Skip to content
Back to search

geoml

MarketplaceWorks with Claude CodeGitHub

Spatial modeling using machine learning concepts

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/italo-goncalves/geoML with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/italo-goncalves/geoML'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/italo-goncalves--geoml/badge.svg)](/listings/italo-goncalves--geoml)

HTML

<a href="/listings/italo-goncalves--geoml"><img src="/api/listings/italo-goncalves--geoml/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

pip install git+https://github.com/italo-goncalves/geoML

Python 3.10 or newer. The dependencies — NumPy, SciPy, pandas, scikit-learn, scikit-image, TensorFlow, TensorFlow Probability, Zarr, xarray, dask, PyVista, VTK, Matplotlib, Plotly, ezdxf and openpyxl — are declared with their lower bounds in `pyproject.toml` and installed with the package. `pip install -e .[dev]` adds what the documentation and the type check need.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 26 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "geoml",
  3. "owner": {
  4. "name": "Ítalo Gomes Gonçalves",
  5. "email": "italogoncalves.igg@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Claude Code extensions for the geoML package.",
  9. "version": "1.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "geoml",
  14. "source": "./plugins/geoml",
  15. "description": "Working knowledge of the geoML package: the object model, the module layout, the modelling workflow, and the notebook conventions its examples follow.",
  16. "category": "knowledge",
  17. "keywords": [
  18. "gaussian-process",
  19. "geostatistics",
  20. "spatial",
  21. "geoscience",
  22. "machine-learning"
  23. ]
  24. }
  25. ]
  26. }
README.md · README · 125 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="/geoml/images/geoML logo horizontal.png" width="100%">
  3. </p>
  4. # Spatial modeling using machine learning concepts
  5. [![tests](https://github.com/italo-goncalves/geoML/actions/workflows/tests.yml/badge.svg)](https://github.com/italo-goncalves/geoML/actions/workflows/tests.yml)
  6. [![docs](https://github.com/italo-goncalves/geoML/actions/workflows/docs.yml/badge.svg)](https://github.com/italo-goncalves/geoML/actions/workflows/docs.yml)
  7. 📖 **[Documentation](https://italo-goncalves.github.io/geoML/)** — the API
  8. reference and the design records, published with each release.
  9. Geoscientific data is becoming increasingly larger and more complex. Multiple variables, structural constraints, etc. are becoming the norm rather than the exception.
  10. Conventional modelling approaches are very labour-intensive, subjective, and hard to reproduce. CAD-drawn orebodies, variograms, pre- and post-processing steps can result in workflows so complicated that even professionals can become lost within their own work. geoML is being designed to simplify geomodelling and empower the user with advanced machine larning tools that respect geology.
  11. <p align="center">
  12. <img src="/geoml/images/walker_gif.gif" width="100%">
  13. </p>
  14. This package contains machine learning models specialized in spatial interpolation and smoothing with calibrated confidence intervals. Current functionality includes:
  15. * Gaussian process modeling in 1D, 2D, and 3D, with
  16. anisotropy ellipsoid;
  17. * Variational Gaussian process for classification and multivariate
  18. modeling;
  19. * Support for compositional data;
  20. * Support for directional data (structural geology
  21. measurements, scalar field gradients, etc.);
  22. * Support for implicit modelling with boundary data (points
  23. lying in the boundary between two rock types);
  24. * Deep learning for non-stationary modeling;
  25. * Exports results to [PyVista](https://github.com/pyvista/pyvista) format;
  26. * Back-end powered by [TensorFlow](https://www.tensorflow.org/).
  27. ## Installation
  28. ```
  29. pip install git+https://github.com/italo-goncalves/geoML
  30. ```
  31. Python 3.10 or newer. The dependencies — NumPy, SciPy, pandas, scikit-learn,
  32. scikit-image, TensorFlow, TensorFlow Probability, Zarr, xarray, dask,
  33. PyVista, VTK, Matplotlib, Plotly, ezdxf and openpyxl — are declared with
  34. their lower bounds in `pyproject.toml` and installed with the package.
  35. `pip install -e .[dev]` adds what the documentation and the type check need.
  36. ## Examples
  37. The following notebooks demonstrate the capabilities of the package (if one
  38. of them seems broken, it is probably going through an update).
  39. * [Sunspot cycle prediction](https://colab.research.google.com/drive/1tbc7I8K0NmpCM4mOZZ1kghlXWnLamE5l)
  40. * [3D classification](https://colab.research.google.com/drive/1oC8b-eCgrfLxMcVsxVv6EvQyeKelUUjE)
  41. * [Potential field modeling using only directional data](https://colab.research.google.com/drive/141zuv7VH431fVt0dwHQiKCSJmYd6E9u8)
  42. * [Gold modeling with auxiliary variables](https://colab.research.google.com/drive/16OFpI1a-V-Wfsgkw_jhlh2NXGFwuHZ0C?usp=sharing)
