An official website of the United States government
High-flow events that significantly impact Water Resource Recovery Facility (WRRF) operations are rare, but accurately predicting these flows could improve treatment operations. Data-driven modeling approaches could be used; however, high flow events that impact operation are an infrequent occurrence, providing limited data from which to learn meaningful patterns. The performance of a statistical model (logistic regression) and two machine learning (ML) models (support vector machine and random forest) were evaluated to predict high flow events one-day-ahead to two plants located in different parts of the United States, Northern Virginia and the Gulf Coast of Texas, with combined and separate sewers, respectively. We compared baseline models (no synthetic data added) to models trained with synthetic data added from two different sampling techniques (SMOTE and ADASYN) that increased the representation of rare events in the training data. Both techniques enhanced the sample size of the very high-flow class, but ADASYN, which focused on generating synthetic samples near decision boundaries, led to greater improvements in model performance (reduced misclassification rates). Random forest combined with ADASYN achieved the best overall performance for both plants, demonstrating its robustness in identifying one-day-ahead extreme flow events to treatment plants. These results suggest that combining sampling techniques with ML has the potential to significantly improve the modeling of high-flow events at treatment plants. Our work will prove useful in building reliable predictive models that can inform management decisions needed for the better control of treatment operations.
more »
« less
Predicting glass structure by physics-informed machine learning
Abstract Machine learning (ML) is emerging as a powerful tool to predict the properties of materials, including glasses. Informing ML models with knowledge of how glass composition affects short-range atomic structure has the potential to enhance the ability of composition-property models to extrapolate accurately outside of their training sets. Here, we introduce an approach wherein statistical mechanics informs a ML model that can predict the non-linear composition-structure relations in oxide glasses. This combined model offers an improved prediction compared to models relying solely on statistical physics or machine learning individually. Specifically, we show that the combined model accurately both interpolates and extrapolates the structure of Na2O–SiO2glasses. Importantly, the model is able to extrapolate predictions outside its training set, which is evidenced by the fact that it is able to predict the structure of a glass series that was kept fully hidden from the model during its training.
more »
« less
- PAR ID:
- 10370667
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- npj Computational Materials
- Volume:
- 8
- Issue:
- 1
- ISSN:
- 2057-3960
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We propose a machine learning (ML) non-Markovian closure modelling framework for accurate predictions of statistical responses of turbulent dynamical systems subjected to external forcings. One of the difficulties in this statistical closure problem is the lack of training data, which is a configuration that is not desirable in supervised learning with neural network models. In this study with the 40-dimensional Lorenz-96 model, the shortage of data is due to the stationarity of the statistics beyond the decorrelation time. Thus, the only informative content in the training data is from the short-time transient statistics. We adopt a unified closure framework on various truncation regimes, including and excluding the detailed dynamical equations for the variances. The closure framework employs a Long-Short-Term-Memory architecture to represent the higher-order unresolved statistical feedbacks with a choice of ansatz that accounts for the intrinsic instability yet produces stable long-time predictions. We found that this unified agnostic ML approach performs well under various truncation scenarios. Numerically, it is shown that the ML closure model can accurately predict the long-time statistical responses subjected to various time-dependent external forces that have larger maximum forcing amplitudes and are not in the training dataset. This article is part of the theme issue ‘Data-driven prediction in dynamical systems’.more » « less
-
null (Ed.)Glasses have been an integral part of human life for more than 2000 years. Despite several years of research and analysis, some fundamental and practical questions on glasses still remain unanswered. While most of the earlier approaches were based on (i) expert knowledge and intuition, (ii) Edisonian trial and error, or (iii) physics-driven modeling and analysis, recent studies suggest that data-driven techniques, such as artificial intelligence (AI) and machine learning (ML), can provide fresh perspectives to tackle some of these questions. In this article, we identify 21 grand challenges in glass science, the solutions of which are either enabling AI and ML or enabled by AI and ML to accelerate the field of glass science. The challenges presented here range from fundamental questions related to glass formation and composition–processing–property relationships to industrial problems such as automated flaw detection in glass manufacturing. We believe that the present article will instill enthusiasm among the readers to explore some of the grand challenges outlined here and to discover many more challenges that can advance the field of glass science, engineering, and technology.more » « less
-
Projecting climate change is a generalization problem: We extrapolate the recent past using physical models across past, present, and future climates. Current climate models require representations of processes that occur at scales smaller than model grid size, which have been the main source of model projection uncertainty. Recent machine learning (ML) algorithms hold promise to improve such process representations but tend to extrapolate poorly to climate regimes that they were not trained on. To get the best of the physical and statistical worlds, we propose a framework, termed “climate-invariant” ML, incorporating knowledge of climate processes into ML algorithms, and show that it can maintain high offline accuracy across a wide range of climate conditions and configurations in three distinct atmospheric models. Our results suggest that explicitly incorporating physical knowledge into data-driven models of Earth system processes can improve their consistency, data efficiency, and generalizability across climate regimes.more » « less
-
Abstract The preparation of 0.58 Li2S + 0.315 SiS2+ 0.105 LiPO3glass, and the impacts of polysulfide and P1Pdefect structure impurities on the glass transition temperature (Tg), crystallization temperature (Tc), working range (ΔT≡ Tc‐ Tg), fragility index, and the Raman spectra were evaluated using statistical analysis. In this study, 33 samples of this glass composition were synthesized through melt‐quenching. Thermal analysis was conducted to determine the glass transition temperature, crystallization temperature, working range, and fragility index through differential scanning calorimetry. The quantity of the impurities described above was determined through Raman spectroscopy peak analysis. Elemental sulfur was doped into a glass to quantify the wt% sulfur content in the glasses. Linear regression analysis was conducted to determine the impact of polysulfide impurities and P1Pdefect impurities on the thermal properties. Polysulfide impurities were found to decrease theTgat rate of nearly 12°C per 1 wt% increase in sulfur concentration. The sulfur concentration does not have a statistically significant impact on the other properties (α = 0.05). The P1Pdefect structure appears to decrease the resistance to crystallization of the glass by measurably decreasing the working range of the glasses, but further study is necessary to fully quantify and determine this.more » « less
