Добрый день, Коллеги. Важное сообщение, просьба принять участие. Музей Ферсмана ищет помощь для реставрационных работ в помещении. Подробности по ссылке
Статья посвящена исследованию новых возможностей пространственной трехмерной интерполяции методами машинного обучения для решения традиционных геологических задач с недостатком данных. Впечатляющий успех моделей машинного обучения определяется богатыми возможностями и простотой в использовании, позволяющими воспроизводить чрезвычайно сложные зависимости за счет способности самообучаться.
In geospatial data interpolation, as in mapping, mineral resource estimation, modeling and numerical modeling in geosciences, kriging has been a central technique since the advent of geostatistics. Here, we introduce a new method for spatial interpolation in 2D and 3D using a block discretization technique (i.e., microblocking) using purely machine-learning algorithms and workflow design.
Описываются алгоритмы процедур оценивания параметров распределений и проверки гипотез с помощью статистических критериев. Алгоритмы рассматриваются применительно к их машинной реализации.
Для статистиков, экономистов и специалистов, использующих методы прикладного статистического анализа
The book MATLAB Recipes for Earth Sciences is designed to help undergraduate and PhD students, postdocs, and professionals to fi nd quick solutions for common problems in data analysis in earth sciences.
Th e book MATLAB Recipes for Earth Sciences is designed to help undergraduate and postgraduate students, doctoral students, post-doctoral researchers, and professionals fi nd quick solutions for common data analysis problems in earth sciences. It provides a minimal amount of theoretical background and demonstrates the application of all described methods through the use of examples.
Behold the power of the microcomputer before your very eyes! This book took less than a year to complete from the initial conversations between Dan Merriam and myself to final typeset copy. This would have been impossible when the first volume of this book was published. All of the papers in this volume, with one exception, arrived on floppy disk but in four different disk formats and many wordprocessing formats. These were all handled elegantly by our typesetter and converted into the appropriate Macintosh file format. Even some of the figures were placed in the book electronically. I see this as a great boon to the world of science because of the much shorter time between inception and dispersal of scientific knowledge. As a result of using microcomputers to typeset this book, the information contained in it is current and fresh. <...>
Geostatistics is a subset of statistics specialized in analysis and interpretation of geographically referenced data (Goovaerts, 1997; Webster and Oliver, 2001; Nielsen and Wendroth, 2003). In other words, geostatistics comprises statistical techniques that are adjusted to spatial data. Typical questions of interest to a geostatistician are:
how does a variable vary in space?
what controls its variation in space?
where to locate samples to describe its spatial variability?
how many samples are needed to represent its spatial variability?
what is a value of a variable at some new location?
Nowadays, many surficial mineral deposits are being mined out, leaving only deep-seated mineral deposits for feeding raw materials into the industry. Therefore techniques applied to mineral exploration need to be revisited for discovering new mineral resources, which may be located in harsh and remote regions. Over the past decades, remote sensing technology and geographic information system (GIS) techniques have been incorporated into several mineral exploration projects worldwide. This aim is to bridge the knowledge gap for the geospatial-based discovery of buried, covered, and blind mineral deposits. This book details the main aspects of the state-of-the-art remote sensing imagery, geochemical data, geophysical data, geological data, and geospatial toolbox required to explore ore deposits. It covers advances in remote sensing data processing algorithms, geochemical data analysis, geophysical data analysis, and machine learning algorithms in mineral exploration. It also presents approaches on recent remote sensing and GIS-based mineral prospectivity modeling, which offer a piece of excellent information to professional earth scientists, researchers, mineral exploration communities, and mining companies <...>
