No description available.

No description available.

No description available.

No description available.

No description available.

Changes in precipitation patterns, temperature, and other climatic variables have been shown to modify thehydrological cycle and hydrological systems, potentially resulting in a shift in river runoff behavior and an increasedrisk of floods. There have been several instances of devastating floods throughout Europe’s history, which haveresulted in devastation and enormous economic losses. As a result of the effects of climate change, floods areoccurring more frequently in Sweden as well as across Europe. Research on the subject of flood prediction has beengoing on for decades, where particularly data-driven models have advanced in recent years. This study examinedtwo different machine learning (data-driven) models for forecasting river discharge in the Nissan River: Linearregression and Random Forrest regression (RFR), with the use of ECMWF Reanalysis v5 ( ERA5 ) data and historicaldischarge data. The Linear regression model yielded a r2 score of 0.45 and could not be considered an acceptablemodel. The RFR model had a r2 score of 0.71. This implies, given ERA5 reanalysis data, that one might generatea moderately performing machine learning model for Nissan river. An additional investigation was carried out,to see if the trained model could be used with EC-EARTH CMIP6 future projection. The findings resulting fromapplying the EC-EARTH CMIP6 future data on the trained RFR indicated too many uncertainties, necessitatingmore investigation before any conclusions can be drawn.

No / Recently, automatic age progression has gained popularity due to its nu-merous applications. Among these is the search for missing people, in the UK alone up to 300,000 people are reported missing every year. Although many algorithms have been proposed, most of the methods are affected by image noise, illumination variations, and most importantly facial expres-sions. To this end we propose to build an age progression framework that utilizes image de-noising and expression normalizing capabilities of kernel principal component analysis (Kernel PCA). Here, Kernel PCA a nonlinear form of PCA that explores higher order correlations between input varia-bles, is used to build a model that captures the shape and texture variations of the human face. The extracted facial features are then used to perform age progression via a regression procedure. To evaluate the performance of the framework, rigorous tests are conducted on the FGNET ageing data-base. Furthermore, the proposed algorithm is used to progress images of Mary Boyle; a six-year-old that went missing over 39 years ago, she is considered Ireland’s youngest missing person. The algorithm presented in this paper could potentially aid, among other applications, the search for missing people worldwide.

Current eastern wild turkey (<I>Meleagris gallopavo silvestris</I>) harvest models assume density-independent population dynamics despite indications that populations are subject to a form of density dependence. I suggest that both density-dependent and independent factors operate simultaneously on wild turkey populations, where the relative strength of each is governed by population density. I attempt to estimate the form of the density dependence relationship in wild turkey population growth using the theta-Ricker model. Density-independent relationships are explored between production and rainfall and temperature correlates for possible inclusion in the harvest model. Density-dependent and independent effects are then combined in the model to compare multiple harvest strategies. To estimate a functional relationship between population growth and density, I fit the theta-Ricker model to harvest index time-series from 11 state wildlife agencies. To model density-independent effects on population growth, I explored the ability of rainfall, temperature, and mast during the nesting and brooding season to predict observed production indices for 7 states. I then built a harvest model incorporating estimates to determine their influence on the mean and variability of the fall and spring harvest. Estimated density-dependent growth rates produced a left-skewed yield curve maximized at ~40% of carrying capacity, with large residuals. Density-independent models of production varied widely and were characterized by high model uncertainty. Results indicate a non-linear density dependence effect strongest at low population densities. High residuals from the model fit indicate that extrinsic factors will overshadow density-dependent factors at most population densities. However, environmental models were weak, requiring more data with higher precision. This indicates that density-independence can be correctly and more easily modeled as random error. The constructed model uses both density dependence and density-independent stochastic error as a tool to explore harvest strategies for biologists. The inclusion of weak density dependence changes expected harvest rates little from density-independent models. However, it does lower the probability of overharvest at low densities. Alternatives to proportional harvesting are explored to reduce the uncertainty in annual harvests. / Ph. D.

