BibSonomy publications for /http://www.bibsonomy.org/BibSonomy RSS feed for /2015-03-29T22:49:29+02:00Statistik für Human- und Sozialwissenschaftlerhttp://www.bibsonomy.org/bibtex/20b2dd5f3ea68182fe3640b8046462889/clemensbaierclemensbaier2015-03-29T22:26:04+02:00thesis <span class="authorEditorList"><a href="/author/Bortz">Jürgen Bortz</a>. </span><em>Springer Medizin Verlag, </em><em>Heidelberg, </em><em>6. edition, </em>(<em>2005</em>)Sun Mar 29 22:26:04 CEST 2015Heidelberg6.Statistik f{\"u}r Human- und Sozialwissenschaftler2005thesis Introduction to Machine Learninghttp://www.bibsonomy.org/bibtex/2697ffb3b7e245f062c40b55813b98038/clemensbaierclemensbaier2015-03-29T21:33:02+02:00thesis <span class="authorEditorList"><a href="/author/Alpaydin">Ethem Alpaydin</a>. </span><em>The MIT Press, </em>(<em>2014</em>)Sun Mar 29 21:33:02 CEST 2015Introduction to Machine Learning2014thesis The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. Subjects include supervised learning; Bayesian decision theory; parametric, semi-parametric, and nonparametric methods; multivariate analysis; hidden Markov models; reinforcement learning; kernel machines; graphical models; Bayesian estimation; and statistical testing. Machine learning is rapidly becoming a skill that computer science students must master before graduation. The third edition of Introduction to Machine Learning reflects this shift, with added support for beginners, including selected solutions for exercises and additional example data sets (with code available online). Other substantial changes include discussions of outlier detection; ranking algorithms for perceptrons and support vector machines; matrix decomposition and spectral methods; distance estimation; new kernel algorithms; deep learning in multilayered perceptrons; and the nonparametric approach to Bayesian methods. All learning algorithms are explained so that students can easily move from the equations in the book to a computer program. The book can be used by both advanced undergraduates and graduate students. It will also be of interest to professionals who are concerned with the application of machine learning methods.Introduction to Machine LearningThe representation of location by regional climate models in complex terrainhttp://www.bibsonomy.org/bibtex/2a0c19cabf2de6ec9dffe11712cf27abc/marsianusmarsianus2015-03-29T19:06:00+02:00BiasCorrection ReliefEnergy precipitation <span class="authorEditorList"><a href="/author/Maraun">D. Maraun</a>, and <a href="/author/Widmann">M. Widmann</a>. </span><em>Hydrology and Earth System Sciences Discussions</em> (<em>2015</em>)Sun Mar 29 19:06:00 CEST 2015Hydrology and Earth System Sciences Discussions3011--3028The representation of location by regional climate models in complex terrain122015BiasCorrection ReliefEnergy precipitation To assess potential impacts of climate change for a specific location, one typically employs climate model simulations at the grid box corresponding to the same geographical location. But based on regional climate model simulations, we show that simulated climate might be systematically displaced compared to observations. In particular in the rain shadow of moutain ranges, a local grid box is therefore often not representative of observed climate: the simulated windward weather does not flow far enough across the mountains; local grid boxes experience the wrong airmasses and atmospheric circulation. In some cases, also the local climate change signal is deteriorated. Classical bias correction methods fail to correct these location errors. Often, however, a distant simulated time series is representative of the considered observed precipitation, such that a non-local bias correction is possible. These findings also clarify limitations of bias correcting global model errors, and of bias correction against station data.
Resolution dependence of European precipitation in a state-of-the-art atmospheric general circulation modelhttp://www.bibsonomy.org/bibtex/26f556f1c8556e19cf96ee230d0459e00/marsianusmarsianus2015-03-29T19:01:15+02:00Europe GCM precipitation resolution <span class="authorEditorList"><a href="/author/van+Haren">Ronald van Haren</a>, <a href="/author/Haarsma">Reindert J. Haarsma</a>, <a href="/author/van+Oldenborgh">Geert Jan van Oldenborgh</a>, and <a href="/author/Hazeleger">Wilco Hazeleger</a>. </span><em>Journal of Climate</em> <em>0(0):null</em> (<em>0</em>)Sun Mar 29 19:01:15 CEST 2015Journal of Climate0nullResolution dependence of European precipitation in a state-of-the-art atmospheric general circulation model00Europe GCM precipitation resolution Using a decomposition of the precipitation difference between the medium- and high resolution model in a part related and a part unrelated to a difference in the distribution of vertical atmospheric velocity, we find that the smaller precipitation bias in central and northern Europe is largely unrelated to a difference in vertical velocity distribution. The smaller precipitation amount in these areas is in agreement with less moisture transport over this area in the high resolution model. We found that in areas with orography the change in vertical velocity distribution is more important.AMS Journals Online - Resolution dependence of European precipitation in a state-of-the-art atmospheric general circulation modelStatistical precipitation bias correction of gridded model data using point measurementshttp://www.bibsonomy.org/bibtex/2a9a61f4109bf99c7081e36f5e5635c3a/marsianusmarsianus2015-03-29T18:59:12+02:00BiasCorrection precipitation <span class="authorEditorList"><a href="/author/Haerter">Jan O. Haerter</a>, <a href="/author/Eggert">Bastian Eggert</a>, <a href="/author/Moseley">Christopher Moseley</a>, <a href="/author/Piani">Claudio Piani</a>, and <a href="/author/Berg">Peter Berg</a>. </span><em>Geophysical Research Letters</em> (<em>2015</em>)Sun Mar 29 18:59:12 CEST 2015Geophysical Research Lettersn/a--n/aStatistical precipitation bias correction of gridded model data using point measurements2015BiasCorrection precipitation It is well known that climate model output data cannot be used directly as input to impact models, e.g., hydrology models, due to climate model errors. Recently, it has become customary to apply statistical bias correction to achieve better statistical correspondence to observational data. As climate model output should be interpreted as the space-time average over a given model grid box and output time step, the status quo in bias correction is to employ matching gridded observational data to yield optimal results. Here we show that when gridded observational data are not available, statistical bias correction can be carried out using point measurements, e.g., rain gauges. Our nonparametric method, which we call scale-adapted statistical bias correction (SABC), is achieved by data aggregation of either the available modeled or gauge data. SABC is a straightforward application of the well-known Taylor hypothesis of frozen turbulence. Using climate model and rain gauge data, we show that SABC performs significantly better than equal-time period statistical bias correction.Statistical precipitation bias correction of gridded model data using point measurements - Haerter - 2015 - Geophysical Research Letters - Wiley Online Library