@phdthesis{Che2017,
  author    = {Che, Xiaoyin},
  title     = {E-lecture material enhancement based on automatic multimedia analysis},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-408224},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xviii, 148},
  year      = {2017},
  abstract  = {In this era of high-speed informatization and globalization, online education is no longer an exquisite concept in the ivory tower, but a rapidly developing industry closely relevant to people's daily lives. Numerous lectures are recorded in form of multimedia data, uploaded to the Internet and made publicly accessible from anywhere in this world. These lectures are generally addressed as e-lectures. In recent year, a new popular form of e-lectures, the Massive Open Online Courses (MOOCs), boosts the growth of online education industry and somehow turns "learning online" into a fashion. As an e-learning provider, besides to keep improving the quality of e-lecture content, to provide better learning environment for online learners is also a highly important task. This task can be preceded in various ways, and one of them is to enhance and upgrade the learning materials provided: e-lectures could be more than videos. Moreover, this process of enhancement or upgrading should be done automatically, without giving extra burdens to the lecturers or teaching teams, and this is the aim of this thesis. The first part of this thesis is an integrated framework of multi-lingual subtitles production, which can help online learners penetrate the language barrier. The framework consists of Automatic Speech Recognition (ASR), Sentence Boundary Detection (SBD) and Machine Translation (MT), among which the proposed SBD solution is major technical contribution, building on Deep Neural Network (DNN) and Word Vector (WV) and achieving state-of-the-art performance. Besides, a quantitative evaluation with dozens of volunteers is also introduced to measure how these auto-generated subtitles could actually help in context of e-lectures. Secondly, a technical solution "TOG" (Tree-Structure Outline Generation) is proposed to extract textual content from the displaying slides recorded in video and re-organize them into a hierarchical lecture outline, which may serve in multiple functions, such like preview, navigation and retrieval. TOG runs adaptively and can be roughly divided into intra-slide and inter-slides phases. Table detection and lecture video segmentation can be implemented as sub- or post-application in these two phases respectively. Evaluation on diverse e-lectures shows that all the outlines, tables and segments achieved are trustworthily accurate. Based on the subtitles and outlines previously created, lecture videos can be further split into sentence units and slide-based segment units. A lecture highlighting process is further applied on these units, in order to capture and mark the most important parts within the corresponding lecture, just as what people do with a pen when reading paper books. Sentence-level highlighting depends on the acoustic analysis on the audio track, while segment-level highlighting focuses on exploring clues from the statistical information of related transcripts and slide content. Both objective and subjective evaluations prove that the proposed lecture highlighting solution is with decent precision and welcomed by users. All above enhanced e-lecture materials have been already implemented in actual use or made available for implementation by convenient interfaces.},
  language  = {en}
}
@phdthesis{Kriegerowski2019,
  author    = {Kriegerowski, Marius},
  title     = {Development of waveform-based, automatic analysis tools for the spatio-temporal characterization of massive earthquake clusters and swarms},
  doi       = {10.25932/publishup-44404},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-444040},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 83},
  year      = {2019},
  abstract  = {Earthquake swarms are characterized by large numbers of events occurring in a short period of time within a confined source volume and without significant mainshock aftershock pattern as opposed to tectonic sequences. Intraplate swarms in the absence of active volcanism usually occur in continental rifts as for example in the Eger Rift zone in North West Bohemia, Czech Republic. A common hypothesis links event triggering to pressurized fluids. However, the exact causal chain is often poorly understood since the underlying geotectonic processes are slow compared to tectonic sequences. The high event rate during active periods challenges standard seismological routines as these are often designed for single events and therefore costly in terms of human resources when working with phase picks or computationally costly when exploiting full waveforms. This methodological thesis develops new approaches to analyze earthquake swarm seismicity as well as the underlying seismogenic volume. It focuses on the region of North West (NW) Bohemia, a well studied, well monitored earthquake swarm region. In this work I develop and test an innovative approach to detect and locate earthquakes using deep convolutional neural networks. This