  43. * [Dealing with faults (experimental)](https://colab.research.google.com/drive/1O_EsFy6bGbUIpzYySafUYrscUcbmTUHc?usp=sharing)
  44. ## Learning materials
  45. * [geoML short course presentation](https://1drv.ms/p/c/4a4617b38edb43d3/ERKF7Z9DUQNPon_oZGSxclwB_rneluFp9bAhep6lpbtP6g?e=stGHkW)
  46. * [Notebook 01 - covariance functions](https://colab.research.google.com/drive/1_LS-tem6ATRi62inKvZVOPJRJPjlzGxO?usp=sharing)
  47. * [Notebook 02 - Gaussian process](https://colab.research.google.com/drive/1dq19BU-vgsQAlAyx2gZjiGTPM-d2Oh26?usp=sharing)
  48. * [Notebook 03 - 2D modelling with warping](https://colab.research.google.com/drive/136aCKd9df39S4PmShZ0KIbfmQjaRWkP_?usp=sharing)
  49. * [Notebook 04 - multivariate modelling](https://colab.research.google.com/drive/1ZqeQhbrbVHKEVJgwLQT2jY8AmZR6ENhd?usp=drive_link)
  50. * [Notebook 05 - implicit modelling](https://colab.research.google.com/drive/1mKcRF_Kme6ac-nNzj6dON_updZk01LAS?usp=drive_link)
  51. * [Notebook 06 - gradients](https://colab.research.google.com/drive/1SUNlzThWzg5sbj5sK878WOkgVILdRLjV?usp=drive_link)
  52. * [Notebook 07 - deep Gaussian process](https://colab.research.google.com/drive/1kWvsTAfVMs_K4eHwImJDlPnDUt9k3kZd?usp=sharing)
  53. * [Notebook 08 - multivariate non-stationary modelling](https://colab.research.google.com/drive/1HotYLXScQT-J-aqBMrvI_vR2UOyIWn2o?usp=drive_link)
  54. * [Notebook 09 - compositional data](https://colab.research.google.com/drive/1oxFsdAvouiJSmsiDhs4vh-DsWGvaAUMm?usp=drive_link)
  55. ## Using geoML with Claude Code
  56. This repository ships a [Claude Code](https://claude.com/claude-code) plugin
  57. carrying the package's own working knowledge: the object model, the module
  58. layout, the modelling workflow, and the notebook conventions the examples
  59. above follow. It means Claude writes geoML code the way geoML is meant to be
  60. written, rather than guessing an API from its name.
  61. Install it from within Claude Code:
  62. ```
  63. /plugin marketplace add italo-goncalves/geoML
  64. ```
  65. ```
  66. /plugin install geoml@geoml
  67. ```
  68. Claude then loads it by itself whenever a task involves geoML, or you can
  69. invoke it directly with `/geoml:geoml`. It costs about 200 tokens per
  70. session until it is used.
  71. ## References
  72. * [2020 - Sunspot Cycle Prediction Using Warped Gaussian Process Regression](https://www.sciencedirect.com/science/article/pii/S0273117719308026)
  73. * [2021 - A machine learning model for structural trend fields](https://doi.org/10.1016/j.cageo.2021.104715)
  74. * [2022 - Learning spatial patterns with variational Gaussian processes: Regression](https://doi.org/10.1016/j.cageo.2022.105056)
  75. * [2023 - Variational Gaussian processes for implicit geological modeling](https://linkinghub.elsevier.com/retrieve/pii/S0098300423000274)
  76. * [2024 - Moho depth model of South America from a machine learning approach](https://www.sciencedirect.com/science/article/abs/pii/S0895981124003377)
  77. * [2025 - Uncertainty Propagation in Deep Gaussian Process Networks (open access)](https://link.springer.com/10.1007/s11004-025-10187-4)
  78. * [2026 - Scalable variational Gaussian process framework for implicit geological modelling and compositional grade interpolation (open access)](https://doi.org/10.1016/j.aiig.2026.100218)
  79. ## External links
  80. * [Gaussian process book](https://gaussianprocess.org/gpml/)
  81. * [A Visual Exploration of Gaussian Processes](https://distill.pub/2019/visual-exploration-gaussian-processes/)
  82. * [Interactive Gaussian Process Visualization](https://www.infinitecuriosity.org/vizgp/)
  83. ## Licensing
  84. geoML is available under a dual license model:
  85. ### Open-Source License (GPL v3)
  86. geoML is free and open-source software licensed under the GNU General Public License v3.0. Under this license, you may use, study, modify, and distribute geoML at no cost, provided that any software incorporating geoML is also distributed under the GPL v3. This applies to academic research, personal projects, and any open-source work.
  87. ### Commercial License
  88. If you wish to integrate geoML into a proprietary or closed-source product — such as commercial geostatistical software, consulting workflows, or any application whose source code will not be made publicly available under the GPL — a separate commercial license is required. The commercial license grants you the right to use geoML without the copyleft obligations of the GPL.
  89. Typical use cases for a commercial license include:
  90. * Embedding geoML in commercial mining, oil & gas, or environmental software
  91. * Using geoML in paid consulting deliverables distributed as closed-source tools
  92. * Integrating geoML into a SaaS platform
  93. To inquire about commercial licensing terms and pricing, please fill [this contact form](https://forms.gle/zh73ZUjFEFhxvxLN7).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.