The Current Landscape of Mineral Exploration

We already know that almost everyone in mineral exploration has traditionally relied on tried-and-true practices, but these are not without their challenges. From Geologists to DBAs often find themselves using paper/pdf plods, interpreting handwritten logs, and manually logging intricate details of their findings. Although these methods have stood the test of time, they can be inefficient and lead to data inconsistencies.

I've written extensively about the the high costs of this low tech. Geologists spend countless hours transferring data to spreadsheets and ensuring its accuracy, which diverts them from interpreting data and making pivotal decisions. To address these issues, drill contractors are increasingly moving towards digital systems to improve data management, accuracy, and collaboration among exploration teams. But are mining companies ready using this data effectively?

Traditional data management systems often lack transparency and insight, which can result in misunderstandings, disputes, and even derailment of drill programs. However, with the global digital revolution and the increasing availability of sophisticated technological tools, the industry is shifting towards modern, data-driven approaches.

But with Siloe’d franken-stack of dated on-prem systems, SQL databases and non automated processes make it difficult to make the shift from the old way to data driven operations, let alone surfacing insights using AI.

As Alex aptly says it, "Exploration is no longer a walk in the bush - it's much more complex to make a discovery today." The need for these modern approaches in mineral exploration has never been more evident.

‍

The Potential of AI in Drilling Data Analysis: A Guide for Exploration Managers, Geological Data Managers, and Geologists

While I'm more at home kicking rocks than interpreting drill cores, my daily interactions with exploration managers, data managers, geologists, and MDs have given me a deep appreciation for the immense challenges and risks they face during drilling operations.

Every phase, from predrilling assessments to post-drilling evaluations, is critical. Could AI offer tools tailored to enhance each of these stages, promising a more streamlined, efficient, and insightful drilling program? Here are some thoughts on a high level.

Predictive Analysis for Strategic Planning: Imagine if Exploration Managers could leverage AI to optimize predrilling assessments. By analyzing historical data, could AI predict ground conditions, helping managers anticipate challenges and allocate resources effectively - especially when it comes to sourcing drill contractors and geology teams? This could ensure that exploration strategies are not only data-driven but also proactive in addressing potential hurdles.
Real-time Insights for Drill Hole Progress: As drilling commences, geologists could potentially benefit from AI-driven insights into drill hole progress. AI algorithms could analyze data in real-time, offering immediate feedback on the depth, angle, and geological formations being encountered. These real-time insights, generated based on countless datasets, could be invaluable for geologists, allowing them to adapt strategies based on the ground realities.
Optimized Data Management and Program Budgeting: Geological Data Managers often face the daunting task of managing vast datasets, from earthworks data to tenement expenditure. Could AI streamline this, offering tools for automated data categorization, analysis, and retrieval? Furthermore, AI could potentially assist Exploration Managers in program budgeting, analyzing historical expenditure data to predict costs and optimize budget allocations.
Safety and Operational Protocols: AI's ability to predict potential safety hazards based on historical accident data could be a boon for both Exploration Managers and Geologists. This has already been proven in other industries such as shipping. But coming back to drill program operations, think of how post-drilling evaluations could be conducted and analyzed to offer insights into equipment and consumables performance to on the ground process optimization.
Enhanced Collaboration through Data Integration: Geological Data Managers could potentially harness AI to integrate data from various phases of the drilling program, from predrilling assessments to post-drilling evaluations. Think about having identified anomalies instantly or red flags based on data being received or ‘verified’. This could ensure that all stakeholders, be it the exploration manager or the on-ground geologist, have a holistic view of the program. Such a unified perspective could be crucial for strategic decision-making, especially when considering earthworks and tenement expenditure.
Post-Drilling Analysis and Reporting: Once drilling concludes, AI could potentially assist in post-drilling data analysis, offering insights into the success of the program, deviations from initial predictions, and areas of improvement. This data could be invaluable for Exploration Managers as they plan future drilling programs and allocate resources.

For those at the forefront of drill programs in Mining and Exploration companies, embracing AI is not just about adopting new technology; it's about envisioning a revolution in the entire drilling process.

From the initial planning stages to post-drilling evaluations, AI promises to enhance efficiency, accuracy, and collaboration, potentially setting the stage for a new era in mineral exploration.

‍

Steps to Make Your Company AI-Ready: A Guide for Mineral Exploration

The potential of AI in drilling data analysis is vast, but how can a company in the mineral exploration industry prepare to embrace this technology?

The journey to AI readiness involves a series of strategic steps:

Digitization: The first step towards becoming AI-ready is to enable digital data capture. This means investing in infrastructure such as a Drilling Program Data Platform like CorePlan or a Geological Database like MXDeposits. For those brave enough, investing in AWS and Snowflake might be worthwhile, but this can be brought in after the initial data infrastructure is set up. The stage then involves transitioning the culture from traditional, manual methods of data collection to more systematic and digital methods. By removing low-value manual tasks from knowledge workers, you can ensure data consistency, accuracy, and availability, setting the stage for further transformation.
Digitalization: The next step is to streamline and automate internal processes. This further removes manual tasks and allows for seamless data cleaning, transformation, and normalization. By digitalizing your operations, you're not only improving efficiency but also preparing your data for advanced analysis.
Data-Driven Problem Solving Operations: With digitization and digitalization in place, your company can move towards data-driven operations. Upskilling your team to use data for good at this stage is important. Focus on the metrics that matter to solve problems instead of barking at ghosts or just making pretty charts using their new BI tool. By providing the right training, you not only ensure that staff are able to effectively use and interpret data but also foster a data-driven culture and enable continuous learning and adaptation. Once you've equipped your employees, they can use real-time reports and conduct analysis across the organization. This stage allows you to identify the problems you're facing and really understand how to use data to solve them. This is absolutely critical for the next step.
AI-Driven Operations: Once you have a thorough understanding of your data and have identified how it can solve your problems, you can move towards AI-driven operations. This stage involves building trained models based on the insights gained in the data-driven operations stage. AI-driven operations can provide deeper insights, predictive analysis, and automated decision-making.

‍

Start Small and Scale Up

‍One important lesson we've learned from onboarding 80+ companies at CorePlan, and from my previous experience in tech, is that it's easy to make a mistake by trying to do too much too quickly. Many organizations that aim for perfection right from the start end up moving slower, facing complex problems, and even stagnating.

Instead, it's important to prioritize ruthlessly and begin with a small, manageable project. This approach lets you test the waters, learn from mistakes, and build confidence within your team.

Navigating the data world can feel like a maze, and getting AI-ready might seem like a huge mountain to climb. But let's not forget the cool stuff AI can bring to the table - better efficiency, smarter decision-making, saving bucks, and reducing risks.

Sure, there'll be bumps along the road, and yep, it'll need a bit of a mindset shift. But with the right game plan, the right backup, and a dash of adaptability, it's totally doable.

Adopting AI is not just about new technology, it's about revolutionizing the entire drilling process and being at the forefront of a new era in mineral exploration.

If you're keen to chat about getting AI-ready with your drilling data, I'm all ears. Shoot me a message, and let's get the ball rolling.

‍

This post was also published on Sachee's Medium Account

Download the checklist here

Drilling into the future: Is your drilling data ready for AI?

Download the checklist here

Related Articles