technology offers great potential as it allows to efficiently process large amounts of data which becomes increasingly important given that seismological data storage grows at increasing pace. The proposed deep neural network trained on NW Bohemian earthquake swarm records is able to locate 1000 events in less than 1 second using full waveforms while approaching precision of double difference relocated catalogs. A further technological novelty is that the trained filters of the deep neural network's first layer can be repurposed to function as a pattern matching event detector without additional training on noise datasets. For further methodological development and benchmarking, I present a new toolbox to generate realistic earthquake cluster catalogs as well as synthetic full waveforms of those clusters in an automated fashion. The input is parameterized using constraints on source volume geometry, nucleation and frequency-magnitude relations. It harnesses recorded noise to produce highly realistic synthetic data for benchmarking and development. This tool is used to study and assess detection performance in terms of magnitude of completeness Mc of a full waveform detector applied to synthetic data of a hydrofracturing experiment at the Wysin site, Poland. Finally, I present and demonstrate a novel approach to overcome the masking effects of wave propagation between earthquake and stations and to determine source volume attenuation directly in the source volume where clustered earthquakes occur. The new event couple spectral ratio approach exploits high frequency spectral slopes of two events sharing the greater part of their rays. Synthetic tests based on the toolbox mentioned before show that this method is able to infer seismic wave attenuation within the source volume at high spatial resolution. Furthermore, it is independent from the distance towards a station as well as the complexity of the attenuation and velocity structure outside of the source volume of swarms. The application to recordings of the NW Bohemian earthquake swarm shows increased P phase attenuation within the source volume (Qp < 100) based on results at a station located close to the village Luby (LBC). The recordings of a station located in epicentral proximity, close to Nov{\´y} Kostel (NKC), show a relatively high complexity indicating that waves arriving at that station experience more scattering than signals recorded at other stations. The high level of complexity destabilizes the inversion. Therefore, the Q estimate at NKC is not reliable and an independent proof of the high attenuation finding given the geometrical and frequency constraints is still to be done. However, a high attenuation in the source volume of NW Bohemian swarms has been postulated before in relation to an expected, highly damaged zone bearing CO 2 at high pressure. The methods developed in the course of this thesis yield the potential to improve our understanding regarding the role of fluids and gases in intraplate event clustering.},
  language  = {en}
}
@phdthesis{Rezaei2019,
  author    = {Rezaei, Mina},
  title     = {Deep representation learning from imbalanced medical imaging},
  doi       = {10.25932/publishup-44275},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-442759},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxviii, 160},
  year      = {2019},
  abstract  = {Medical imaging plays an important role in disease diagnosis, treatment planning, and clinical monitoring. One of the major challenges in medical image analysis is imbalanced training data, in which the class of interest is much rarer than the other classes. Canonical machine learning algorithms suppose that the number of samples from different classes in the training dataset is roughly similar or balance. Training a machine learning model on an imbalanced dataset can introduce unique challenges to the learning problem. A model learned from imbalanced training data is biased towards the high-frequency samples. The predicted results of such networks have low sensitivity and high precision. In medical applications, the cost of misclassification of the minority class could be more than the cost of misclassification of the majority class. For example, the risk of not detecting a tumor could be much higher than referring to a healthy subject to a doctor. The current Ph.D. thesis introduces several deep learning-based approaches for handling class imbalanced problems for learning multi-task such as disease classification and semantic segmentation. At the data-level, the objective is to balance the data distribution through re-sampling the data space: we propose novel approaches to correct internal bias towards fewer frequency samples. These approaches include patient-wise batch sampling, complimentary labels, supervised and unsupervised minority oversampling using generative adversarial networks for all. On the other hand, at algorithm-level, we modify the learning algorithm to alleviate the bias towards majority classes. In this regard, we propose different generative adversarial networks for cost-sensitive learning, ensemble learning, and mutual learning to deal with highly imbalanced imaging data. We show evidence that the proposed approaches are applicable to different types of medical images of varied sizes on different applications of routine clinical tasks, such as disease classification and semantic segmentation. Our various implemented algorithms have shown outstanding results on different medical imaging challenges.},
