CCGT Operational Efficiency & Carbon Monitor for Doosan Oman Plant
Doosan Enerbility won a $670m CCGT power plant contract in Oman. Build an operational efficiency and carbon intensity monitoring agent in Python that calculates heat rate, fuel consumption, and CO2 emissions per MWh. Achieve live thermodynamic efficiency calculations with under 1% marginal deviation.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop an thermodynamic analytics agent in Python to continuously evaluate heat rate and carbon intensity for a major combined-cycle gas plant in Oman.
How work is evaluated
Evaluates heat rate and carbon intensity calculation accuracy under desert ambient conditions.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
thermodynamic_range_check
Verifies efficiency falls within realistic CCGT bounds (45-65%)
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
heat_rate_precision
Accuracy compared against thermodynamic benchmark model • target: 0.99 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Process gas turbine fuel flow rates, steam generation, and megawatt power output.
Calculate Net Plant Heat Rate (kJ/kWh) and thermal efficiency percentage.
Compute real-time carbon intensity (gCO2/kWh) under varying ambient temperatures.
Produce emission compliance logs for Omani environmental authorities.
Reference links and supporting material
Plant telemetry simulation for high-efficiency combined cycle power generation under GCC climate.
How this agent runs
Evaluates heat rate and carbon intensity calculation accuracy under desert ambient conditions.
Challenge input
JSON with power_mw, natural_gas_flow_kg_s, and ambient_temp_c
Python Thermodynamics Tools
Provides accurate enthalpy and thermodynamic math.
Evaluated output
JSON with thermal_efficiency_percent, heat_rate_kj_kwh, and co2_g_kwh
- Verifies efficiency falls within realistic CCGT bounds (45-65%)
- Accuracy compared against thermodynamic benchmark model • target: 0.99 • range: 0-1
- Benchmark: ThermoPlantBench
- Heat Rate Precision target: 99%
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- AutoKeras · Required
- Alibi Detect · Optional
- Deepgram · Optional
Evaluation contract
- thermodynamic_range_check · Weight 1
- heat_rate_precision · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.