The objective of this paper is to discuss the capability of an Artificial Neural Network to classify the thermal conductivity of glycol concentrations in water. This was done by creating a COMSOL model of a micropipette thermal sensor in an infinite media and simulating a 500 µs laser pulse at the tip. Parameter approximation of the 2^nd order heat transfer PDE permits concentration classification. The temperature profile dataset generated would then be fed into a trained ANN to classify the thermal conductivity, whose value would be used to distinguish the glycol concentration difference of up to 10%. Training of the ANN yielded an overall classification accuracy of 99.99% after 108 epochs.