  language  = {en}
}
@phdthesis{Ayzel2021,
  author    = {Ayzel, Georgy},
  title     = {Advancing radar-based precipitation nowcasting},
  doi       = {10.25932/publishup-50426},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-504267},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xx, 68},
  year      = {2021},
  abstract  = {Precipitation forecasting has an important place in everyday life - during the day we may have tens of small talks discussing the likelihood that it will rain this evening or weekend. Should you take an umbrella for a walk? Or should you invite your friends for a barbecue? It will certainly depend on what your weather application shows. While for years people were guided by the precipitation forecasts issued for a particular region or city several times a day, the widespread availability of weather radars allowed us to obtain forecasts at much higher spatiotemporal resolution of minutes in time and hundreds of meters in space. Hence, radar-based precipitation nowcasting, that is, very-short-range forecasting (typically up to 1-3 h), has become an essential technique, also in various professional application contexts, e.g., early warning, sewage control, or agriculture. There are two major components comprising a system for precipitation nowcasting: radar-based precipitation estimates, and models to extrapolate that precipitation to the imminent future. While acknowledging the fundamental importance of radar-based precipitation retrieval for precipitation nowcasts, this thesis focuses only on the model development: the establishment of open and competitive benchmark models, the investigation of the potential of deep learning, and the development of procedures for nowcast errors diagnosis and isolation that can guide model development. The present landscape of computational models for precipitation nowcasting still struggles with the availability of open software implementations that could serve as benchmarks for measuring progress. Focusing on this gap, we have developed and extensively benchmarked a stack of models based on different optical flow algorithms for the tracking step and a set of parsimonious extrapolation procedures based on image warping and advection. We demonstrate that these models provide skillful predictions comparable with or even superior to state-of-the-art operational software. We distribute the corresponding set of models as a software library, rainymotion, which is written in the Python programming language and openly available at GitHub (https://github.com/hydrogo/rainymotion). That way, the library acts as a tool for providing fast, open, and transparent solutions that could serve as a benchmark for further model development and hypothesis testing. One of the promising directions for model development is to challenge the potential of deep learning - a subfield of machine learning that refers to artificial neural networks with deep architectures, which may consist of many computational layers. Deep learning showed promising results in many fields of computer science, such as image and speech recognition, or natural language processing, where it started to dramatically outperform reference methods. The high benefit of using "big data" for training is among the main reasons for that. Hence, the emerging interest in deep learning in atmospheric sciences is also caused and concerted with the increasing availability of data - both observational and model-based. The large archives of weather radar data provide a solid basis for investigation of deep learning potential in precipitation nowcasting: one year of national 5-min composites for Germany comprises around 85 billion data points. To this aim, we present RainNet, a deep convolutional neural network for radar-based precipitation nowcasting. RainNet was trained to predict continuous precipitation intensities at a lead time of 5 min, using several years of quality-controlled weather radar composites provided by the German Weather Service (DWD). That data set covers Germany with a spatial domain of 900 km x 900 km and has a resolution of 1 km in space and 5 min in time. Independent verification experiments were carried out on 11 summer precipitation events from 2016 to 2017. In these experiments, RainNet was applied recursively in order to achieve lead times of up to 1 h. In the verification experiments, trivial Eulerian persistence and a conventional model based on optical flow served as benchmarks. The latter is available in the previously developed rainymotion library. RainNet significantly outperformed the benchmark models at all lead times up to 60 min for the routine verification metrics mean absolute error (MAE) and critical success index (CSI) at intensity thresholds of 0.125, 1, and 5 mm/h. However, rainymotion turned out to be superior in predicting the exceedance of