An Artificial Intelligence-driven Approach to Mineral Exploration in Botswana
1.
An Artificial Intelligence-drivenApproach to
Mineral Exploration in Botswana
James AH Campbell
Managing Director, Botswana Diamonds plc
African Mining Summit (AMS 2025)
Gaborone
15-16 October 2025
2.
African Mining Summit(AMS) 2025
2
AMS 2025
An Artificial Intelligence-driven Approach to Mineral Exploration in Botswana
AGENDA
⧫ Global demand: exploration crisis
⧫ AI foundations: remote sensing, geophysics, data fusion
⧫ Company landscape and case studies
⧫ Cost/time benefits: juniors vs majors
⧫ BOD strategy: dataset and AI-screened targets
⧫ Polymetallic and kimberlite examples
⧫ AI vs traditional methods: future of AI
Marsfontein blow pit and dumps when active
Saiwa, 2025
Global Demand forCritical Minerals
⧫ Energy transition drives
unprecedented demand for
Cu, Li, Co, Ni, REEs.
⧫ Lithium demand projected >5×
by 2040; Ni/Co/REEs to at least
double.
⧫ Botswana prospective for Cu–
Ni–Co–PGEs alongside
diamonds.
⧫ Forecast supply gaps of 30–40%
by mid-2030s.
4
AMS 2025
Deloitte, 2024
5.
Exploration Crisis: RisingCosts, Fewer Discoveries
⧫ Global discovery rates have gone
down 75% since 2010 despite higher
spending.
⧫ Greenfield success rate ~0.02% (1 in
5,000 drillholes).
⧫ Deposits under cover need new
geoscience and computational tools.
⧫ AI offers systematic, data-driven
targeting.
5
AMS 2025
Bond, 2025
6.
Juniors vs Majorsin Discovery
⧫ >60% of discoveries in the past
20 years by juniors.
⧫ Majors focus on acquisitions;
juniors chiefly underfunded with
>90% failure rate.
⧫ If the junior is incubated, the
failure rate is considerably lower.
⧫ AI reduces risk and improves
financing potential for juniors.
⧫ Partnerships enable
complementary strengths.
6
AMS 2025
Visualcapitalist, 2024
Artificial Intelligence inMineral Exploration
⧫ Integrates geology, geochemistry,
geophysics, and remote sensing.
⧫ Techniques include Machine
Learning, ensembles, and Bayesian
frameworks.
⧫ Outputs: prospectivity maps, ranked
targets with uncertainty.
⧫ Continuous retraining improves
decision quality.
8
AMS 2025
Yang et al, 2024
9.
Remote Sensing andGeophysical AI
⧫ Hyperspectral/UAV imagery
mapped with Machine Learning.
⧫ AI inversion of gravity, magnetics,
and EM improves subsurface
imaging.
⧫ Data fusion across methods
reduces ambiguity.
⧫ Rapid screening focuses budgets
on highest priority targets.
9
AMS 2025
Javan et al, 2024
10.
Data Fusion andProspectivity Modelling
⧫ Combines knowledge-driven
models with Machine Learning.
⧫ Features: litho-structural context,
basin architecture.
⧫ Ensembles yield class probabilities
with uncertainty.
⧫ Governance avoids over-fitting
and bias.
10
AMS 2025
Bell Geospace, 2024
Case Study: KoBoldMetals (Zambia Copper)
⧫ Mingomba discovery: largest
Cu find in Zambia in a century.
⧫ AI targeting confirmed in ~1
year of drilling.
⧫ Portfolio learning enables
redeployment across districts.
⧫ Algorithms prioritise drilling with
maximum information.
⧫ Funded by Gates/Bezos with
$500M capital.
13
AMS 2025
KoBold, 2024
14.
Case Study: EarthAI (Australia)
⧫ ~75% drill-hole success on
AI-generated targets.
⧫ Satellite analytics + geological
Machine Learning + rapid
drilling.
⧫ Cost reductions of ~80% via
tighter targeting.
⧫ Data + execution integration
improves confidence.
14
AMS 2025
Mining.com, 2025
15.
Planetary AI 'Xplore’(Botswana)
⧫ 57+ deposit models + Machine Learning at basin/country scales.
⧫ Semantic AI grounds Machine Learning in geological context: boosting accuracy, clarifying
uncertainty and elevating confidence.
⧫ Transparent prospectivity maps with quantified uncertainty.
⧫ Supports governments and explorers.
15
AMS 2025
16.
AI Cost andTime Benefits
⧫ AI narrows search space,
improves hit ratios.
⧫ Exploration cycles compress
with automation (4x faster).
⧫ Discovery cost reduction up to
~80%.
⧫ Industry savings: $300B+ annually
by 2035.
16
AMS 2025
CleanTech, 2025
17.
Differential Impact
Juniors
⧫ AIprocesses legacy datasets
cheaply.
⧫ Raises confidence, improves
access to capital.
⧫ Outputs are transparent and
explainable.
⧫ AI-ready data rooms enhance
transactions.
17
AMS 2025
Majors
⧫ Portfolio-scale ranking and
optimisation.
⧫ Standardised data pipelines
enable comparability.
⧫ Decision analytics quantify ESG
and reserve trade-offs.
⧫ AI extends brownfields mine life.
Botswana Diamonds plc(BOD): Strategy Overview
⧫ BOD applies AI to a national-scale
archive.
⧫ Partnership with Planetary AI for
ground selection.
⧫ Focus on polymetals and diamonds.
⧫ Objective: secure licences, drill-ready
targets, JVs.
19
AMS 2025
20.
BOD Legacy Dataset(Scale & Composition)
⧫ Covers ~225,000 km², 383 GB data:
⧫ ~375,000 line km airborne geophysics.
