clementetienam

Cluster-Classify-regress-A-general-method-for-learning-discountinous-functions

Data_Driven_MPC_Controller_Using_CCR

DeepLearningExamples

Deep Learning Examples

Ensemble-based-History-Matching-with-a-Machine-Learning-Surrogate-Reservoir-Simulator

We have used a novel supervised learning, Cluster Classify Regress algorithm (CCR) for approximating 2 phase flow in a synthetic toy reservoir with very high accuracy. We compared the performance of CCR with a single DNN architecture in recovering the evolving pressure and saturation fields. The method consists of creating different surrogate machines equivalent to the number of time-steps (dynamic pressure and saturation snapshots). The inputs to the machine are the x,y,z spatial pixel (grid) location, the absolute permeability at each grid, effective porosity at each grid and the pressure and saturation field for each grid, for the previous time step. The outputs are the pressure and saturation field for the current time step Prediction is computationally cheap as each pressure and saturation map (for each time step) is recovered from each of the machines. The initial pressure and saturation field (Time 0) is fixed and set in the ECLIPSE data file. Learning of the function is first initiated by running eclipse once for the “1st time step” alone to get the preceding pressure and saturation field, CCR and DNN was then used to construct the different machines for each of the snap shots. CCR attained R2 accuracies of greater than 96% for both the recovery of the pressure and saturation field and Structural similarity index metric (SSIM) value of greater than 90% to the true pressure and saturation fields. We also use this newly constructed surrogate model in an ensemble based history matching frame-work. We show the overall frame work gives an acceptable history match (avoiding an inverse crime) to the synthetic true reservoir model. Finally we show the wall cock performance time of CCR in prediction (9.25 seconds on a standard personal laptop computer) compared to the full fidelity ECLIPSE reservoir solver to be 19.34 seconds. This is crucial in an ensemble based uncertainty quantification (UQ) task where the size of the ensemble ranges from 100 to 500 for full field reservoir history matching problems.

GeoFacies_DL

Grid_CarbonIntensity_Modelling

Reservoir-History-Matching

Codes associated with PhD thesis titled "Structural and Shape construction using inverse problems and machine earning techniques"

Reservoir-History-Matching-code-in-Python

Python script that conducts Reservoir History matching using the ES-MDA method

Ultra-Fast-Mixture-of-Experts-Regression

modulus-sym

Framework providing pythonic APIs, algorithms and utilities to be used with Modulus core to physics inform model training as well as higher level abstraction for domain experts

clementetienam/Reservoir-History-Matching-code-in-Python

Python script that conducts Reservoir History matching using the ES-MDA method

clementetienam/autokeras

AutoML library for deep learning

clementetienam/DeepLearningExamples

Deep Learning Examples

clementetienam/devito

Code generation framework for automated finite difference computation

clementetienam/HistoryMatching

Tutorial on history matching with ensembles

clementetienam/modulus-sym

An abstracted framework for training AI surrogates of physical systems using physics-based symbolic loss functions

clementetienam/PINO

clementetienam/CUQIpy-demos

Repo for demo files and training materials

clementetienam/DeepField

Machine learning framework for reservoir simulation

clementetienam/deepxde

Deep learning library for solving differential equations and more

clementetienam/DMoGPE

clementetienam/ert

clementetienam/FasterTransformer

Transformer related optimization, including BERT, GPT

clementetienam/fourier_neural_operator

Use Fourier transform to learn operators in differential equations.

clementetienam/GEOSX

GEOSX Simulation Framework

clementetienam/Hands-On-GPU-Programming-with-Python-and-CUDA

Hands-On GPU Programming with Python and CUDA, published by Packt

clementetienam/hyperas

Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization

clementetienam/ISMOE

Importance Sampled Mixture of Experts Code

clementetienam/MH-MDGM

MH-MDGM for Bayesian inverse problems

clementetienam/modulus

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

clementetienam/modulus-toolchain

Suite of utilities aiming to simplify the workflow required to build models using Physics Informed Neural Networks and, eventually, Physics ML more broadly. This includes facilities for project management, problem definition, debugging, model configuration and training, and model inference.

clementetienam/mpslib

A C++ class for Mutiple Point Simulation algorithms

clementetienam/neural-operator

Neural networks designed for operator-valued functional learning problems.

clementetienam/nvaitc-toolkit

Open source code base to showcase interoperability of CUDA-X AI software stack in multi-GPU environments and thus provide researchers a reference framework to build new projects on.

clementetienam/nvidia-NIM-RAG

Project demonstrates the power and simplicity of NVIDIA NIM (NVIDIA Inference Model), a suite of optimized cloud-native microservices, by setting up and running a Retrieval-Augmented Generation (RAG) pipeline.

clementetienam/pyamgx

GPU accelerated multigrid library for Python

clementetienam/pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

clementetienam/REnKF_parameter_estimation

clementetienam/SDEdit

PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

clementetienam/simple-local-rag

Build a RAG (Retrieval Augmented Generation) pipeline from scratch and have it all run locally.