higher intensity thresholds (here 10 and 15 mm/h). The limited ability of RainNet to predict high rainfall intensities is an undesirable property which we attribute to a high level of spatial smoothing introduced by the model. At a lead time of 5 min, an analysis of power spectral density confirmed a significant loss of spectral power at length scales of 16 km and below. Obviously, RainNet had learned an optimal level of smoothing to produce a nowcast at 5 min lead time. In that sense, the loss of spectral power at small scales is informative, too, as it reflects the limits of predictability as a function of spatial scale. Beyond the lead time of 5 min, however, the increasing level of smoothing is a mere artifact - an analogue to numerical diffusion - that is not a property of RainNet itself but of its recursive application. In the context of early warning, the smoothing is particularly unfavorable since pronounced features of intense precipitation tend to get lost over longer lead times. Hence, we propose several options to address this issue in prospective research on model development for precipitation nowcasting, including an adjustment of the loss function for model training, model training for longer lead times, and the prediction of threshold exceedance. The model development together with the verification experiments for both conventional and deep learning model predictions also revealed the need to better understand the source of forecast errors. Understanding the dominant sources of error in specific situations should help in guiding further model improvement. The total error of a precipitation nowcast consists of an error in the predicted location of a precipitation feature and an error in the change of precipitation intensity over lead time. So far, verification measures did not allow to isolate the location error, making it difficult to specifically improve nowcast models with regard to location prediction. To fill this gap, we introduced a framework to directly quantify the location error. To that end, we detect and track scale-invariant precipitation features (corners) in radar images. We then consider these observed tracks as the true reference in order to evaluate the performance (or, inversely, the error) of any model that aims to predict the future location of a precipitation feature. Hence, the location error of a forecast at any lead time ahead of the forecast time corresponds to the Euclidean distance between the observed and the predicted feature location at the corresponding lead time. Based on this framework, we carried out a benchmarking case study using one year worth of weather radar composites of the DWD. We evaluated the performance of four extrapolation models, two of which are based on the linear extrapolation of corner motion; and the remaining two are based on the Dense Inverse Search (DIS) method: motion vectors obtained from DIS are used to predict feature locations by linear and Semi-Lagrangian extrapolation. For all competing models, the mean location error exceeds a distance of 5 km after 60 min, and 10 km after 110 min. At least 25\% of all forecasts exceed an error of 5 km after 50 min, and of 10 km after 90 min. Even for the best models in our experiment, at least 5 percent of the forecasts will have a location error of more than 10 km after 45 min. When we relate such errors to application scenarios that are typically suggested for precipitation nowcasting, e.g., early warning, it becomes obvious that location errors matter: the order of magnitude of these errors is about the same as the typical extent of a convective cell. Hence, the uncertainty of precipitation nowcasts at such length scales - just as a result of locational errors - can be substantial already at lead times of less than 1 h. Being able to quantify the location error should hence guide any model development that is targeted towards its minimization. To that aim, we also consider the high potential of using deep learning architectures specific to the assimilation of sequential (track) data. Last but not least, the thesis demonstrates the benefits of a general movement towards open science for model development in the field of precipitation nowcasting. All the presented models and frameworks are distributed as open repositories, thus enhancing transparency and reproducibility of the methodological approach. Furthermore, they are readily available to be used for further research studies, as well as for practical applications.},
  language  = {en}
}
@phdthesis{TorcatoMordido2021,
  author    = {Torcato Mordido, Gon{\c{c}}alo Filipe},
  title     = {Diversification, compression, and evaluation methods for generative adversarial networks},
  doi       = {10.25932/publishup-53546},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535460},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiii, 148},
  year      = {2021},
