@article{BaerenzungHolschneiderWichtetal.2018, author = {B{\"a}renzung, Julien and Holschneider, Matthias and Wicht, Johannes and Sanchez, Sabrina and Lesur, Vincent}, title = {Modeling and predicting the short-term evolution of the geomagnetic field}, series = {Journal of geophysical research : Solid earth}, volume = {123}, journal = {Journal of geophysical research : Solid earth}, number = {6}, publisher = {American Geophysical Union}, address = {Washington}, issn = {2169-9313}, doi = {10.1029/2017JB015115}, pages = {4539 -- 4560}, year = {2018}, abstract = {We propose a reduced dynamical system describing the coupled evolution of fluid flow and magnetic field at the top of the Earth's core between the years 1900 and 2014. The flow evolution is modeled with a first-order autoregressive process, while the magnetic field obeys the classical frozen flux equation. An ensemble Kalman filter algorithm serves to constrain the dynamics with the geomagnetic field and its secular variation given by the COV-OBS.x1 model. Using a large ensemble with 40,000 members provides meaningful statistics including reliable error estimates. The model highlights two distinct flow scales. Slowly varying large-scale elements include the already documented eccentric gyre. Localized short-lived structures include distinctly ageostophic features like the high-latitude polar jet on the Northern Hemisphere. Comparisons with independent observations of the length-of-day variations not only validate the flow estimates but also suggest an acceleration of the geostrophic flows over the last century. Hindcasting tests show that our model outperforms simpler predictions bases (linear extrapolation and stationary flow). The predictability limit, of about 2,000 years for the magnetic dipole component, is mostly determined by the random fast varying dynamics of the flow and much less by the geomagnetic data quality or lack of small-scale information.}, language = {en} } @article{ChristakoudiTsilidisMulleretal.2020, author = {Christakoudi, Sofa and Tsilidis, Konstantinos K. and Muller, David C. and Freisling, Heinz and Weiderpass, Elisabete and Overvad, Kim and S{\"o}derberg, Stefan and H{\"a}ggstr{\"o}m, Christel and Pischon, Tobias and Dahm, Christina C. and Zhang, Jie and Tj{\o}nneland, Anne and Schulze, Matthias Bernd}, title = {A Body Shape Index (ABSI) achieves better mortality risk stratification than alternative indices of abdominal obesity: results from a large European cohort}, series = {Scientific Reports}, volume = {10}, journal = {Scientific Reports}, number = {1}, publisher = {Springer Nature}, address = {Berlin}, pages = {15}, year = {2020}, abstract = {Abdominal and general adiposity are independently associated with mortality, but there is no consensus on how best to assess abdominal adiposity. We compared the ability of alternative waist indices to complement body mass index (BMI) when assessing all-cause mortality. We used data from 352,985 participants in the European Prospective Investigation into Cancer and Nutrition (EPIC) and Cox proportional hazards models adjusted for other risk factors. During a mean follow-up of 16.1 years, 38,178 participants died. Combining in one model BMI and a strongly correlated waist index altered the association patterns with mortality, to a predominantly negative association for BMI and a stronger positive association for the waist index, while combining BMI with the uncorrelated A Body Shape Index (ABSI) preserved the association patterns. Sex-specific cohort-wide quartiles of waist indices correlated with BMI could not separate high-risk from low-risk individuals within underweight (BMI<18.5 kg/m(2)) or obese (BMI30 kg/m(2)) categories, while the highest quartile of ABSI separated 18-39\% of the individuals within each BMI category, which had 22-55\% higher risk of death. In conclusion, only a waist index independent of BMI by design, such as ABSI, complements BMI and enables efficient risk stratification, which could facilitate personalisation of screening, treatment and monitoring.}, language = {en} } @misc{ChristakoudiTsilidisMulleretal.2020, author = {Christakoudi, Sofa and Tsilidis, Konstantinos K. and Muller, David C. and Freisling, Heinz and Weiderpass, Elisabete and Overvad, Kim and S{\"o}derberg, Stefan and H{\"a}ggstr{\"o}m, Christel and Pischon, Tobias and Dahm, Christina C. and Zhang, Jie and Tj{\o}nneland, Anne and Schulze, Matthias Bernd}, title = {A Body Shape Index (ABSI) achieves better mortality risk stratification than alternative indices of abdominal obesity: results from a large European cohort}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {1}, issn = {1866-8372}, doi = {10.25932/publishup-52582}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-525827}, pages = {17}, year = {2020}, abstract = {Abdominal and general adiposity are independently associated with mortality, but there is no consensus on how best to assess abdominal adiposity. We compared the ability of alternative waist indices to complement body mass index (BMI) when assessing all-cause mortality. We used data from 352,985 participants in the European Prospective Investigation into Cancer and Nutrition (EPIC) and Cox proportional hazards models adjusted for other risk factors. During a mean follow-up of 16.1 years, 38,178 participants died. Combining in one model BMI and a strongly correlated waist index altered the association patterns with mortality, to a predominantly negative association for BMI and a stronger positive association for the waist index, while combining BMI with the uncorrelated A Body Shape Index (ABSI) preserved the association patterns. Sex-specific cohort-wide quartiles of waist indices correlated with BMI could not separate high-risk from low-risk individuals within underweight (BMI<18.5 kg/m(2)) or obese (BMI30 kg/m(2)) categories, while the highest quartile of ABSI separated 18-39\% of the individuals within each BMI category, which had 22-55\% higher risk of death. In conclusion, only a waist index independent of BMI by design, such as ABSI, complements BMI and enables efficient risk stratification, which could facilitate personalisation of screening, treatment and monitoring.