Dear Editors, We are pleased to submit our research paper entitled “Learning Semantic Association Rules from Internet of Things Data” for consideration by Neurosymbolic Artificial Intelligence Journal’s Special Issue on Neurosymbolic AI for Cyberphysical Systems. Rule learning is part of Interpretable Machine Learning (ML) research that especially plays a major role in high-stake decision-making processes. Internet of Things (IoT) systems (e.g., of critical infrastructures such as water networks) also include high-stakes decision-making. In line with this research field, our paper introduces two contributions: i) a novel rule learning pipeline for IoT systems that make use of both sensor data and semantics (IoT knowledge graphs) as opposed to state-of-the-art sensor data-only approaches, ii) a neurosymbolic rule learning approach named Aerial that enables learning a more concise set of high-quality rules than the state-of-the-art. Our proposed Aerial approach creates a neural representation of given input data and then extracts logical rules from the neural representation. The approach is applied to the IoT data. We confirm that this work is original and has not been published elsewhere, nor is it currently under consideration for publication elsewhere. Thank you for your time and consideration. Kind regards, Erkan Karabulut, Paul Groth, Victoria Degeler University of Amsterdam, The Netherlands Corresponding Author: Erkan Karabulut (e.karabulut@uva.nl)