Data for 'Reproducible Reservoir Computing with Thermally Driven Superparamagnets: Controlling Temperature Sensitivity'

This repository contains the supporting data and Python computational scripts for the research article: "Reproducible Reservoir Computing with Thermally Driven Superparamagnets: Controlling Temperature Sensitivity".1. Multi-Objective Optimization (MOO) DataThe data regarding the system's performance trade-offs was generated using the Optuna optimization framework. All relevant files are located in the Pareto_front_Fig.3 folder.Study Name: MOO_test_21; The file MOO_test_21_20251210_110829_pareto contains the subset of trials that constitute the Pareto front (non-dominated solutions). This data illustrates the optimal balance between miniNRMSE and averageNRMSE; The file MOO_test_21_20251210_110829_trials records all optimization trials conducted during the study.<br>2. Computational Code &amp; VisualizationFig2.py: The script contains the complete Python code to simulate the thermally driven superparamagnetic reservoir and plot the results shown in Figure 2 of the article.