greenhouse effect. In the field of construction, several options are proposed to reach nearly-Zero Energy Building (nZEB) standards. Obviously, before undertaking a modification in any part of a building focused on improving the energy performance, it is generally better to carry out simulations to evaluate its effectiveness. Using Artificial Neural Networks (ANNs) allows a digital twin of the building to be obtained for specific characteristics without using very expensive software. This can simulate the effect of a single or combined intervention on a particular floor or an event on the remaining floors. In this paper, an example has been developed based on ANN. The results show a reasonable correlation between the real data of the Operative Temperature with the Energy Consumption and their estimates obtained through an ANN model, trained using an hourly basis, on each of the floors of an office building. This model confirms it is possible to obtain simulations in existing public buildings with an acceptable degree of precision and without laborious modelling, which would make it easier to achieve the nZEB target, especially in existing public office buildings.

show abstract

Section: Methodsmentioning

confidence: 99%

Energy and thermal modelling of an office building to develop an artificial neural networks model

Santos-Herrero

López-Guede

Flores-Abascal

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Research can also be done to incorporate domain knowledge into the deep network used to generate synthetic data. It can also be used alongside real-world applications (Zou et al 2019b,a;Konstantakopoulos et al 2019;Chen et al 2021;Periyakoil et al 2021;Das et al , 2020Liu 2018;Liu et al 2019b;Donti and Kolter 2021;Jin et al 2018) where challenges such as class-imbalance and privacy is important and thus generating conditional synthetic data is helpful.…”

Section: Future Workmentioning

confidence: 99%

Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data

Das

Tran

Singh

et al. 2022

AAAI

View full text Add to dashboard Cite

Background: At the onset of a pandemic, such as COVID-19, data with proper labeling/attributes corresponding to the new disease might be unavailable or sparse. Machine Learning (ML) models trained with the available data, which is limited in quantity and poor in diversity, will often be biased and inaccurate. At the same time, ML algorithms designed to fight pandemics must have good performance and be developed in a time-sensitive manner. To tackle the challenges of limited data, and label scarcity in the available data, we propose generating conditional synthetic data, to be used alongside real data for developing robust ML models. Methods: We present a hybrid model consisting of a conditional generative flow and a classifier for conditional synthetic data generation. The classifier decouples the feature representation for the condition, which is fed to the flow to extract the local noise. We generate synthetic data by manipulating the local noise with fixed conditional feature representation. We also propose a semi-supervised approach to generate synthetic samples in the absence of labels for a majority of the available data. Results: We performed conditional synthetic generation for chest computed tomography (CT) scans corresponding to normal, COVID-19, and pneumonia afflicted patients. We show that our method significantly outperforms existing models both on qualitative and quantitative performance, and our semi-supervised approach can efficiently synthesize conditional samples under label scarcity. As an example of downstream use of synthetic data, we show improvement in COVID-19 detection from CT scans with conditional synthetic data augmentation.

show abstract

“…ML is the science of getting computers to act without being explicitly programmed. In recent decades, ML has proven to be a powerful tool for deriving insights from data [33,34]. It has been applied successfully in self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome thanks to many practical algorithms developed.…”

Section: Machine Learning Modelsmentioning

confidence: 99%

Recognition of Geothermal Surface Manifestations: A Comparison of Machine Learning and Deep Learning

Xiong

Zhu

et al. 2022

Preprint

View full text Add to dashboard Cite

Geothermal surface manifestations (GSMs) are direct clues towards hydrothermal activities of a geothermal system in the subsurface and significant indications for geothermal resource exploration. It is essential to recognize various GSMs for potential geothermal energy exploration. However, there is a lack of work to fulfill this task using Deep Learning (DL), which has achieved unprecedented successes in computer vision and image interpretation. This study aims to explore the feasibility of using a DL model to fulfill the recognition of GSMs with photographs. A new image dataset was created for the GSM recognition by preprocessing and visual interpretation with expert knowledge and a high-quality check after downloading images from the Internet. The dataset consists of seven GSM types, i.e., warm spring, hot spring, geyser, fumarole, mud pot, hydrothermal alteration, crater lake, and one type of none GSM, including 500 images of different photographs for each type. The recognition results of the GoogLeNet model were compared with those of three Machine Learning (ML) algorithms, i.e., Support Vector Machine (SVM), Decision Tree (DT), and K-Nearest Neighbor (KNN), by using the assessment metrics of Overall Accuracy (OA), Overall F1 score (OF) and Computational Time (CT) for training and testing the models via cross-validation. The results show that the retrained GoogLeNet model using transfer learning has significant advantages of accuracies and performances over the three ML classifiers with the highest OA and the biggest OF for both validation and test, and the fastest CT for both validation and test. On the contrary, the three selected ML classifiers perform poorly for this task due to their low OA, small OF, and long CT. It suggests that transfer learning with a pretrained network be a feasible method to fulfill the recognition of the GSMs. Hopefully, this study provides a reference paradigm to help promote further research on the application of state-of-the-art DL in the geothermics domain.

show abstract

Machine Learning for Sustainable Energy Systems

Cited by 53 publications

References 127 publications

Energy and thermal modelling of an office building to develop an artificial neural networks model

Energy and thermal modelling of an office building to develop an artificial neural networks model

Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data

Recognition of Geothermal Surface Manifestations: A Comparison of Machine Learning and Deep Learning

Contact Info

Product

Resources

About