The project I’m working on emulates a scientific abstract. I’m not a scientist by any means, but am adapting an abstract to the public transit system in NYC. I will publish the project on my website when it’s done. I think it’s a few weeks away. I built the dataset, now doing experimental model training. If I can get acceptable accuracy, I will deploy in a production system and build a UI.

Here is a scientific abstract that inspired my to start building this system. -> https://arxiv.org/html/2510.03121

I am unfamiliar with agent based models, sorry I can’t offer any personal insight there, but I ran your question through Gemini and here is the AI response:

Based on the scientific abstract of the paper *"Real Time Headway Predictions in Urban Rail Systems and Implications for Service Control: A Deep Learning Approach"* (arXiv:2510.03121), agent-based models (ABMs) and deep learning (DL) approaches compare as follows:

### 1. Computational Efficiency and Real-Time Application

* *Deep Learning (DL):* The paper proposes a *ConvLSTM* (Convolutional Long Short-Term Memory) framework designed for high computational efficiency. It is specifically intended to provide real-time predictions, enabling dispatchers to evaluate operational decisions instantly. * *Agent-Based Models (ABM):* While the paper does not use ABMs, it contrasts its DL approach with traditional *"computationally intensive simulations"*—a category that includes microscopic agent-based models. ABMs often require significant processing time to simulate individual train and passenger interactions, making them less suitable for immediate, real-time dispatching decisions during operations.

### 2. Modeling Methodology

* *Deep Learning (DL):* The approach is *data-driven*, learning spatiotemporal patterns and the propagation of train headways from historical datasets. It captures spatial dependencies (between stations) and temporal evolution (over time) through convolutional filters and memory states without needing explicit rules for train behavior. * *Agent-Based Models (ABM):* These are typically *rule-based and bottom-up*, modeling the movement of each train "agent" based on signaling rules, spacing, and train-following logic. While highly detailed, they require precise calibration of individual agent parameters.

### 3. Handling Operational Control

* *Deep Learning (DL):* A key innovation in this paper is the direct integration of *target terminal headways* (dispatcher decisions) as inputs. This allows the model to predict the downstream impacts of a specific control action (like holding a train) by processing it as a data feature. * *Agent-Based Models (ABM):* To evaluate a dispatcher's decision in an ABM, the entire simulation must typically be re-run with new parameters for the affected agents, which is time-consuming and difficult to scale across an entire metro line in real-time.

### 4. Use Case Scenarios

* *Deep Learning (DL):* Optimized for *proactive operational control* and real-time decision-making. It is most effective when large amounts of historical tracking data are available to train the spatiotemporal relationships. * *Agent-Based Models (ABM):* Often preferred for *off-line evaluation* of complex infrastructure changes, bottleneck mitigation strategies, or microscopic safety analyses where the "why" behind individual train behavior is more important than prediction speed.