PetroSIM

AI-Assisted Petrophysical Simulation Engine

Transforming Raw Data into Rock Intelligence

PetroSIM is our foundational engine. It applies machine learning algorithms (Manifold Learning, K-Means) and stochastic modeling directly to well logs and core data to classify facies and predict petrophysical properties.

The 8-Step Simulation Pipeline

Extracción y Enriquecimiento

Data preparation and transformation

Estrategia bajo Riesgo

Uncertainty modeling strategy

Advanced Machine Learning

Manifold learning & clustering

Mapas de Parámetros

Probability distributions definition

Markov Chain Monte Carlo

MCMC implementation

Simulación de Escenarios

Building the scenario space

Calibración Core

Convergence of core variables

Interpretación Avanzada

Decision making & value function

Ecosistema Algorítmico Interactivo

Explora las conexiones entre los algoritmos y los procesos físicos. Arrastra los nodos para ver la física en acción.

Unsupervised Learning: Facies Classification

We implement a pipeline of manifold learning (dimensionality reduction via t-SNE) followed by clustering to reveal latent structures in petrophysical logs. This assigns probabilistic facies memberships (soft clustering).

The clustering is powered by algorithms like K-Means, which minimizes the intra-cluster variance, or inertia:

$$ J = \sum_{j=1}^{k} \sum_{i \in S_j} || x_i - \mu_j ||^2 $$

Expert Validation & Metrics: Quality is strictly audited using Silhouette and Trustworthiness scores, alongside our in-house metric: the Structural Consistency Index (SCI). This guarantees stable multi-well partitions that support the identification of gas zones with quantified uncertainty.

Latent Space Embedding (t-SNE)
2D Embedding View
3D Facies Clusters

Visual representation of high-dimensional log clustering.

Stochastic Simulation: MCMC

Instead of single deterministic values, PetroSIM computes probability density functions (PDFs). We build the scenario space utilizing Markov Chain Monte Carlo (MCMC).

MCMC allows us to sample from complex posterior probability distributions based on Bayes' Theorem:

$$ P(\theta|D) = \frac{P(D|\theta)P(\theta)}{P(D)} $$

Where \(P(\theta|D)\) is the posterior probability of the reservoir parameters \(\theta\) given the well log data \(D\). By generating thousands of realizations, we calibrate the results against core variables and map the full spectrum of geological uncertainty (P10, P50, P90).

The Outcome

  • Soft Clustering: Overlapping probability maps.
  • Explicability: Local feature attributions to back operative decisions.
  • Value Generation: Identifying levers of value directly linked to robustly selected zones of interest.