|   | 
Details
   web
Records
Author Hirn, J.; Garcia, J.E.; Montesinos-Navarro, A.; Sanchez-Martin, R.; Sanz, V.; Verdu, M.
Title (up) A deep Generative Artificial Intelligence system to predict species coexistence patterns Type Journal Article
Year 2022 Publication Methods in Ecology and Evolution Abbreviated Journal Methods Ecol. Evol.
Volume 13 Issue Pages 1052-1061
Keywords artificial intelligence; direct interactions; generative adversarial networks; indirect interactions; species coexistence; variational AutoEncoders
Abstract Predicting coexistence patterns is a current challenge to understand diversity maintenance, especially in rich communities where these patterns' complexity is magnified through indirect interactions that prevent their approximation with classical experimental approaches. We explore cutting-edge Machine Learning techniques called Generative Artificial Intelligence (GenAI) to predict species coexistence patterns in vegetation patches, training generative adversarial networks (GAN) and variational AutoEncoders (VAE) that are then used to unravel some of the mechanisms behind community assemblage. The GAN accurately reproduces real patches' species composition and plant species' affinity to different soil types, and the VAE also reaches a high level of accuracy, above 99%. Using the artificially generated patches, we found that high-order interactions tend to suppress the positive effects of low-order interactions. Finally, by reconstructing successional trajectories, we could identify the pioneer species with larger potential to generate a high diversity of distinct patches in terms of species composition. Understanding the complexity of species coexistence patterns in diverse ecological communities requires new approaches beyond heuristic rules. Generative Artificial Intelligence can be a powerful tool to this end as it allows to overcome the inherent dimensionality of this challenge.
Address [Hirn, Johannes; Enrique Garcia, Jose; Sanz, Veronica] Univ Valencia, CSIC, Inst Fis Corpuscular IFIC, Valencia, Spain, Email: miguel.verdu@ext.uv.es
Corporate Author Thesis
Publisher Wiley Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2041-210x ISBN Medium
Area Expedition Conference
Notes WOS:000765239700001 Approved no
Is ISI yes International Collaboration yes
Call Number IFIC @ pastor @ Serial 5155
Permanent link to this record
 

 
Author Khosa, C.K.; Sanz, V.; Soughton, M.
Title (up) A simple guide from machine learning outputs to statistical criteria in particle physics Type Journal Article
Year 2022 Publication Scipost Physics Core Abbreviated Journal SciPost Phys. Core
Volume 5 Issue 4 Pages 050 - 31pp
Keywords
Abstract In this paper we propose ways to incorporate Machine Learning training outputs into a study of statistical significance. We describe these methods in supervised classification tasks using a CNN and a DNN output, and unsupervised learning based on a VAE. As use cases, we consider two physical situations where Machine Learning are often used: high-pT hadronic activity, and boosted Higgs in association with a massive vector boson.
Address [Khosa, Charanjit Kaur] Univ Bristol, HH Wills Phys Lab, Tyndall Ave, Bristol BS8 1TL, Avon, England, Email: Charanjit.Kaur@bristol.ac.uk;
Corporate Author Thesis
Publisher Scipost Foundation Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes WOS:000929724800002 Approved no
Is ISI yes International Collaboration yes
Call Number IFIC @ pastor @ Serial 5475
Permanent link to this record
 

 
Author Khosa, C.K.; Sanz, V.
Title (up) Anomaly Awareness Type Journal Article
Year 2023 Publication Scipost Physics Abbreviated Journal SciPost Phys.
Volume 15 Issue 2 Pages 053 - 24pp
Keywords
Abstract We present a new algorithm for anomaly detection called Anomaly Awareness. The algorithm learns about normal events while being made aware of the anomalies through a modification of the cost function. We show how this method works in different Particle Physics situations and in standard Computer Vision tasks. For example, we apply the method to images from a Fat Jet topology generated by Standard Model Top and QCD events, and test it against an array of new physics scenarios, including Higgs production with EFT effects and resonances decaying into two, three or four subjets. We find that the algorithm is effective identifying anomalies not seen before, and becomes robust as we make it aware of a varied-enough set of anomalies.
Address [Khosa, Charanjit K.] Univ Manchester, Dept Phys & Astron, Manchester M13 9PL, England
Corporate Author Thesis
Publisher Scipost Foundation Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2542-4653 ISBN Medium
Area Expedition Conference
Notes WOS:001048488200002 Approved no
Is ISI yes International Collaboration yes
Call Number IFIC @ pastor @ Serial 5610
Permanent link to this record
 

