![Tang Aurora ESP](/sites/default/files/styles/965x543/public/2020-05/Tang-ESP_frnn.png?itok=fqIRoQRK)
The team’s Fusion Recurrent Neural Network uses convolutional and recurrent neural network components to integrate both spatial and temporal information for predicting disruptions in tokamak plasmas. Image: Julian Kates-Harbeck, Harvard University; Eliot Feibush, Princeton Plasma Physics Laboratory