Parametric Probabilistic Models for Fluid Diffusivity Inversion and Forward Microseismic Generation Using Seismicity Rates

Voice based computing applications, such as phone communication and speech recognition, use microphone arrays to capture voice from a human speaker. In many environments of interest, however, sounds from other sources interfere with the speaker's voice, posing severe problems for subsequent processing. This paper describes a new framework for treating this problem, and presents and demonstrates a new algorithm for the cancellation of interfering sounds. Our framework combines techniques from statistical machine learning with ideas from speech and audio processing. An important feature involves training rich probabilistic models on data from different types of relevant sound sources. Those source models are then incorporated into a larger probabilistic model of the observed microphone data. Using that model we derive our algorithm, which is of the expectation-maximization type and infers from data the clean sound of separate individual sources. We report very good results on data recorded in different environments

Probabilistic prediction model of steel to concrete bond failure under high temperature by machine learning

Probabilistic Prediction Model for the Chloride Diffusion Coefficient of Concrete under Tensile and Compressive Stresses

This paper develops probabilistic predictive models for the unconfined compressive strength of intact rock based on the point load strength tests. A database of point load strength and unconfined compressive strength measurements for sedimentary, igneous and metamorphic rocks is first developed. The measurements are corrected to their standard equivalent values, namely unconfined compressive strength and point load strength for specimens with 50 mm diameter. A Bayesian framework is used to assess different candidate model forms and to estimate the corresponding model parameters. This Bayesian approach uses the prior information for the values of the unconfined compressive strength and point load strength measurements to develop an unbiased method for prediction of unconfined compressive strength based on point load strength tests. The Bayesian estimation of the model parameters accounts for the relevant sources of uncertainty including aleatory and epistemic uncertainties and for possible measurement errors in the point load strength test data. Probabilistic models are developed for sedimentary, igneous and metamorphic rocks. It is found that (i) a model of form provides the best fit to the laboratory data, and (ii) accounting for measurement errors and separating the database into subgroups based on different rock types decrease the model uncertainty.

Petroleum producers are currently engaged in significant expenditure towards exploration and development in unconventional oil and gas plays in Western Canada. Finding & Development costs are different in various plays and strategies. But where the producer should focus their resources to achieve most cost efficient production? The paper describes methodology of analysis of Finding & Development cost. A probabilistic model was developed to quantitatively assess exploration and development expenditure, production, and reserves for various producers for different oil and gas plays. The model employs a number of key performance indicators (KPIs) such as Finding & Development costs with and without acquisitions, reserves life, reinvestment, and others. The methodology was applied to a comprehensive study of Finding & Development expenditure in Western Canada focused mostly on unconventional oil and gas. The study included more than 80 oil and gas companies. Each company may be involved in exploration and development of many plays. The expenditure, production, and reserves were analyzed for the last 12 years. The companies were subdivided into three groups based on their production. Each company’s Finding & Development costs and other KPIs were calculated for Western Canada as a whole and for a particular strategy or play where the company was operating, as well as for CBM, tight, and shale gas. The study found significant variance in finding and development cost in Western Canada. All companies and all strategies are ranked based on their Finding & Development costs and other KPIs. The results of the study can be applied to the comparative analysis of efficiency of the exploration and development expenditure, which in turn can help improve portfolio management and decision making processes.

Aiming to improve the predictive ability of Walker model for fatigue life prediction and taking the turbine disc alloy GH4133 as the application example, this paper investigates a new approach for probabilistic fatigue life prediction when considering parameter uncertainty inherent in the life prediction model. Firstly, experimental data are used to update the model parameters using Bayes’ theorem, so as to obtain the posterior probability distribution functions of two parameters of the Walker model, as well to achieve the probabilistic life prediction model for turbine disc. During the updating process, Markov Chain Monte Carlo (MCMC) technique is used to generate samples of the given distribution and estimating the parameters distinctly. After that, the turbine disc life is predicted using the probabilistic Walker model based on Monte Carlo simulation technique. The experimental results indicate that: (1) after using the small sample test data obtained from turbine disc, parameter uncertainty of the Walker model can be quantified and the corresponding probabilistic model for fatigue life prediction can be established using Bayes’ theorem; (2) there exists obvious dispersion of life data for turbine disc when predicting fatigue life in practical engineering application.

A probabilistic predictive model for assessing the economic reusability of load-bearing building components: Developing a Circular Economy framework

Two problems concerning anticipation effort as an important cognitive resource for improved avionics safety are addressed: (1) assessment of the probability that the random actual (‘subjective’) anticipation time is below the (also random) available (‘objective’) time and (2) evaluation of the likelihood of success of the random short-term anticipation from the predetermined (non-random) long-term anticipation. Unlike the traditional statistical approach, when experimentations are done first and are followed by statistical analyses, our novel concept suggests that probabilistic predictive modelling is done first and is followed by experimentation. The concept proceeds from the fundamental understanding that nobody and nothing is perfect and that the difference between a success and a failure in a particular effort, a situation, or a mission is, in effect, ‘merely’ the difference in the level of the never-zero probability of failure.

