# Inter-Stop Energy Prediction and Causal Driver Quantification for Dual-Source Trolleybuses via a Time-Aware Tabular Deep Learning Architecture

arXiv: https://arxiv.org/abs/2607.11349 · HTML: https://mlsanity.com/paper/2607.11349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 44 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 4 of 4)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [Foundation Models for Clean Energy Forecasting: A Comprehensive Review](https://mlsanity.com/paper/2507.23147/) (2025)
- [ZTBus: A Large Dataset of Time-Resolved City Bus Driving Missions](https://mlsanity.com/paper/2303.08667/) (2023)

## Abstract (arXiv)

Dual-source trolleybuses alternate between overhead catenary supply and on-board battery operation, creating energy-use patterns driven by route attributes, high-frequency trajectories, and hourly weather. Existing models struggle to represent these heterogeneous inputs and rarely explain the causal drivers of consumption. This paper proposes a time-aware tabular deep learning framework for inter-stop energy management. Periodic time encoding is integrated into a parameter-efficient batch-ensemble backbone to jointly learn static and sequential features, while Bayesian optimization with tree-structured density estimation tunes hyperparameters. To move beyond prediction, a three-layer causal explanation pipeline combines feature attribution for marginal effects, a linear non-Gaussian acyclic model for causal direction discovery, and a meta-learner for net average treatment effects. Experiments on the Zurich trolleybus dataset enriched with meteorological records achieve a MAPE of 6.52% and R of 0.982, outperforming ten statistical, tree-ensemble, and deep learning baselines. Ablation results show that periodic time encoding contributes most to the accuracy gain. Causal analysis identifies regenerative braking ratio and average speed as the strongest energy-saving factors, while coasting distance is the main driver of excess consumption. The findings offer actionable thresholds for vehicle technology, driving behavior, capacity allocation, and catenary network planning.