To improve, predictions of composite behavior under thermal loads, there is a need to measure the axial thermophysical properties of thin fibers. Current methods to accomplish this have prohibitively long lead times due to extensive sample preparation, This work details the use of quantum dots thermomarkers to measure the surface temperature of thin fibers in a non-contact manner and determine the fibers' thermal diffusivity. Neural networks are trained on extracting the temperature of a sample from fluorescence spectra in calibrated, steady-state conditions, based on different spectral features such as peak intensity and peak wavelength. The trained neural networks are then used to reconstruct the evolution of the surface temperature in transient heating experiments. In order to determine the thermal properties of a thin fiber, modulated laser heating is applied and an FFT-based method is used to extract the phase and amplitude response of the temperature field at the modulation frequency. The spatiotemporal dependence of the fluorescence signal, obtained by scanning the distance between the excitation and detection laser spots and varying the frequency response due to an axial scan and a frequency scan, is then curve-fit to the resulting decay curves by a photothermal model in order to determine the thermal diffusivity of the fiber. The measured thermal diffusivity (3.3 +/- 0.8 x 10(-7) m(2) s(-1)) of a synthetic spider silk fiber by the current method has similar properties to other synthetic silk fibers, and demonstrates the ability of the current method to more rapidly measure thermophysical properties of thin fibers. (C) 2017 Elsevier Ltd. All rights reserved.