L'objectif de cette thèse est d'expliquer les avantages qu'offrent la reconstruction de l'architecture des unités géologiques, leurs déformations ainsi que leurs variations au cours du temps à l'exploration de ressources minérales, tout en appliquant des méthodes et outils de modélisation 3D et 4D. La modélisation et la restauration structurale sont utilisées ici pour estimer des attributs géologiques qui peuvent aider à la compréhension de la formation des gisements, et à l'identification des zones favorables aux minéralisations. Cette thèse est axée sur l'application de la modélisation 3D et 4D à des cas réels pour trouver le lien entre une minéralisation et des processus géologiques tel que l'exhumation des terrains, l'activité des failles et la fracturation résultant d'un évènement de déformation. Ce mémoire est organisé en trois parties : (i) la modélisation structurale ainsi que la restauration surfacique ont été appliquées au district minier de la Ceinture de Cuivre de Legnica-Glogów (sud-ouest de la Pologne), pour estimer les conditions favorables à la fracturation hydraulique. Cette fracturation est intervenue dans le nord de l'Europe lors d'une phase d'inversion à la fin du Crétacé et au début du Paléocène. Dans notre hypothèse de départ, la fracturation hydraulique développée au cours de cette période a joué un rôle important dans la distribution en cuivre observée aujourd'hui dans le district minier ; (ii) la courbure des surfaces triangulées, représentant les horizons de la région des Sudètes polonaises, permet de mettre en évidence les systèmes de failles dans le socle. En particulier, des méthodes de restauration surfaciques ont été utilisées pour évaluer l'activité de des failles au cours du temps, en se basant sur la courbure des surfaces obtenues à chaque étape de la restauration. Les zones de fortes activités sont ici associées aux processus de minéralisation cuprifère de la région ; (iii) la restauration mécanique de la région de Mount Pleasant (Australie occidentale), a permis de simuler un évènement de raccourcissement apparu dans l'Archéen et qui est lié à un processus de minéralisation aurifère. La restauration mécanique est appliquée pour estimer le champ des déformations de la région au moment du raccourcissement. Avec ce champ de déformation, il est possible de calculer les paramètres d'endommagement de la masse rocheuse qui semblent liés aux zones aurifères situées hors des systèmes principaux de failles. Cette thèse a ainsi permis de mettre en évidence l'aspect prometteur de la modélisation et de la restauration structurale pour identifier des zones potentiellement minéralisées, mettant en valeur leur utilisation pour l'exploration des gisements et des ressources minérales / The objective of this Ph.D. thesis is to apply 3D and 4D modeling methods to reconstruct the architecture and deformations over time of geological entities in a defined region. Structural restoration modeling is used here to estimate geological, physical and structural attributes for understanding the origin of ore-deposits, and for identifying potential mineralized areas. We focused this thesis on 3D and 4D modeling on real case studies with different geological contexts (e.g. uplifting, fault activity and shortening), demonstrating the advantages and drawbacks on their use for similar situations. This thesis is organized into three parts: (i) the application of structural modeling in the mining district of the Copper Belt of Legnica-Glogów (south-west Poland). A surface-restoration approach was applied to estimate favorable conditions for hydraulic fracturing during an inversion, occurred in the northern part of Europe at Late Cretaceous--Early Paleocene. In our hypothesis, hydraulic fracturing developed at that time played an important role in the distribution of copper content observed in present days in the mining district. (ii) The curvature calculated on triangulated surfaces that represent the stratigraphic horizons in the Fore-Sudetic region (Poland), are used to highlight the fault systems in the basement as well as their activity. High curvature values reveal the fault activity which is associated with the copper mineralization process in the region. (iii) Mechanical restoration of the Mount Pleasant, Western Australia, simulates an Archean shortening event which occurred in the area linked to the gold mineralization process. The mechanical restoration was used to estimate the strain field in the region at the time of shortening. This deformation field was used to estimate the damage parameters of the rock mass. They show new potential gold areas located in off-fault gold systems. In conclusion, it is shown that 3D modeling and structural restoration could be used to identify potential favorable zones for the presence of mineralization, and seem promising as a tool for the exploration of ore-deposits and mineral resources

