Example: Pressure Distribution of Single Phase Flow in Five Spot Wells Patterns, see Tutorials.

We are happy to announce the reslease of the first version of ReservoirFlow: Reservoir Simulation and Engineering Library in Python. ReservoirFlow is the first reservoir simulator based on physics-informed neural network models and one of its kind in a sense that it allows comparing and combining analytical solutions, numerical solutions, and neurical solutions (i.e. solutions based on artificial neural networks).

ReservoirFlow is designed based on the modern Python stack for data science, scientific computing, machine learning, and deep learning with the objective to support high-performance computing including multithreading, parallelism, GPU, and TPU. Throughout our computing problems based on large simulation models, intensive benchmarking well be carefully designed and carried out to evaluate the performance of computing software (i.e. frameworks) and hardware (e.g. GPUs). The outcome of these tests will be used to further improve the performance of ReservoirFlow and to provide materials with recommendations about available computing tools, techniques and frameworks. ReservoirFlow is planned to support different backends including NumPy, Scipy, JAX, PyTorch, TensorFlow, and more.

The first version supports basic functionality and we are looking forward to improve it during the following years. We invite reservoir professional and academics over all the world to start using this library and interact with us throughout GitHub or the Documenation.

Login to be able to share, comment, and see other comments.