Search

Compound flood (CF) modeling enables the simulation of nonlinear water level dynamics in which concurrent or successive flood drivers synergize, producing larger impacts than those from individual drivers. However, CF modeling is subject to four main sources of uncertainty: (i) the initial condition, (ii) the forcing (or boundary) conditions, (iii) the model parameters, and (iv) the model structure. These sources of uncertainty, if not quantified and effectively reduced, cascade in series throughout the modeling chain and compromise the accuracy of CF hazard assessments. Here, we characterize cascading uncertainty using linked process-based and machine learning (PB–ML) models for a well-known CF event, namely, Hurricane Harvey in Galveston Bay, TX. For this, we run a set of hydrodynamic model scenarios to quantify isolated and cascading uncertainty in terms of maximum water level residuals; additionally, we track the evolution of residuals during the onset, peak, and dissipation of Hurricane Harvey. We then develop multiple linear regression (MLR) and PB–ML models to estimate the relative and cumulative contribution of the four sources of uncertainty to total uncertainty over time. Results from this study show that the proposed PB–ML model captures "hidden" nonlinear associations and interactions among the sources of uncertainty, thereby outperforming conventional MLR models. The model structure and forcing conditions are the main sources of uncertainty in CF modeling, and their corresponding model scenarios, or input features, contribute to 56 % of variance reduction in the estimation of maximum water level residuals. Following these results, we conclude that PB–ML models are a feasible alternative for quantifying cascading uncertainty in CF modeling. [ABSTRACT FROM AUTHOR]

Sea level rise (SLR) affects coastal flood regimes and poses serious challenges to flood risk management, particularly on ungauged coasts. To address the challenge of monitoring SLR at local scales, we propose a high tide flood (HTF) thresholding system that leverages machine learning (ML) techniques to estimate SLR and HTF thresholds at a relatively fine spatial resolution (10 km) along the United States' coastlines. The proposed system, complementing conventional linear- and point-based estimations of HTF thresholds and SLR rates, can estimate these values at ungauged stretches of the coast. Trained and validated against National Oceanic and Atmospheric Administration (NOAA) gauge data, our system demonstrates promising skills with an average Kling-Gupta Efficiency (KGE) of 0.77. The results can raise community awareness about SLR impacts by documenting the chronic signal of HTF and providing useful information for adaptation planning. The findings encourage further application of ML in achieving spatially distributed thresholds. Using machine learning algorithms, this study estimates sea level rise and high tide flooding thresholds every 10 km along the United States' coasts, complementing conventional linear-/point-based estimates and offering insights for ungauged areas. [ABSTRACT FROM AUTHOR]

Copyright of Cuadernos.info is the property of Pontificia Universidad Catolica de Chile, Facultad de Comunicaciones and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As reported by several authors, for some samples from a Johnson unbounded (SU) distribution, the log-likelihood function does not have a local maximum with respect to the shift and scale parameters or may not satisfy the required regularity conditions to achieve the asymptotic efficiency of the maximum likelihood (ML) method for parameter estimation. This non-regularity of the likelihood function caused occasional non-convergence of algorithms to apply the ML method to estimate the parameters of a Johnson SU distribution. This is why there has been several alternative proposals to estimate these parameters, including the four-quantile matching rule of Slifker and Shapiro, a method based on moments proposed by Tuenter, and a method based on ML and regression proposed by George and Ramachandran. However, all the above-mentioned methods need some conditions on the sample to fit the Johnson SU distribution. In this article, we report the C++ implementation to fit a Johnson SU distribution, and the empirical comparison of the methods of ML, Slifker-Shapiro, Tuenter and George and Ramachandran, plus an implementation based on the minimization of the Cramér-von Mises distance. We present experimental results that show that the implementation based on minimum Cramér-von Mises distance performs very well, with apparently no requirements to produce reasonable estimates, achieving lower bias than the ML method for small sample sizes. [ABSTRACT FROM AUTHOR]

The hip fracture is one of the most common diseases for elder people and also, one of the most worrying one since it usually is the starting point of further complications for both, the health of the patient and their daily life. Additionally, reports shown that there exist differences between people living in different regions, thus limiting the use of global models. In this work we propose a hip fracture prediction tool for a local region, using clinical data of the population of that region. The data is processed with a dimensionality reduction tool in combination with and hyper-parametrization process and the corresponding hyper-parameter optimization process for obtaining good predictions in the diagnoses, as the results shown. [ABSTRACT FROM AUTHOR]

In Deep Learning, training a model properly with a high quantity and quality of data is crucial in order to achieve a good performance. In some tasks, however, the necessary data is not available at a particular moment and only becomes available over time. In which case, incremental learning is used to train the model correctly. An open problem remains, however, in the form of the stability–plasticity dilemma: how to incrementally train a model that is able to respond well to new data (plasticity) while also retaining previous knowledge (stability). In this paper, an incremental learning model inspired in Rehearsal (recall of past memories based on a subset of data) named CRIF is proposed, and two instances for the framework are employed — one using a random-based selection of representative samples (Naive Incremental Learning, NIL), the other using Crowding Distance and Best vs. Second Best metrics in conjunction for this task (RILBC). The experiments were performed on five datasets — MNIST, Fashion-MNIST, CIFAR-10, Caltech 101, and Tiny ImageNet, in two different incremental scenarios: a strictly class-incremental scenario, and a pseudo class-incremental scenario with unbalanced data. In Caltech 101, Transfer Learning was used, and in this scenario as well as in the other three datasets, the proposed method, NIL, achieved better results in most of the quality metrics than comparison algorithms such as RMSProp Inc (base line) and iCaRL (state-of-the-art proposal) and outperformed the other proposed method, RILBC. NIL also requires less time to achieve these results. • An incremental learning model inspired in Rehearsal (recall of past memories based on a subset of data) is proposed. • Experiments were performed over MNIST, Fashion-MNIST, CIFAR-10 and Caltech 101 in two different scenarios. • Several metrics were used to compare learning quality results when each new megabatch of data is used. • Friedman's non-parametric statistical test and Holm post-hoc test were used for supporting the analysis of the results. • Random-based selection of representative samples obtains the best results. [ABSTRACT FROM AUTHOR]

Complex industrial problems coupled with the availability of a more robust computing infrastructure present many challenges and opportunities for machine learning (ML) in the construction industry. This paper reviews the ML techniques applied to the construction industry, mainly to identify areas of application and future projection in this industry. Studies from 2015 to 2022 were analyzed to assess the latest applications of ML techniques in construction. A methodology was proposed that automatically identifies topics through the analysis of abstracts using the Bidirectional Encoder Representations from Transformers technique to select main topics manually subsequently. Relevant categories of machine learning applications in construction were identified and analyzed, including applications in concrete technology, retaining wall design, pavement engineering, tunneling, and construction management. Multiple techniques were discussed, including various supervised, deep, and evolutionary ML algorithms. This review study provides future guidelines to researchers regarding ML applications in construction. • State-of-the-art developed using natural language processing techniques. • Topics analyzed and validated by experts for consistency and relevance. • Topics deepened through application of bigram analysis and clustering in addition to traditional bibliographic analysis. • Identified five large areas, and detailed two to three groups of relevant lines of research. [ABSTRACT FROM AUTHOR]