}, language = {en} } @misc{CiemerRehmKurthsetal.2020, author = {Ciemer, Catrin and Rehm, Lars and Kurths, J{\"u}rgen and Donner, Reik Volker and Winkelmann, Ricarda and Boers, Niklas}, title = {An early-warning indicator for Amazon droughts exclusively based on tropical Atlantic sea surface temperatures}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {9}, issn = {1866-8372}, doi = {10.25932/publishup-52586}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-525863}, pages = {12}, year = {2020}, abstract = {Droughts in tropical South America have an imminent and severe impact on the Amazon rainforest and affect the livelihoods of millions of people. Extremely dry conditions in Amazonia have been previously linked to sea surface temperature (SST) anomalies in the adjacent tropical oceans. Although the sources and impacts of such droughts have been widely studied, establishing reliable multi-year lead statistical forecasts of their occurrence is still an ongoing challenge. Here, we further investigate the relationship between SST and rainfall anomalies using a complex network approach. We identify four ocean regions which exhibit the strongest overall SST correlations with central Amazon rainfall, including two particularly prominent regions in the northern and southern tropical Atlantic. Based on the time-dependent correlation between SST anomalies in these two regions alone, we establish a new early-warning method for droughts in the central Amazon basin and demonstrate its robustness in hindcasting past major drought events with lead-times up to 18 months.}, language = {en} } @article{CiemerRehmKurthsetal.2020, author = {Ciemer, Catrin and Rehm, Lars and Kurths, J{\"u}rgen and Donner, Reik Volker and Winkelmann, Ricarda and Boers, Niklas}, title = {An early-warning indicator for Amazon droughts exclusively based on tropical Atlantic sea surface temperatures}, series = {Environmental Research Letters}, volume = {15}, journal = {Environmental Research Letters}, number = {9}, publisher = {IOP - Institute of Physics Publishing}, address = {Bristol}, pages = {10}, year = {2020}, abstract = {Droughts in tropical South America have an imminent and severe impact on the Amazon rainforest and affect the livelihoods of millions of people. Extremely dry conditions in Amazonia have been previously linked to sea surface temperature (SST) anomalies in the adjacent tropical oceans. Although the sources and impacts of such droughts have been widely studied, establishing reliable multi-year lead statistical forecasts of their occurrence is still an ongoing challenge. Here, we further investigate the relationship between SST and rainfall anomalies using a complex network approach. We identify four ocean regions which exhibit the strongest overall SST correlations with central Amazon rainfall, including two particularly prominent regions in the northern and southern tropical Atlantic. Based on the time-dependent correlation between SST anomalies in these two regions alone, we establish a new early-warning method for droughts in the central Amazon basin and demonstrate its robustness in hindcasting past major drought events with lead-times up to 18 months.}, language = {en} } @phdthesis{Elsaid2022, author = {Elsaid, Mohamed Esameldin Mohamed}, title = {Virtual machines live migration cost modeling and prediction}, doi = {10.25932/publishup-54001}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-540013}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 107}, year = {2022}, abstract = {Dynamic resource management is an essential requirement for private and public cloud computing environments. With dynamic resource management, the physical resources assignment to the cloud virtual resources depends on the actual need of the applications or the running services, which enhances the cloud physical resources utilization and reduces the offered services cost. In addition, the virtual resources can be moved across different physical resources in the cloud environment without an obvious impact on the running applications or services production. This means that the availability of the running services and applications in the cloud is independent on the hardware resources including the servers, switches and storage failures. This increases the reliability of using cloud services compared to the classical data-centers environments. In this thesis we briefly discuss the dynamic resource management topic and then deeply focus on live migration as the definition of the compute resource dynamic management. Live migration is a commonly used and an essential feature in cloud and virtual data-centers environments. Cloud computing load balance, power saving and fault tolerance features are all dependent on live migration to optimize the virtual and physical resources usage. As we will discuss in this thesis, live migration shows many benefits to cloud and virtual data-centers environments, however the cost of live migration can not be ignored. Live migration cost includes the migration time, downtime, network overhead, power consumption increases and CPU overhead. IT admins run virtual machines live migrations without an idea about the migration cost. So, resources bottlenecks, higher migration cost and migration failures might happen. The first problem that we discuss in this thesis is how to model the cost of the virtual machines live migration. Secondly, we investigate how to make use of machine learning techniques to help the cloud admins getting an estimation of this cost before initiating the migration for one of multiple virtual machines. Also, we discuss the optimal timing for a specific virtual machine before live migration to another server. Finally, we propose practical solutions that can be used by the cloud admins to be integrated with the cloud administration portals to answer the raised research questions above. Our research methodology to achieve the project objectives is to propose empirical models based on using VMware test-beds with different benchmarks tools. Then we make use of the machine learning techniques to propose a prediction approach for virtual machines live migration cost. Timing optimization for live migration is also proposed in this thesis based on using the cost prediction and data-centers network utilization prediction. Live migration with persistent memory clusters is also discussed at the end of the thesis. The cost prediction and timing optimization techniques proposed in this thesis could be practically integrated with VMware vSphere cluster portal such that the IT admins can now use the cost prediction feature and timing optimization option before proceeding with a virtual machine live migration. Testing results show that our proposed approach for VMs live migration cost prediction shows acceptable results with less than 20\% prediction error and can be easily implemented and integrated with VMware vSphere as an example of a commonly used resource management portal for virtual data-centers and private cloud environments. The results show that using our proposed VMs migration timing optimization technique also could save up to 51\% of migration time of the VMs migration time for memory intensive workloads and up to 27\% of the migration time for network intensive workloads. This timing optimization technique can be useful for network admins to save migration time with utilizing higher network rate and higher probability of success. At the end of this thesis, we discuss the persistent memory technology as a new trend in servers memory technology. Persistent memory modes of operation and configurations are discussed in detail to explain how live migration works between servers with different memory configuration set up. Then, we build a VMware cluster with persistent memory inside server and also with DRAM only servers to show the live migration cost difference between the VMs with DRAM only versus the VMs with persistent memory inside.