227 Hits in 4.5 sec

Reconstruction of low-rank aggregation kernels in univariate population balance equations

Robin Ahrens, Sabine Le Borne
2021 Advances in Computational Mathematics  
The low-rank assumption for the kernel allows the application of fast techniques for the evaluation of the aggregation integral ($\mathcal {O}(n\log n)$ O ( n log n ) instead of $\mathcal {O}(n^{2})$ O  ...  In this work, we focus on the aggregation problem and present an approach to estimate the aggregation kernel in discrete, low rank form from given (measured or simulated) data.  ...  The main idea is the assumption of a discrete low-rank kernel of the form K = USU T which allows the fast evaluation of aggregation integrals introduced in [8, 10] in nonlinear optimization procedures  ... 
doi:10.1007/s10444-021-09871-w fatcat:5wujlmt32zg5fdrp5kwicknfie

CRPS Learning [article]

Jonathan Berrisch, Florian Ziel
2021 arXiv   pre-print
We discuss pointwise combination algorithms based on aggregation across quantiles that optimize with respect to the continuous ranked probability score (CRPS).  ...  After analyzing the theoretical properties of pointwise CRPS learning, we discuss B- and P-Spline-based estimation techniques for batch and online learning, based on quantile regression and prediction  ...  In applications, we are considering the function based optimization problem (41) only on the equidistant probability grid P = (p 1 , . . . , p M ) of size M .  ... 
arXiv:2102.00968v3 fatcat:6fm7bvkwafa3vn6mhtqkr4skna

Static and Dynamic Models for Multivariate Distribution Forecasts: Proper Scoring Rule Tests of Factor-Quantile vs. Multivariate GARCH Models [article]

Carol Alexander, Yang Han
2022 arXiv   pre-print
We approach this highly complex problem using a variety of proper multivariate scoring rules to evaluate over 100,000 forecasts of eight-dimensional multivariate distributions: of exchange rates, interest  ...  While numerous studies examine the accuracy of multivariate models for forecasting risk metrics, there is little research on accurately predicting the entire multivariate distribution.  ...  Both |Q| = 35 and |Q| = 50 use an equidistant quantile grid.  ... 
arXiv:2004.14108v2 fatcat:7bwgnbmivje5bm5d7xbqirkdsa

Flexible, boundary adapted, nonparametric methods for the estimation of univariate piecewise-smooth functions

Umberto Amato, Anestis Antoniadis, Italia De Feis
2020 Statistics Survey  
We introduce new ones based on adaptive combinations of two estimators.  ...  To study the performance of the proposed approaches we have conducted an extensive set of simulations on synthetic data.  ...  Picone", National Research Council, Naples, Italy, with the support of INDAM -Visiting Professors Program.  ... 
doi:10.1214/20-ss128 fatcat:o55zcby5tngqlnfaauzrr47leu

A comparison of Hurst exponent estimators in long-range dependent curve time series [article]

Han Lin Shang
2020 arXiv   pre-print
Within the context of functional autoregressive fractionally integrated moving average models, we compare finite-sample bias, variance and mean square error among some time- and frequency-domain Hurst  ...  spanning the dominant sub-space of functional time series.  ...  With the univariate time series of scores β, we evaluate and compare some Hurst exponent estimators from long-memory univariate time-series literature.  ... 
arXiv:2003.08787v1 fatcat:ebgiv2abw5arflr67yvlsey5qq

Estimation of aggregation kernels based on Laurent polynomial approximation

H. Eisenschmidt, M. Soumaya, N. Bajcinca, S. Le Borne, K. Sundmacher
2017 Computers and Chemical Engineering  
This approach is based on the approximation of the aggregation kernel by use of Laurent polynomials.  ...  The dynamics of particulate processes can be described by population balance equations which are governed by the phenomena of growth, nucleation, aggregation and breakage.  ...  of the priority program SPP 1679 "Dynamische Simulation vernetzter Feststoffprozesse".  ... 
doi:10.1016/j.compchemeng.2017.03.018 fatcat:fpxrtsgx45hyfo64doielszh2m

Max-and-Smooth: A Two-Step Approach for Approximate Bayesian Inference in Latent Gaussian Models

Birgir Hrafnkelsson, Stefan Siegert, Raphaël Huser, Haakon Bakka, Árni V. Jóhannesson
2020 Bayesian Analysis  
Our results show that Max-and-Smooth is accurate and fast.  ...  We introduce Max-and-Smooth, an approximate Bayesian inference scheme for a flexible class of latent Gaussian models (LGMs) where one or more of the likelihood parameters are modeled by latent additive  ...  Acknowledgments We would like to acknowledge support from the EPSRC ReCoVer network, UK National Environment Research Council (NERC) and the University of Iceland Research Fund.  ... 
doi:10.1214/20-ba1219 fatcat:qre6abd4uzgc5iij3muvjsjhnm

Interactive visualization of streaming data with Kernel Density Estimation

Ove Daae Lampe, Helwig Hauser
2011 2011 IEEE Pacific Visualization Symposium  
Abstract I n this paper, we discuss the extension and integration of the statistical concept of Kernel Density Estimation (KDE) in a scatterplotlike visualization for dynamic data at interactive rates.  ...  Finally, we demonstrate the usefulness of our approach in the context of three application scenarios -one studying streaming ship traffic data, another one from the oil & gas domain, where process data  ...  Figure 12: Run times (in seconds) for evaluating grids of different sizes, for three different implementations of kernel density estimation, all using same dataset, kernel and bandwidth.  ... 
doi:10.1109/pacificvis.2011.5742387 dblp:conf/apvis/LampeH11 fatcat:qecr7iyvkremplz2svjegkugle

