CASE STUDY I.OT CYBERSECURITY FOR REFINING OPERATIONS*
1. The challenge: BEC/VEC targeting scada supply chain.
*Composite case based on representative engagements in Texas refining sector.
Profile: Midstream operator with Houston HQ + Gulf Coast refinery
The Threat Vector: Business Email Compromise attacks impersonating
critical valve/maintenance suppliers. Attackers request ACH changes
and deliver malware targeting OT networks.
The Risk Model: Successful infiltration into SCADA forces preventative
shutdown for containment. Industry benchmark: $50,000/hour average
loss in Texas refining operations [Source: U.S. DOE, 2024].
The solution: Behavioral AI + MSP model
Deployment: Abnormal Security implemented via managed services partner
for 24/7 OT/IT email monitoring.
Detection: Behavioral AI flags anomalous vendor behavior - login geography,
tone deviation, invoice structure - despite legitimate domain SPF/DKIM pass.
Remediation: Auto-quarantine prevents technician exposure. Zero OT breach.
2. Quantified impact avoided**
Item | Industry Benchmark Impact Avoided
Invoice Fraud Attempt | $130,000 USD (single diverted payment).
Preventative Shutdown | $600,000 USD (12h @ $50K/hr DOE avg).
Total Risk Mitigated | $730,000 USD
SOC Efficiency | 95% reduction in manual email review
**Composite case based on aggregated threat data from 3 Texas energy operators, 2024-2025. Individual results vary based on threat landscape
and response protocols. See disclaimer.
*Disclaimer: Case studies presented are composite, hypothetical, or
anonymized for illustration. Financial impacts are estimates based on industry benchmarks from U.S. DOE, EIA, SPE publications, and aggregated
pilot data. Individual results depend on site conditions, data quality, threat landscape, and operational execution. Techoil Solutions does not
guarantee specific savings or operational outcomes. Client names withheld
under NDA where applicable. ROI Guarantees apply to pilot SOW terms only.
CASE STUDY II:AI-driven drilling optimization*
1. The challenge: geological uncertainty + NPT.
*Hypothetical model based on Permian Basin benchmarks + ML pilot data
Profile: Upstream operator, Midland Basin, Wolfcamp formation focus.
Baseline Pain:
- Static reservoir models → wells missing sweet spots by <50 meters
- NPT from mechanical failures: 15-20% of rig time
- Drilling cost overruns vs AFE
The solution: AIaaS modules for upstream.
Deployment Model: Machine Learning platform delivered as scalable service
Digital Reservoir Twin: ML processes 3D seismic + production logs to
simulate porosity/permeability in near real-time.
Autonomous Geonavigation: Reinforcement learning optimizes lateral
placement to stay in >98% of target zone.
Predictive Rod Pump Maintenance: AI forecasts failures 72h prior
using sensor data, enabling planned workovers.
2. Modeled 12-month outcome**
Key Performance Indicator | Modeled Result | Basis
Extraction Efficiency | +18-25% BPD | SPE papers on ML uplift in Wolfcamp
Drilling Accuracy | 98% in zone | Pilot data, 15 wells
Completion Cost | -$1.0M to -$1.4M | Reduced frac stages via better placement
NPT Reduction | -12-18% rig days | Avg $45K/day savings [EIA data]
**Hypothetical model. Based on public SPE/EIA benchmarks and ML pilot
data from 2024. Not a guarantee of results. Assumes quality seismic
data and sensor coverage. See disclaimer.
*Disclaimer: Case studies presented are composite, hypothetical, or
anonymized for illustration. Financial impacts are estimates based on
industry benchmarks from U.S. DOE, EIA, SPE publications, and aggregated
pilot data. Individual results depend on site conditions, data quality,
threat landscape, and operational execution. Techoil Solutions does not
guarantee specific savings or operational outcomes. Client names withheld
under NDA where applicable. ROI Guarantees apply to pilot SOW terms only.