Predicting hurricane evacuation decisions: When, how many, and how far

Traffic from major hurricane evacuations is known to cause severe gridlocks on evacuation routes. Better prediction of the expected amount of evacuation traffic is needed to improve the decision-making process for the required evacuation routes and possible deployment of special traffic operations, such as contraflow. The objective of this dissertation is to develop prediction models to predict the number of daily trips and the evacuation distance during a hurricane evacuation. ^ Two data sets from the surveys of the evacuees from Hurricanes Katrina and Ivan were used in the models' development. The data sets included detailed information on the evacuees, including their evacuation days, evacuation distance, distance to the hurricane location, and their associated socioeconomic characteristics, including gender, age, race, household size, rental status, income, and education level. ^ Three prediction models were developed. The evacuation trip and rate models were developed using logistic regression. Together, they were used to predict the number of daily trips generated before hurricane landfall. These daily predictions allowed for more detailed planning over the traditional models, which predicted the total number of trips generated from an entire evacuation. A third model developed attempted to predict the evacuation distance using Geographically Weighted Regression (GWR), which was able to account for the spatial variations found among the different evacuation areas, in terms of impacts from the model predictors. All three models were developed using the survey data set from Hurricane Katrina and then evaluated using the survey data set from Hurricane Ivan. ^ All of the models developed provided logical results. The logistic models showed that larger households with people under age six were more likely to evacuate than smaller households. The GWR-based evacuation distance model showed that the household with children under age six, income, and proximity of household to hurricane path, all had an impact on the evacuation distances. While the models were found to provide logical results, it was recognized that they were calibrated and evaluated with relatively limited survey data. The models can be refined with additional data from future hurricane surveys, including additional variables, such as the time of day of the evacuation. ^

Development of methods for spatial modeling of sediments quality in Lake Okeechobee, Florida

The major objectives of this dissertation were to develop optimal spatial techniques to model the spatial-temporal changes of the lake sediments and their nutrients from 1988 to 2006, and evaluate the impacts of the hurricanes occurred during 1998–2006. Mud zone reduced about 10.5% from 1988 to 1998, and increased about 6.2% from 1998 to 2006. Mud areas, volumes and weight were calculated using validated Kriging models. From 1988 to 1998, mud thicknesses increased up to 26 cm in the central lake area. The mud area and volume decreased about 13.78% and 10.26%, respectively. From 1998 to 2006, mud depths declined by up to 41 cm in the central lake area, mud volume reduced about 27%. Mud weight increased up to 29.32% from 1988 to 1998, but reduced over 20% from 1998 to 2006. The reduction of mud sediments is likely due to re-suspension and redistribution by waves and currents produced by large storm events, particularly Hurricanes Frances and Jeanne in 2004 and Wilma in 2005. Regression, kriging, geographically weighted regression (GWR) and regression-kriging models have been calibrated and validated for the spatial analysis of the sediments TP and TN of the lake. GWR models provide the most accurate predictions for TP and TN based on model performance and error analysis. TP values declined from an average of 651 to 593 mg/kg from 1998 to 2006, especially in the lake’s western and southern regions. From 1988 to 1998, TP declined in the northern and southern areas, and increased in the central-western part of the lake. The TP weights increased about 37.99%–43.68% from 1988 to 1998 and decreased about 29.72%–34.42% from 1998 to 2006. From 1988 to 1998, TN decreased in most areas, especially in the northern and southern lake regions; western littoral zone had the biggest increase, up to 40,000 mg/kg. From 1998 to 2006, TN declined from an average of 9,363 to 8,926 mg/kg, especially in the central and southern regions. The biggest increases occurred in the northern lake and southern edge areas. TN weights increased about 15%–16.2% from 1988 to 1998, and decreased about 7%–11% from 1998 to 2006.

Abundance, biomass and secondary production of benthic megafauna on the Barents Sea shelf in 2008 and 2009

Megabenthos plays a major role in the overall energy flow on Arctic shelves, but information on megabenthic secondary production on large spatial scales is scarce. Here, we estimated for the first time megabenthic secondary production for the entire Barents Sea shelf by applying a species-based empirical model to an extensive dataset from the joint Norwegian? Russian ecosystem survey. Spatial patterns and relationships were analyzed within a GIS. The environmental drivers behind the observed production pattern were identified by applying an ordinary least squares regression model. Geographically weighted regression (GWR) was used to examine the varying relationship of secondary production and the environment on a shelfwide scale. Significantly higher megabenthic secondary production was found in the northeastern, seasonally ice-covered regions of the Barents Sea than in the permanently ice-free southwest. The environmental parameters that significantly relate to the observed pattern are bottom temperature and salinity, sea ice cover, new primary production, trawling pressure, and bottom current speed. The GWR proved to be a versatile tool for analyzing the regionally varying relationships of benthic secondary production and its environmental drivers (R² = 0.73). The observed pattern indicates tight pelagic? benthic coupling in the realm of the productive marginal ice zone. Ongoing decrease of winter sea ice extent and the associated poleward movement of the seasonal ice edge point towards a distinct decline of benthic secondary production in the northeastern Barents Sea in the future.

