Skip to content

Physical reservoir computing with nonlinear temperature characteristics of thermal conductivity

Sep 2026 · Applied Physics Letters · Vol 129 · 0 citations · 34 references

TL;DR

The results demonstrate that memory capacity and nonlinear transformation capability can be tuned by adjusting the heat-input magnitude and the thermal diffusion time scale and indicate that engineered thermal media can serve as effective physical reservoirs with material-level tunability for energy-efficient computing systems.

Abstract

Physical reservoir computing (PRC) has emerged as a low-cost machine-learning framework for edge computing applications, where real-time processing and energy efficiency are critical due to the rapid growth of data generated by Internet-of-Things devices. This study proposes a PRC scheme based on nonlinear heat-conduction phenomena arising from the nonlinear temperature-dependent thermal conductivity of materials and examines its computational properties using a one-dimensional model. Information is encoded as transient thermal inputs applied at one boundary, while the resulting temporal temperature responses at multiple spatial positions constitute the reservoir states. Nondimensionalization of the governing heat equation reveals key dimensionless parameters that govern dynamical memory and nonlinearity, enabling systematic exploration of the design space independent of specific physical units. Performance is evaluated using benchmark tasks, including the short-term memory task and the parity check task. The results demonstrate that memory capacity and nonlinear transformation capability can be tuned by adjusting the heat-input magnitude and the thermal diffusion time scale. The proposed heat-conduction-based PRC successfully performs both benchmark tasks, demonstrating the feasibility of implementing PRC through nonlinear thermal transport in materials with temperature-dependent thermal conductivity. These findings indicate that engineered thermal media can serve as effective physical reservoirs with material-level tunability for energy-efficient computing systems.

View source

Similar papers

Open access Oct 2026

Mathematical Modeling of Nonlinear Physical Phenomena in Nanomaterials for Advanced Energy Applications

The unique thermal, electric, optical, mechanical, and electrochemical properties obtained due to their nanoscale size have made nanomaterials important building blocks for high-tech energy technologies. But such properties are nonlinear and frequently have characteristics of a particle interaction, Quantum Confinement...

Amit Prakash, G. Gurulakshmi, Avinash J. Kamble et al. · 0 citations
Open access Oct 2026

Machine learning-powered prediction of argon thermophysical properties for hot isostatic pressing

Argon is the primary pressure-transmitting medium in Hot Isostatic Pressing (HIP), and its thermophysical properties under high-temperature, high-pressure conditions strongly affect control accuracy and component quality. However, accurate and efficient property prediction remains difficult because conventional equatio...

Zhou-Jin Lv, Lei Chen, Jia-Hui Liang et al. · 0 citations
Open access Oct 2026

Artificial Neural Network Surrogate for Entropy Generation Analysis in PCM-Based Thermal Energy Storage

Latent heat thermal energy storage (LHTES) systems based on phase change materials (PCMs) are central to improving energy efficiency in solar–thermal, waste-heat recovery, and building energy management applications; however, minimizing the thermodynamic losses that degrade their exergetic performance requires fast and...

Ł. Łach · 0 citations
Review Open access Nov 2026

Machine Learning for Predicting Dielectric Energy-Storage Properties of Perovskite Oxides

Perovskite oxides with the ABO₃ structure are core candidates for dielectric energy-storage capacitors, whose recoverable energy density is governed by the dielectric constant, the breakdown field strength, and the nonlinear polarization response. This review surveys recent machine-learning studies on predicting these...

Geng Liu · 0 citations
Oct 2026

Artificial Neural Networks for Performance Prediction of CO2 Transcritical Heat Pump System

The rising global demand for energy-efficient heating systems has increased interest in [Formula: see text]-based transcritical heat pumps due to their unique thermodynamic behavior and environmental advantages. However, conventional models struggle with the nonlinear nature of transcritical cycles, and existing artifi...

V. C. Todkari, Jatoth Heeraman, Omprakash S. Patil et al. · 0 citations
Open access Oct 2026

Multiscale Digital-Twin Modeling of Energy-Storage Materials by Integrating First-Principles Calculations and Machine-Learning Interatomic Potentials

Conventional modeling of energy-storage materials is constrained by the computational cost of first-principles calculations, limited electrochemical-state awareness in machine-learning interatomic potentials, and weak coupling between materials-scale models and online battery decision-making. This study proposes a firs...

Yan Li, Duo-Chang Tang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.