Applied Geostatistics Training Catalog

Geostatistical inputs to resource classification

CLASSIFICATION · JORC · KRIGING

Turn geostatistics into defensible resource classification. This course shows you how to assess estimate confidence with kriging, simulations, and uncertainty quantification then apply quantitative, auditable criteria to classify resources into Inferred, Indicated, and Measured under the JORC Code. Join the training to classify with confidence.

Drill Hole Spacing Analysis – DHSA

DHSA · DRILL HOLE SPACING· SIMULATION

Drill smarter, not more. This hands-on, two-day course teaches you to quantify grade uncertainty as a function of drill spacing and design optimal drilling meshes that balance cost, recovery, and dilution all in Isatis.neo. Join the training to improve resource classification and reduce geological risk.

““The DHSA training was really great! Even though it was only a two-day course, everything was clearly explained and easy to follow. I especially liked that, even without much simulation experience, we could still follow along using Isatis.neo. I can already see how it will help me improve my work.” ”

Recoverable Resource Estimation by nonlinear geostatistics – Module 3: Simulations

SIMULATIONS · CONDITIONAL EXPECTATION · RECOVERABLE ·

Capture the full range of possible outcomes. This module introduces two conditional simulation techniques for grades and shows you how to post-process them into accurate grade-tonnage curves. Join the training to quantify uncertainty and estimate recoverable resources with realism.

Recoverable Resource Estimation by nonlinear geostatistics – Module 2: Multiple Indicator Kriging and Conditional Expectation

INDICATOR KRIGING · CONDITIONAL EXPECTATION · RECOVERABLE ·

Choose the right tool for the deposit. This module gives you a working command of Multiple Indicator Kriging and Conditional Expectation and, crucially, the judgment to know when each one fits. Join the training to estimate recoverable resources with the right method every time.

Recoverable Resource Estimation by nonlinear geostatistics – Module 1: Uniform Conditioning

UNIFORM CONDITIONING · NONLINEAR · GRADE TONNAGE ·

Get unbiased grade-tonnage curves even from sparse sampling. This module gives you a deep, practical command of Uniform Conditioning, computing grade, tonnage, and metal quantities across any cut-off with Isatis.neo. Join the training to estimate recoverable resources with confidence.

Mineral Resource Estimation by linear geostatistics – Module 2: multivariate context

MULTIVARIATE RESOURCE ESTIMATION · KRIGING · PCA ·

Take your estimation skills into the multivariate world. This module shows you how to model multi-element orebodies with PCA, kriging, and co-kriging producing consistent models that respect the real ratios between metals, oxides, and elements. Join the training to handle complex deposits with precision.

Mineral Resource Estimation by linear geostatistics – Module 1: univariate context

MRE · KRIGING · LINEAR GEOSTATISTICS

Build the foundation every resource geologist needs. In this hands-on module, you'll master the standard univariate workflow from data analysis and variography to block modeling, kriging, and validation and walk away able to produce reliable grade-tonnage curves for short-term resources. Join the training to estimate with confidence.

Multiple-Point Statistics simulations (MPS) with Isatis.neo

MULTIPLE POINT STATISTICS · KRIGING · ISATIS.NEO · DeeSse ENGINE

Learn Multiple-Point Statistics (MPS) simulation in Isatis.neo with the DeeSse engine model complex geology from training images. Hands-on training course.

Geological modeling by geostatistics

GEOLOGICAL MODELLING · GEOSTASTICAL MODELING COURSE · ISATIS.NEO

Learn to build realistic, uncertainty-aware geological models with advanced geostatistics Indicator Kriging, SIS, TGS, PGS and implicit modeling in Isatis.neo.

Machine Learning applied to geosciences and mining

MACHINE LEARNING · MINERAL RESOURCE MODELING · ISATIS.NEO

Hands-on machine learning course for mining: define domains, run classification and regression, and link scikit-learn with Isatis.neo.