Autism Spectrum Disorder (ASD) is part of the developmental disabilities. There are numerous symptoms for ASD patients, including lack of abilities in social interaction, communication obstacle and repeatable behaviors. Meanwhile, the rate of ASD prevalence has kept rising by the past 20 years from 1 out of 150 in 2000 to 1 out of 54 in 2016. In addition, the ASD population is quite large. Specifically, 3.5 million Americans live with ASD in the year of 2014, which will cost U.S. citizens $236-$262 billion dollars annually for autism services. So, it is critical to make an accurate diagnosis for preschool age children with ASD, in order to give them a better life. Instead of using traditional ASD behavioral tests, such as ADI-R, ADOS, and DSM-IV, we applied brain MRI images as input to make diagnosis. We revised 3D-ResNet structure to fit 110 preschool children's brain MRI data, along with Convolution 3D and VGG model. The prediction accuracy with raw data is 65.22%. The accuracy is significantly improved to 82.61% by removing the noise around the brain. We also showed the speed of ML prediction is 308 times faster than behavior tests.

The aim of the study was to evaluate dierent types of logistic regression to find the optimal model to predict the gender of hospitalized COVID-19 patients. The models were based on COVID-19 case series data from Pakistan using a set of 18 explanatory variables out of which patient age and BMI were numerical and the rest were categorical variables, expressing symptoms and previous health issues.  Compared were a logistic regression using all variables, a logistic regression that used stepwise variable selection with 4 explanatory variables, a logistic Ridge regression model, a logistic Lasso regression model and a logistic Elastic Net regression model.  Based on several metrics assessing the goodness of fit of the models and the evaluation of predictive power using the area under the ROC curve the Elastic Net that was only using the Lasso penalty had the best result and was able to predict 82.5% of the test cases correctly.

This paper proposes an innovative way to address real cases of production prediction. This approach consists in the decomposition of original time series into time sub-series according to a group of factors in order to generate a predictive model from the partial predictive models of the sub-series. The adjustment of the models is carried out by means of a set of statistic techniques and Automatic Learning. This method was compared to an intuitive method consisting of a direct prediction of time series. The results show that this approach achieves better predictive performance than the direct way, so applying a decomposition method is more appropriate for this problem than non-decomposition.

<p>Problem nedostajućih podataka je često prisutan prilikom razvoja<br />prediktivnih modela. Umesto uklanjanja podataka koji sadrže<br />vrednosti koje nedostaju mogu se primeniti metode za njihovu<br />imputaciju. Disertacija predlaže metodologiju za pristup analizi<br />uspešnosti imputacija prilikom razvoja prediktivnih modela. Na<br />osnovu iznete metodologije prikazuju se rezultati primene algoritama<br />mašinskog učenja, kao metoda imputacije, prilikom razvoja određenih,<br />konkretnih prediktivnih modela.</p> / <p>The problem of missing data is often present when developing predictive<br />models. Instead of removing data containing missing values, methods for<br />imputation can be applied. The dissertation proposes a methodology for<br />analysis of imputation performance in the development of predictive models.<br />Based on the proposed methodology, results of the application of machine<br />learning algorithms, as an imputation method in the development of specific<br />models, are presented.</p>