Proceedings of GSM 2020

Imboden, Christoph (Hrsg.), Bošnjak, Davor (Hrsg.), Friedrich, Andreas K. (Hrsg.), Hatziargyriou, Nikos (Hrsg.), Kudela, Thomas (Hrsg.), Nucci, Carlo Alberto (Hrsg.), Schwark, Bastian (Hrsg.), Svendstrup-Bjerre, Andreas (Hrsg.), Ziegler, Sebastian (Hrsg.), Hock, James (Hrsg.), Moore, Fiona (Hrsg.), Spirig, Michael (Hrsg.)
2020 Zenodo  
The European perspective on energy transition and the flexibility roadmap were delved into along with national perspectives for the implementation of harmonized grid services markets, where their orientation  ...  From October 19 to 20 2020, 78 experts from industry, administration and academia discussed for the fourth time the effects, prospects and solutions of grid services for a transforming electricity system  ...  Disclaimer This conference article is based on the German publication in [9].  ... 
doi:10.5281/zenodo.4284324 fatcat:6u4jopqwlrfhjncmulyldu2h2y

Assessing Spatial and Temporal Distribution of Algal Blooms Using Gini Coefficient and Lorenz Asymmetry Coefficient

Ting Zhou, Cheng Ni, Ming Zhang, Ping Xia
2022 Frontiers in Environmental Science  
Satellite remote sensing provides a fast and efficient way to capture algal bloom distribution at a large scale, but it is difficult to directly derive accurate and quantitative assessment based on satellite  ...  Two coefficients, Gini coefficient and Lorenz asymmetry coefficient, were used to evaluate the overall intensity, unevenness, and attribution of algal bloom in Chaohu Lake from 2011 to 2020.  ...  By dividing 61 remote sensing images into equidistant grid cells, statistical analysis can be carried out based on grid cell data to explore spatial and temporal distribution and trend in a quantitative  ... 
doi:10.3389/fenvs.2022.810902 fatcat:xk6dnrtunbcbthunw2e35ofbmq

Stochastic Distance Transform: Theory, Algorithms and Applications

Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje
2020 Journal of Mathematical Imaging and Vision  
We evaluate the accuracy of the SDT and the proposed framework on images of thin line structures and disks corrupted by salt and pepper noise and observe excellent performance.  ...  Finally, we evaluate the SDT and observe very good performance, on simulated images from localization microscopy, a state-of-the-art super-resolution microscopy technique which yields highly spatially  ...  convolution operation which is used in the literature for fast KDE on discrete grids [51, 52, 60] , and FŶ which denotes an indicator function ofŶ .  ... 
doi:10.1007/s10851-020-00964-7 fatcat:edyh6xpclfdzjggelfky63773i

Point process-based modeling of multiple debris flow landslides using INLA: an application to the 2009 Messina disaster [article]

Luigi Lombardo, Thomas Opitz, Raphael Huser
2017 arXiv   pre-print
We develop a stochastic modeling approach based on spatial point processes of log-Gaussian Cox type for a collection of around 5000 landslide events provoked by a precipitation trigger in Sicily, Italy  ...  These units hierarchically subdivide the geographic space from the highest grid-based resolution to the stronger morphodynamic-oriented slope units.  ...  Acknowledgement Part of the satellite images used to generate the landslide inventory were obtained thanks to the European Space Agency Project (ID: 14151) titled: A remote sensing based approach for storm  ... 
arXiv:1708.03156v1 fatcat:x7qdqdawp5awffbij5tq6qqfne

Recursive bias estimation for multivariate regression smoothers

Pierre-André Cornillon, N. W. Hengartner, E. Matzner-Løber
2014 E S A I M: Probability & Statistics  
On a real example, the Boston Housing Data, our method reduces the out of sample prediction error by 20%.  ...  Our estimator is easily computed by successive application of existing base smoothers (without the need of selecting an optimal smoothing parameter), such as thin-plate spline or kernel smoothers.  ...  TPS regression smoothers from 100 noisy observations from (3.2) (see Fig. 1) evaluated on a regular grid on [0, 1] × [0, 1].  ... 
doi:10.1051/ps/2013046 fatcat:gmduu36dmrglzmtlv6daopxssu

Rapid adjustment and post‐processing of temperature forecast trajectories

N. Schuhen, T. L. Thorarinsdottir, A. Lenkoski
2019 Quarterly Journal of the Royal Meteorological Society  
The aggregated ensemble can then outperform the much smaller ensemble consisting of equidistant quantiles (Wilks, 2014 ) .  ...  Richardson, Cloke, and Pappenberger ( 2020 ) recently proposed to evaluate the consistency of ensemble forecasts on the basis of the integrated quadratic distance (see Section 4.4 ) at different lead times  ...  tool for gridded forecasts and spatial fields, as these are usually compared with an analysis or a similar gridded observation product.  ... 
doi:10.1002/qj.3718 fatcat:il5xx74qszb23gsyc7erfk62nq

Visually Comparing Weather Features in Forecasts

P. Samuel Quinan, Miriah Meyer
2016 IEEE Transactions on Visualization and Computer Graphics  
We discuss the integration of these contributions into a functional prototype tool, and also reflect on the many practical challenges that arise when working with weather data.  ...  In this work, we present a characterization of the problems and data associated with meteorological forecasting, we propose a set of informed default encoding choices that integrate existing meteorological  ...  As NCEP's SREF is run on a Lambert Conic Conformal grid, we found that treating the forecast data as an equidistant grid overlaid on top of a pre-projected Lambert Conic Conformal map provided a sufficient  ... 
doi:10.1109/tvcg.2015.2467754 pmid:26390490 fatcat:a2jdk2nxvvf4ha5lugz2eoj7mu
« Previous Showing results 1 — 15 out of 227 results