Jalil Latrach

Jalil Latrach

PhD Student · Energy & Petroleum Engineering

University of Wyoming

I am a PhD student at the University of Wyoming working on geological carbon storage, geochemistry, unconventional oil and gas resources, and machine learning applications in subsurface energy systems.

Education

MEng, Petroleum Engineering University of North Dakota 2021–2022
PhD, Energy & Petroleum Engineering University of Wyoming 2022–present

Research Interests

  • Geological carbon storage & CO₂ geochemistry
  • Rock physics modeling (DEM, Gassmann)
  • Seismic monitoring & CO₂ detectability
  • Unconventional oil & gas resources
  • Physics-informed machine learning
  • LLM development & agentic AI for scientific computing

Publications

A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems

Abdeldjalil Latrach, Mohamed Malki, Misael Morales, Mohamed Mehana, Minou Rabiei

Geoenergy Science and Engineering · Elsevier · August 2024

73 citations BibTeX APA MLA

Class VI Database project: Drill-stem test data from Sweetwater County, Wyoming, USA

Abdeldjalil Latrach, Lily J. Jackson, Christian Martinez

Data in Brief · Elsevier · August 2025

0 citations BibTeX APA MLA

Identification and Quantification of the Effect of Fracture-Driven Interactions on Production from Parent and Child Wells in Williston Basin

Abdeldjalil Latrach, Ahmed Merzoug, Cilia Abdelhamid, Ilyas Mellal, Minou Rabiei

Unconventional Resources Technology Conference · SPE/AAPG/SEG · June 2023

3 citations BibTeX APA MLA

Feasibility of Repurposing Oil and Gas Wells for Geothermal Energy Production in Wyoming, USA

Abdeldjalil Latrach, Abdesselem Dehdouh, Cilia Abdelhamid, Ilyas Mellal, Minou Rabiei

Rock Mechanics/Geomechanics Symposium · ARMA · June 2024

2 citations BibTeX APA MLA

Formation Evaluation Challenges of Tight and Shale Reservoirs. A Case Study of the Bakken Petroleum System

Ilyas Mellal, Vamegh Rasouli, Abdesselem Dehdouh, Abdeldjalil Latrach, Cilia Abdelhamid, Mohamed Malki, Omar Bakelli

Rock Mechanics/Geomechanics Symposium · ARMA · June 2023

7 citations BibTeX APA MLA

Novel Approach for Elastic Anisotropy Assessment in Organic-Rich Shales: A Case Study from Early-Mature Region of the Bakken Formation

Mohamed Malki, Vamegh Rasouli, Abdeldjalil Latrach, Ilyas Mellal, Billel Sennaoui, Hichem AK Chellal, Anis Larbi

Rock Mechanics/Geomechanics Symposium · ARMA · June 2023

1 citation BibTeX APA MLA

Projects

Carbonex

Python Machine learning Geochemical modeling Agentic AI

A suite of tools for CO₂ geological storage research—combining physics-informed solubility estimation with LLM-driven geochemical and rock physics simulation.

Carbonex App

A web-based platform for high-accuracy estimation of CO₂ solubility in multi-salt brines across a wide range of pressures, temperatures, and salinities. Uses a physics-informed neural network trained on simulation data and fine-tuned on experimental data with a modified physics-enforcing loss function.

Carbonex Agent ↗

An LLM agent (Gemini 2.5 Flash) for CO₂ geological storage research. It drives validated PHREEQC geochemistry and carbonate rock physics simulations via tool calling, and interprets the results in natural language. All values come from deterministic simulation tools—the agent never fabricates or estimates. Every run logs the full tool-call trace for reproducibility.

Carbonex Agent interface

BladeStim

Python Qt

BladeStim, developed for Blade Energy Partners, is a multi-modular platform for data analyses and calculations related to completion and stimulation of hydraulically fractured oil and gas wells—including step-rate analyses and unified fracture design. It provides a streamlined workflow to import, clean, and process raw field data for visualization, analysis, and export.

BladeStim main interface BladeStim showcase

Wyoming Class VI Site Characterization Database

Python ArcGIS

A collaboration between the University of Wyoming, the Wyoming State Geological Survey, and the Wyoming Department of Environmental Quality to develop a geologic site characterization database compiled from public databases and scientific literature—aimed at expediting Class VI CO₂ injection well permitting in Sweetwater County within the Greater Green River Basin.