Train models to generate energy optimization code from flow battery scheduling requirements and operating constraints.

Train models to assess grid requirement feasibility and changing use cases by comparing power, energy, and duration constraints across storage configurations.

The open-pit mine boundary detection image dataset is used to improve the accuracy and efficiency of mine boundary identification.

Verify offshore drilling and well operation procedures against web evidence for professional fact-checking and automated model evaluation.

Build text-to-SQL capability for mining equipment maintenance with paired business queries, database schemas, and SQL statements.

Train models to assess commercial and industrial rooftop solar feasibility by reasoning across roof, load, structural, shading, and grid constraints.

Evaluate whether models can verify agrivoltaic design claims against engineering evidence and provide traceable judgments.

Train models to explain how small wind turbine configuration changes may affect performance under real-world operating constraints.

Train models to assess offshore oil well intervention applicability and explain their reasoning from well facts and operational rules.

Train and evaluate domain models with answered and explained practice questions on relay protection principles and power engineering applications.

Train multi-step reasoning about self-consumption, grid exports, and curtailment under commercial solar operating constraints.

Pair continuous operating telemetry with annotated state changes to evaluate next-stage state prediction for sodium-ion energy storage systems.

Explore grid-connected, curtailed, islanded, and reconnection states in distributed wind power to detect grid-interaction changes and predict system operation.

Provides a time series dataset of customer hourly electricity consumption from 2012 to 2014.

Test whether electrical faults remain possible when key conditions change, and train models to reason about risk chains in floating solar PV systems.

Train models to spot non-compliant operations in selective lignite mining using seam constraints and step-level verification results.

Verify subsea production integrity claims against web evidence, spanning critical components, inspection methods, and repair management.

Train models to interpret fault conditions and protection responses in battery management firmware through code snippets and structured explanations.

Train models to make evidence-based electrical safety judgments with explicit premises and reasoning chains for floating solar PV.

Check safety constraints step by step to pinpoint omitted controls, incorrect ordering, and conflicts in mine-work responses.