  abstract  = {Generative adversarial networks (GANs) have been broadly applied to a wide range of application domains since their proposal. In this thesis, we propose several methods that aim to tackle different existing problems in GANs. Particularly, even though GANs are generally able to generate high-quality samples, the diversity of the generated set is often sub-optimal. Moreover, the common increase of the number of models in the original GANs framework, as well as their architectural sizes, introduces additional costs. Additionally, even though challenging, the proper evaluation of a generated set is an important direction to ultimately improve the generation process in GANs. We start by introducing two diversification methods that extend the original GANs framework to multiple adversaries to stimulate sample diversity in a generated set. Then, we introduce a new post-training compression method based on Monte Carlo methods and importance sampling to quantize and prune the weights and activations of pre-trained neural networks without any additional training. The previous method may be used to reduce the memory and computational costs introduced by increasing the number of models in the original GANs framework. Moreover, we use a similar procedure to quantize and prune gradients during training, which also reduces the communication costs between different workers in a distributed training setting. We introduce several topology-based evaluation methods to assess data generation in different settings, namely image generation and language generation. Our methods retrieve both single-valued and double-valued metrics, which, given a real set, may be used to broadly assess a generated set or separately evaluate sample quality and sample diversity, respectively. Moreover, two of our metrics use locality-sensitive hashing to accurately assess the generated sets of highly compressed GANs. The analysis of the compression effects in GANs paves the way for their efficient employment in real-world applications. Given their general applicability, the methods proposed in this thesis may be extended beyond the context of GANs. Hence, they may be generally applied to enhance existing neural networks and, in particular, generative frameworks.},
  language  = {en}
}
@phdthesis{Galetzka2022,
  author    = {Galetzka, Fabian},
  title     = {Investigating and improving background context consistency in neural conversation models},
  doi       = {10.25932/publishup-58463},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-584637},
  school      = {Universit{\"a}t Potsdam},
  pages     = {viii, 173},
  year      = {2022},
  abstract  = {Neural conversation models aim to predict appropriate contributions to a (given) conversation by using neural networks trained on dialogue data. A specific strand focuses on non-goal driven dialogues, first proposed by Ritter et al. (2011): They investigated the task of transforming an utterance into an appropriate reply. Then, this strand evolved into dialogue system approaches using long dialogue histories and additional background context. Contributing meaningful and appropriate to a conversation is a complex task, and therefore research in this area has been very diverse: Serban et al. (2016), for example, looked into utilizing variable length dialogue histories, Zhang et al. (2018) added additional context to the dialogue history, Wolf et al. (2019) proposed a model based on pre-trained Self-Attention neural networks (Vasvani et al., 2017), and Dinan et al. (2021) investigated safety issues of these approaches. This trend can be seen as a transformation from trying to somehow carry on a conversation to generating appropriate replies in a controlled and reliable way. In this thesis, we first elaborate the meaning of appropriateness in the context of neural conversation models by drawing inspiration from the Cooperative Principle (Grice, 1975). We first define what an appropriate contribution has to be by operationalizing these maxims as demands on conversation models: being fluent, informative, consistent towards given context, coherent and following a social norm. Then, we identify different targets (or intervention points) to achieve the conversational appropriateness by investigating recent research in that field. In this thesis, we investigate the aspect of consistency towards context in greater detail, being one aspect of our interpretation of appropriateness. During the research, we developed a new context-based dialogue dataset (KOMODIS) that combines factual and opinionated context to dialogues. The KOMODIS dataset is publicly available and we use the data in this thesis to gather new insights in context-augmented dialogue generation. We further introduced a new way of encoding context within Self-Attention based neural networks. For that, we elaborate the issue of space complexity from knowledge graphs, and propose a concise encoding strategy for structured context inspired from graph neural networks (Gilmer et al., 2017) to reduce the space complexity of the additional context. We discuss limitations of context-augmentation for neural conversation models, explore the characteristics of knowledge graphs, and explain how we create and augment knowledge graphs for our experiments. Lastly, we analyzed the potential of reinforcement and transfer learning to improve context-consistency for neural conversation models. We find that current reward functions need to be more precise to enable the potential of reinforcement learning, and that sequential transfer learning can improve the subjective quality of generated dialogues.},
