In recent years, mining giants, including BHP and Rio Tinto, began touting the use of AI in minerals exploration, mapping, and mining. Automation has long been used successfully in mining and continues to improve processes. It began back in the 1900s. More recently, AI has been gaining in exploring for minerals and mapping them in more detail once they have been located.
BHP, Rio Tinto, and Vale announced a collaborative effort to pursue AI/Machine Learning applications for mineral exploration in early 2024. They have pledged to share knowledge and technological advancements. An article by Forte Precious Metals describes the potential geological benefits of applying machine learning and AI to delineate mineral deposits. These are summarized below:
As an article by BHP notes,
AI can be employed throughout the mining value chain for optimization of many
processes. On-site sensors and other monitoring systems collect data that can
be analyzed to inform decisions.
“Over the years, AI has helped BHP unlock potential
value through innovations such as predictive maintenance, energy optimisation,
autonomous vehicle and machinery operation, data-driven decision making and
real-time monitoring and reporting. AI is helping keep our workers safe. It is
building efficiency in what we do. It is helping to solve operational problems
and realise new business opportunities. It is helping increase our speed of
resource discovery. It is optimising our ore quality and improving customer
management. It is helping reduce our power and water consumption.”
AI can develop advanced
algorithms to identify mineral deposits and optimize processes. AI can
incorporate many different kinds of data into composite exploration models. BHP
notes that AI, along with human ingenuity, led to new copper deposit
discoveries in Australia and the U.S. They also tout advances in the
geophysical technique of muon tomography. Muons are a type of cosmic radiation
that can be used to scan and map underground formations. In alliance with
partner Ivanhoe Electric, they are generating better signals and interpreting
tomography data with machine learning algorithms. This is used to search for
sulfide deposits of copper, nickel, gold, and silver at depths of over 1.5km.
AI has found success in the
realm of predictive maintenance. Collecting data can enable the prediction of
maintenance needs, timing, and assist maintenance planning, reducing downtime
and saving money. It can assess equipment health and improve safety. BHP runs
predictive analytics models on its material transports and handling systems.
They note that AI was key to the mitigation of a vibration problem at a
materials handling facility.
In mining and other fields,
AI is used for energy management, which leads to efficiencies that save money,
reduce impacts and emissions, and reduce water use. AI can analyze and optimize
energy use.
BHP touts the use of AI in
environmental science as acoustic monitoring for endangered species calls,
combined with satellite, drone imagery, and object detection.
Autonomous mining vehicles
have proved successful. There is still a need to improve safety in more
populated areas. BHP also pioneered autonomous long-haul rail transport from
mines.
“Automation can improve productivity and utilise less
energy by implementing streamlined, repetitive actions. These autonomous
systems can navigate challenging terrains and perform tasks with precision,
reducing the likelihood of human error.”
According to an article in
Engineering & Mining Journal:
“Rio Tinto estimates that, on average, during 2018, each
of its autonomous trucks operated 700 hours more than conventional haul trucks
would, with 15% lower costs, delivering clear productivity benefits. It noted
that these systems also take truck operators out of harm’s way, reducing the
risks associated with working around heavy machinery.”
Rio Tinto has a Mine
Automation System (MAS) that acts as a server to coordinate and integrate the
large amounts of data. The visual displays available to employees are the
result of a 3D visualization tool based on a gaming engine. The MAS also allows
them to integrate data from different manufacturers.
“At our bauxite mine in Weipa, special mathematical
software helps our port schedulers manage hundreds of ships a year. Using data
in these ways helps us minimize downtime, reduce energy use and cut operating
costs,” Rio Tinto added. “Every day our automated drills, trucks, shovels,
conveyors, trains and ships produce huge amounts of valuable data. By combining
this data with clever analytics, AI, ML and automation, we are making our
business safer and more productive.”
A similar central automation
system, called The Hive, has been developed by Australian iron ore producer
Fortescue Metals Group (FMG), strategically integrating AI for efficiency,
safety, and sustainability. It remotely manages the supply chain from pit to
port, they say. See below:
“AI is becoming increasingly valuable to Fortescue’s
operations, unlocking significant time and cost savings,” said the company on
its website. “By automating routine tasks and removing manual processes, AI
empowers our teams to focus on higher-level problem-solving and
decision-making. Tools, such as schedule optimization software, chatbots, and
AI-driven product design are examples of how this technology is used to enhance
operational efficiency.”
BHP is building digital twins
to identify key performance drivers, risks, and opportunities for optimization.
This has resulted in improvements in mine haulage, ore fragmentation, material
handling, and in debottlenecking surface operations. Digital twins can provide
insight that can optimize material flows in mines and processing plants.
Digital twins can be integrated into advanced process controls to tweak
real-time data to inform ore blending and setpoint adjustments. Microsoft Azure
is one program that can run digital twins. BHP explains another success:
“To increase copper production at Escondida, we use
advanced analytics to understand the impacts of different ore characteristics
and granulometry on semi-autogenous grinding (SAG) mill performance,” the
company explained in an online article. “A digital twin of the Escondida value
chain and Gen AI models inform ore blasting and blending strategies, identify
mine areas with challenging ore characteristics, and support the implementation
of SAG mill model predictive control. By mitigating the impacts of varying
mineral characteristics, we have reduced monthly production losses due to
granulometry by an average of 70%.”
