In this paper, we propose artificial-neural-network-based (ANN-based) nonlinear algebraic models for the large-eddy simulation (LES) of compressible wall-bounded turbulence. An innovative modification is applied to the invariants and the tensor bases of the nonlinear algebraic models through using the local grid widths along each direction to normalise the corresponding gradients of the flow variables. Furthermore, the dimensionless model coefficients are determined by the ANN method. The modified ANN-based nonlinear algebraic model (MANA model) has much higher correlation coefficients and much lower relative errors than the dynamic Smagorinsky model (DSM), Vreman model and wall-adapting local eddy-viscosity model in the a priori test. The significantly more accurate estimations of the mean subgrid-scale (SGS) fluxes of the kinetic energy and temperature variance are also obtained by the MANA models in the a priori test. Furthermore, in the a posteriori test, the MANA model can give much more accurate predictions of the flow statistics and the mean SGS fluxes of the kinetic energy and the temperature variance than other traditional eddy-viscosity models in compressible turbulent channel flows with untrained Reynolds numbers, Mach numbers and grid resolutions. The MANA model has a better performance in predicting the flow statistics in supersonic turbulent boundary layer. The MANA model can well predict both direct and inverse transfer of the kinetic energy and temperature variance, which overcomes the inherent shortcoming that the traditional eddy-viscosity models cannot predict the inverse energy transfer. Moreover, the MANA model is computationally more efficient than the DSM.

A model based on a convolutional neural network (CNN) is designed to reconstruct the three-dimensional turbulent flows beneath a free surface using surface measurements, including the surface elevation and surface velocity. Trained on datasets obtained from the direct numerical simulation of turbulent open-channel flows with a deformable free surface, the proposed model can accurately reconstruct the near-surface flow field and capture the characteristic large-scale flow structures away from the surface. The reconstruction performance of the model, measured by metrics such as the normalised mean squared reconstruction errors and scale-specific errors, is considerably better than that of the traditional linear stochastic estimation (LSE) method. We further analyse the saliency maps of the CNN model and the kernels of the LSE model and obtain insights into how the two models utilise surface features to reconstruct subsurface flows. The importance of different surface variables is analysed based on the saliency map of the CNN, which reveals knowledge about the surface–subsurface relations. The CNN is also shown to have a good generalisation capability with respect to the Froude number if a model trained for a flow with a high Froude number is applied to predict flows with lower Froude numbers. The results presented in this work indicate that the CNN is effective regarding the detection of subsurface flow structures and by interpreting the surface–subsurface relations underlying the reconstruction model, the CNN can be a promising tool for assisting with the physical understanding of free-surface turbulence.

Large-scale microdata on group identity are critical for studies on identity politics and violence but remain largely unavailable for developing countries. We use personal names to infer religion in South Asia—where religion is a salient social division, and yet, disaggregated data on it are scarce. Existing work predicts religion using a dictionary-based method and, therefore, cannot classify unseen names. We provide character-based machine-learning models that can classify unseen names too with high accuracy. Our models are also much faster and, hence, scalable to large datasets. We explain the classification decisions of one of our models using the layer-wise relevance propagation technique. The character patterns learned by the classifier are rooted in the linguistic origins of names. We apply these to infer the religion of electoral candidates using historical data on Indian elections and observe a trend of declining Muslim representation. Our approach can be used to detect identity groups across the world for whom the underlying names might have different linguistic roots.

Research of judges and courts traditionally centers on judgments, treating each judgment as a unit of observation. However, judgments often address multiple distinct and more or less unrelated issues. Studying judicial behavior on a judgment level therefore loses potentially important details and risks drawing false conclusions from the data. We present a method to assist researchers with splitting judgments by issues using a supervised machine learning classifier. Applying our approach to splitting judgments by the Court of Justice of the European Union into issues, we show that this approach is practically feasible and provides benefits for text-based analysis of judicial behavior.

