(710a) Ontology Engineering for the Development of Industrial Symbiosis Networks
Industrial Symbiosis (IS), a part of industrial ecology, is an innovative approach that aims in creating industrial networks set to process waste and to trade materials, energy and water to gain economic, environmental and social benefits. Economic benefits are generated mainly by reduced costs of waste or by-products, by using alternative energy sources and by environmental savings. Environmental benefits are inherent in IS as landfill diversion but also as reduction in emission and by water savings. Operating within confined geographic and administrative boundaries, IS also generates tangible social benefits to local communities, including job generation and retention, as well as new investments.
Identification of opportunities and creation of IS network is a complex task which requires expertise, hence knowledge in different areas, i.e. waste composition, capability of processing technologies and environmental effect among others. The whole process is currently managed by trained practitioners supported by datasets from mainly proprietary databases. Limited to the level of expertise and intuition of practitioners and lacking readily available repository of tacit knowledge, the all operation is backward looking and focusing on past successful examples with innovative networks being incidental.
This paper presents design and implementation of a semantic web platform, the eSymbiosis platform, which supports IS practice by screening the opportunities and by automating creation of innovative symbiotic networks. The platform employs ontologies to embed tacit knowledge in the domain of IS, knowledge gained from past experience but also from the latest research and otherwise advances in IS. More specifically, a set of integrated ontologies address off-spec nature of waste, i.e. variability in composition, dynamics in availability and pricing, as well as economic and environmental properties including hazardousness. By the same token, processing technologies are also modeled in terms of their processing capabilities, which include range of type of inputs, conversion rates, water and energy requirements, range of capacities, emissions as well as fixed and operational costs and environmental effects. Explicit knowledge is collected in the process of ontology instantiation with actual data collected from the IS participants during the registration and hence storred in respective repository. The ontologies are designed using ontology web language and hence prepared to grow and to share. In the current implementation more than 1500 different waste types and over 200 different technologies have been included.
Purpose designed matchmaker identify synergies between participants on their semantic and explicit relevance. Semantic relevance defines suitability from the type of waste/by-product and range of technology inputs, including complex composites of waste, i.e. biodegradable waste, and it is calculated from distance between the two instances in the respective ontology. Semantic relevance also includes participant general suitability for particular type of IS. Explicit relevance is calculated using vector similarity algorithm for respective properties, such as quantity, availability, geographical location and hazardousness. More intuitive and complex IS networks are proposed by reclusively repeating matches between two participants which in turn gives an opportunity for even better economic and environmental savings and/or targeted production. Both semantic and explicit matching relevance are aggregated in into a numerical values use for match ranking.
The eSymbiosis platform has been implemented as a web service with performance validated verified in the industrial region in Viotia, Greece and with several hundred participating companies.
The effort has been funded by the LIFE+ initiative (LIFE 09 ENV/GR/000300), which authors acknowledge.