}, language = {en} } @phdthesis{GamezLopez2006, author = {G{\´a}mez L{\´o}pez, Antonio Juan}, title = {Application of nonlinear dimensionality reduction to climate data for prediction}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-10956}, school = {Universit{\"a}t Potsdam}, year = {2006}, abstract = {This Thesis was devoted to the study of the coupled system composed by El Ni{\~n}o/Southern Oscillation and the Annual Cycle. More precisely, the work was focused on two main problems: 1. How to separate both oscillations into an affordable model for understanding the behaviour of the whole system. 2. How to model the system in order to achieve a better understanding of the interaction, as well as to predict future states of the system. We focused our efforts in the Sea Surface Temperature equations, considering that atmospheric effects were secondary to the ocean dynamics. The results found may be summarised as follows: 1. Linear methods are not suitable for characterising the dimensionality of the sea surface temperature in the tropical Pacific Ocean. Therefore they do not help to separate the oscillations by themselves. Instead, nonlinear methods of dimensionality reduction are proven to be better in defining a lower limit for the dimensionality of the system as well as in explaining the statistical results in a more physical way [1]. In particular, Isomap, a nonlinear modification of Multidimensional Scaling methods, provides a physically appealing method of decomposing the data, as it substitutes the euclidean distances in the manifold by an approximation of the geodesic distances. We expect that this method could be successfully applied to other oscillatory extended systems and, in particular, to meteorological systems. 2. A three dimensional dynamical system could be modeled, using a backfitting algorithm, for describing the dynamics of the sea surface temperature in the tropical Pacific Ocean. We observed that, although there were few data points available, we could predict future behaviours of the coupled ENSO-Annual Cycle system with an accuracy of less than six months, although the constructed system presented several drawbacks: few data points to input in the backfitting algorithm, untrained model, lack of forcing with external data and simplification using a close system. Anyway, ensemble prediction techniques showed that the prediction skills of the three dimensional time series were as good as those found in much more complex models. This suggests that the climatological system in the tropics is mainly explained by ocean dynamics, while the atmosphere plays a secondary role in the physics of the process. Relevant predictions for short lead times can be made using a low dimensional system, despite its simplicity. The analysis of the SST data suggests that nonlinear interaction between the oscillations is small, and that noise plays a secondary role in the fundamental dynamics of the oscillations [2]. A global view of the work shows a general procedure to face modeling of climatological systems. First, we should find a suitable method of either linear or nonlinear dimensionality reduction. Then, low dimensional time series could be extracted out of the method applied. Finally, a low dimensional model could be found using a backfitting algorithm in order to predict future states of the system.}, subject = {Nichtlineare Dynamik}, language = {en} } @phdthesis{Haider2013, author = {Haider, Peter}, title = {Prediction with Mixture Models}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69617}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Learning a model for the relationship between the attributes and the annotated labels of data examples serves two purposes. Firstly, it enables the prediction of the label for examples without annotation. Secondly, the parameters of the model can provide useful insights into the structure of the data. If the data has an inherent partitioned structure, it is natural to mirror this structure in the model. Such mixture models predict by combining the individual predictions generated by the mixture components which correspond to the partitions in the data. Often the partitioned structure is latent, and has to be inferred when learning the mixture model. Directly evaluating the accuracy of the inferred partition structure is, in many cases, impossible because the ground truth cannot be obtained for comparison. However it can be assessed indirectly by measuring the prediction accuracy of the mixture model that arises from it. This thesis addresses the interplay between the improvement of predictive accuracy by uncovering latent cluster structure in data, and further addresses the validation of the estimated structure by measuring the accuracy of the resulting predictive model. In the application of filtering unsolicited emails, the emails in the training set are latently clustered into advertisement campaigns. Uncovering this latent structure allows filtering of future emails with very low false positive rates. In order to model the cluster structure, a Bayesian clustering model for dependent binary features is developed in this thesis. Knowing the clustering of emails into campaigns can also aid in uncovering which emails have been sent on behalf of the same network of captured hosts, so-called botnets. This association of emails to networks is another layer of latent clustering. Uncovering this latent structure allows service providers to further increase the accuracy of email filtering and to effectively defend against distributed denial-of-service attacks. To this end, a discriminative clustering model is derived in this thesis that is based