GPS Filling (Part 1)

What is GPS Filling and Why is it Needed?

Christopher D'Almeida avatar
Written by Christopher D'Almeida
Updated over a week ago

Problem:


Invalid or missing GPS data can occur for various reasons including faulty equipment or loss of machine network connection at site. GPS coordinates are a primary source of information for the Digital Stockpile model and inaccuracies in the model could occur without this information. Location labels are used as a secondary information source. Rectifying the root cause/s of the issue/s on site is the best way to handle erroneous raw data. The Site Data Quality Dashboard allows the user to find out what issues might be present with their data, where and when they occur, allowing the user to do a root cause analysis.

Our Solution:


The impact of the invalid/missing data is alleviated in the interim by GPS Filling (neural network fill approach), which will identify complex spatial patterns and other correlations within stockpile events through a supervised learning problem approach, which can use historical data as a learning source. In sum, this approach improves the raw data and the resulting model.

Value

  • Improved data, where events that were deemed as invalid rectified, so less data is lost;

  • More accurate 3D Block Model, that will have more correct information of events that happened within the stockpile;

  • More accurate Brains.app dashboard information, that will report to the user more authentic material content that is present in a stockpile, dumped, and reclaimed from it.

Further reading:

Did this answer your question?