A common element in modelling forest fires and earthquakes is the need to develop space-time point process models that can be used to quantify the evolving risk from forest fires (or earthquakes) as a function of time, location, and background factors. This paper is intended as an introduction to space-time point process modelling. It includes brief summaries of the most relevant point process properties, starting from the description and estimation of first and second order moment properties, proceeding to a description of conditional intensity or dynamic models, and ending with an introduction to some of the models and estimation procedures which are currently being used in seismology. A short final section contrasts the modelling problems for seismology and for forest fires.