Botswana Minerals Plc · LSE:BMIN
Botswana Minerals — Botswana Diamonds — African Exploration Showcase 2025
34 slides from Botswana Minerals's conference presentation, Nov 13, 2025
Slide 1: An Artificial Intelligence-driven Approach to Mineral Exploration in Botswana
An Artificial Intelligence-driven Approach to Mineral Exploration in Botswana James AH Campbell Managing Director, Botswana Diamonds plc African Exploration Showcase Geological Society of South Africa Johannesburg 13 November 2025
Slide 2: Agenda
African Exploration Showcase 2025 An Artificial Intelligence-driven Approach to Mineral Exploration in Botswana Marsfontein blow pit and dumps when active AGENDA ⧫ Global demand: exploration crisis ⧫ AI foundations: remote sensing, geophysics, data fusion ⧫ Company landscape & case studies ⧫ Cost/ti
Slide 3: Global demand: exploration crisis
Global demand: exploration crisis AES, GSSA 2025 3
Slide 4: Global Demand for Critical Minerals
Global Demand for Critical Minerals ⧫ The energy transition is accelerating demand for copper, lithium, cobalt, nickel, graphite and rare earths used in batteries, renewables and grid storage. ⧫ Authoritative outlooks indicate lithium demand may rise more than fivefold by 2040, with nickel, cobalt a
Slide 5: Exploration Crisis: Rising Costs, Fewer Discoveries
Exploration Crisis: Rising Costs, Fewer Discoveries ⧫ Global discovery rates have fallen significantly since 2010 despite higher spend; greenfield success is commonly cited at ~0.02% (≈1 in 5,000 drillholes). ⧫ Shallow, outcropping deposits are largely exhausted; deeper targets under cover require n
Slide 6: Juniors vs Majors in Discovery
Juniors vs Majors in Discovery ⧫ Historically, >60% of commercial discoveries are credited to junior explorers who specialise in high-risk front-end work. ⧫ Majors increasingly replace reserves by acquiring advanced projects rather than leading greenfield search in frontier terrains. ⧫ Tighter capit
Slide 7: AI foundations: remote sensing, geophysics, data fusion
AI foundations: remote sensing, geophysics, data fusion AES, GSSA 2025 7
Slide 8: Artificial Intelligence in Mineral Exploration
Artificial Intelligence in Mineral Exploration ⧫ AI integrates geological, geochemical, geophysical and remote-sensing data to reveal patterns that are difficult to detect with manual methods. ⧫ Common techniques include supervised and unsupervised learning, ensemble models, anomaly detection and Ba
Slide 9: Remote Sensing and Geophysical AI
Remote Sensing and Geophysical AI ⧫ Multispectral/hyperspectral satellites and UAVs map alteration, structure and regolith; AI automates pixel-to-mineral information extraction. ⧫ Machine Learning assisted inversion and clustering of gravity, magnetics, and EM improve depth estimates and structure/h
Slide 10: Data Fusion and Prospectivity Modelling
Data Fusion and Prospectivity Modelling ⧫ Knowledge-driven rules (deposit models, expert features) are combined with data-driven learning to compute pixel-level prospectivity. ⧫ Feature engineering captures litho-structural context (e.g., contacts, dilational jogs, dyke swarms, basin architecture) a
Slide 11: Company landscape and case studies
Company landscape and case studies AES, GSSA 2025 11
Slide 12: Select Companies Applying AI
Select Companies Applying AI ⧫ KoBold Metals applies decision theoretical targeting ('Intelligent Prospector') to accelerate discovery of Cu–Ni–Co–Li deposits. ⧫ Earth AI integrates in-house data science with nimble drilling capability, reporting materially higher drill-hit ratios than historical no
Slide 13: Case Study: KoBold Metals (Zambia Copper)
Case Study: KoBold Metals (Zambia Copper) ⧫ Applied Machine Learning and decision analytics to legacy and new data, delineating the Mingomba orebody reported as Zambia’s most significant copper discovery in a century. ⧫ Rapid drill confirmation (~1 year) contrasts with typical multi-year campaigns i
Slide 14: Case Study: Earth AI (Australia)
Case Study: Earth AI (Australia) ⧫ Reports ~75% drill-hole success on AI-generated targets versus sub-1% historical norms for greenfields in similar terrains. ⧫ Combines satellite analytics, geological Machine Learning and rapid drilling to close the loop between prediction and testing. ⧫ Cost reduc
Slide 15: Planetary AI 'Xplore' (Botswana)
Planetary AI 'Xplore’ (Botswana) ⧫ Combines 57+ deposit models with Machine Learning to compute prospectivity at multiple scales ('glass-box' interpretability). ⧫ Semantic methods capture geological context (e.g. proximity to structures, host lithologies, permissive facies). ⧫ Delivers ranked target
Slide 16: AI Cost and Time Benefits