on the graph of observed emails. The partitionings inferred using this model are evaluated through their capacity to predict the campaigns of new emails. Furthermore, when classifying the content of emails, statistical information about the sending server can be valuable. Learning a model that is able to make use of it requires training data that includes server statistics. In order to also use training data where the server statistics are missing, a model that is a mixture over potentially all substitutions thereof is developed. Another application is to predict the navigation behavior of the users of a website. Here, there is no a priori partitioning of the users into clusters, but to understand different usage scenarios and design different layouts for them, imposing a partitioning is necessary. The presented approach simultaneously optimizes the discriminative as well as the predictive power of the clusters. Each model is evaluated on real-world data and compared to baseline methods. The results show that explicitly modeling the assumptions about the latent cluster structure leads to improved predictions compared to the baselines. It is beneficial to incorporate a small number of hyperparameters that can be tuned to yield the best predictions in cases where the prediction accuracy can not be optimized directly.}, language = {en} } @article{HartmannEhlertFritz2019, author = {Hartmann, Julia and Ehlert, Antje and Fritz, Annemarie}, title = {Welche Rolle spielen sprachliche Parameter f{\"u}r die Entwicklung integrierter verbal-numerischer Konzepte im vierten Lebensjahr?}, series = {Fr{\"u}he Bildung : interdisziplin{\"a}re Zeitschrift f{\"u}r Forschung, Ausbildung und Praxis}, volume = {8}, journal = {Fr{\"u}he Bildung : interdisziplin{\"a}re Zeitschrift f{\"u}r Forschung, Ausbildung und Praxis}, number = {1}, publisher = {Hogrefe}, address = {G{\"o}ttingen}, issn = {2191-9186}, doi = {10.1026/2191-9186/a000410}, pages = {44 -- 52}, year = {2019}, abstract = {Der Beitrag untersucht, ob und zu welchen Anteilen fr{\"u}he sprachliche Kompetenzen numerische Kompetenzen vorhersagen. An 72 dreij{\"a}hrigen Kindern wurden numerische, verbal produktive und rezeptive sowie grammatische Leistungen zwei Mal im Abstand von drei Monaten erhoben. Mithilfe von Strukturgleichungsmodellen kann gezeigt werden, dass sprachliche und numerische Leistungen in diesem Alter noch wenig distinkt sind. F{\"u}r die numerischen Kompetenzen findet sich bereits in diesem Alter eine hohe interindividuelle Entwicklungsstabilit{\"a}t. Ein bedeutsamer Einfluss sprachlicher Kompetenz auf den Zuwachs mathematischer Kompetenz im vierten Lebensjahr konnte nicht nachgewiesen werden. Wir diskutieren die Ergebnisse vor dem Hintergrund der aktuellen Thesen zum Zusammenhang von Sprache und Numerik in der Entwicklung.}, language = {de} } @misc{HischeLarhlimiSchwarzetal.2012, author = {Hische, Manuela and Larhlimi, Abdelhalim and Schwarz, Franziska and Fischer-Rosinsk{\´y}, Antje and Bobbert, Thomas and Assmann, Anke and Catchpole, Gareth S. and Pfeiffer, Andreas F. H. and Willmitzer, Lothar and Selbig, Joachim and Spranger, Joachim}, title = {A distinct metabolic signature predictsdevelopment of fasting plasma glucose}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {850}, issn = {1866-8372}, doi = {10.25932/publishup-42740}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-427400}, pages = {12}, year = {2012}, abstract = {Background High blood glucose and diabetes are amongst the conditions causing the greatest losses in years of healthy life worldwide. Therefore, numerous studies aim to identify reliable risk markers for development of impaired glucose metabolism and type 2 diabetes. However, the molecular basis of impaired glucose metabolism is so far insufficiently understood. The development of so called 'omics' approaches in the recent years promises to identify molecular markers and to further understand the molecular basis of impaired glucose metabolism and type 2 diabetes. Although univariate statistical approaches are often applied, we demonstrate here that the application of multivariate statistical approaches is highly recommended to fully capture the complexity of data gained using high-throughput methods. Methods We took blood plasma samples from 172 subjects who participated in the prospective Metabolic Syndrome Berlin Potsdam follow-up study (MESY-BEPO Follow-up). We analysed these samples using Gas Chromatography coupled with Mass Spectrometry (GC-MS), and measured 286 metabolites. Furthermore, fasting glucose levels were measured using standard methods at baseline, and after an average of six years. We did correlation analysis and built linear regression models as well as Random Forest regression models to identify metabolites that predict the development of fasting glucose in our cohort. Results We found a metabolic pattern consisting of nine metabolites that predicted fasting glucose development with an accuracy of 0.47 in tenfold cross-validation using Random Forest regression. We also showed that adding established risk markers did not improve the model accuracy. However, external validation is eventually desirable. Although not all metabolites belonging to the final pattern are identified yet, the pattern directs attention to amino acid metabolism, energy metabolism and redox homeostasis. Conclusions We demonstrate that metabolites identified using a high-throughput method (GC-MS) perform well in predicting the development of fasting plasma glucose over several years. Notably, not single, but a complex pattern of metabolites propels the prediction and therefore reflects the complexity of the underlying molecular mechanisms. This result could only be captured by application of multivariate statistical approaches. Therefore, we highly recommend the usage of statistical methods that seize the complexity of the information given by high-throughput methods.