D. Orlov

D. Sorokin, M. Stokolesov, A. Granovskiy et al.

Plasma shape control in tokamaks requires a real-time controller that tracks dynamically changing shape targets while tolerating diagnostic failures. Classical approaches decompose the problem into equilibrium reconstruction followed by a linear controller, and assume a fixed, fully operational sensor set. We present a reinforcement learning agent that addresses both limitations simultaneously. The agent is trained in NSFsim, a high-fidelity tokamak simulator configured for DIII-D, on a curated dataset of 120 experimental plasma shapes. The shape targets are resampled as random step changes every 0.25 s, exposing the agent to diverse transitions across the full shape envelope. At test time the agent zero-shot tracks dynamic shape sequences; on a held-out static configuration in simulation it achieves a mean shape error of 2.01 cm, and dynamic trajectory following is demonstrated qualitatively in simulation and on the physical device. Diagnostic dropout randomly masks 30% of magnetic sensors per episode, yielding a single policy robust to arbitrary sensor subsets without backup controllers or mode-switching logic. An asymmetric actor-critic architecture with privileged equilibrium information improves value estimation under partial observability; an auxiliary shape reconstruction head on the actor enables end-to-end shape reconstruction from raw diagnostics and serves as an interpretability tool for policy analysis. The policy transfers to experimental DIII-D shots, where it directly commands the coil actuators on two dynamic shape maneuvers, and to the independent GSevolve simulator.

E. Illarionov, P. Temirchev, D. Voloskov et al.

Reservoir simulation and adaptation (also known as history matching) are typically considered as separate problems. While a set of models are aimed at the solution of the forward simulation problem assuming all initial geological parameters are known, the other set of models adjust geological parameters under the fixed forward simulation model to fit production data. This results in many difficulties for both reservoir engineers and developers of new efficient computation schemes. We present a unified approach to reservoir simulation and adaptation problems. A single neural network model allows a forward pass from initial geological parameters of the 3D reservoir model through dynamic state variables to well's production rates and backward gradient propagation to any model inputs and variables. The model fitting and geological parameters adaptation both become the optimization problem over specific parts of the same neural network model. Standard gradient-based optimization schemes can be used to find the optimal solution. Using real-world oilfield model and historical production rates we demonstrate that the suggested approach allows reservoir simulation and history matching with a benefit of several orders of magnitude simulation speed-up. Finally, to propagate this research we open-source a Python-based framework DeepField that allows standard processing of reservoir models and reproducing the approach presented in this paper.