Isatis.neo | Geostatistics made accessible
Isatis.neo is the leading and most comprehensive software solution for geostatistics. Featuring an intuitive user interface, it results from Geovariances’ dual commitment to developing breakthrough technology and making premium geostatistics accessible to more users.
Designed for every business dealing with spatialized data, Isatis.neo exceeds industry standards in geostatistics. The software enables thorough data analysis and visualization, produces high-quality maps and models, and allows you to carry out extensive uncertainty and risk analyses that optimize your decision-making process.
Available in a Standard Edition, Isatis.neo is also offered in two special versions, Petroleum Edition and Mining Edition, to better meet the specific requirements of these two industries. In addition to business-oriented tools, the Petroleum Edition offers a preconfigured workflow for Time-to-Depth Conversion with comprehensive uncertainty analysis.
Improve your performance
Geostatistics can appear daunting if you are not familiar with the approach. This is why we have been working to make Isatis.neo straightforward to use so that you only focus on your geostatistical analysis, not on how to use the tool. Your performance is boosted thanks to its intuitive interface, but also by cutting-edge parallelized algorithms and powerful scripting procedures that allow fast and easy model updating.
Tailor your project to your needs
Isatis.neo provides a complete set of powerful and intuitive statistical and geostatistical tools in a fully flexible package letting you design your process to best address your specific issues. And if you need further analyses, Isatis.neo enables you to write python coding into your batch processes, allowing for a high degree of customization required for optimized workflows.
Make better decisions
Isatis.neo makes you benefit from Geovariances’ technical excellence in geostatistics. The software derives from robust, tried and tested Isatis software and 35 years of know-how in developing geostatistics-based software solutions in partnership with the French Mining School of Paris. With Isatis.neo, you are certain to hold the keys for data and risk-informed decision making.
Go beyond with Machine Learning
With Isatis.neo, you may combine geostatistics with Machine Learning techniques to solve real and complex problems.
Dans le cadre d’un test réalisé pour Eiffage Génie Civil, Geovariances a généré un modèle de sous-sol complètement cohérent avec celui généré avec leurs outils habituels, avec en plus pour l'approche géostatistique, rapidité et arguments nécessaires à sa justification.
A top-ten iron producing company sought a solution to produce weekly resource models instead of monthly models to improve their decision process regarding the destination of the mined materials. Geovariances developed automated routines based on Isatis.neo batch and Python coding
Maxwell GeoSystems help their clients reduce risk and improve construction performance. They integrate geostatistics with Isatis.neo in their modeling process to quantify the uncertainty of their interpretation for a greater understanding of the ground conditions.
"Conversions & Uncertainties Workflow is an operational tool that can eventually add value to our portfolio of prospects thanks to robust, reliable and easy-to-compare methodology. That is really a huge improvement."
Hear from our customers
Discover Isatis.neo at our upcoming events
Events
Resources
Use of Simulations for Mining Applications
Linear interpolation techniques – such as kriging – are inappropriate for dealing with issues that require a full characterization of spatial distribution (for example, probability of exceeding a threshold, variability of a product per mining period, recoverable resources at various cut-offs, etc.).
Only conditional simulations reproduce the true variability of your orebody. They are flexible in their application to complex mining processes and uncertainty assessment.
Through Geovariances’ multiple experiences in developing a variety of simulation strategies in different environments: kimberlite pipes, turbiditic and carbonate reservoirs, porphyry copper, alteration and hyd,rothermal type deposits, learn how geostatistical simulations can help in resource estimation and classification.
Hydrogeological Facies Modeling
Stochastic Methods for geological modeling and links with fluid flow simulations
Whatever the application domain – oil & gas production, aquifer pollution characterization, uranium production by lixiviation – characterizing the geological parameters and capturing their variability is essential to ensure realistic flow modeling…
Time to Depth Conversion
Time to depth conversion of geological surfaces is critical for structural model building. Quantifying the uncertainty attached to the conversion is also of primordial importance for assessing GRV uncertainties. Traditional velocity models used in time to depth conversion could benefit from geostatistical techniques used in data integration. The advantage of using geostatistical methods is that they fit the data in one step and allow quantifying the uncertainty attached to the prediction by mean of the generation of equiprobable realizations.
Through Geovariances long-lasting experience in geostatistical depth conversion studies, learn how geostatistics helps you improve the accuracy of your reservoir structural model and assess the uncertainties on surfaces.
Mapping with auxiliary data
Through this white paper, discover how you canimprove significantly map reliability and quality by incorporating various sources of information in the interpolation process.
This document details the different methods for assimilating various sources of information, taking into account the reliability of each source and how the uncertainty associated with any mapping result can be estimated and reduced.
Which block size for mineral resource estimation
A key aspect of mineral resource estimation (MRE) is the definition of the block dimensions used to estimate the deposit attributes.
A satisfactory compromise is to be found to get an estimate that allows making decisions upon volumes that are representative of the physical reality of the operation while being aware that the density of information available at the time of estimation probably does not warrant the direct estimation of such volumes.
Through this white paper, learn how to choose a relevant support size for mineral resource estimation.
-
Amélioration de l’estimation des teneurs en alumine d’un gisement de kaolin à l’aide des simulations par bandes tournantes | XVe Journées de géostatistique 2021 - V. Bouchet (Imerys), M.C. Febvey (Geovariances), Hélène Binet (Geovariances), Armand Dubus (Geovariances)
-
Utilisation d’un algorithme de classification par Machine Learning pour la caractérisation géomécanique des sols | CFMS 2020 - par Marie-Cecile Febvey
-
Co-kriging of log ratios: a worked alternative method | Clint Ward, Cliffs, Ute Mueller ECU
-
Local Uncertainty Benchmarking – A coal case study | Written by C. Mawdesley, D. Barry, O. Bertoli and R. Saha
-
Sensitivity study of the estimation variance approximation of a quotient | Comparison with Conditional Simulations in the Mn Deposit of Bangombé (Gabon)
-
A novel geostatistical index of uncertainty for short-term mining plan | G. M. C. Dias, M. M. Rocha & V. M. Silva (2023) - CIM Journal, DOI: 10.1080/19236026.2022.2145077
-
Application de la géostatistique dans l’analyse de risque géotechnique lié à la liquéfaction du sol | Gestion des Données et Nouvel Environnement numérique en Géotechnique - Journée technique CFMS 15 nov 2022
-
Geostatistical Modeling of Overburden Lithofacies to Optimize Continuous Mining in the Ptolemais Lignite Mines, Greece | Modis, K.; Sideri, D.; Roumpos, C.; Binet, H.; Pavloudakis, F.; Paraskevis, N. - Minerals 2022, 12, 1109
-
Comparison of geostatistical and machine learning models for predicting geochemical concentration of iron: case of the Nkout iron deposit (south Cameroon) | André William Boroh, Sylvain Kouayep Lawou, Martin Luther Mfenjou, Ismaïla Ngounouno - Journal of African Earth Sciences, Volume 195, 2022
-
Full paper: On measuring the spatial sampling density of a deposit for mineral resource classification | Full paper - On measuring the spatial sampling density of a deposit for mineral resource classification by Marie-Cécile Febvey, Benjamin Martin and Jacques Rivoirard