The purpose of this research is to provide an extensive evaluation of neural network models for the prediction and the simulation of some key air pollutants in Hamilton, Ontario, Canada. Hamilton experiences one of Canada's highest air pollution exposures because of the dual problem associated with continuing industrial emission and gradual increase of traffic related emissions along with the transboundary air pollutions from heavily industrialized neighboring north-eastern and mid-western US cities. These factors combined with meteorology, cause large degradation of Hamilton's air quality. Hence an appropriate and robust method is of most importance in order to get an early notification of the future air quality situation. Data driven methods such as neural networks (NNs) are becoming very popular due to their inherent capability to capture the complex non-linear relationships between pollutants, climatic and other non-climatic variables such as traffic variables, emission factors, etc. This study investigates dynamic neural networks, namely time lagged feed-forward neural network (TLFN), Bayesian neural network (BNN) and recurrent neural network (RNN) for short term forecasting. The results are being compared with the benchmark static multilayer perceptron (MLP) models. The analysis shows that TLFN model with its time delay memory and RNN with its adaptive memory has outperformed the static MLP models in ground level ozone (O_3) forecasting for up to 12 hours ahead. Furthermore the model developed using the annual database is able to map the variations in the seasonal concentrations. On the other hand, MLP model was quite competitive for nitrogen dioxide (NO_2) prediction when compared to the dynamic NN based models. The study further assesses the ability of the neural network models to generate pollutant concentrations at sites where sampling has not been done. Using these neural network models, data values were generated for total suspended particulate (TSP) and inhalable particulates (PM_10) concentrations. The obtained results show promising potential. Although there were under-predictions and over-predictions on some occasions, the neural network models, in general were able to generate the missing information and to obtain air quality situation in the study area. / Thesis / Master of Applied Science (MASc)

In this dissertation, the generalized score tests based on weighted estimating equations are proposed for missing covariate data. Their properties, including the effects of nuisance functions on the forms of the test statistics and efficiency of the tests, are investigated. Different versions of the test statistic are properly defined for various parametric and semiparametric settings. Their asymptotic distributions are also derived. It is shown that when models for the nuisance functions are correct, appropriate test statistics can be obtained via plugging the estimates of the nuisance functions into the appropriate test statistic for the case that the nuisance functions are known. Furthermore, the optimal test is obtained using the relative efficiency measure. As an application of the proposed tests, a formal model validation procedure is developed for generalized linear models in the presence of missing covariates. The asymptotic distribution of the data driven methods is provided. A simulation study in both linear and logistic regressions illustrates the applicability and the finite sample performance of the methodology. Our methods are also employed to analyze a coronary artery disease diagnostic dataset.

Debris-slides are fast-moving landslides that occur in the Appalachian region including the Great Smoky Mountains National Park (GRSM). Various knowledge and data-driven approaches using spatial distribution of the past slides and associated factors could be used to estimate the region’s debris-slide susceptibility. This study developed two debris-slide susceptibility models for GRSM using knowledge-driven and data-driven methods in GIS. Six debris-slide causing factors (slope curvature, elevation, soil texture, land cover, annual rainfall, and bedrock discontinuity), and 256 known debris-slide locations were used in the analysis. Knowledge-driven weighted overlay and data-driven bivariate frequency ratio analyses were performed. Both models are helpful; however, each come with a set of advantages and disadvantages regarding degree of complexity, time-dependency, and experience of the analyst. The susceptibility maps are useful to the planners, developers, and engineers for maintaining the park’s infrastructures and delineating zones for further detailed geotechnical investigation.

Automatic three-dimensional (3D) building model reconstruction using remote sensing data is crucial in applications which require large-scale and frequent building model updates, such as disaster monitoring and urban management, to avoid huge manual efforts and costs. Recent advances in the availability of very high-resolution satellite data together with efficient data acquisition and large area coverage have led to an upward trend in their applications for 3D building model reconstructions. In this dissertation, a novel multistage hybrid automatic 3D building model reconstruction approach is proposed which reconstructs building models in level of details 2 (LOD2) based on digital surface model (DSM) data generated from the very high-resolution stereo imagery of the WorldView-2 satellite. This approach uses DSM data in combination with orthorectified panchromatic (PAN) and pan-sharpened data of multispectral satellite imagery to overcome the drawbacks of DSM data, such as blurred building boundaries, rough building shapes unwanted failures in the roof geometries. In the first stage, the rough building boundaries in the DSM-based building masks are refined by classifying the geometrical features of the corresponding PAN images. The refined boundaries are then simplified in the second stage through a parameterization procedure which represents the boundaries by a set of line segments. The main orientations of buildings are then determined, and the line segments are regularized accordingly. The regularized line segments are then connected to each other based on a rule-based method to form polygonal building boundaries. In the third stage, a novel technique is proposed to decompose the building polygons into a number of rectangles under the assumption that buildings are usually composed of rectangular structures. In the fourth stage, a roof model library is defined, which includes flat, gable, half-hip, hip, pyramid and mansard roofs. These primitive roof types are then assigned to the rectangles based on a deep learning-based classification method. In the fifth stage, a novel approach is developed to reconstruct watertight parameterized 3D building models based on the results of the previous stages and normalized DSM (nDSM) of satellite imagery. In the final stage, a novel approach is proposed to optimize building parameters based on an exhaustive search, so that the two-dimensional (2D) distance between the 3D building models and the building boundaries (obtained from building masks and PAN image) as well as the 3D normal distance between the 3D building models and the 3D point clouds (obtained from nDSM) are minimized. Different parts of the building blocks are then merged through a newly proposed intersection and merging process. All corresponding experiments were conducted on four areas of the city of Munich including 208 buildings and the results were evaluated qualitatively and quantitatively. According to the results, the proposed approach could accurately reconstruct 3D models of buildings, even the complex ones with several inner yards and multiple orientations. Furthermore, the proposed approach provided a high level of automation by the limited number of primitive roof model types required and by performing automatic parameter initialization. In addition, the proposed boundary refinement method improved the DSM-based building masks specified by 8 % in area accuracy. Furthermore, the ridge line directions and roof types were detected accurately for most of the buildings. The combination of the first three stages improved the accuracy of the building boundaries by 70 % in comparison to using line segments extracted from building masks without refinement. Moreover, the proposed optimization approach could achieve in most cases the best combinations of 2D and 3D geometrical parameters of roof models. Finally, the intersection and merging process could successfully merge different parts of the complex building models.