Optimising Weakly Connected Chemical Oscillators in a Hybrid Digital–Chemical Platform via Generative AI Surrogate Modelling

Herein, we present a 3D-printed platform consisting of a rectangular 2D-array of interconnected cells containing the Belousov-Zhabotinsky (BZ) reaction. This reaction can be made to oscillate between two states to simulate the binary codification of digital electronics. Within the platform each cell contains a magnetic stirrer that can be individually stirred to control the local oscillations of the BZ reaction in that cell. Moreover, all the cells are also weakly interconnected through the common medium, and their collective oscillatory dynamics can be used to perform heterotic computations. The 3D-printed vessel can be fabricated using different architectures to, for example, define how the cells are connected, and thus controlling how the oscillations propagate between them. We took advantage of these features to simulate the "AND", "OR", and "XOR" logic gates. To increase the experimental throughput of our platform and further investigate its computability capabilities, we modelled it using Generative Artificial Intelligence (AI). Then, the AI model was used as an in-silico surrogate, in combination with a Genetic Algorithm, to explore and optimise the behaviour of our platform towards user-defined objectives. The results presented here provide a proof of concept for combining hybrid digital-chemical platforms with Generative AI surrogate modelling to explore unconventional computation, which might potentially enhance future Artificial Life implementations more effectively than current silicon-based advancements.