DIII-D
PulseAugur coverage of DIII-D — every cluster mentioning DIII-D across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New trust layer enhances AI predictions for fusion energy research
Researchers have developed a novel trust layer for machine learning surrogates used in fusion energy research. This layer provides calibrated error bars and out-of-distribution alarms, allowing for more reliable predict…
-
New Dataset Tokamak-SI Enhances Interpretation of Tokamak Discharges
Researchers have developed Tokamak-SI, a new dataset designed to interpret tokamak discharges by combining labels from various earlier studies. This dataset aims to create a scalable, time-aligned, and categorical catal…
-
New benchmark standardizes offline RL for nuclear fusion plasma control
Researchers have introduced RL4F, a new benchmark designed to standardize the evaluation of offline reinforcement learning for plasma control in nuclear fusion. This benchmark utilizes historical data from the DIII-D to…
-
Offline RL trains tokamak fusion reactor control using historical data
Researchers have developed an offline reinforcement learning approach to control the plasma rotation profile within tokamaks, devices crucial for fusion energy research. This method trains solely on historical data from…