Identifying cross-cutting capabilities to extract information from big geospatial datasets
Dr Sanjeev Srivastava1, Dr Kheeran Dharmawardena2, Dr Michael Rigby3, Dr Jens Klump4, Dr Lesley Wyborn5
1University Of The Sunshine Coast, Sippy Downs, Australia, 2Cytrax Consulting, Australia, 3The University of Melbourne, Australia, 4CSIRO Mineral Resources, Perth, Australia, 5Australian Research Data Commons, Australia
Modern challenges of climate change, disaster management, public health and safety, resources management, and logistics can only be addressed through big data analytics. A variety of modern technologies are generating massive volumes of conventional and non-conventional geospatial data at local and global scales. Examples include data from earth observation (satellites and drones), IoT, mobility, and social media. Additionally, modern computer systems and algorithms are enabling the analysis of archived data sets, e.g. digital photogrammetric analysis of archived aerial and declassified satellite images.
Most of this data includes geospatial data components and are analysed using spatial algorithms. However, at this scale, the management and analysis of big geospatial data, conventional data models and spatial analysis methods are insufficient, leading to the evolution of new data formats (e.g. hierarchical data format). Similarly, ignoring the geospatial component of big data can lead to an inappropriate interpretation of extracted information. For example, big geospatial data analytics require the application of AI and similarly, analytics on big data with a strong geospatial component need to consider geospatial properties of data and their implications across scale (geospatial framework, spatial relationships, etc.).
The Australian Geospatial Capabilities Community of Practice, an interdisciplinary collaboration of subject matter specialists, computational and geospatial scientists, will be facilitating this BoF. After short presentations to set the scene, we will seek audience feedback on how to utilise the best AI-based algorithms whilst also considering the properties of the data and how to identify the geospatial as well as computational capabilities for such analytics.
Dr Srivastava has several years of experience in the application of geospatial techniques to natural resource and urban resources management. He is teaching and coordinating spatial science courses which include geographical information systems (GIS) and remote sensing and surveying courses.