  language  = {en}
}
@phdthesis{Seleem2023,
  author    = {Seleem, Omar},
  title     = {Towards urban pluvial flood mapping using data-driven models},
  doi       = {10.25932/publishup-59813},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-598137},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 95},
  year      = {2023},
  abstract  = {Casualties and damages from urban pluvial flooding are increasing. Triggered by short, localized, and intensive rainfall events, urban pluvial floods can occur anywhere, even in areas without a history of flooding. Urban pluvial floods have relatively small temporal and spatial scales. Although cumulative losses from urban pluvial floods are comparable, most flood risk management and mitigation strategies focus on fluvial and coastal flooding. Numerical-physical-hydrodynamic models are considered the best tool to represent the complex nature of urban pluvial floods; however, they are computationally expensive and time-consuming. These sophisticated models make large-scale analysis and operational forecasting prohibitive. Therefore, it is crucial to evaluate and benchmark the performance of other alternative methods. The findings of this cumulative thesis are represented in three research articles. The first study evaluates two topographic-based methods to map urban pluvial flooding, fill-spill-merge (FSM) and topographic wetness index (TWI), by comparing them against a sophisticated hydrodynamic model. The FSM method identifies flood-prone areas within topographic depressions while the TWI method employs maximum likelihood estimation to calibrate a TWI threshold (τ) based on inundation maps from the 2D hydrodynamic model. The results point out that the FSM method outperforms the TWI method. The study highlights then the advantage and limitations of both methods. Data-driven models provide a promising alternative to computationally expensive hydrodynamic models. However, the literature lacks benchmarking studies to evaluate the different models' performance, advantages and limitations. Model transferability in space is a crucial problem. Most studies focus on river flooding, likely due to the relative availability of flow and rain gauge records for training and validation. Furthermore, they consider these models as black boxes. The second study uses a flood inventory for the city of Berlin and 11 predictive features which potentially indicate an increased pluvial flooding hazard to map urban pluvial flood susceptibility using a convolutional neural network (CNN), an artificial neural network (ANN) and the benchmarking machine learning models random forest (RF) and support vector machine (SVM). I investigate the influence of spatial resolution on the implemented models, the models' transferability in space and the importance of the predictive features. The results show that all models perform well and the RF models are superior to the other models within and outside the training domain. The models developed using fine spatial resolution (2 and 5 m) could better identify flood-prone areas. Finally, the results point out that aspect is the most important predictive feature for the CNN models, and altitude is for the other models. While flood susceptibility maps identify flood-prone areas, they do not represent flood variables such as velocity and depth which are necessary for effective flood risk management. To address this, the third study investigates data-driven models' transferability to predict urban pluvial floodwater depth and the models' ability to enhance their predictions using transfer learning techniques. It compares the performance of RF (the best-performing model in the previous study) and CNN models using 12 predictive features and output from a hydrodynamic model. The findings in the third study suggest that while CNN models tend to generalise and smooth the target function on the training dataset, RF models suffer from overfitting. Hence, RF models are superior for predictions inside the training domains but fail outside them while CNN models could control the relative loss in performance outside the training domains. Finally, the CNN models benefit more from transfer learning techniques than RF models, boosting their performance outside training domains. In conclusion, this thesis has evaluated both topographic-based methods and data-driven models to map urban pluvial flooding. However, further studies are crucial to have methods that completely overcome the limitation of 2D hydrodynamic models.},
  language  = {en}
}
@phdthesis{Pfrang2023,
  author    = {Pfrang, Konstantin Johannes},
  title     = {Search for light primordial black holes with VERITAS using gamma γ-ray and optical observations},
  doi       = {10.25932/publishup-58726},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-587266},
  school      = {Universit{\"a}t Potsdam},
  pages     = {139},
  year      = {2023},