⧫ 606 ground geophysical surveys
⧫ ~358,000 soil sample results.
⧫ ~32,000 drill logs.
⧫ Data standardised and fused for AI.
⧫ Coverage: Ngamiland, SE Botswana,
kimberlite terranes.
⧫ Enables unbiased province-scale ranking.
20
AMS 2025
21.
BOD Licence Applications:AI-Screened Results
⧫ Applications over ~7,500 km².
⧫ 11 polymetallic + 3 kimberlite targets
identified.
⧫ Selection based on permissive geology
+ adjacency.
⧫ Phased acquisition and drilling.
21
AMS 2025
22.
BOD’s Competitive Advantage
FivePillar approach
⧫ Data. BOD already has an extensive database in Botswana and proposes to acquire
more across Southern Africa.
⧫ AI technology. BOD also has access to this through an alliance with Planetary AI Xplore,
which utilises a proprietary platform which unlocks mineral wealth with advanced
knowledge-driven prospectivity analysis combined with machine learning technologies.
⧫ Government relations. The ability to apply for and receive Prospecting Licenses. BOD
has a demonstrated track record in this regard in Southern Africa.
⧫ Field and commercial skills. Once a Prospecting License has been granted, the ability
to conduct field and other technical work to achieve a rapid commercial conclusion.
BOD has a proven track record in this area, as well as running a very tight and lean
company.
⧫ Cash …
22
AMS 2025
BOD Polymetallic Targeting(Example)
⧫ Ngamiland: Cu-Pb-Zn-Ag ± V,
Co, PGEs.
⧫ SE Botswana: Cu-Ni-Co with
ultramafic/mafic hosts.
⧫ Historic Zn-Pb-Ag resources
validate predictions.
⧫ Next: geochem/EM to refine
drill collars.
24
AMS 2025
25.
BOD Kimberlite Targeting(Example)
⧫ KIM populations differentiated to
guide dispersion.
⧫ Gravity lows + magnetics identify
prospective zones.
⧫ Clusters distal from known fields
suggest new pipes.
⧫ Captured in licence applications
for drilling.
25
AMS 2025
Possible Future State(2030–2035)
⧫ District digital twins update
in real time.
⧫ Autonomous UAVs/robotic
drills with active learning.
⧫ Next-generation sensors
probe deeper cover.
⧫ Geologists as data
scientists.
28
AMS 2025
Yang et al, 2024
29.
Policy, Investment andESG Context
⧫ Strategic finance favours efficient
and successful commercial
discovery.
⧫ AI reduces footprint by focusing on
the best targets.
⧫ Auditable models aid permitting and
engagement.
⧫ Botswana's stable jurisdiction
enhances the case.
29
AMS 2025
EY.com, 2024
30.
Conclusions and StrategicOutlook
⧫ AI reshaping discovery economics.
⧫ Botswana is an ideal testbed given the
geology/data.
⧫ Juniors increase financing potential,
and majors gain optimisation.
⧫ Early adopters will dominate the next
cycle.
30
AMS 2025
Yang et al, 2024
About the Author
⧫James Campbell is Managing Director of Botswana Diamonds plc (a diamond development
company active in Botswana, South Africa and Zimbabwe and listed on London AIM and the
Botswana Stock Exchange). He has spent over forty years in the diamond industry in a variety of
leadership roles both in major and junior companies.
⧫ Previous roles include Non-Executive Director of Shefa Gems (where he is still Technical Advisor); Chief
Executive Officer and President of Rockwell Diamonds Inc; Non-Executive Director of Stellar Diamonds
plc; Vice President - New Business for Lucara Diamond Corp, Managing Director of African Diamonds
plc; Executive Deputy Chairman of West African Diamonds plc and Director of Swala Resources plc
and Bugeco sa.
⧫ James also worked at De Beers for over twenty years; his roles included General Manager for
Advanced Exploration and Resource Delivery and the Executive Chairman Nicky Oppenheimer’s first
Personal Assistant.
⧫ James holds degrees in Mining and Exploration Geology from the Royal School of Mines (Imperial
College, London University) and an MBA with distinction (and top student prize) from Durham
University. He is a Fellow of the Geological Society of South Africa, Institute of Mining, Metallurgy and
Materials, South African Institute of Mining and Metallurgy and Institute of Directors of South Africa. He
is also a Chartered Engineer (UK), Chartered Scientist (UK) and a Professional Natural Scientist (RSA).
⧫ James is also chairman and founding director of Common Purpose South Africa NPC (a not-for-profit
organization that develops leaders who can cross boundaries and is synonymous with the terms
‘cultural intelligence’ and ‘leadership beyond authority’). CPSA celebrated its twentieth anniversary
in 2020. He was also a director, trustee and chairman of the Joburg Ballet for almost fifteen years.
32
https://twitter.com/JAHC1
https://www.linkedin.com/in/jamesahcampbell/
https://www.slideshare.net/JamesAHCampbell1
https://www.youtube.com/JamesCampbell_JAC
AMS 2025
33.
References
⧫ International EnergyAgency (2025).
Global Critical Minerals Outlook. Paris: IEA.
⧫ Botswana Diamonds plc (2024–2025).
Strategy and AI exploration materials.
⧫ Planetary AI. Xplore prospectivity platform
overview and method notes.
⧫ KoBold Metals case reports and industry
coverage (e.g., Mining.com, Reuters).
⧫ Earth AI technical briefs and public case
studies (Australia).
⧫ NASA Earth Observatory. Botswana
diamond mines satellite imagery
(contextual).
⧫ Cleantech/industry analyses on AI in
exploration and discovery efficiency.
33
AMS 2025