Agent-based model simulator for air quality and pandemic risk assessment in architectural spaces

Overview

Agent-based model simulation for air quality and pandemic risk assessment in architectural spaces.

PyPI Status PyPI Version License Actions Top Language Github Issues

User Guide

archABM is a fast and open source agent-based modelling framework that simulates complex human-building-interaction patterns and estimates indoor air quality across an entire building, while taking into account potential airborne virus concentrations.


Disclaimer: archABM is an evolving research tool designed to familiarize the interested user with factors influencing the potential indoor airborne transmission of viruses (such as SARS-CoV-2) and the generation of carbon-dioxide (CO2) indoors. Calculations of virus and CO2 levels within ArchABM are based on recently published aerosol models [1,2], which however have not been validated in the context of agent-based modeling (ABM) yet. We note that uncertainty in and intrinsic variability of model parameters as well as underlying assumptions concerning model parameters may lead to errors regarding the simulated results. Use of archABM is the sole responsibility of the user. It is being made available without guarantee or warranty of any kind. The authors do not accept any liability from its use.

[1] Peng, Zhe, and Jose L. Jimenez. "Exhaled CO2 as a COVID-19 infection risk proxy for different indoor environments and activities." Environmental Science & Technology Letters 8.5 (2021): 392-397.

[2] Lelieveld, Jos, et al. "Model calculations of aerosol transmission and infection risk of COVID-19 in indoor environments." International journal of environmental research and public health 17.21 (2020): 8114.


Installation

As the compiled archABM package is hosted on the Python Package Index (PyPI) you can easily install it with pip. To install archABM, run this command in your terminal of choice:

$ pip install archABM

or, alternatively:

$ python -m pip install archABM

If you want to get archABM's latest version, you can refer to the repository hosted at github:

python -m pip install https://github.com/Vicomtech/ArchABM/archive/main.zip

Getting Started

Use the following template to run a simulation with archABM:

from archABM.engine import Engine
import json
import pandas as pd

# Read config data from JSON
def read_json(file_path):
    with open(str(file_path)) as json_file:
        result = json.load(json_file)
    return result

config_data = read_json("config.json")
# WARNING - for further processing ->
# config_data["options"]["return_output"] = True

# Create ArchABM simulation engine
simulation = Engine(config_data)

# Run simulation
results = simulation.run()

# Create dataframes based on the results
df_people = pd.DataFrame(results["results"]["people"])
df_places = pd.DataFrame(results["results"]["places"])

Developers can also use the command-line interface with the main.py file from the source code repository.

$ python main.py config.json

To run an example, use the config.json found at the data directory of archABM repository.

Check the --help option to get more information about the optional parameters:

$ python main.py --help
Usage: main.py [OPTIONS] CONFIG_FILE

  ArchABM simulation helper

Arguments:
  CONFIG_FILE  The name of the configuration file  [required]

Options:
  -i, --interactive     Interactive CLI mode  [default: False]
  -l, --save-log        Save events logs  [default: False]
  -c, --save-config     Save configuration file  [default: True]
  -t, --save-csv        Export results to csv format  [default: True]
  -j, --save-json       Export results to json format  [default: False]
  -o, --return-output   Return results dictionary  [default: False]
  --install-completion  Install completion for the current shell.
  --show-completion     Show completion for the current shell, to copy it or
                        customize the installation.

  --help                Show this message and exit.

Inputs

In order to run a simulation, information about the event types, people, places, and the aerosol model must be provided to the ArchABM framework.

