GEOSTATISTICS Rss FeedSpecial Issue in Mathematical Geosciences
MATHEMATICAL GEOSCIENCES SPECIAL ISSUE ON Geostatistics and Machine Learning
The Special Issue has been published! Check out the editorial and the articles of the SI here.
The SI has been published online. It includes the following six papers:
“A comparison between machine learning and functional geostatistics approaches for data-driven analyses of solid transport in a pre-Alpine stream” by Oleksandr Didkovskyi, Vladislav Ivanov, Alessio Radice, Monica Papini, Laura Longoni, and Alessandra Menafoglio
“Bayesian deep learning for spatial interpolation in the presence of auxiliary information” by Charlie Kirkwood, Theo Economou, Nicolas Pugeault & Henry Odbert
“Surface Warping Incorporating Machine Learning Assisted Domain Likelihood Estimation: A New Paradigm in Mine Geology Modelling and Automation” by Raymond Leung, Mehala Balamurali & Alexander Lowe
“A Hybrid Estimation Technique Using Elliptical Radial Basis Neural Networks and Cokriging” by Matthew Samson and Clayton V. Deutsch
“Stochastic Modelling of Mineral Exploration Targets” by Hasan Talebi, Ute Mueller, Luk J. M. Peeters, Alex Otto, Patrice de Caritat, Raimon Tolosana-Delgado & K. Gerald van den Boogaart
“Robust Feature Extraction for Geochemical Anomaly Recognition Using a Stacked Convolutional Denoising Autoencoder” by Yihui Xiong and Renguang Zuo
The editorial introduction is open access and is found at this address: Article Special Issue: Geostatistics and Machine Learning
Guest Editors:
Sandra De Iaco (University of Salento, Italy)
Dionissios Hristopulos (Technical University of Crete, Greece)
Guang Lin (Purdue University, United States of America)
This special issue will explore the connections between Geostatistics and Machine Learning, in particular deep learning, and their applications in spatial data processing and modeling. We welcome critical and synthetic reviews of relevant contributions in the literature as well as papers that provide new ideas regarding deep neural networks, kernel classes and hybrid models for mapping problems and the classification of environmental and pollution data; such contributions may include the use of automatic algorithms and optimization (design/redesign) of monitoring networks. Novel applications and comparative studies of geostatistical and machine learning methods are also appreciated.
Main topics:
• Integrated/hybrid spatial models for prediction and simulation
• Spatio-temporal modeling and prediction
• Classification models
• Inverse problems
• Big data and data mining modeling
• Software and routines
• Deep learning applications to spatial problems
Timelines:
A tentative title and an abstract (300–500 words) should be sent to the Guest Editors by March 15th, 2020. Full manuscripts should respect the journal’s guidelines for authors and be submitted online using the Editorial Manager system.
• Paper submission before: July 15th, 2020
• Return of reviews to authors before October 15th, 2020
• Submission of final papers deadline: January 31st, 2021
• Publication: Mid 2021
Submit Papers online through the journal’s website
www.springer.com/journal/11004
When submitting, you must choose, under ‘Select Article Type,’ the SI: “Geostatistics and Machine Learning.”
Submitted manuscripts must fully comply with the journal’s Instructions for Authors in preparing manuscripts.
For inquiries please contact the Guest Editors:
Sandra De Iaco Dionissios Hristopulos Guang Lin
sandra.deiaco@unisalento.it dionisi@mred.tuc.gr guanglin@purdue.edu