}, language = {en} } @phdthesis{Jaeger2015, author = {J{\"a}ger, Lena Ann}, title = {Working memory and prediction in human sentence parsing}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-82517}, school = {Universit{\"a}t Potsdam}, pages = {xi, 144}, year = {2015}, abstract = {This dissertation investigates the working memory mechanism subserving human sentence processing and its relative contribution to processing difficulty as compared to syntactic prediction. Within the last decades, evidence for a content-addressable memory system underlying human cognition in general has accumulated (e.g., Anderson et al., 2004). In sentence processing research, it has been proposed that this general content-addressable architecture is also used for language processing (e.g., McElree, 2000). Although there is a growing body of evidence from various kinds of linguistic dependencies that is consistent with a general content-addressable memory subserving sentence processing (e.g., McElree et al., 2003; VanDyke2006), the case of reflexive-antecedent dependencies has challenged this view. It has been proposed that in the processing of reflexive-antecedent dependencies, a syntactic-structure based memory access is used rather than cue-based retrieval within a content-addressable framework (e.g., Sturt, 2003). Two eye-tracking experiments on Chinese reflexives were designed to tease apart accounts assuming a syntactic-structure based memory access mechanism from cue-based retrieval (implemented in ACT-R as proposed by Lewis and Vasishth (2005). In both experiments, interference effects were observed from noun phrases which syntactically do not qualify as the reflexive's antecedent but match the animacy requirement the reflexive imposes on its antecedent. These results are interpreted as evidence against a purely syntactic-structure based memory access. However, the exact pattern of effects observed in the data is only partially compatible with the Lewis and Vasishth cue-based parsing model. Therefore, an extension of the Lewis and Vasishth model is proposed. Two principles are added to the original model, namely 'cue confusion' and 'distractor prominence'. Although interference effects are generally interpreted in favor of a content-addressable memory architecture, an alternative explanation for interference effects in reflexive processing has been proposed which, crucially, might reconcile interference effects with a structure-based account. It has been argued that interference effects do not necessarily reflect cue-based retrieval interference in a content-addressable memory but might equally well be accounted for by interference effects which have already occurred at the moment of encoding the antecedent in memory (Dillon, 2011). Three experiments (eye-tracking and self-paced reading) on German reflexives and Swedish possessives were designed to tease apart cue-based retrieval interference from encoding interference. The results of all three experiments suggest that there is no evidence that encoding interference affects the retrieval of a reflexive's antecedent. Taken together, these findings suggest that the processing of reflexives can be explained with the same cue-based retrieval mechanism that has been invoked to explain syntactic dependency resolution in a range of other structures. This supports the view that the language processing system is located within a general cognitive architecture, with a general-purpose content-addressable working memory system operating on linguistic expressions. Finally, two experiments (self-paced reading and eye-tracking) using Chinese relative clauses were conducted to determine the relative contribution to sentence processing difficulty of working-memory processes as compared to syntactic prediction during incremental parsing. Chinese has the cross-linguistically rare property of being a language with subject-verb-object word order and pre-nominal relative clauses. This property leads to opposing predictions of expectation-based accounts and memory-based accounts with respect to the relative processing difficulty of subject vs. object relatives. Previous studies showed contradictory results, which has been attributed to different kinds local ambiguities confounding the materials (Lin and Bever, 2011). The two experiments presented are the first to compare Chinese relatives clauses in syntactically unambiguous contexts. The results of both experiments were consistent with the predictions of the expectation-based account of sentence processing but not with the memory-based account. From these findings, I conclude that any theory of human sentence processing needs to take into account the power of predictive processes unfolding in the human mind.}, language = {en} } @misc{KaminskiSchlagenhaufRappetal.2018, author = {Kaminski, Jakob A. and Schlagenhauf, Florian and Rapp, Michael A. and Awasthi, Swapnil and Ruggeri, Barbara and Deserno, Lorenz and Banaschewski, Tobias and Bokde, Arun L. W. and Bromberg, Uli and B{\"u}chel, Christian and Quinlan, Erin Burke and Desrivi{\`e}res, Sylvane and Flor, Herta and Frouin, Vincent and Garavan, Hugh and Gowland, Penny and Ittermann, Bernd and Martinot, Jean-Luc and Paill{\`e}re Martinot, Marie-Laure and Nees, Frauke and Papadopoulos Orfanos, Dimitri and Paus, Tom{\´a}š and Poustka, Luise and Smolka, Michael N. and Fr{\"o}hner, Juliane H. and Walter, Henrik and Whelan, Robert and Ripke, Stephan and Schumann, Gunter and Heinz, Andreas}, title = {Epigenetic variance in dopamine D2 receptor}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {950}, issn = {1866-8372}, doi = {10.25932/publishup-42568}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-425687}, pages = {13}, year = {2018}, abstract = {Genetic and environmental factors both contribute to cognitive test performance. A substantial increase in average intelligence test results in the second half of the previous century within one generation is unlikely to be explained by genetic changes. One possible explanation for the strong malleability of cognitive performance measure is that environmental factors modify gene expression via epigenetic mechanisms. Epigenetic factors may help to understand the recent observations of an association between dopamine-dependent encoding of reward prediction errors and cognitive capacity, which was modulated by adverse life events. The possible manifestation of malleable biomarkers contributing to variance in cognitive test performance, and thus possibly contributing to the "missing heritability" between estimates from twin studies and variance explained by genetic markers, is still unclear. Here we show in 1475 healthy adolescents from the IMaging and GENetics (IMAGEN) sample that general IQ (gIQ) is associated with (1) polygenic scores for intelligence, (2) epigenetic modification of DRD2 gene, (3) gray matter density in striatum, and (4) functional striatal activation elicited by temporarily surprising reward-predicting cues. Comparing the relative importance for the prediction of gIQ in an overlapping subsample, our results demonstrate neurobiological correlates of the malleability of gIQ and point to equal importance of genetic variance, epigenetic modification of DRD2 receptor gene, as well as functional striatal activation, known to influence dopamine neurotransmission. Peripheral epigenetic markers are in need of confirmation in the central nervous system and should be tested in longitudinal settings specifically assessing individual and environmental factors that modify epigenetic structure.