Band-Selective LDOS Engineering of Yb/Er Upconversion: an Electromagnetic-Kinetic Diagnostic Framework

TL;DR

This paper demonstrates a band-selective plasmonic platform for Yb/Er upconversion, combining experimental LDOS engineering with a coupled electromagnetic-kinetic model to analyze emission modulation and discrepancies.

Contribution

It introduces a diagnostic framework that integrates full-wave simulations and rate equations to understand LDOS effects in plasmonic upconversion systems.

Findings

Red emission rate is modulated by +/-15% at 670 nm with spacer thickness.

Green emission remains invariant across spacer thickness.

The model reproduces some experimental results but misses a dip at 15 nm spacer thickness.

Abstract

A central challenge in plasmonic upconversion is coupling between near-field engineering at the pump wavelength and local-density-of-optical-states (LDOS) engineering at the emission wavelengths. Here we show that a corrugated SU8/Au/Al2O3 grating coated with a dense NaYF4:Yb(20%),Er(5%) upconversion nanoparticle (UCNP) monolayer realises a band-selective platform: a broad plasmonic resonance near 670 nm aligned with the red 4F9/2 -> 4I15/2 Er3+ transition modulates the red decay rate by +/-15% as a function of the Al2O3 spacer thickness d, while the green 2H11/2 / 4S3/2 -> 4I15/2 transition is experimentally invariant (|k/k_ref - 1| < 1% across all d). The pump field at 980 nm is monotonically suppressed below the free-space reference (<f_exc> from 0.27 to 0.48 between d = 5 and 25 nm), so observables cleanly probe the emission-side LDOS without pump-side interference. We rationalise these results with a coupled electromagnetic-kinetic framework combining full-wave FDTD pump enhancement and orientation-averaged Purcell factors with a six-level Yb/Er rate-equation model separating radiative, intrinsic nonradiative and environment-induced nonradiative channels. The framework reproduces the 670 nm extinction resonance, the +/-10-15% red-band decay-rate modulation, and the monotonic decrease of the green/red ratio with d, but predicts a monotonic red-band trend that misses the experimental dip at d = 15 nm and over-predicts a green-band reduction (k/k_ref^550 approx. 0.73 vs. 1.00). Ridge-tip smoothing (h_round in {0, 5, 10} nm) shifts Purcell factors by only 1-3%, ruling out apex shape as the dominant cause. The framework thus serves as a diagnostic tool, isolating the green-band discrepancy as needing corrections beyond the half-ellipse model - likely grain-boundary damping in the evaporated gold or extra non-radiative channels at 550 nm not in the six-level kinetic model.