Alternating direction method of multipliers (ADMM) receives much attention in the field of optimization and computer science, etc. The generalized ADMM (G-ADMM) proposed by Eckstein and Bertsekas incorporates an acceleration factor and is more efficient than the original ADMM. However, G-ADMM is not applicable in some models where the objective function value (or its gradient) is computationally costly or even impossible to compute. In this paper, we consider the two-block separable convex optimization problem with linear constraints, where only noisy estimations of the gradient of the objective function are accessible. Under this setting, we propose a stochastic linearized generalized ADMM (called SLG-ADMM) where two subproblems are approximated by some linearization strategies. And in theory, we analyze the expected convergence rates and large deviation properties of SLG-ADMM. In particular, we show that the worst-case expected convergence rates of SLG-ADMM are $\mathcal{O}\left( {{N}^{-1/2}}\right)$ and $\mathcal{O}\left({\ln N} \cdot {N}^{-1}\right)$ for solving general convex and strongly convex problems, respectively, where N is the iteration number, similarly hereinafter, and with high probability, SLG-ADMM has $\mathcal{O}\left ( \ln N \cdot N^{-1/2} \right ) $ and $\mathcal{O}\left ( \left ( \ln N \right )^{2} \cdot N^{-1} \right ) $ constraint violation bounds and objective error bounds for general convex and strongly convex problems, respectively.

This work deals with the investigation and modelling of wall pressure fluctuations induced by a supersonic jet over a tangential flat plate. The analysis is performed at several nozzle pressure ratios around the nozzle design Mach number, including slightly over-expanded and under-expanded conditions, and for different radial positions of the rigid plate. Pitot measurements and flow visualizations through the background oriented schlieren technique provided a general overview of the aerodynamic interactions between the jet flow and the plate at the different regimes and configurations. Wall pressure fluctuations were measured using a couple of piezoelectric pressure transducers flush mounted over the plate surface. The spectral analysis has been carried out to clarify the effect of the plate position on the single and multivariate wall pressure statistics, including the screech tone amplitude. The experimental dataset is used to assess and validate a surrogate model based on artificial neural networks. Sound pressure levels and coherence functions are modelled by means of a single fully connected network, built on the basis of a recently implemented fully deterministic topology optimization algorithm. The metamodel uncertainty is also quantified using the spatial correlation function. It is shown that the flow behaviour as well as the screech and broadband noise signatures are significantly influenced by the presence of the plate, and the effects on spectral quantities are correctly reproduced by the proposed data-driven model that provides predictions in agreement with the available data.

We propose and explore the possibility that language models can be studied as effective proxies for specific human subpopulations in social science research. Practical and research applications of artificial intelligence tools have sometimes been limited by problematic biases (such as racism or sexism), which are often treated as uniform properties of the models. We show that the “algorithmic bias” within one such tool—the GPT-3 language model—is instead both fine-grained and demographically correlated, meaning that proper conditioning will cause it to accurately emulate response distributions from a wide variety of human subgroups. We term this property algorithmic fidelity and explore its extent in GPT-3. We create “silicon samples” by conditioning the model on thousands of sociodemographic backstories from real human participants in multiple large surveys conducted in the United States. We then compare the silicon and human samples to demonstrate that the information contained in GPT-3 goes far beyond surface similarity. It is nuanced, multifaceted, and reflects the complex interplay between ideas, attitudes, and sociocultural context that characterize human attitudes. We suggest that language models with sufficient algorithmic fidelity thus constitute a novel and powerful tool to advance understanding of humans and society across a variety of disciplines.

Explainability is highly desired in machine learning (ML) systems supporting high-stakes policy decisions in areas such as health, criminal justice, education, and employment. While the field of explainable ML has expanded in recent years, much of this work has not taken real-world needs into account. A majority of proposed methods are designed with generic explainability goals without well-defined use cases or intended end users and evaluated on simplified tasks, benchmark problems/datasets, or with proxy users (e.g., Amazon Mechanical Turk). We argue that these simplified evaluation settings do not capture the nuances and complexities of real-world applications. As a result, the applicability and effectiveness of this large body of theoretical and methodological work in real-world applications are unclear. In this work, we take steps toward addressing this gap for the domain of public policy. First, we identify the primary use cases of explainable ML within public policy problems. For each use case, we define the end users of explanations and the specific goals the explanations have to fulfill. Finally, we map existing work in explainable ML to these use cases, identify gaps in established capabilities, and propose research directions to fill those gaps to have a practical societal impact through ML. The contribution is (a) a methodology for explainable ML researchers to identify use cases and develop methods targeted at them and (b) using that methodology for the domain of public policy and giving an example for the researchers on developing explainable ML methods that result in real-world impact.