BHP recently added Gen AI to
a digital twin, which enables non-technical employees to ask questions. This
may lead to more insights and the discovery of more performance improvements.
Engineering & Mining
Journal reports that a 2018 collaboration between Freeport McMoran and McKinsey
data scientists resulted in vast improvements at the Bagdad mine in Arizona.
“We put in the recommended AI engine and saw 10%
improvement in production,” said Cory Stevens, President, Mining Services at
Freeport in the McKinsey case study. “And we thought, if we do the
implementation at all seven of our sites right, it’s almost like having a
brand-new plant without having to go through permitting processes and
disturbing a new area. It’s in the billions of dollars that we’re offsetting by
going through the transformation.”
In Western Australia, BHP
utilizes eight automated ship loaders at its Port Hedland Export Facility that
are operated remotely from Perth. Mine trucks continue to be converted from
manual to autonomous. These actions have led to increased productivity and
improved safety. They have also implemented AI-integrated wearable health
devices to monitor employee health, even a hard hat that can analyze brain
waves to predict driver fatigue. They can identify safety issues.
O&M costs for mining
equipment can be high and result in downtime and lost productivity.
“Implementing predictive and prescriptive maintenance
approaches using AI and ML algorithms can help miners to take a proactive
stance on the maintenance of vehicles and machinery, lowering the cost of
materials, parts and labor and reducing the likelihood of equipment failures.”
The use of digital signals
for predictive maintenance is a new way of assessing equipment health. Canadian
company Teck chose AspenTech’s MTell for their predictive maintenance program.
“Mtell has a broad set of monitoring technologies,
including rules-based and condition-based monitoring, first principles
modelling, AI, ML and custom models from data science teams.”
“Teck used signals, like vibration, pressure, flow,
temperature and current, to build Mtell agents and identify and monitor real
time changes, like differential pressures in bag houses; water flow and
temperature in furnace cooling systems; heat exchanger temperature
differentials and current for pumps.”
Teck is partnered with Google
Cloud and Pythian. They have had significant success in identifying maintenance
issues early, even unexpected ones. The project has resulted in very
significant cost savings.
AI can also be used to design
better mines and do it faster. It can also be used to optimize energy use and
water use.
BHP also compares mining AI
to AI in other areas such as healthcare, finance, manufacturing,
transportation, and agriculture, noting that it is used universally for
predictive maintenance, asset optimization, automation, and optimized
extraction processes. Uses are summarized below.
Deloitte noted in the 2025
edition of their annual Tracking the Trends report:
“When treated as part of a systematic approach to
mineral exploration, precompetitive geoscience data on properties and deposits
can be leveraged by geologists [alongside AI] to better inform their
exploration programs. This, in turn, can generate cost and time savings… It can
also speed the identification of potential drill targets and help companies
better understand mineralization systems that could lead to subsequent
discoveries.”
AI can help high-grade
mineral prospects and find the highest concentrations. Deloitte details some of
these capabilities in their Tracking the Trends 2025 report, specifically Trend
4: Enhancing Mineral Exploration with AI: Utilizing Precompetitive Geoscience
Data.
Precompetitive geoscience data can be leveraged for faster and more successful exploration timelines with the help of AI and data analytics.
Deloitte notes the collaboration between
U.S. Critical Minerals Corp. and U.S.-based VerAI Discoveries.
“VerAI’s methodology combines AI/ML technology with
geoscience knowledge to generate an objective, reproducible targeting platform
for use in mineral exploration. This utilizes tailor-made datasets for
undercover location of economic greenfield and brownfield mineral deposits.
VerAI generates high-probability target portfolios that are at drill-ready
stage, then collaborates with explorers to develop them. Value id generated
through monetizing equity and royalty from successful assets. The company
claims its approach can increase the probability of success in discovering
economic deposits by two orders of magnitude and reduce targeting costs by more
than 90%.”
Below are Deloitte’s
recommendations for optimizing the use of precompetitive geoscience data:
Deloitte also covers the use
of AI in business models, the use of Gen-AI in workforce development, digital
twins, smart operations, smart leadership, and smart business modeling.
S&P Global notes:
“Since OpenAI LLC's release of the GPT-3 large language
model, AI has emerged as one of the most exciting and debated topics within the
investor community.”
They also note that there are risks, including “high integration costs, data security concerns, overreliance on empirical and modeled data, and ethical dilemmas.” As shown below, they note that “surged 30% from November 2022 — when OpenAI launched the chatbot app — to November 2023.”
Automation
in mining is long established, but integrating AI with the automation continues
to evolve. At Rio Tinto’s Pilbara mine in Western Australia:
“AI has been integrated into mine automation and
simulation systems, autonomous trucks, drills, trains, water carts,
long-distance heavy-haul trains and a fully automated laboratory. In addition,
about 80% of the haul truck fleet at Pilbara operations is now automated, with
Rio Tinto operating about 200 trains through its proprietary AutoHaul
technology. According to the company, these automation efforts improve
efficiency and safer operations by eliminating driver error.”