Method validation using weighted linear regression models for quantification of UV filters in water samples

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Lazy Lasso for local regression

Locally weighted regression is a technique that predicts the response for new data items from their neighbors in the training data set, where closer data items are assigned higher weights in the prediction. However, the original method may suffer from overfitting and fail to select the relevant variables. In this paper we propose combining a regularization approach with locally weighted regression to achieve sparse models. Specifically, the lasso is a shrinkage and selection method for linear regression. We present an algorithm that embeds lasso in an iterative procedure that alternatively computes weights and performs lasso-wise regression. The algorithm is tested on three synthetic scenarios and two real data sets. Results show that the proposed method outperforms linear and local models for several kinds of scenarios

Regressão Logística Geograficamente Ponderada aplicada a modelos de Credit Scoring

Dissertação (mestrado)—Universidade de Brasília, Faculdade de Economia, Administração e Contabilidade, Programa de Pós-Graduação em Administração, 2016.

Metodologia para a suavização de dados biomecanicos por função não parametrica ponderada local robusta

Universidade Estadual de Campinas. Faculdade de Educação Física

Determinants of salivary cotinine level: a population-based study in Brazil

OBJECTIVE: A cross-sectional population-based study was conducted to assess, in active smokers, the relationship of number of cigarettes smoked and other characteristics to salivary cotinine concentrations. METHODS: A random sample of active smokers aged 15 years or older was selected using a stepwise cluster sample strategy, in the year 2000 in Rio de Janeiro, Brazil. The study included 401 subjects. Salivary cotinine concentration was determined using gas chromatography with nitrogen-phosphorus detection. A standard questionnaire was used to collect demographic and smoking behavioral data. The relation between the number of cigarettes smoked in the last 24h and cotinine level was examined by means of a nonparametric fitting technique of robust locally weighted regression. RESULTS: Significantly (p<0.05) higher adjusted mean cotinine levels were found in subjects smoking their first cigarette within five minutes after waking up, and in those smoking 1-20 cigarettes in the last 24h who reported inhaling more than ½ the time. In those smoking 1-20 cigarettes, the slope was significantly higher for those subjects waiting for more than five minutes before smoking their first cigarette after waking up, and those smoking "light" cigarettes when compared with their counterparts. These heterogeneities became negligible and non-significant when subjects with cotinine >40 ng/mL per cigarette were excluded. CONCLUSIONS: There was found a positive association between self-reporting smoking five minutes after waking up, and inhaling more than ½ the time are consistent and higher cotinine levels. These can be markers of dependence and higher nicotine intake. Salivary cotinine proved to be a useful biomarker of recent smoking and can be used in epidemiological studies and smoking cessation programs.

Cardiovascular risk factor profiles and their social gradient from adolescence to age 74 in a Swiss region.

BACKGROUND: Few European studies have investigated how cardiovascular risk factors (CRF) in adults relate to those observed in younger generations. OBJECTIVE: To explore this issue in a Swiss region using two population health surveys of 3636 adolescents ages 9-19 years and 3299 adults ages 25-74 years. METHODS: Age patterns of continuous CRF were estimated by robust locally weighted regression and those of high-risk groups were calculated using adult criteria with appropriate adjustment for children. RESULTS: Gender differences in height, weight, blood pressure, and HDL cholesterol observed in adults were found to emerge in adolescents. Overweight, affecting 10-12% of adolescents, was increasing steeply in young adults (three times among males and twice among females) in parallel with inactivity. Median age at smoking initiation was decreasing rapidly from 18 to 20 years in young adults to 15 in adolescents. A statistically significant social gradient in disfavor of the lower education level was observed for overweight in all age groups of women above 16 (odds ratios (ORs) 2.4 to 3.3, P < 0.01), for inactivity in adult males (ORs 1.6 to 2.0, P < 0.05), and for regular smoking in older adolescents (OR 1.9 for males, 2.7 for females, P < 0.005), but not for elevated blood pressure. CONCLUSION: Discontinuities in the cross-sectional age patterns of CRF indicated the emergence of a social gradient and the need for preventive actions against the early adoption of persistent unhealthy behaviors, to which low-educated girls and women are particularly exposed.

