top of page

Machine learning method applied to optimization of cooling nanodevices

Publication in Scientific Reports!

Cooling devices grounded in solid-state physics are promising candidates for integrated-chip nanocooling applications. These devices are modeled by coupling the quantum non-equilibrium Green’s function for electrons with the heat equation (NEGF+H), which allows to accurately describe the energetic and thermal properties. We propose a novel machine learning (ML) workflow to accelerate the design optimization process of these cooling devices, alleviating the high computational demands of NEGF+H (see Figure). This methodology, trained with NEGF+H data, obtains the optimum heterostructure designs that provide the best trade-off between the cooling power of the lattice (CP) and the electron temperature (Te). Using a vast search space of 1.18 × 10−5 different device configurations, we obtained a set of optimum devices with prediction relative errors lower than 4 % for CP and 1 % for Te. The ML workflow reduces the computational resources needed, from two days for a single NEGF+H simulation to 10 s to find the optimum designs.





Fig. 1: Machine learning procedure. From the combination of the design parameters (Lb1, LQW, Lb2, γ) and the material energy gaps, the first solution of the potential profile (PP0) is constructed, and its features are reduced by applying the principal component analysis (PCA(PP0 )) to obtain the PP0 principal components (PCs). The PP0PCs combined with the V are the inputs of the first multi-layer perceptron (MLP1), which gives the difference between potential profile (PP) and PP0 (PP-PP0) PCs as the output. The PP of the device is obtained by applying the inverse principal component analysis (PCA) (PCA−1(PP-PP0) and adding the PP0. The inputs of the second multi-layer perceptron (MLP2) are the PP PCs obtained from the application of PCA(PP) to the PP. Finally, the MLP2 provides, as output the information about the cooling properties (CP, Te ) and the device activation energies (W1, W2).


Ref : J. G. Fernandez, G. Etesse, N. Seoane, E. Comesaña, K. Hirakawa, A. Garcia-Loureiro, M. Bescond, "A novel machine learning workflow to optimize cooling devices grounded in solid-state physics," Sci Rep 14, 28545 (2024).

Comments


bottom of page