S&P Global also notes
that AI can be combined with remote sensing data to help detect illegal mining
sites. They note that the alliance of tech and mining is showing great results.
Examples are numerous.
“US-based mining startup KoBold Metals Co., which
recently raised $537 million in funding to develop existing projects into mines
— including the Mingomba copper mine in Zambia — through its proprietary
TerraShed system and Machine Prospector software. A significant portion of
their funding success was attributed to the company's AI-driven approach to
exploration.”
“In 2018, before its acquisition by Newmont Mining
Corp., Goldcorp Inc. developed an AI model in conjunction with IBM Canada Ltd.
to enhance predictability for gold exploration at the Red Lake project in
Ontario and accelerate target identification through machine learning and
spatial analytics.”
“Fleet Space Technologies Pty Ltd., an Australia-based
tech firm, recently partnered with Barrick Gold Corp. to implement AI-driven
exploration at its Reko Diq copper mine in Pakistan. Utilizing Fleet Space
Technologies's ExoSphere system, copper exploration is enhanced through 3D
subsurface maps that help identify features such as groundwater systems and
copper ore bodies. The system aims to accelerate exploration at the site while
minimizing the environmental impact associated with traditional exploration methods.”
Regarding the risks of AI,
S&P notes:
“Integrating and maintaining AI systems can be costly.
Whether these expenses are factored into total minesite costs or development
and expansion capital expenditures, mining companies will need to grapple with
additional costs for purchasing hardware and software, training the workforce
and providing ongoing technical support and maintenance.”
Canadian Company GeologicAI is Analyzing Core with AI and
Integrating with Other Data
Canadian company GeologicAI
is integrating core analysis, XRF, hyperspectral analyses, and RGB imaging with
AI algorithms to speed up standard core logging by 4 times. Turnaround times
are typically 24-48 hours. This can accelerate projects and free up geologists
to do more data interpretation and less data acquisition.
This can lead to better
mapping of mineral zonation. AAPG Enspired editor Sarah Compton cites quotes
from mining executives. The VP of Ventures at BHP, Laural Buckner, pointed out
that:
“GeologicAI is addressing one of the mining sector’s
most pressing challenges…Their game-changing technology is disrupting
traditional time– and cost-intensive workflows with AI-powered analytics and
modeling solutions. This technology has the power to reshape how we discover,
evaluate, and source ore bodies.”
The Head of Growth and
Ventures at Rio Tinto, Pekka Santasalo, also praised GeologicAI:
“Their high-resolution approach and real-time data
capabilities have the potential to transform how we think about project
development timelines and risk.”
BHP and Rio Tinto, along with
Blue Earth Capital, are funding GeologicAI, announcing in July $44 million in
Series B funding. GeologicAI described their capabilities and what they plan to
do with the capital:
“Our solution combines cutting-edge sensors, advanced
AI, and deep geoscience expertise to intensively scan drill core onsite, and to
analyze, interpret, and visualize this enhanced data in real time. The result?
A new standard in high-resolution data and decision-making.”
With this new investment, we will:
· Expand
to more mining jurisdictions across five continents
· Advance
our proprietary AI tools and hardware
· Deliver
even greater value to our strategic customers and partners
Carmichael Roberts of
Breakthrough Energy Ventures noted:
“GeologicAI’s AI-driven process is accelerating the
discovery and development of new deposits, strengthening the mineral pipeline
that’s essential for electrification.”
References:
AI
Comes for Your Core. Sarah Compton. AAPG Enspired. July 29, 2025.
GeologicAI
Raises $44M Series B. GeologicalAI. July 17, 2025. GeologicAI
Raises $44M Series B — GeologicAI
Artificial
Intelligence is unearthing a smarter future. BHP. August 1, 2024. Artificial
Intelligence is unearthing a smarter future
Mining
Giants Unite: AI-Powered Revolution in Mineral Exploration: Explore the
collaboration of mining behemoths BHP, Rio Tinto, and Vale as they harness
AI-powered mineral exploration. Forte Precision Metals. January 30, 2024. AI-Powered
Revolution in Mineral Exploration
AI:
Bringing Mining Companies Closer to Their Data. Carly Leonida, European Editor.
Engineering & Mining Journal. April 2025. AI:
Bringing Mining Companies Closer to Their Data - E & MJ
Innovative
leadership and AI integration pave the way in the mining and metals sector.
Deloitte. January 29, 2025. Innovative
leadership and AI integration pave the way in the mining and metals sector |
Deloitte Australia
A peek
at AI revolution in mining: promise meets peril. Jasper Ivan Madlangbayan
Tamara Thorne. S&P Global. February 25, 2025. A
peek at AI revolution in mining: promise meets peril | S&P Global
Tracking
the Trends 2025. Leading through transformational change in ming and metals.
Deloitte. Tracking
the trends 2025
No comments:
Post a Comment