}, language = {en} } @misc{KisslingDormannGroeneveldetal.2012, author = {Kissling, W. D. and Dormann, Carsten F. and Groeneveld, Juergen and Hickler, Thomas and K{\"u}hn, Ingolf and McInerny, Greg J. and Montoya, Jose M. and R{\"o}mermann, Christine and Schiffers, Katja and Schurr, Frank Martin and Singer, Alexander and Svenning, Jens-Christian and Zimmermann, Niklaus E. and O'Hara, Robert B.}, title = {Towards novel approaches to modelling biotic interactions in multispecies assemblages at large spatial extents}, series = {Journal of biogeography}, volume = {39}, journal = {Journal of biogeography}, number = {12}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {0305-0270}, doi = {10.1111/j.1365-2699.2011.02663.x}, pages = {2163 -- 2178}, year = {2012}, abstract = {Aim Biotic interactions within guilds or across trophic levels have widely been ignored in species distribution models (SDMs). This synthesis outlines the development of species interaction distribution models (SIDMs), which aim to incorporate multispecies interactions at large spatial extents using interaction matrices. Location Local to global. Methods We review recent approaches for extending classical SDMs to incorporate biotic interactions, and identify some methodological and conceptual limitations. To illustrate possible directions for conceptual advancement we explore three principal ways of modelling multispecies interactions using interaction matrices: simple qualitative linkages between species, quantitative interaction coefficients reflecting interaction strengths, and interactions mediated by interaction currencies. We explain methodological advancements for static interaction data and multispecies time series, and outline methods to reduce complexity when modelling multispecies interactions. Results Classical SDMs ignore biotic interactions and recent SDM extensions only include the unidirectional influence of one or a few species. However, novel methods using error matrices in multivariate regression models allow interactions between multiple species to be modelled explicitly with spatial co-occurrence data. If time series are available, multivariate versions of population dynamic models can be applied that account for the effects and relative importance of species interactions and environmental drivers. These methods need to be extended by incorporating the non-stationarity in interaction coefficients across space and time, and are challenged by the limited empirical knowledge on spatio-temporal variation in the existence and strength of species interactions. Model complexity may be reduced by: (1) using prior ecological knowledge to set a subset of interaction coefficients to zero, (2) modelling guilds and functional groups rather than individual species, and (3) modelling interaction currencies and species effect and response traits. Main conclusions There is great potential for developing novel approaches that incorporate multispecies interactions into the projection of species distributions and community structure at large spatial extents. Progress can be made by: (1) developing statistical models with interaction matrices for multispecies co-occurrence datasets across large-scale environmental gradients, (2) testing the potential and limitations of methods for complexity reduction, and (3) sampling and monitoring comprehensive spatio-temporal data on biotic interactions in multispecies communities.}, language = {en} } @misc{Korup2020, author = {Korup, Oliver}, title = {Bayesian geomorphology}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {1}, issn = {1866-8372}, doi = {10.25932/publishup-53989}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-539892}, pages = {24}, year = {2020}, abstract = {The rapidly growing amount and diversity of data are confronting us more than ever with the need to make informed predictions under uncertainty. The adverse impacts of climate change and natural hazards also motivate our search for reliable predictions. The range of statistical techniques that geomorphologists use to tackle this challenge has been growing, but rarely involves Bayesian methods. Instead, many geomorphic models rely on estimated averages that largely miss out on the variability of form and process. Yet seemingly fixed estimates of channel heads, sediment rating curves or glacier equilibrium lines, for example, are all prone to uncertainties. Neighbouring scientific disciplines such as physics, hydrology or ecology have readily embraced Bayesian methods to fully capture and better explain such uncertainties, as the necessary computational tools have advanced greatly. The aim of this article is to introduce the Bayesian toolkit to scientists concerned with Earth surface processes and landforms, and to show how geomorphic models might benefit from probabilistic concepts. I briefly review the use of Bayesian reasoning in geomorphology, and outline the corresponding variants of regression and classification in several worked examples.}, language = {en} } @article{Korup2020, author = {Korup, Oliver}, title = {Bayesian geomorphology}, series = {Earth surface processes and landforms : the journal of the British Geomorphological Research Group}, volume = {46}, journal = {Earth surface processes and landforms : the journal of the British Geomorphological Research Group}, number = {1}, publisher = {Wiley}, address = {Hoboken}, issn = {0197-9337}, doi = {10.1002/esp.4995}, pages = {151 -- 172}, year = {2020}, abstract = {The rapidly growing amount and diversity of data are confronting us more than ever with the need to make informed predictions under uncertainty. The adverse impacts of climate change and natural hazards also motivate our search for reliable predictions. The range of statistical techniques that geomorphologists use to tackle this challenge has been growing, but rarely involves Bayesian methods. Instead, many geomorphic models rely on estimated averages that largely miss out on the variability of form and process. Yet seemingly fixed estimates of channel heads, sediment rating curves or glacier equilibrium lines, for example, are all prone to uncertainties. Neighbouring scientific disciplines such as physics, hydrology or ecology have readily embraced Bayesian methods to fully capture and better explain such uncertainties, as the necessary computational tools have advanced greatly. The aim of this article is to introduce the Bayesian toolkit to scientists concerned with Earth surface processes and landforms, and to show how geomorphic models might benefit from probabilistic concepts. I briefly review the use of Bayesian reasoning in geomorphology, and outline the corresponding variants of regression and classification in several worked examples.