Texas A&M researchers design reinforcement-based system that automates prediction of subsurface environments Texas A&M researchers designed a new reinforcement-based system that automates the prediction of subsurface environments. Posted at 7:24 PM, Feb 26, 2021 and last updated 2021-02-26 20:24:51-05 Researchers at Texas A&M University have created a new way to predict the amount of natural resources. Texas A&M University researchers have designed a reinforcement-based algorithm that automates the process of predicting the properties of the underground environment, facilitating the accurate forecasting of oil and gas reserves. The technology would be put into the drilling well bores that contain data censors which sends messages to each other to better map underground oil and gas reserves.