Log in

goodpods headphones icon

To access all our features

Open the Goodpods app
Close icon
Fresh Thinking by Snowden Optiro - 101: Machine Learning - Case Study

101: Machine Learning - Case Study

03/13/25 • 9 min

Fresh Thinking by Snowden Optiro

101: Machine Learning – Case Study

In this podcast, Susan Havlin, Managing Consultant APAC and Dr Gregory Zhang, Senior Geology Consultant discuss the application of machine learning for geological domaining in Resource Estimation, with specific reference to a project that Dr Gregory Zhang worked on.

This podcast at a glance:

1.21 A case study using the k-means algorithm

0.55 Why was an alternative approach needed?

2:10 What is the k-means algorithm and why is it suitable?

3:10 What steps were used to apply k-means to the data set?

4:20 What were the key outcomes?

5:20 Any limitations?

7:40 Speed of getting results

8:12 Who can use this method?

If you'd like to connect with Susan Havlin and Dr Gregory Zhang, please email them: [email protected]

This audio podcast is also available as a free video podcast on Snowden Optiro’s YouTube channel.

Snowden Optiro is a resources consulting and advisory group that provides independent advice, consulting and training to mining and exploration companies, their advisors and investors. We help mine developers to advance their projects, mining companies to improve their operations and their professionals, and investors to de-risk their investments by the provision of quality advice, training and software in the field of Mineral Resources and Mineral/Ore Reserves.

https://snowdenoptiro.com

https://snowdenoptiro.com/professiona...

[email protected]

plus icon
bookmark

101: Machine Learning – Case Study

In this podcast, Susan Havlin, Managing Consultant APAC and Dr Gregory Zhang, Senior Geology Consultant discuss the application of machine learning for geological domaining in Resource Estimation, with specific reference to a project that Dr Gregory Zhang worked on.

This podcast at a glance:

1.21 A case study using the k-means algorithm

0.55 Why was an alternative approach needed?

2:10 What is the k-means algorithm and why is it suitable?

3:10 What steps were used to apply k-means to the data set?

4:20 What were the key outcomes?

5:20 Any limitations?

7:40 Speed of getting results

8:12 Who can use this method?

If you'd like to connect with Susan Havlin and Dr Gregory Zhang, please email them: [email protected]

This audio podcast is also available as a free video podcast on Snowden Optiro’s YouTube channel.

Snowden Optiro is a resources consulting and advisory group that provides independent advice, consulting and training to mining and exploration companies, their advisors and investors. We help mine developers to advance their projects, mining companies to improve their operations and their professionals, and investors to de-risk their investments by the provision of quality advice, training and software in the field of Mineral Resources and Mineral/Ore Reserves.

https://snowdenoptiro.com

https://snowdenoptiro.com/professiona...

[email protected]

Previous Episode

undefined - 100: A thorny and divisive topic!

100: A thorny and divisive topic!

In this episode, Ian Glacken our Executive Consultant in Perth, Australia discusses the thorny and divisive topic about whether we should be trying to minimise conditional bias in an estimate or should we be striving for a better idea of grade/tonnage relationship at the time of mining? Ian is joined in this discussion by Graeme Lyall our Executive Consultant who is based in Santiago, and Dr Oscar Rondon, Principal Geostatistician Datamine.

1:26 This podcast video at a glance

3:03 What is conditional bias

4:19 Schools of thought about conditional bias

6:19 The kriging oxymoron

7:00 The least of 2 evils

7:47 Important difference between the 2 schools of thought

8:40 Conditional bias and smoothing

11:42 What is KNA?

15:00 Discrete Gaussian method

Suggested papers to read.

D.G Krige - A practical Analysis of the effects of spatial structure and of data available and accessed, on conditional biases in ordinary kriging.

Quantitative kriging neighbourhood analysis for the mining geologist - A description of the method with worked case examples by J.Vann, S. Jackson and Olivier Bertoli.

If you'd like to connect with Ian, Graeme or Oscar please email them: [email protected]

This podcast is also available as a free video podcast on Snowden Optiro’s YouTube channel: https://www.youtube.com/playlist?list=PLZm0zjSNmpo27fX_tfI79Yzhxy3VXjvMt

Snowden Optiro is a resources consulting and advisory group that provides independent advice, consulting and training to mining and exploration companies, their advisors and investors. We help mine developers to advance their projects, mining companies to improve their operations and their professionals, and investors to derisk their investments by the provision of quality advice, training and software in the field of Mineral Resources and Mineral/Ore Reserves.

https://snowdenoptiro.com

https://snowdenoptiro.com/professiona...

Email: [email protected]

Next Episode

undefined - 102: Cleaner - Quieter - Safer

102: Cleaner - Quieter - Safer

Discover how battery electric vehicles (BEVs) are transforming underground mining operations. In this episode of Fresh Thinking by Snowden Optiro, Managing Consultant Hamish Guthrie chats with Principal Consultant Sarah de Vries about the significant safety and health benefits of battery-operated vehicles (BEVs)—improved air quality, lower heat, reduced noise, and less vibration. They also discuss the challenges of transitioning to electric fleets and the future of mine electrification.

This podcast at a glance:

0:00 – Introduction

1:00 – Why are mining companies moving towards BEVs?

1:40 – How BEVs improve underground air quality and OHS

2:45 – Heat reduction: BEVs vs Diesel engines

3:45 – Noise & vibration reductions with BEVs

5:00 – Applications that benefit most from BEVs

5:50 – Challenges of adopting BEVs underground

7:00 – Future of mine electrification

If you'd like to connect with Hamish Guthrie and Sarah de Vries, please email them: [email protected]

This video podcast is also available as a free video podcast on our Snowden Optiro YouTube channel.

Snowden Optiro is a resources consulting and advisory group that provides independent advice, consulting and training to mining and exploration companies, their advisors and investors.

We help mine developers to advance their projects, mining companies to improve their operations and their professionals, and investors to de-risk their investments by the provision of quality advice, training and software in the field of Mineral Resources and Mineral/Ore Reserves.

https://snowdenoptiro.com

https://snowdenoptiro.com/professiona...

[email protected]

Episode Comments

Generate a badge

Get a badge for your website that links back to this episode

Select type & size
Open dropdown icon
share badge image

<a href="https://goodpods.com/podcasts/fresh-thinking-by-snowden-optiro-394315/101-machine-learning-case-study-87358316"> <img src="https://storage.googleapis.com/goodpods-images-bucket/badges/generic-badge-1.svg" alt="listen to 101: machine learning - case study on goodpods" style="width: 225px" /> </a>

Copy