}, language = {en} } @article{MooijTrolleJeppesenetal.2010, author = {Mooij, Wolf M. and Trolle, Dennis and Jeppesen, Erik and Arhonditsis, George B. and Belolipetsky, Pavel V. and Chitamwebwa, Deonatus B. R. and Degermendzhy, Andrey G. and DeAngelis, Donald L. and Domis, Lisette Nicole de Senerpont and Downing, Andrea S. and Elliott, J. Alex and Fragoso Jr, Carlos Ruberto and Gaedke, Ursula and Genova, Svetlana N. and Gulati, Ramesh D. and H{\aa}kanson, Lars and Hamilton, David P. and Hipsey, Matthew R. and 't Hoen, Jochem and H{\"u}lsmann, Stephan and Los, F. Hans and Makler-Pick, Vardit and Petzoldt, Thomas and Prokopkin, Igor G. and Rinke, Karsten and Schep, Sebastiaan A. and Tominaga, Koji and Van Dam, Anne A. and Van Nes, Egbert H. and Wells, Scott A. and Janse, Jan H.}, title = {Challenges and opportunities for integrating lake ecosystem modelling approaches}, series = {Aquatic ecology}, volume = {44}, journal = {Aquatic ecology}, publisher = {Springer Science + Business Media B.V.}, address = {Dordrecht}, issn = {1573-5125}, doi = {10.1007/s10452-010-9339-3}, pages = {633 -- 667}, year = {2010}, abstract = {A large number and wide variety of lake ecosystem models have been developed and published during the past four decades. We identify two challenges for making further progress in this field. One such challenge is to avoid developing more models largely following the concept of others ('reinventing the wheel'). The other challenge is to avoid focusing on only one type of model, while ignoring new and diverse approaches that have become available ('having tunnel vision'). In this paper, we aim at improving the awareness of existing models and knowledge of concurrent approaches in lake ecosystem modelling, without covering all possible model tools and avenues. First, we present a broad variety of modelling approaches. To illustrate these approaches, we give brief descriptions of rather arbitrarily selected sets of specific models. We deal with static models (steady state and regression models), complex dynamic models (CAEDYM, CE-QUAL-W2, Delft 3D-ECO, LakeMab, LakeWeb, MyLake, PCLake, PROTECH, SALMO), structurally dynamic models and minimal dynamic models. We also discuss a group of approaches that could all be classified as individual based: super-individual models (Piscator, Charisma), physiologically structured models, stage-structured models and traitbased models. We briefly mention genetic algorithms, neural networks, Kalman filters and fuzzy logic. Thereafter, we zoom in, as an in-depth example, on the multi-decadal development and application of the lake ecosystem model PCLake and related models (PCLake Metamodel, Lake Shira Model, IPH-TRIM3D-PCLake). In the discussion, we argue that while the historical development of each approach and model is understandable given its 'leading principle', there are many opportunities for combining approaches. We take the point of view that a single 'right' approach does not exist and should not be strived for. Instead, multiple modelling approaches, applied concurrently to a given problem, can help develop an integrative view on the functioning of lake ecosystems. We end with a set of specific recommendations that may be of help in the further development of lake ecosystem models.}, language = {en} } @misc{MooijTrolleJeppesenetal.2010, author = {Mooij, Wolf M. and Trolle, Dennis and Jeppesen, Erik and Arhonditsis, George B. and Belolipetsky, Pavel V. and Chitamwebwa, Deonatus B. R. and Degermendzhy, Andrey G. and DeAngelis, Donald L. and Domis, Lisette Nicole de Senerpont and Downing, Andrea S. and Elliott, J. Alex and Fragoso Jr., Carlos Ruberto and Gaedke, Ursula and Genova, Svetlana N. and Gulati, Ramesh D. and H{\aa}kanson, Lars and Hamilton, David P. and Hipsey, Matthew R. and 't Hoen, Jochem and H{\"u}lsmann, Stephan and Los, F. Hans and Makler-Pick, Vardit and Petzoldt, Thomas and Prokopkin, Igor G. and Rinke, Karsten and Schep, Sebastiaan A. and Tominaga, Koji and Van Dam, Anne A. and Van Nes, Egbert H. and Wells, Scott A. and Janse, Jan H.}, title = {Challenges and opportunities for integrating lake ecosystem modelling approaches}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {1326}, issn = {1866-8372}, doi = {10.25932/publishup-42983}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-429839}, pages = {35}, year = {2010}, abstract = {A large number and wide variety of lake ecosystem models have been developed and published during the past four decades. We identify two challenges for making further progress in this field. One such challenge is to avoid developing more models largely following the concept of others ('reinventing the wheel'). The other challenge is to avoid focusing on only one type of model, while ignoring new and diverse approaches that have become available ('having tunnel vision'). In this paper, we aim at improving the awareness of existing models and knowledge of concurrent approaches in lake ecosystem modelling, without covering all possible model tools and avenues. First, we present a broad variety of modelling approaches. To illustrate these approaches, we give brief descriptions of rather arbitrarily selected sets of specific models. We deal with static models (steady state and regression models), complex dynamic models (CAEDYM, CE-QUAL-W2, Delft 3D-ECO, LakeMab, LakeWeb, MyLake, PCLake, PROTECH, SALMO), structurally dynamic models and minimal dynamic models. We also discuss a group of approaches that could all be classified as individual based: super-individual models (Piscator, Charisma), physiologically structured models, stage-structured models and traitbased models. We briefly mention genetic algorithms, neural networks, Kalman filters and fuzzy logic. Thereafter, we zoom in, as an in-depth example, on the multi-decadal development and application of the lake ecosystem model PCLake and related models (PCLake Metamodel, Lake Shira Model, IPH-TRIM3D-PCLake). In the discussion, we argue that while the historical development of each approach and model is understandable given its 'leading principle', there are many opportunities for combining approaches. We take the point of view that a single 'right' approach does not exist and should not be strived for. Instead, multiple modelling approaches, applied concurrently to a given problem, can help develop an integrative view on the functioning of lake ecosystems. We end with a set of specific recommendations that may be of help in the further development of lake ecosystem models.