AI Cost and Time Benefits ⧫ AI narrows search space early, focusing drilling on high-probability targets and lifting drill-hit ratios from sub-1% to orders-of-magnitude higher in some reports. ⧫ Exploration cycles compress (planning → test → learn) through automated data prep, rapid modelling and ad
Slide 17: Differential Impact
Differential Impact Juniors Majors ⧫ Juniors can leverage AI to process large ⧫ Majors can apply AI at portfolio scale to legacy datasets, lifting target quality rank districts, optimise capital allocation without adding fixed headcount. and integrate brownfields with greenfields. ⧫ Higher-confidenc
Slide 18: BOD strategy: dataset and AI-screened targets
BOD strategy: dataset and AI-screened targets AES, GSSA 2025 18
Slide 19: Botswana Diamonds plc (BOD): Strategy Overview
Botswana Diamonds plc (BOD): Strategy Overview ⧫ BOD’s strategy is to exploit a proprietary, comprehensive Botswana dataset accumulated over ~20 years and to apply AI for rapid prospectivity screening. ⧫ Partnership with Planetary AI enables country-scale analysis before license applications, improv
Slide 20: BOD Legacy Dataset: Scale & Composition
BOD Legacy Dataset: Scale & Composition ⧫ ~225,000 km² of spatial coverage and ~383 GB of data comprising: ⧫ ~375,000 line km airborne geophysics, ⧫ 606 ground geophysical surveys, ⧫ ~358,000 soil sample results and ⧫ ~32,000 drill logs. ⧫ Datasets were standardised, georeferenced and fused for AI i
Slide 21: BOD License Applications: AI-Screened Results
BOD License Applications: AI-Screened Results ⧫ First AI pass generated applications over ~7,500 km²: 11 polymetallic and 3 kimberlite targets meeting de-risking criteria. ⧫ Selection emphasised permissive geology, multi-commodity potential and adjacency to undercapitalised neighbours. ⧫ AI ranking
Slide 22: BOD's Competitive Advantage
BOD’s Competitive Advantage Five Pillar 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 unloc
Slide 23: Polymetallic and kimberlite examples
Polymetallic and kimberlite examples AES, GSSA 2025 23
Slide 24: BOD Polymetallic Targeting: Examples
BOD Polymetallic Targeting: Examples ⧫ Ngamiland terranes flagged as permissive for Cu-Pb-Zn-Ag with associated V-Co-Ge-Au-PGE signatures across multiple deposit styles. ⧫ SE Botswana blocks prioritised for Cu-Ni-Co with ultramafic/mafic hosts and shear-related traps. ⧫ Historic resources and showin
Slide 25: BOD Kimberlite Targeting: Examples
BOD Kimberlite Targeting: Examples ⧫ Indicator mineral (KIM) differentiation isolates key garnet/spinel populations that drive dispersion trends. ⧫ Geophysical context (gravity lows, moderate magnetics) is used to focus under-cover kimberlite searches. ⧫ Clusters of KIMs far from known fields sugges
Slide 26: AI vs traditional methods: future of AI
AI vs traditional methods: future of AI AES, GSSA 2025 26
Slide 27: AI vs Traditional Exploration
AI vs Traditional Exploration ⧫ Traditional: sequential, expert-led overlay mapping; slow feedback and limited hypothesis throughput. ⧫ AI-enabled: parallel hypothesis generation, probabilistic ranking and adaptive survey design with rapid feedback loops. ⧫ Explainability and uncertainty quantificat
Slide 28: Possible Future State (2030–2035)
Possible Future State (2030–2035) ⧫ Digital twins of districts/ore bodies that update with drilling, sensing and operational data to guide real-time decisions. ⧫ Autonomous UAVs and robotic drills integrated with active learning to test the highest potential holes first. ⧫ Next-generation sensors (q
Slide 29: Policy, Investment and ESG Context
Policy, Investment and ESG Context ⧫ Critical-minerals policies (US, EU and others) and strategic finance favour projects that demonstrate efficient, low-impact and successful commercial discovery. ⧫ AI reduces unnecessary disturbance by focusing work on the highest-probability targets and documenti
Slide 30: Conclusions and Strategic Outlook
Conclusions and Strategic Outlook ⧫ AI is reshaping exploration economics by raising hit rates, compressing timelines and lowering unit costs across commodities and terrains. ⧫ Botswana’s geology, data depth and stability make it an ideal proving ground for AI-enabled exploration. ⧫ For juniors, exp
Slide 31: Thank You Questions & Discussion
Thank You Questions & Discussion Photo: Andreas Stelzer AES, GSSA 2025 31
Slide 32: References
References ⧫ International Energy Agency (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.
Slide 33: About the Author
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 rol
Slide 34: Contact details
162 Clontarf Road Clontarf Dublin 3 Ph: +27 83 457 3724 Web: www.botswanadiamonds.co.uk Twitter: @BotswanaDiamond Email: james@botswanadiamonds.co.uk AES, GSSA 2025 34
Botswana Diamonds — African Exploration Showcase 2025 on 6ix