Search for: All records

Optical transmission systems require accurate modeling and performance estimation for autonomous adaption and reconfiguration. We present efficient and scalable machine learning (ML) methods for modeling optical networks at component- and network-level with minimized data collection. 

Scalable methods for optical transmission performance prediction using machine learning (ML) are studied in metro reconfigurable optical add-drop multiplexer (ROADM) networks. A cascaded learning framework is introduced to encompass the use of cascaded component models for end-to-end (E2E) optical path prediction augmented with different combinations of E2E performance data and models. Additional E2E optical path data and models are used to reduce the prediction error accumulation in the cascade. Off-line training (pre-trained prior to deployment) and transfer learning are used for component-level erbium-doped fiber amplifier (EDFA) gain models to ensure scalability. Considering channel power prediction, we show that the data collection process of the pre-trained EDFA model can be reduced to only 5% of the original training set using transfer learning. We evaluate the proposed method under three different topologies with field deployed fibers and achieve a mean absolute error of 0.16 dB with a single (one-shot) E2E measurement on the deployed 6-span system with 12 EDFAs. 

We implement a cascaded learning framework using component-level EDFA models for optical power spectrum prediction in multi-span networks, achieving a mean absolute error of 0.17 dB across 6 spans and 12 EDFAs with only one-shot measurement. 

Abstract Surface ligands play an important role in shape‐controlled growth and stabilization of colloidal nanocrystals. Their quick removal tends to cause structural deformation and/or aggregation to the nanocrystals. Herein, we demonstrate that the surface ligand based on poly(vinylpyrrolidone) (PVP) can be slowly removed from Pd nanosheets (NSs, 0.93±0.17 nm in thickness) by simply aging the colloidal suspension. The aged Pd NSs show well‐preserved morphology, together with significantly enhanced stability toward both e‐beam irradiation and electrocatalysis (e.g., ethanol oxidation). It is revealed that the slow desorption of PVP during aging forces the re‐exposed Pd atoms to reorganize, facilitating the surface to transform from being nearly perfect to defect‐rich. The resultant Pd NSs with abundant defects no longer rely on surface ligand to stabilize the atomic arrangement and thus show excellent structural and electrochemical stability. This work provides a facile and effective method to maintain the integrity of colloidal nanocrystals by slowly removing the surface ligand.