Functional data analysis (FDA) studies data in the form of measurements over a domain as whole entities. Our first focus is on the post-hoc analysis with pairwise and contrast comparisons of the popular functional ANOVA model comparing groups of functional data. Existing contrast tests assume independent functional observations within group. In reality, this assumption may not be satisfactory since functional data are often collected continually overtime on a subject. In this work, we introduce a new linear contrast test that accounts for time dependency among functional group members. For a significant contrast test, it can be beneficial to identify the region of significant difference. In the second part, we propose a non-parametric regression procedure to obtain a locally sparse estimate of functional contrast. Our work is motivated by a biomedical study using Raman spectroscopy to monitor hemodialysis treatment near real-time. With contrast test and sparse estimation, practitioners can monitor the progress of the hemodialysis within session and identify important chemicals for dialysis adequacy monitoring. In the third part, we propose a functional data model for degradation analysis of functional data. Motivated by degradation analysis application of rechargeable Li-ion batteries, we combine state-of-the-art functional linear models to produce fully functional prediction for curves on heterogenous domains. Simulation studies and data analysis demonstrate the advantage of the proposed method in predicting degradation measure than existing method using aggregation method. / Doctor of Philosophy / Functional data analysis (FDA) studies complex data structure in the form of curves and shapes. Our work is motivated by two applications concerning data from Raman spectroscopy and battery degradation study. Raman spectra of a liquid sample are curves with measurements over a domain of wavelengths that can identify chemical composition and whose values signify the constituent concentrations in the sample. We first propose a statistical procedure to test the significance of a functional contrast formed by spectra collected at beginning and at later time points during a dialysis session. Then a follow-up procedure is developed to produce a sparse representation of the contrast functional contrast with clearly identified zero and nonzero regions. The use of this method on contrast formed by Raman spectra of used dialysate collected at different time points during hemodialysis sessions can be adapted for evaluating the treatment efficacy in real time. In a third project, we apply state-of-the-art methodologies from FDA to a degradation study of rechargeable Li-ion batteries. Our proposed methods produce fully functional prediction of voltage discharge curves allowing flexibility in monitoring battery health.

Machine learning methods are now extensively applied in various scientific research areas to make models. Unlike regular models, machine learning based models use a data-driven approach. Machine learning algorithms can learn knowledge that are hard to be recognized, from available data. The data-driven approaches enhance the role of algorithms and computers and then accelerate the computation using alternative views. In this thesis, we explore the possibility of applying machine learning models in the prediction of chromatographic retention behaviors. Chromatographic separation is a key technique for the discovery and analysis of fullerenes. In previous studies, differential equation models have achieved great success in predictions of chromatographic retentions. However, most of the differential equation models require experimental measurements or theoretical computations for many parameters, which are not easy to obtain. Fullerenes/metallofullerenes are rigid and spherical molecules with only carbon atoms, which makes the predictions of chromatographic retention behaviors as well as other properties much simpler than other flexible molecules that have more variations on conformations. In this thesis, I propose the polarizability of a fullerene molecule is able to be estimated directly from the structures. Structural motifs are used to simplify the model and the models with motifs provide satisfying predictions. The data set contains 31947 isomers and their polarizability data and is split into a training set with 90% data points and a complementary testing set. In addition, a second testing set of large fullerene isomers is also prepared and it is used to testing whether a model can be trained by small fullerenes and then gives ideal predictions on large fullerenes. / Machine learning models are capable to be applied in a wide range of areas, such as scientific research. In this thesis, machine learning models are applied to predict chromatography behaviors of fullerenes based on the molecular structures. Chromatography is a common technique for mixture separations, and the separation is because of the difference of interactions between molecules and a stationary phase. In real experiments, a mixture usually contains a large family of different compounds and it requires lots of work and resources to figure out the target compound. Therefore, models are extremely import for studies of chromatography. Traditional models are built based on physics rules, and involves several parameters. The physics parameters are measured by experiments or theoretically computed. However, both of them are time consuming and not easy to be conducted. For fullerenes, in my previous studies, it has been shown that the chromatography model can be simplified and only one parameter, polarizability, is required. A machine learning approach is introduced to enhance the model by predicting the molecular polarizabilities of fullerenes based on structures. The structure of a fullerene is represented by several local structures. Several types of machine learning models are built and tested on our data set and the result shows neural network gives the best predictions.