John R. Williams

Omar S. Alolayan, Abdullah O. Alomar, John R. Williams

Reformulating the history matching problem from a least-square mathematical optimization problem into a Markov Decision Process introduces a method in which reinforcement learning can be utilized to solve the problem. This method provides a mechanism where an artificial deep neural network agent can interact with the reservoir simulator and find multiple different solutions to the problem. Such formulation allows for solving the problem in parallel by launching multiple concurrent environments enabling the agent to learn simultaneously from all the environments at once, achieving significant speed up.

Saleem A. Al Dajani, Abel Sanchez, John R. Williams

Generative AI foundation models offer transformative potential for processing structured biological data, particularly in single-cell RNA sequencing, where datasets are rapidly scaling toward billions of cells. We propose the use of agentic foundation models with real-time web search to automate the labeling of experimental data, achieving up to 82.5% accuracy. This addresses a key bottleneck in supervised learning for structured omics data by increasing annotation throughput without manual curation and human error. Our approach enables the development of virtual cell foundation models capable of downstream tasks such as cell-typing and perturbation prediction. As data volume grows, these models may surpass human performance in labeling, paving the way for reliable inference in large-scale perturbation screens. This application demonstrates domain-specific innovation in health monitoring and diagnostics, aligned with efforts like the Human Cell Atlas and Human Tumor Atlas Network.

Omar S. Alolayan, Samuel J. Raymond, Justin B. Montgomery et al.

Deep neural networks can generate more accurate shale gas production forecasts in counties with a limited number of sample wells by utilizing transfer learning. This paper provides a way of transferring the knowledge gained from other deep neural network models trained on adjacent counties into the county of interest. The paper uses data from more than 6000 shale gas wells across 17 counties from Texas Barnett and Pennsylvania Marcellus shale formations to test the capabilities of transfer learning. The results reduce the forecasting error between 11% and 47% compared to the widely used Arps decline curve model.

Marıa Arenas-Martınez, Sergio Herrero-Lopez, Abel Sanchez et al.

A number of governments and organizations around the world agree that the first step to address national and international problems such as energy independence, global warming or emergency resilience, is the redesign of electricity networks, known as Smart Grids. Typically, power grids have broadcast power from generation plants to large population of consumers on a sub-optimal way. Nevertheless, the fusion of energy delivery networks and digital information networks, along with the introduction of intelligent monitoring systems (Smart Meters) and renewable energies, would enable two-way electricity trading relationships between electricity suppliers and electricity consumers. The availability of real-time information on electricity demand and pricing, would enable suppliers optimizing their delivery systems, while consumers would have the means to minimize their bill by turning on appliances at off-peak hours. The construction of the Smart Grid entails the design and deployment of information networks and systems of unprecedented requirements on storage, real-time event processing and availability. In this paper, a series of system architectures to store and process Smart Meter reading data are explored and compared aiming to establish a solid foundation in which future intelligent systems could be supported.