About

Project background, author, and contact information.

Project

OTM-Agent is an LLM-orchestrated agentic system for satellite-based commodity intelligence. It wraps an operational three-stage pipeline — Sentinel-1 SAR processing, feature engineering with market data, and signal generation — with a typed skill library (20 skills), four-tier memory, Bayesian persona vectors (64 dimensions), and a multi-objective reward function.

The system monitors 13 floating-roof oil storage tanks across 4 global hubs (Cushing, Rotterdam, Fujairah, Singapore) using daily Sentinel-1 SAR satellite imagery processed on Google Cloud Platform.

This is a research project. Paper trading only. Not investment advice.

Author

Oguzhan Tekin

Machine Learning and Artificial Intelligence Researcher

GitHub · Email

Infrastructure

ComponentTechnology
Cloud PlatformGoogle Cloud Platform (GCP)
ComputeCloud Run (Jobs + Services)
Data WarehouseBigQuery (31 tables, 6 datasets)
StorageCloud Storage (5 buckets)
SAR SourceSentinel-1 GRD IW VV via Google Earth Engine
ML ModelsLightGBM (regime, spread, EIA)
LLM (Planner)Claude Sonnet 4 (via Anthropic API)
LLM (Executor)Claude Haiku 4.5
Fine-tune TargetQwen 2.5 7B (DPO, pending)
State EstimationKalman filter
Persona Model64-d Bayesian posterior, Kalman-updated
IaCTerraform
Public SiteStatic HTML/CSS on GitHub Pages

License

This project is released under the MIT License. See the GitHub repository for details.

Disclaimer

This is a research project for educational and demonstration purposes only. All trading is simulated (paper trading). Nothing on this site constitutes investment advice. The authors are not responsible for any decisions made based on information presented here. Past performance of models does not guarantee future results.