  abstract  = {The Very Energetic Radiation Imaging Telescope Array System (VERITAS) is an array of four imaging atmospheric Cherenkov telescopes (IACTs). VERITAS is sensitive to very-high-energy gamma-rays in the range of 100 GeV to >30 TeV. Hypothesized primordial black holes (PBHs) are attractive targets for IACTs. If they exist, their potential cosmological impact reaches beyond the candidacy for constituents of dark matter. The sublunar mass window is the largest unconstrained range of PBH masses. This thesis aims to develop novel concepts searching for light PBHs with VERITAS. PBHs below the sublunar window lose mass due to Hawking radiation. They would evaporate at the end of their lifetime, leading to a short burst of gamma-rays. If PBHs formed at about 10^15 g, the evaporation would occur nowadays. Detecting these signals might not only confirm the existence of PBHs but also prove the theory of Hawking radiation. This thesis probes archival VERITAS data recorded between 2012 and 2021 for possible PBH signals. This work presents a new automatic approach to assess the quality of the VERITAS data. The array-trigger rate and far infrared temperature are well suited to identify periods with poor data quality. These are masked by time cuts to obtain a consistent and clean dataset which contains about 4222 hours. The PBH evaporations could occur at any location in the field of view or time within this data. Only a blind search can be performed to identify these short signals. This thesis implements a data-driven deep learning based method to search for short transient signals with VERITAS. It does not depend on the modelling of the effective area and radial acceptance. This work presents the first application of this method to actual observational IACT data. This thesis develops new concepts dealing with the specifics of the data and the transient detection method. These are reflected in the developed data preparation pipeline and search strategies. After correction for trial factors, no candidate PBH evaporation is found in the data. Thus, new constraints of the local rate of PBH evaporations are derived. At the 99\% confidence limit it is below <1.07 * 10^5 pc^-3 yr^-1. This constraint with the new, independent analysis approach is in the range of existing limits for the evaporation rate. This thesis also investigates an alternative novel approach to searching for PBHs with IACTs. Above the sublunar window, the PBH abundance is constrained by optical microlensing studies. The sampling speed, which is of order of minutes to hours for traditional optical telescopes, is a limiting factor in expanding the limits to lower masses. IACTs are also powerful instruments for fast transient optical astronomy with up to O(ns) sampling. This thesis investigates whether IACTs might constrain the sublunar window with optical microlensing observations. This study confirms that, in principle, the fast sampling speed might allow extending microlensing searches into the sublunar mass window. However, the limiting factor for IACTs is the modest sensitivity to detect changes in optical fluxes. This thesis presents the expected rate of detectable events for VERITAS as well as prospects of possible future next-generation IACTs. For VERITAS, the rate of detectable microlensing events in the sublunar range is ~10^-6 per year of observation time. The future prospects for a 100 times more sensitive instrument are at ~0.05 events per year.},
  language  = {en}
}
@phdthesis{Panzer2024,
  author    = {Panzer, Marcel},
  title     = {Design of a hyper-heuristics based control framework for modular production systems},
  doi       = {10.25932/publishup-63300},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-633006},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vi, 334},
  year      = {2024},
  abstract  = {Volatile supply and sales markets, coupled with increasing product individualization and complex production processes, present significant challenges for manufacturing companies. These must navigate and adapt to ever-shifting external and internal factors while ensuring robustness against process variabilities and unforeseen events. This has a pronounced impact on production control, which serves as the operational intersection between production planning and the shop- floor resources, and necessitates the capability to manage intricate process interdependencies effectively. Considering the increasing dynamics and product diversification, alongside the need to maintain constant production performances, the implementation of innovative control strategies becomes crucial. In recent years, the integration of Industry 4.0 technologies and machine learning methods has gained prominence in addressing emerging challenges in production applications. Within this context, this cumulative thesis analyzes deep learning based production systems based on five publications. Particular attention is paid to the applications of deep reinforcement learning, aiming to explore its potential in dynamic control contexts. Analysis reveal that deep reinforcement learning excels in various applications, especially in dynamic production control tasks. Its efficacy can be attributed to its interactive learning and real-time operational model. However, despite its evident utility, there are notable