Abstract: Methods, apparatus, and processor-readable storage media for detecting physical anomalies of a computing environment using machine learning techniques are provided herein. An example computer-implemented method includes monitoring a physical environment corresponding to at least one component of a distributed computing system using at least one sensor that is one or more of: at least partially within the at least one component and attached to the at least one component; performing, by the at least one component, a machine learning process comprising: analyzing data generated by the at least one sensor to detect one or more physical anomalies associated with the physical environment, and in response to detecting a physical anomaly, selecting at least one automated action, involving at least one additional component of the distributed computing system, to at least partially mitigate the physical anomaly; and initiating a performance of the at least one automated action.