Big Data: from earth to the heavens, 8th May 2017

Many thanks to KPMG for hosting our May meeting, and to Ben Talbot from KPMG for organizing the event and being the MC for the night. 68 people attended and there were plenty of lively conversations during the drinks and nibbles afterward.

Dr Penny Stewart gave an excellent overview of the activity of her company Petra Data Science, which is focused on using trans-disciplinary data in the resources sector.  She gave two very good examples:  1) for mine pump failure predictions integrating data from geology, water table, blasting, the minerals processing plant and weather. Eventually after looking back for up to 48 hours they could predict failure was coming based on changes in the processing circuit and 2) using algorithms to predict an hour in advance the overloading of SAG mills. Last year there were 100 shutdowns and since Jan 2017  there have been none.  These predictions for failure have been very successful and reduced down time costs substantially.  A number of people during the networking said they had got a lot out of Penny’s presentation.

Kevin Vinsen of the International Centre for Radio Astronomy Research (ICRAR) gave an engaging presentation on the SKA and big data collection, storage and retrieval for analysis.  In his lively and informative talk Kevin pointed out that radio astronomy signals can be used to detect the basic building blocks of the stars, planets and life including H2, H2O, H2S, NH3, CO, formaldehyde and simple sugars. Kevin has a TedX youtube video which is similar to his presentation on the night.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s