Synthetic data generator to determine the best location and quantity of ambulances for the 30 largest cities in the state of São Paulo-Brazil

This dataset was developed to support research and decision-making regarding the ideal location and quantity of ambulances in emergency medical services. It is primarily intended for discrete event simulation (DES) applications and was generated using the NotebookLM tool, which was used to define the emergency response flowchart and probability distributions for response times. Synthetic data generated to represent the cities of Sorocaba and Campinas, two of the largest cities in the state of São Paulo, Brazil, are shared here. Data for the 30 largest municipalities in São Paulo can be generated through the Google Colab environment using the link provided in the article. Care Flowchart and Time Markers (T1 to T5) T1 - Interval between successive call arrivals T2 - Dispatch time (time between receiving the call and the ambulance leaving for the call) T3 - Travel Time: Calculated from the latitude and longitude of the call T4 - Local Response Time and Dispatch to Hospital (minutes) T5 - Time for vehicle cleaning and release Probability Distributions Used Data can be generated for any of the 30 largest cities in the state of São Paulo - Brazil using any of the following probability distributions: Normal Lognormal Gamma Exponential Triangular Uniform Using the parameters p1, p2, or p3 according to the chosen distribution. - Daily demand pattern: · 00:00–08:00: 20% of daily calls · 08:00–16:00: 35% of daily calls · 16:00–00:00: 45% of daily calls CSV File Format Column Type Description Municipio string Name of chosen city Simulation day number (starting from 0). latitude float64 Generated latitude of the incident. longitude float64 Generated longitude of the incident. T1 float64 Interval between successive call arrivals T2 float64 Dispatch time (time between receiving the call and the ambulance leaving for the call) T4 float64 On-site care time in minutes. T5 float64 Transport and hospital release time in minutes. Arrival_Time string date and time of call Arrival_Date date date of call Arrival_Hour float64 the hour of the day of the call Arrival_Day_Offset float64 day of the call Arrival_Time_Str hour hour of day of call Care_type string Type of care ("basic" or "advanced"). Dataset Applications · Modeling and simulation of healthcare systems. · Studies on ambulance allocation. · Impact analysis of response times. · Support for public policy and management decisions. Access and Reproducibility · Download .CSV from Sorocaba: https://drive.google.com/file/d/1p7L_xVoSPbdlMX2fG4YuehSjkKI9teA0/view?usp=sharing · Regenerate data on Google Colab: https://colab.research.google.com/drive/14SsawsTOpDNSQEfFcj3vRT-Bgt6Zikkc?usp=sharing Related Publications Gigante, R. L., & Azevedo, A. T. (2022). Study of the impact of the start time of work shift on the efficiency of an emergency system through a simulation model of discrete events. Gestão & Produção, 29, e4421. DOI: https://doi.org/10.1590/1806-9649-2022v29e4421 Gigante, R. L., Azevedo, A. T. de, & Ohishi, T. (2024). Optimizing ambulance base locations: A clustering-based approach. In 5th South American IEOM Conference. DOI: https://doi.org/10.46254/SA05.20240171