 
Author Khosa, C.K.; Mars, L.; Richards, J.; Sanz, V.
Title (up) Convolutional neural networks for direct detection of dark matter Type Journal Article
Year 2020 Publication Journal of Physics G Abbreviated Journal J. Phys. G
Volume 47 Issue 9 Pages 095201 - 20pp
Keywords dark matter; dark matter detection; neural networks; xenon1T; WIMPs
Abstract The XENON1T experiment uses a time projection chamber (TPC) with liquid xenon to search for weakly interacting massive particles (WIMPs), a proposed dark matter particle, via direct detection. As this experiment relies on capturing rare events, the focus is on achieving a high recall of WIMP events. Hence the ability to distinguish between WIMP and the background is extremely important. To accomplish this, we suggest using convolutional neural networks (CNNs); a machine learning procedure mainly used in image recognition tasks. To explore this technique we use XENON collaboration open-source software to simulate the TPC graphical output of dark matter signals and main backgrounds. A CNN turns out to be a suitable tool for this purpose, as it can identify features in the images that differentiate the two types of events without the need to manipulate or remove data in order to focus on a particular region of the detector. We find that the CNN can distinguish between the dominant background events (ER) and 500 GeV WIMP events with a recall of 93.4%, precision of 81.2% and an accuracy of 87.2%.
Address [Khosa, Charanjit K.; Mars, Lucy; Richards, Joel; Sanz, Veronica] Univ Sussex, Dept Phys & Astron, Brighton BN1 9QH, E Sussex, England, Email: charanjit.kaur@sussex.ac.uk;
Corporate Author Thesis
Publisher Iop Publishing Ltd Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0954-3899 ISBN Medium
Area Expedition Conference
Notes WOS:000555607800001 Approved no
Is ISI yes International Collaboration yes
Call Number IFIC @ pastor @ Serial 4485
Permanent link to this record
 

 
Author Folgado, M.G.; Sanz, V.
Title (up) Exploring the political pulse of a country using data science tools Type Journal Article
Year 2022 Publication Journal of Computational Social Science Abbreviated Journal J. Comput. Soc. Sci.
Volume 5 Issue Pages 987-1000
Keywords Politics; Spain; Sentiment analysis; Artificial Intelligence; Machine learning; Neural networks; Natural Language Processing (NLP)
Abstract In this paper we illustrate the use of Data Science techniques to analyse complex human communication. In particular, we consider tweets from leaders of political parties as a dynamical proxy to political programmes and ideas. We also study the temporal evolution of their contents as a reaction to specific events. We analyse levels of positive and negative sentiment in the tweets using new tools adapted to social media. We also train a Fully-Connected Neural Network (FCNN) to recognise the political affiliation of a tweet. The FCNN is able to predict the origin of the tweet with a precision in the range of 71-75%, and the political leaning (left or right) with a precision of around 90%. This study is meant to be viewed as an example of how to use Twitter data and different types of Data Science tools for a political analysis.
Address [Folgado, Miguel G.; Sanz, Veronica] Univ Valencia, Inst Fis Corpuscular IFIC, CSIC, Valencia 46980, Spain, Email: migarfol@upvnet.upv.es;
Corporate Author Thesis
Publisher Springernature Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2432-2717 ISBN Medium
Area Expedition Conference
Notes WOS:000742263500002 Approved no
Is ISI yes International Collaboration yes
Call Number IFIC @ pastor @ Serial 5077
Permanent link to this record