}, language = {en} } @misc{ProtGentileAndersonetal.2013, author = {Prot, Sara and Gentile, Douglas A. and Anderson, Craig A. and Suzuki, Kanae and Swing, Edward and Lim, Kam Ming and Horiuchi, Yukiko and Jelic, Margareta and Krah{\´e}, Barbara and Liuqing, Wei and Liau, Albert K. and Khoo, Angeline and Petrescu, Poesis Diana and Sakamoto, Akira and Tajima, Sachi and Toma, Roxana Andreea and Warburton, Wayne and Zhang, Xuemin and Lam, Ben Chun Pan}, title = {Long-term relations among prosocial-media use, empathy, and prosocial behavior}, series = {Postprints der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe}, number = {389}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-404136}, pages = {11}, year = {2013}, abstract = {Despite recent growth of research on the effects of prosocial media, processes underlying these effects are not well understood. Two studies explored theoretically relevant mediators and moderators of the effects of prosocial media on helping. Study 1 examined associations among prosocial- and violent-media use, empathy, and helping in samples from seven countries. Prosocial-media use was positively associated with helping. This effect was mediated by empathy and was similar across cultures. Study 2 explored longitudinal relations among prosocial-video-game use, violent-video-game use, empathy, and helping in a large sample of Singaporean children and adolescents measured three times across 2 years. Path analyses showed significant longitudinal effects of prosocial- and violent-video-game use on prosocial behavior through empathy. Latent-growth-curve modeling for the 2-year period revealed that change in video-game use significantly affected change in helping, and that this relationship was mediated by change in empathy.}, language = {en} } @article{ProtGentileAndersonetal.2014, author = {Prot, Sara and Gentile, Douglas A. and Anderson, Craig A. and Suzuki, Kanae and Swing, Edward and Lim, Kam Ming and Horiuchi, Yukiko and Jelic, Margareta and Krah{\´e}, Barbara and Wei Liuqing, and Liau, Albert K. and Khoo, Angeline and Petrescu, Poesis Diana and Sakamoto, Akira and Tajima, Sachi and Toma, Roxana Andreea and Warburton, Wayne and Zhang, Xuemin and Lam, Ben Chun Pan}, title = {Long-term relations among prosocial-media use, empathy, and prosocial behavior}, series = {Psychological science : research, theory, \& application in psychology and related sciences}, volume = {25}, journal = {Psychological science : research, theory, \& application in psychology and related sciences}, number = {2}, publisher = {Sage Publ.}, address = {Thousand Oaks}, issn = {0956-7976}, doi = {10.1177/0956797613503854}, pages = {358 -- 368}, year = {2014}, abstract = {Despite recent growth of research on the effects of prosocial media, processes underlying these effects are not well understood. Two studies explored theoretically relevant mediators and moderators of the effects of prosocial media on helping. Study 1 examined associations among prosocial- and violent-media use, empathy, and helping in samples from seven countries. Prosocial-media use was positively associated with helping. This effect was mediated by empathy and was similar across cultures. Study 2 explored longitudinal relations among prosocial-video-game use, violent-video-game use, empathy, and helping in a large sample of Singaporean children and adolescents measured three times across 2 years. Path analyses showed significant longitudinal effects of prosocial- and violent-video-game use on prosocial behavior through empathy. Latent-growth-curve modeling for the 2-year period revealed that change in video-game use significantly affected change in helping, and that this relationship was mediated by change in empathy.}, language = {en} } @phdthesis{Quade2018, author = {Quade, Markus}, title = {Symbolic regression for identification, prediction, and control of dynamical systems}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-419790}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 134}, year = {2018}, abstract = {In the present work, we use symbolic regression for automated modeling of dynamical systems. Symbolic regression is a powerful and general method suitable for data-driven identification of mathematical expressions. In particular, the structure and parameters of those expressions are identified simultaneously. We consider two main variants of symbolic regression: sparse regression-based and genetic programming-based symbolic regression. Both are applied to identification, prediction and control of dynamical systems. We introduce a new methodology for the data-driven identification of nonlinear dynamics for systems undergoing abrupt changes. Building on a sparse regression algorithm derived earlier, the model after the change is defined as a minimum update with respect to a reference model of the system identified prior to the change. The technique is successfully exemplified on the chaotic Lorenz system and the van der Pol oscillator. Issues such as computational complexity, robustness against noise and requirements with respect to data volume are investigated. We show how symbolic regression can be used for time series prediction. Again, issues such as robustness against noise and convergence rate are investigated us- ing the harmonic oscillator as a toy problem. In combination with embedding, we demonstrate the prediction of a propagating front in coupled FitzHugh-Nagumo oscillators. Additionally, we show how we can enhance numerical weather predictions to commercially forecast power production of green energy power plants. We employ symbolic regression for synchronization control in coupled van der Pol oscillators. Different coupling topologies are investigated. We address issues such as plausibility and stability of the control laws found. The toolkit has been made open source and is used in turbulence control applications. Genetic programming based symbolic regression is very versatile and can be adapted to many optimization problems. The heuristic-based algorithm allows for cost efficient optimization of complex tasks. We emphasize the ability of symbolic regression to yield white-box models. In contrast to black-box models, such models are accessible and interpretable which allows the usage of established tool chains.}, language = {en} }