Enhanced geothermal systems (EGS) are promising for generating clean power by extracting heat energy from injection and extraction of water in geothermal reservoirs. The stimulation process involves hydroshearing which reactivates pre-existing cracks for creating permeability and meanwhile inducing microearthquakes. Locating these microearthquakes provide reliable feedback on the stimulation progress, but it poses a challenging nonlinear inverse problem. Current deep learning methods for locating earthquakes require extensive datasets for training, which is problematic as detected microearthquakes are often limited. To address the scarcity of training data, we propose a transfer learning workflow using probabilistic multilayer perceptron (PMLP) which predicts microearthquake locations from cross-correlation time lags in waveforms. Utilizing a 3D velocity model of Newberry site derived from ambient noise interferometry, we generate numerous synthetic microearthquakes and 3D acoustic waveforms for PMLP training. Accurate synthetic tests prompt us to apply the trained network to the 2012 and 2014 stimulation field waveforms. Predictions on the 2012 stimulation dataset show major microseismic activity at depths of 0.5–1.2 km, correlating with a known casing leakage scenario. In the 2014 dataset, the majority of predictions concentrate at 2.0–2.9 km depths, consistent with results obtained from conventional physics-based inversion, and align with the presence of natural fractures from 2.0–2.7 km. We validate our findings by comparing the synthetic and field picks, demonstrating a satisfactory match for the first arrivals. By combining the benefits of quick inference speeds and accurate location predictions, we demonstrate the feasibility of using transfer learning to locate microseismicity for EGS monitoring.