structural, organizational, and algorithmic gaps in the prevailing research. A predominant portion of deep reinforcement learning based approaches is limited to specific job shop scenarios and often overlooks the potential synergies in combined resources. Furthermore, it highlights the rare implementation of multi-agent systems and semi-heterarchical systems in practical settings. A notable gap remains in the integration of deep reinforcement learning into a hyper-heuristic. To bridge these research gaps, this thesis introduces a deep reinforcement learning based hyper- heuristic for the control of modular production systems, developed in accordance with the design science research methodology. Implemented within a semi-heterarchical multi-agent framework, this approach achieves a threefold reduction in control and optimisation complexity while ensuring high scalability, adaptability, and robustness of the system. In comparative benchmarks, this control methodology outperforms rule-based heuristics, reducing throughput times and tardiness, and effectively incorporates customer and order-centric metrics. The control artifact facilitates a rapid scenario generation, motivating for further research efforts and bridging the gap to real-world applications. The overarching goal is to foster a synergy between theoretical insights and practical solutions, thereby enriching scientific discourse and addressing current industrial challenges.},
  language  = {en}
}
@phdthesis{Lilienkamp2024,
  author    = {Lilienkamp, Henning},
  title     = {Enhanced computational approaches for data-driven characterization of earthquake ground motion and rapid earthquake impact assessment},
  doi       = {10.25932/publishup-63195},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-631954},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 145},
  year      = {2024},
  abstract  = {Rapidly growing seismic and macroseismic databases and simplified access to advanced machine learning methods have in recent years opened up vast opportunities to address challenges in engineering and strong motion seismology from novel, datacentric perspectives. In this thesis, I explore the opportunities of such perspectives for the tasks of ground motion modeling and rapid earthquake impact assessment, tasks with major implications for long-term earthquake disaster mitigation. In my first study, I utilize the rich strong motion database from the Kanto basin, Japan, and apply the U-Net artificial neural network architecture to develop a deep learning based ground motion model. The operational prototype provides statistical estimates of expected ground shaking, given descriptions of a specific earthquake source, wave propagation paths, and geophysical site conditions. The U-Net interprets ground motion data in its spatial context, potentially taking into account, for example, the geological properties in the vicinity of observation sites. Predictions of ground motion intensity are thereby calibrated to individual observation sites and earthquake locations. The second study addresses the explicit incorporation of rupture forward directivity into ground motion modeling. Incorporation of this phenomenon, causing strong, pulse like ground shaking in the vicinity of earthquake sources, is usually associated with an intolerable increase in computational demand during probabilistic seismic hazard analysis (PSHA) calculations. I suggest an approach in which I utilize an artificial neural network to efficiently approximate the average, directivity-related adjustment to ground motion predictions for earthquake ruptures from the 2022 New Zealand National Seismic Hazard Model. The practical implementation in an actual PSHA calculation demonstrates the efficiency and operational readiness of my model. In a follow-up study, I present a proof of concept for an alternative strategy in which I target the generalizing applicability to ruptures other than those from the New Zealand National Seismic Hazard Model. In the third study, I address the usability of pseudo-intensity reports obtained from macroseismic observations by non-expert citizens for rapid impact assessment. I demonstrate that the statistical properties of pseudo-intensity collections describing the intensity of shaking are correlated with the societal impact of earthquakes. In a second step, I develop a probabilistic model that, within minutes of an event, quantifies the probability of an earthquake to cause considerable societal impact. Under certain conditions, such a quick and preliminary method might be useful to support decision makers in their efforts to organize auxiliary measures for earthquake disaster response while results from more elaborate impact assessment frameworks are not yet available. The application of machine learning methods to datasets that only partially reveal characteristics of Big Data, qualify the majority of results obtained in this thesis as explorative insights rather than ready-to-use solutions to real world problems. The practical usefulness of this work will be better assessed in the future by applying the approaches developed to growing and increasingly complex data sets.},
  language  = {en}
}