A segmental probabilistic model of speech using an orthogonal polynomial representation: Application to text-independent speaker verification

The reactive evaluation approach and the predictive approach for modeling and analyzing breaks in deteriorating water distribution systems have been tried. Descriptive statistical studies have been used to analyse pipe failure. Predictive models are classified into three basic categories: aggregate type models, regression type models, and probabilistic predictive models. The Proportional Hazards Model is a probabilistic predictive model, and is applied to predict failure probabilities in deteriorating water pipes. This methodology possesses high flexibility for adapting to particular system characteristics. Economic studies have been performed to determine an optimum replacement time for breaking mains. Once the total cost (direct and social) is known, the next questions to be answered are which pipes should be replaced and when they should be replaced.

Water supply pipes age, deteriorate and break, which puts at risk the continuous provision of safe potable water endangering the public health in cities. Risk management methods are increasingly applied to optimise the capital investment for pipe replacement and rehabilitation, taking into account the probability and hydraulic impact of pipe breaks. As part of this process, however, historic pipe break data and statistical methods should be utilised to gather causal insights for past breaks to inform operational changes and/or capital investment decisions in order to reduce future breaks. This paper presents a comparative study of statistical and machine learning methods to carry out an exploratory causal analysis for historic pipe breaks in an operational water supply network. Regression models for count data and probabilistic models have been developed. The performance of these models was assessed and enhanced with the introduction of interactions and the inclusion of different network representations.

Precise probabilistic forecasts are fundamental for energy risk management, and there is a wide range of both statistical and machine learning models for this purpose. Inherent to these probabilistic models is some form of uncertainty quantification. However, most models do not capture the full extent of uncertainty, which arises not only from the data itself but also from model and distributional choices. In this study, we examine uncertainty quantification in state-of-the-art statistical and deep learning probabilistic forecasting models for electricity price forecasting in the German market. In particular, we consider distributional deep neural networks (DDNNs) and augment them with an ensemble approach, Monte Carlo (MC) dropout, LASSO-estimated autoregressive (LEAR), and conformal prediction to account for model uncertainty. Additionally, we consider the eXtreme Gradient Boosting (XGBoost) approach combined with quantile regression averaging (QRA), generalized autoregressive conditional heteroskedasticity (GARCH), and conformal prediction. Across a range of performance metrics, we find that the XGBoost-based models perform well in terms of probabilistic forecasting, irrespective of the uncertainty quantification method. Furthermore, we find that DDNNs benefit from incorporating both data and model uncertainty, improving both point and probabilistic forecasting. Uncertainty itself appears to be best captured by the models using conformal prediction. Overall, our extensive study shows that all models under consideration perform competitively. However, their relative performance depends on the choice of metrics for point and probabilistic forecasting.

In view of preserving the historical heritage, the deterioration processes of masonry materials and the long term damage of multiple leaf historic buildings is studied from an experimental and a numerical point of view. Durability tests and pseudo-creep tests have been carried out and interpreted through probabilistic models for the service life prediction. The precocious recognition of structural critical states will allow to design repair and strengthening interventions and to prevent total or partial failure of the constructions.

Identification of ionic liquids with low toxicity is paramount for applications in various domains. Traditional approaches used for determining the toxicity of ionic liquids are often expensive, and can be labor intensive and time consuming. In order to mitigate these limitations, researchers have resorted to using computational models. This work presents a probabilistic model built from deep kernel learning with the aim of predicting the toxicity of ionic liquids in the leukemia rat cell line (IPC-81). Only open source tools, namely, RDKit and Mol2vec, are required to generate predictors for this model; as such, its predictions are solely based on chemical structure of the ionic liquids and no manual extraction of features is needed. The model recorded an RMSE of 0.228 and of 0.943. These results indicate that the model is both reliable and accurate. Furthermore, this model provides an accompanying uncertainty level for every prediction it makes. This is important because discrepancies in experimental measurements that generated the dataset used herein are inevitable, and ought to be modeled. A user-friendly web server was developed as well, enabling researchers and practitioners ti make predictions using this model.

Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes are hybrid closed-loop systems, which require the user to announce every meal and its size. However, estimating the amount of carbohydrates in a meal and announcing each and every meal is an error-prone process that introduces important uncertainties to the problem, which when not considered, lead to sub-optimal outcomes of the controller. To address this problem, we propose a novel deep-learning-based model for probabilistic glucose prediction, called the Input and State Recurrent Kalman Network (ISRKN), which consists in the incorporation of an input and state Kalman filter in the latent space of a deep neural network so that the posterior distributions can be computed in closed form and the uncertainty can be propagated using the Kalman equations. In addition, the proposed architecture allows explicit estimation of the meal uncertainty distribution, whose parameters are encoded in the filter parameters. Results using the UVA/Padova simulator and data from a clinical trial show that the proposed model outperforms other probabilistic models using several probabilistic metrics across different degrees of distributional shifts.