<p>Precise knowledge of the location and height of the volcanic SO<sub>2</sub> plumes is essential for accurate determination of SO<sub>2</sub> emitted by volcanic eruptions for aviation control applications, but so far very time-consuming to retrieve from UV satellite data. The SO<sub>2</sub> height is furthermore one of the most critical parameters that determine the impact on the climate. We have developed an extremely fast yet accurate SO<sub>2</sub> layer height retrieval algorithm using the Full-Physics Inverse Learning Machine (FP_ILM) algorithm, which, for the first time, is applied to TROPOMI aboard Sentinel-5 Precursor. In this work we demonstrate the ability of the FP_ILM algorithm to retrieve layer heights in near-real time applications with an accuracy of better than 2 km for SO<sub>2</sub> total columns larger than 20 DU and show SO<sub>2</sub> layer height results for selected volcanic eruptions.</p>