Geograph Seminar - Dr Chaosheng Zhang, NUI Galway

Dr Chaosheng Zhang
Thursday, February 21, 2019 - 16:00 to 17:00
Rocque Lab, Rhetoric House

Maynooth University Department of  Geography invites you to attend a seminar presented by Dr Chaosheng Zhang - Towards machine learning for identification of hidden spatial patterns and relationships in big data of environmental geochemistry

Environmental geochemistry is playing an increasingly important role in mineral exploration, environmental management and agricultural practices. With rapidly growing databases available at regional, national, and global scales, environmental geochemistry is facing the challenges in the “big data” era. One of the main challenges is to find out useful information hidden in a large volume of data, with the existence of spatial variation found at all the sizes of global, regional (in square kilometres), field (in square meters) and micro scales (in square centimetres). Meanwhile, the rapidly developing techniques in machine learning become useful tools for classification, identification of clusters/patterns, identification of relationships and prediction. Based on spatial variation, this presentation demonstrates the potential uses of a few practical machine learning techniques (spatial analyses) in environmental geochemistry: neighbourhood statistics, hot spot analysis and geographically weighted regression.

Neighbourhood (local) statistics are calculated using data within a neighbourhood such as a moving window. In this way, spatial variation at the local level can be quantified and more details are revealed. Hot spot analysis techniques are capable of revealing hidden spatial patterns. The techniques of hot spot analysis including local index of spatial association (LISA) and Getis Ord Gi* and their applications are explained and investigated using examples of geochemical databases in Ireland, China, the UK and the USA. The geographically weighted regression (GWR) explores the relationships between geochemical parameters and their influencing factors at the local level, which is effective in identifying the complex spatially varying relationships. Machine learning techniques are expected to play more important roles in environmental geochemistry. Challenges for more effective “data analytics” are currently emerging in the era of “big data”.
 

 

  Geography Seminar Series 2018-2019 v9