<p>Anaerobic digestion uses a mixed, microbial community to convert organic wastes to biogas, thereby generating a clean renewable energy and reducing greenhouse gas emissions. However, few studies have quantified the relationship between waste composition and the subsequent physical and chemical changes in the digester. This Ph.D. dissertation aimed to gain new knowledge about how these differences in waste composition ultimately affect digester function. This dissertation examined three areas of digester function: (1) hydrogen sulfide production, (2) digester foaming, and (3) methane yield. </p> <p>To accomplish these aims, a variety of materials from four different large-scale field digesters were collected at different time points and from different locations within the digester systems, including influent, liquid in the middle of the digesters, effluent, and effluent after solids separation. The materials were used for biochemical methane potential (BMP) tests in 43 lab-scale lab-digester groups, each containing triplicate or duplicate digesters. The materials from field digesters and the effluents from the lab-digesters were analyzed for an extensive set of chemical and physical characteristics. The three areas of digester function were examined with the physical and chemical characteristics of the digester materials and effluents, and the BMP performances. </p> <p>Hydrogen sulfide productions in the lab-digesters ranged from non-detectable to 1.29 mL g VS^-1. Higher H₂S concentrations in the biogas were observed within the first ten days of testing. The initial Fe(II) : S ratio and OP concentrations had important influences on H₂S productions. Important parameters of digester influents related to digester foaming were the ratios of Fe(II) : S, Fe(II) : TP, and TVFA : TALK; and the concentrations of Cu. Digesters receiving mixed waste streams could be more vulnerable to foaming. The characteristics of each waste type varied significantly based on substrate and inoculum type, and digester functioning. The influent chemical characteristics of the waste significantly impacted all aspects of digester function. Using multivariate statistics and machine learning, models were developed and the prediction of digester outcomes were simulated based on the initial characteristics of the waste types. </p>

The traditional power systems are statically rated and sometimes renewable energy sources (RES) are curtailed in order not to exceed this static rating. The RES are curtailed because of their intermittent character and therefore, it is difficult to predict their output at specific time periods throughout the day. Dynamic Line Rating (DLR) technology can overcome this constraint by leveraging the available weather data and technical parameters of the transmission line. The main goal of the thesis is to present prediction models of Dynamic Line Rating (DLR) capacity on two days ahead and on one day ahead. The models are evaluated based on their error rate profiles. DLR provides the capability to up-rate the line(s) according to the environmental conditions and has always a much higher profile than the static rating. By implementing DLR a power utility can increase the efficiency of the power system, decrease RES curtailment and optimize their integration within the grid. DLR is mainly dependent on the weather parameters and specifically, in large wind speeds and low ambient temperature, the DLR can register the highest profile. Additionally, this is especially profitable for the wind energy producers that can both, produce more (until pitch control) and transmit more in high wind speeds periods with the same given line(s), thus increasing the energy efficiency.  The DLR was calculated by employing modern Data Science and Machine Learning tools and techniques and leveraged historical weather and transmission line data provided by SMHI and Vattenfall respectively. An initial phase of Exploratory Data Analysis (EDA) was developed to understand data patterns and relationships between different variables, as well as to determine the most predictive variables for DLR. All the predictive models and data processing routines were built in open source R and are available on GitHub. There were three types of models built: for historical data, for one day-ahead and for two days-ahead time-horizons. The models built for both time-horizons registered a low error rate profile of 9% (for day-ahead) and 11% (for two days-ahead). As expected, the predictive models built on historical data were more accurate with an error as low as 2%-3%.  In conclusion, the implemented models met the requirements set by Vattenfall of maximum error of 20% and they can be applied in the control room for that specific line. Moreover, predictive models can also be built for other lines if the required data is available. Therefore, this Master Thesis project’s findings and outcomes can be reproduced in other power lines and geographic locations in order to achieve a more efficient power system and an increased share of RES in the energy mix

