Fire Alerts on the Geospatial Semantic Web

Abstract. CSIR is a South African research institution with broad and extensive experience in the domain of fire, ranging from policy work to basic research into fire and ecology. One of the more visible fire-related applications that CSIR has been involved in is known as the Advanced Fire Information System (AFIS), a joint initiative with Eskom, the South African electricity utility. The application utilises results from remotely sensed data to infer fire occurrence and trigger alarms to Eskom opera-tors based on proximity of fire events to Eskom infrastructure, notably transmission lines and towers. This paper describes the Meraka Institute (African Advanced Institute for ICT – a National Research Centre affiliated with CSIR) view of the fu-ture of AFIS. Meraka intends to migrate AFIS from a narrowly focussed, ‘black-box ’ application to one servicing users in multiple fire-related sce-narios. Future AFIS versions would be based on an open framework of geospatial web services, ontologies and software agents. We aim to draw upon the deep organisational knowledge of fire and fire processes that is held by CSIR and its partners to produce a system that can supply highly tuned, meaningful and customised fire alerts to users. We hope to evolve AFIS from a single use application into an agent-based platform enabling rapid development and deployment of new fire-related appli-cations through concept-based queries of data and knowledge reposito-ries. We believe that AFIS is representative of the evolution that many geospatial applications on the web may have to follow, from being tightly coupled, software dependent applications, through being loosely-coupled, web service and standards-oriented applications to a point where they provide geo-information to the semantic web