... the performance of the surrogate model. Earlier studies were focused on forward problems with well-defined data. The present study attempts to develop models capable of reconstructing the flow-field data from sparse datasets mirroring real-world scenarios. We demonstrated the performance of data-driven models...

... History of the training error and test error for the ANN which predicts A7 Fig. 4 Method for creating the data-driven models Method for creating the data-driven models Fig. 28 Example of how the time-series torque data are used to calculate the features which describe the data...