Automatically extracting knowledge from small datasets with a valid causal ordering is a challenge for current state-of-the-art methods in machine learning. Extracting other type of knowledge is important but challenging for multiple engineering fields where data are scarce and difficult to collect. This research aims to address this problem by presenting a machine learning-based modeling framework leveraging the knowledge available in fundamental units of the variables recorded from data samples, to develop parsimonious, explainable, and graph-based simulation models during the early design stages. The developed approach is exemplified using an engineering design case study of a spherical body moving in a fluid. For the system of interest, two types of intricated models are generated by (1) using an automated selection of variables from datasets and (2) combining the automated extraction with supplementary knowledge about functions and dimensional homogeneity associated with the variables of the system. The effect of design, data, model, and simulation specifications on model fidelity are investigated. The study discusses the interrelationships between fidelity levels, variables, functions, and the available knowledge. The research contributes to the development of a fidelity measurement theory by presenting the premises of a standardized, modeling approach for transforming data into measurable level of fidelities for the produced models. This research shows that structured model building with a focus on model fidelity can support early design reasoning and decision making using for example the dimensional analysis conceptual modeling (DACM) framework.

Archaeologists tend to produce slow data that is contextually rich but often difficult to generalize. An example is the analysis of lithic microdebitage, or knapping debris, that is smaller than 6.3 mm (0.25 in.). So far, scholars have relied on manual approaches that are prone to intra- and interobserver errors. In the following, we present a machine learning–based alternative together with experimental archaeology and dynamic image analysis. We use a dynamic image particle analyzer to measure each particle in experimentally produced lithic microdebitage (N = 5,299) as well as an archaeological soil sample (N = 73,313). We have developed four machine learning models based on Naïve Bayes, glmnet (generalized linear regression), random forest, and XGBoost (“Extreme Gradient Boost[ing]”) algorithms. Hyperparameter tuning optimized each model. A random forest model performed best with a sensitivity of 83.5%. It misclassified only 28 or 0.9% of lithic microdebitage. XGBoost models reached a sensitivity of 67.3%, whereas Naïve Bayes and glmnet models stayed below 50%. Except for glmnet models, transparency proved to be the most critical variable to distinguish microdebitage. Our approach objectifies and standardizes microdebitage analysis. Machine learning allows studying much larger sample sizes. Algorithms differ, though, and a random forest model offers the best performance so far.

This study proposes a newly developed deep-learning-based method to generate turbulent inflow conditions for spatially developing turbulent boundary layer (TBL) simulations. A combination of a transformer and a multiscale-enhanced super-resolution generative adversarial network is utilised to predict velocity fields of a spatially developing TBL at various planes normal to the streamwise direction. Datasets of direct numerical simulation (DNS) of flat plate flow spanning a momentum thickness-based Reynolds number, $Re_\theta = 661.5\unicode{x2013}1502.0$, are used to train and test the model. The model shows a remarkable ability to predict the instantaneous velocity fields with detailed fluctuations and reproduce the turbulence statistics as well as spatial and temporal spectra with commendable accuracy as compared with the DNS results. The proposed model also exhibits a reasonable accuracy for predicting velocity fields at Reynolds numbers that are not used in the training process. With the aid of transfer learning, the computational cost of the proposed model is considered to be effectively low. Furthermore, applying the generated turbulent inflow conditions to an inflow–outflow simulation reveals a negligible development distance for the TBL to reach the target statistics. The results demonstrate for the first time that transformer-based models can be efficient in predicting the dynamics of turbulent flows. They also show that combining these models with generative adversarial networks-based models can be useful in tackling various turbulence-related problems, including the development of efficient synthetic-turbulent inflow generators.