Active Learning with Statistical Models

For many types of learners one can compute the statistically 'optimal' way to select data. We review how these techniques have been used with feedforward neural networks. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

Centennial-scale climate change in Ireland during the Holocene

We examine mid- to late Holocene centennial-scale climate variability in Ireland using proxy data from peatlands, lakes and a speleothem. A high degree of between-record variability is apparent in the proxy data and significant chronological uncertainties are present. However, tephra layers provide a robust tool for correlation and improve the chronological precision of the records. Although we can find no statistically significant coherence in the dataset as a whole, a selection of high-quality peatland water table reconstructions co-vary more than would be expected by chance alone. A locally weighted regression model with bootstrapping can be used to construct a ‘best-estimate’ palaeoclimatic reconstruction from these datasets. Visual comparison and cross-wavelet analysis of peatland water table compilations from Ireland and Northern Britain show that there are some periods of coherence between these records. Some terrestrial palaeoclimatic changes in Ireland appear to coincide with changes in the North Atlantic thermohaline circulation and solar activity. However, these relationships are inconsistent and may be obscured by chronological uncertainties. We conclude by suggesting an agenda for future Holocene climate research in Ireland.

Predicting spectral features in galaxy spectra from broad-band photometry

We explore the prospects of predicting emission-line features present in galaxy spectra given broad-band photometry alone. There is a general consent that colours, and spectral features, most notably the 4000 angstrom break, can predict many properties of galaxies, including star formation rates and hence they could infer some of the line properties. We argue that these techniques have great prospects in helping us understand line emission in extragalactic objects and might speed up future galaxy redshift surveys if they are to target emission-line objects only. We use two independent methods, Artificial Neural Networks (based on the ANNz code) and Locally Weighted Regression (LWR), to retrieve correlations present in the colour N-dimensional space and to predict the equivalent widths present in the corresponding spectra. We also investigate how well it is possible to separate galaxies with and without lines from broad-band photometry only. We find, unsurprisingly, that recombination lines can be well predicted by galaxy colours. However, among collisional lines some can and some cannot be predicted well from galaxy colours alone, without any further redshift information. We also use our techniques to estimate how much information contained in spectral diagnostic diagrams can be recovered from broad-band photometry alone. We find that it is possible to classify active galactic nuclei and star formation objects relatively well using colours only. We suggest that this technique could be used to considerably improve redshift surveys such as the upcoming Fibre Multi Object Spectrograph (FMOS) survey and the planned Wide Field Multi Object Spectrograph (WFMOS) survey.

Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

This study presents an approach to combine uncertainties of the hydrological model outputs predicted from a number of machine learning models. The machine learning based uncertainty prediction approach is very useful for estimation of hydrological models' uncertainty in particular hydro-metrological situation in real-time application [1]. In this approach the hydrological model realizations from Monte Carlo simulations are used to build different machine learning uncertainty models to predict uncertainty (quantiles of pdf) of the a deterministic output from hydrological model . Uncertainty models are trained using antecedent precipitation and streamflows as inputs. The trained models are then employed to predict the model output uncertainty which is specific for the new input data. We used three machine learning models namely artificial neural networks, model tree, locally weighted regression to predict output uncertainties. These three models produce similar verification results, which can be improved by merging their outputs dynamically. We propose an approach to form a committee of the three models to combine their outputs. The approach is applied to estimate uncertainty of streamflows simulation from a conceptual hydrological model in the Brue catchment in UK and the Bagmati catchment in Nepal. The verification results show that merged output is better than an individual model output. [1] D. L. Shrestha, N. Kayastha, and D. P. Solomatine, and R. Price. Encapsulation of parameteric uncertainty statistics by various predictive machine learning models: MLUE method, Journal of Hydroinformatic, in press, 2013.

Modeling Yield Surfaces of Various Structural Shapes

This study investigates the possibility of custom fitting a widely accepted approximate yield surface equation (Ziemian, 2000) to the theoretical yield surfaces of five different structural shapes, which include wide-flange, solid and hollow rectangular, and solid and hollow circular shapes. To achieve this goal, a theoretically “exact” but overly complex representation of the cross section’s yield surface was initially obtained by using fundamental principles of solid mechanics. A weighted regression analysis was performed with the “exact” yield surface data to obtain the specific coefficients of three terms in the approximate yield surface equation. These coefficients were calculated to determine the “best” yield surface equation for a given cross section geometry. Given that the exact yield surface shall have zero percentage of concavity, this investigation evaluated the resulting coefficient of determination (

Building a soil spectral library for Tajikistan comparing local and global modeling approaches

Over the last ~20 years, soil spectral libraries storing near-infrared reflectance (NIR) spectra from diverse soil samples have been built for many places, since almost 10 years also for Tajikistan. Many calibration approaches have been reported and used for prediction from large and heterogeneous libraries, but most are hampered by the high diversity of the soils, where the mineral background is heavily influencing spectral features. In such cases, local learning strategies have the advantage of building locally adapted calibrations, which can deal better with nonlinearities. Therefore, it was our major aim to identify the most efficient approach to develop an accurate and stable locally weigthed calibration model using a spectral library compiled over the past years. Keywords: Tajikistan, Near-Infrared spectroscopy (NIRS), soil organic carbon, locally weighted regression, regional and local spectral library.