Investor briefing — petroleum-ai-platform.pages.dev
A Closed-Loop Framework Integrating Diffusion Models with Multi-Agent Reinforcement Learning for Risk-Aware Petroleum Distribution Networks
Platform overview, live metrics and investment thesis
Live Platform Snapshot
Captured from the running simulation at print time
Report date
—
Active scenario
Geopolitical
45% · 30d
Shock-adjusted start price
$95.38
/bbl
Hedge ratio
0.97
Balanced
Executive Summary
Petroleum product distribution is a high-stakes, multi-scale optimization problem where terminal, fleet and financial decisions interact under deep uncertainty. The Petroleum AI Platform is a three-layer AI system that unifies generative scenario engines, multi-agent reinforcement learning logistics and dynamic hedging under VaR/CVaR constraints. On a simulated US network of 10 terminals, 20 carriers and 5 pipelines, the platform cuts delivered cost by 17.3%, lifts service reliability by 23.8%, reduces value-at-risk by 31.2% and delivers a five-year ROI of 1,332% versus the static baseline.
Proven Impact (Simulated Network)
12-month simulation · 10 terminals · 20 carriers · 5 pipelines
17.3%
Cost Reduction
+23.8%
Service Reliability
−31.2%
Risk Reduction (VaR)
1,332%
5-Year ROI
Three-Layer Architecture
Generative Scenario Engine
Learns the joint distribution of prices, demand and geopolitics, then samples thousands of realistic futures. Every logistics and hedging decision is stress-tested against the full ensemble.
MADRL Logistics Coordinator
A fleet of RL agents — one per terminal, carrier and corridor — negotiate dispatch, routing and inventory policy in real time, balancing service reliability against operating cost.
Financial Risk Module
Translates scenario distributions into optimal hedge positions under Value-at-Risk and Conditional VaR constraints, continuously rebalancing across futures, options and swaps.
Financial Risk Profile
$۸۷٬۲۰۰
VaR (95%)
$۱۱۸٬۹۰۰
CVaR (95%)
1.45
Sharpe Ratio
-8.7%
Max Drawdown
Underlying Research
The distribution of petroleum products is a multi-layered optimization with a multitude of scales, involving gigantic decisions in the terminal, the fleet and the finances, all over a backdrop of high prices uncertainty, high demand uncertainty and geopolitical factors. In this paper, an artificial intelligence (AI) system of three layers is presented. Layer 1 is a generative scenario engine based on time-series diffusion models, providing realistic price and demand paths and is regime-aware. The optimization of service reliability and inventory cost/asset utilization is done in Layer 2 with a multi-agent deep reinforcement learning (MADRL) architecture. The scenario distribution is added to Layer 3 and a financial risk layer is added for dynamic hedging in the scenario space with the constraint of VaR (Value-at-Risk) and CVaR (Conditional Value-at-Risk). The platform achieves a 17.3% cost savings on delivered cost for a simulated US network of 10 terminals, 20 different network carriers and 5 pipelines, a 23.8% improvement in service reliability, and a 31.2% savings in value-at-risk when compared to a static baseline, to achieve a five-year ROI of 1332% against the static baseline. In this talk we discuss the quality measures for the scenarios, the measures of convergence of logistics and the measures of effectiveness of the hedges and we discuss the deployment aspects which makes it difficult to converge the logistics and which aligns with ISO 31000:2018 risk-management guideline and ISO 20815:2018 production-assurance practice.
DOI: 10.1016/j.apenergy.2025.125000