When the Timetable Breaks: Physics-Anchored Scientific Machine Learning for Cold-Wave-Robust Battery-Electric Bus Operations

Abstract

Cold-climate transit agencies are electrifying fixed-timetable fleets, but winter exposes a block-level failure mode hidden by seasonal energy margins: cabin heating can deplete batteries faster than layovers recharge them, causing later trips to start undercharged and making one cold day cascade into timetable infeasibility. We present WeatherRobustBus, an open-data framework that converts this risk into block-level failure probability by injecting real hourly weather into real transit duties and propagating cold-weather energy uncertainty. The framework couples a transparent traction and cabin-thermal backbone with a bounded monotone residual ensemble, and validates cabin heating against an independent EnergyPlus bus-cabin simulation driven by the same Toronto weather record. Against this first-principles reference, it achieves the lowest all-year error (0.213 kWh RMSE over 8760 hours) and remains reliable in the out-of-support cold tail ($T \le -12^\circ$C), where pure machine-learning baselines degrade by 1.5--4x and the best competitor reaches only 1.055 kWh. Embedded in a Monte Carlo block-feasibility simulator over 60 real Toronto TTC vehicle blocks, the model reveals a sharp weather-induced failure envelope. A forecast-triggered robust policy combining opportunity charging, a fuel-fired cabin-heating bridge, and modest buffering reduces mean cold-wave failure probability from 0.759 to 0.112 across eight cold-wave days; a deconfounded ablation shows opportunity charging is the dominant lever and the heater is a low-cost complement. WeatherRobustBus provides a reproducible pathway from weather data to winter-resilience decisions for electric-bus fleets.