Build realistic geological models that reflect complexity and uncertainty. Apply indicator kriging, SIS, TGS, PGS and implicit modeling through hands-on workflows in Isatis.neo.
Deep Kriging · Geometallurgical domains · Lithology classification
Put machine learning to work on real geoscience and mining challenges. Build, evaluate and apply classification and regression models by connecting scikit-learn with Isatis.neo.
Model complex geological patterns beyond traditional two-point methods. Learn MPS simulation with DeeSse in Isatis.neo, from training images to realistic uncertainty-aware realizations.
Turn spatial data into sound decisions. Learn to analyze datasets, map surfaces, model subsurface properties and quantify uncertainty with practical geostatistical workflows.
Make resource classification more quantitative and defensible. Use kriging, simulations and uncertainty measures to apply auditable JORC criteria with greater confidence.
Grade control · Mining dilution · Drilling optimization
Drill smarter, not more. Learn to quantify grade uncertainty by drill spacing and design cost-effective drilling meshes that improve resource classification and reduce geological risk.
Model multi-element deposits with consistency. Use PCA, kriging and cokriging to respect relationships between metals, oxides and elements, and improve multivariate resource estimates.
Build a strong foundation in mineral resource estimation. Follow the univariate workflow, from data analysis and variography to block modeling, kriging, validation and grade-tonnage curves.
Deep Kriging · Geometallurgical domains · Lithology classification
Put machine learning to work on real geoscience and mining challenges. Build, evaluate and apply classification and regression models by connecting scikit-learn with Isatis.neo.
Model complex geological patterns beyond traditional two-point methods. Learn MPS simulation with DeeSse in Isatis.neo, from training images to realistic uncertainty-aware realizations.
Make resource classification more quantitative and defensible. Use kriging, simulations and uncertainty measures to apply auditable JORC criteria with greater confidence.
Capture the full range of possible grade outcomes. Apply conditional simulation and post-processing to quantify uncertainty and produce realistic recoverable resource estimates.
Enter your details to receive your access link by email right away.
Nous utilisons des cookies pour vous garantir la meilleure expérience sur notre site web. Si vous continuez à utiliser ce site, nous supposerons que vous en êtes satisfait.