# Querying Log Data with Metric Temporal Logic (Technical Report)

## TL;DR

This paper introduces datalogMTL, a logic framework that enables efficient ontology-based querying of temporal log data, supporting complex temporal concepts with proven computational properties and demonstrated real-world scalability.

## Contribution

It presents datalogMTL, a novel extension of Horn Datalog with metric temporal logic, providing a decidable and scalable approach for temporal data access.

## Key findings

- datalogMTL is ExpSpace-complete with punctual intervals
- Nonrecursive datalogMTL is PSpace-complete for combined complexity
- Experiments show efficient querying on large datasets

## Abstract

We propose a novel framework for ontology-based access to temporal log data using a datalog extension datalogMTL of a Horn fragment of the metric temporal logic MTL. We show that datalogMTL is ExpSpace-complete even with punctual intervals, in which case full MTL is known to be undecidable. We also prove that nonrecursive datalogMTL is PSpace-complete for combined complexity and in AC0 for data complexity. We demonstrate by two real-world use cases that nonrecursive datalogMTL programs can express complex temporal concepts from typical user queries and thereby facilitate access to temporal log data. Our experiments with Siemens turbine data and MesoWest weather data show that datalogMTL ontology-mediated queries are efficient and scale on large datasets.