<p>Post-disaster temporary housing has been a significant challenge for the emergency management group and industries for many years. According to reports by the Department of Homeland Security (DHS), housing in states and territories is ranked as the second to last proficient in 32 core capabilities for preparedness.The number of temporary housing required in a geographic area is influenced by a variety of factors, including social issues, financial concerns, labor workforce availability, and climate conditions. Acknowledging and creating a balance between these interconnected needs is considered as one of the main challenges that need to be addressed. Post-disaster temporary housing is a multi-objective process, thus reaching the optimized model relies on how different elements and objectives interact, sometimes even conflicting, with each other. This makes decision making in post-disaster construction more restricted and challenging, which has caused ineffective management in post-disaster housing reconstruction.</p> <p>Few researches have studied the use of Artificial Intelligence modeling to reduce the time and cost of post-disaster sheltering. However, there is a lack of research and knowledge gap regarding the selection and the magnitude of effect of different factors of the most optimized type of Temporary Housing Units (THU) in a post-disaster event.</p> The proposed framework in this research uses supervised machine learing to maximize certain design aspects of and minimize some of the difficulties to better support creating temporary houses in post-disaster situations. The outcome in this study is the classification type of the THU, more particularly, classifying THUs based on whether they are built on-site or off-site. In order to collect primary data for creating the model and evaluating the magnitude of effect for each factor in the process, a set of surveys were distributed between the key players and policymakers who play a role in providing temporary housing to people affected by natural disasters in the United States. The outcome of this framework benefits from tacit knowledge of the experts in the field to show the challenges and issues in the subject. The result of this study is a data-based multi-objective decision-making tool for selecting the THU type. Using this tool, policymakers who are in charge of selecting and allocating post-disaster accommodations can select the THU type most responsive to the local needs and characteristics of the affected people in each natural disaster.

The first-principles methods such as density functional theory (DFT) often produce quantitative predictions for physics and chemistry of materials with explicit descriptions of electron’s behavior. We were able to provide information of electronic structures with chemical doping and metal-insulator transition of rare-earth nickelates that cannot be easily accessible with experimental characterizations. Moreover, combining with mean-field microkinetic modeling, we utilized the DFT energetics to model water gas shift reactions catalyzed by Fe3O4at steady-state and determined favorable reaction mechanism. However, the high computational costs of DFT calculations make it impossible to investigate complex chemical processes with hundreds of elementary steps with more than thousands of atoms for realistic systems. The study of molecular high energy (HE) materials using the reactive force field (ReaxFF) has contributed to understand chemically induced detonation process with nanoscale defects as well as defect-free systems. However, the reduced accuracy of the force fields canalso lead to a different conclusion compared to DFT calculations and experimental results. Machine learning force field is a promising alternative to work with comparable simulation size and speed of ReaxFF while maintaining accuracy of DFT. In this respect, we developed a neural network reactive force field (NNRF) that was iteratively parameterized with DFT calculations to solve problems of ReaxFF. We built an efficient and accurate NNRF for complex decomposition reaction of HE materials such as high energy nitramine 1,3,5-Trinitroperhydro-1,3,5-triazine (RDX)and predicted consistent results for experimental findings. This work aims to demonstrate the approaches to clarify the reaction details of materials using the first-principles methods and machine learning force fields to guide quantitative predictions of complex chemical process.

Stimuli caused by our own voluntary actions receive a special treatment in the brain. In auditory processing, the N1 and/or P2 components of the auditory event-related brain potential (ERP) to self-initiated sounds are attenuated compared to passive sound exposure, which has been interpreted as an indicator of a predictive internal forward mechanism. Such a predictive mechanism enables differentiating the sensory consequences of one´s own actions from other sensory input and allows the mind to attribute actions to agents and particularly to the self, usually called the “sense of agency”. However, the notion that N1 and/or P2 attenuation effects to self-initiated sounds reflect internal forward model predictions is still controversial. Furthermore, little is known about the relationship between N1 and/or P2 attenuation effects and the sense of agency. Thus, the aim of the present thesis was to further investigate the nature of the N1 and/or P2 attenuation effect to self-initiated sounds and to examine its specific relationship to the sense of agency. The present thesis provides evidence that N1 and/or P2 attenuation effects to self-initiated sounds are mainly determined by movement intention and predictive internal motor signals involved in movement planning and rules out non-predictive explanations of these effects. Importantly, it is shown that sensory attenuation effects in audition are directly related to the feeling of agency, but occur independent of agency judgments. Taken together, the present thesis supports the assumptions of internal forward model theories.