Structure and representation of ecological data to support knowledge discovery: A case study with bioacoustic data

Bird communities have long been surveyed as key indicators of ecosystem health and biodiversity. Adoption of Autonomous Recording Units (ARUs) to perform avian surveys has shifted the burden of species recognition from “birders” in the field, to “listeners” who review the ARU recordings at a later time. The number of recordings ARUs can produce has created a need to process large amounts of data. Although much research is devoted to fully automating the recognition process, expert humans are still required when entire bird communities must be identified. A framework for a Decision Support System (DSS) is presented which would assist listeners by suggesting likely species. A unique feature of the DSS is the consideration of the recording “context” of time, location and habitat as well as the bioacoustic features to match unknown vocalizations with reference species. In this thesis a data warehouse was built for an existing set of bioacoustic research data as a first–step to creating the DSS. The data set was from ARU deployments in the Lower Athabasca Region of Alberta, Canada. The Knowledge Discovery in Databases (KDD) and Dimensional Design Process protocols were used as guides to build a Kimball–style data warehouse. Data housed in the data warehouse included field data, data derived from GIS analysis, fuzzy logic memberships and symbolic representation of bioacoustic recording using the Piecewise Aggregate Approximation and Symbolic Aggregate approXimation (PAA/SAX). Examples of how missing and erroneous data were detected and processed are given. The sources of uncertainty inherent in ecological data are discussed and fuzzy logic is demonstrated as a soft–computing technique to accommodate this data. Data warehouses are commonly used for business applications but are very applicable for ecological data. As most instructions on building data warehouse are for business data, this thesis is offered as an example for ecologists interested in moving their data to a data warehouse. This thesis presents a case–study of how a data warehouse can be constructed for existing ecological data, whether as part of a DSS or a tool for viewing research data.