The CRDC Sustainability Repository and Data Graph Builder system has been designed and developed to ease the workload of CRDC and other relevant staff to collect and process the sustainability reporting data on Australian Cotton indicators and targets. The Australian research body on Cotton, CRDC (Cotton Research and Development Corporation) publishes data about 120 cotton indicators on a quadrennial sustainability report explaining their sustainable practices on Australian cotton farms. The standard practice is to utilize a manual approach to extract information from heterogeneous sources.

Industries like Agriculture, where the IT resources are scarce, may not possess a centralized repository with temporal and spatial information. This becomes more difficult when the data is scattered over diverse locations in diverse formats. The QUT-CRDC project (2016 – 2019) started with collecting information on various social, environmental and economic indicators and targets, and proposing new ones where applicable. The final component of the project focused on studying the feasibilities of using heterogeneous data sources to extract useful knowledge on cotton indicators and propose an autonomous system that allows to collect, extract, process and query the relevant sustainability indicators information. A data source can be a pdf document, a doc file, an excel sheet or a html page that may contain relevant information for cotton indicators.

In this project, a novel data mining based methodology has been developed to automate the data acquisition, processing and reporting of cotton sustainability indicators information that may be available on multiple heterogeneous data sources. The intuitive tool based on this methodology provides access to social, economic and environmental sustainability indicators, enabling users to generate information and graphics that communicate repository query results to stakeholders efficiently and effectively.

The project team consisted of experts on data mining, software engineering, visualization, environmental science, and design science.

This report gives a brief description of the prototype of the “Sustainability Repository and Data Graph Builder” system.