Search

The length and time scales of atomistic simulations are limited by the computational cost of the methods used to predict material properties. In recent years there has been great progress in the use of machine learning algorithms to develop fast and accurate interatomic potential models, but it remains a challenge to develop models that generalize well and are fast enough to be used at extreme time and length scales. To address this challenge, we have developed a machine learning algorithm based on symbolic regression in the form of genetic programming that is capable of discovering accurate, computationally efficient manybody potential models. The key to our approach is to explore a hypothesis space of models based on fundamental physical principles and select models within this hypothesis space based on their accuracy, speed, and simplicity. The focus on simplicity reduces the risk of overfitting the training data and increases the chances of discovering a model that generalizes well. Our algorithm was validated by rediscovering an exact Lennard-Jones potential and a Sutton Chen embedded atom method potential from training data generated using these models. By using training data generated from density functional theory calculations, we found potential models for elemental copper that are simple, as fast as embedded atom models, and capable of accurately predicting properties outside of their training set. Our approach requires relatively small sets of training data, making it possible to generate training data using highly accurate methods at a reasonable computational cost. We present our approach, the forms of the discovered models, and assessments of their transferability, accuracy and speed.

Sources and transports of CO as measured by the Measurement of Air Pollution from Space (MAPS) over a substantial sector of the southern hemisphere between South America and southern Africa are described by air parcel trajectories based upon European Center for Medium Range Weather Forecasts (ECMWF) model data fields. Observations, made by NASA Shuttle astronauts during the October 1994 mission, of vegetation fires suggest a direct relationship between in situ biomass burning, at least over South America and southern Africa, and coincident tropospheric measurements of CO. Results of this paper indicate that the transport of CO from the surface to the levels of maximum MAPS sensitivity (about 450 hPa) over these regions is not of a direct nature due largely to the well stratified atmospheric environment. The atmospheric transport of CO from biomass burning within this region is found to occur over intercontinental scales over numbers of days to more than a week. Three distinct synoptic circulation and transport classes are found to have occurred over southern Africa during the October 1994 MAPS experiment: (1) transport from South America and Africa to southern Africa associated with elevated MAPS measured CO (> 150 ppbv); (2) weakening anticyclonic transport from South America associated with moderate CO (< 150 ppbv and > 105 ppbv); and (3) transport from the high southern latitudes associated with low CO (<105 ppbv).