Events
Attribute Description Type
name Event name string
schedule When an event is permitted to happen, in minutes list of tuples
duration Event duration lower and upper bounds, in minutes integer,integer
number of repetitions Number of repetitions lower and upper bounds integer,integer
mask efficiency Mask efficiency during an event [0-1] float
collective Event is invoked by one person but involves many boolean
allow Whether such event is allowed in the simulation boolean
Places
Attribute Description Type
name Place name string
activity Activity or event occurring at that place string
department Department name string
building Building name string
area Room floor area in square meters float
height Room height in meters. float
capacity Room people capacity. integer
height Room height in meters. float
ventilation Passive ventilation in hours-1 float
recirculated_flow_rate Active ventilation in cubic meters per hour float
allow Whether such place is allowed in the simulation boolean
People
Attribute Description Type
department Department name string
building Building name string
num_people Number of people integer
Aerosol Model
Attribute Description Type
pressure Ambient pressure in atm float
temperature Ambient temperature in Celsius degrees float
CO2_background Background CO2 concentration in ppm float
decay_rate Decay rate of virus in hours-1 float
deposition_rate Deposition to surfaces in hours-1 float
hepa_flow_rate Hepa filter flow rate in cubic meters per hour float
filter_efficiency Air conditioning filter efficiency float
ducts_removal Air ducts removal loss float
other_removal Extraordinary air removal float
fraction_immune Fraction of people immune to the virus float
breathing_rate Mean breathing flow rate in cubic meters per hour float
CO2_emission_person CO2 emission rate at 273K and 1atm float
quanta_exhalation Quanta exhalation rate in quanta per hour float
quanta_enhancement Quanta enhancement due to variants float
people_with_masks Fraction of people using mask float
Options
Attribute Description Type
movement_buildings Allow people enter to other buildings boolean
movement_department Allow people enter to other departments boolean
number_runs Number of simulations runs to execute integer
save_log Save events logs boolean
save_config Save configuration file boolean
save_csv Export the results to csv format boolean
save_json Export the results to json format boolean
return_output Return a dictionary with the results boolean
directory Directory name to save results string
ratio_infected Ratio of infected to total number of people float
model Aerosol model to be used in the simulation string

Example config.json

config.json
{
    "events": [{
            "activity": "home",
            "schedule": [
                [0, 480],
                [1020, 1440]
            ],
            "repeat_min": 0,
            "repeat_max": null,
            "duration_min": 300,
            "duration_max": 360,
            "mask_efficiency": null,
            "collective": false,
            "shared": false,
            "allow": true
        },
        {
            "activity": "work",
            "schedule": [
                [480, 1020]
            ],
            "repeat_min": 0,
            "repeat_max": null,
            "duration_min": 30,
            "duration_max": 60,
            "mask_efficiency": 0.0,
            "collective": false,
            "shared": true,
            "allow": true
        },
        {
            "activity": "meeting",
            "schedule": [
                [540, 960]
            ],
            "repeat_min": 0,
            "repeat_max": 5,
            "duration_min": 20,
            "duration_max": 90,
            "mask_efficiency": 0.0,
            "collective": true,
            "shared": true,
            "allow": true
        },
        {
            "activity": "lunch",
            "schedule": [
                [780, 900]
            ],
            "repeat_min": 1,
            "repeat_max": 1,
            "duration_min": 20,
            "duration_max": 45,
            "mask_efficiency": 0.0,
            "collective": true,
            "shared": true,
            "allow": true
        },
        {
            "activity": "coffee",
            "schedule": [
                [600, 660],
                [900, 960]
            ],
            "repeat_min": 0,
            "repeat_max": 2,
            "duration_min": 5,
            "duration_max": 15,
            "mask_efficiency": 0.0,
            "collective": true,
            "shared": true,
            "allow": true
        },
        {
            "activity": "restroom",
            "schedule": [
                [480, 1020]
            ],
            "repeat_min": 0,
            "repeat_max": 4,
            "duration_min": 3,
            "duration_max": 6,
            "mask_efficiency": 0.0,
            "collective": false,
            "shared": true,
            "allow": true
        }
    ],
    "places": [{
            "name": "home",
            "activity": "home",
            "building": null,
            "department": null,
            "area": null,
            "height": null,
            "capacity": null,
            "ventilation": null,
            "recirculated_flow_rate": null,
            "allow": true
        },
        {
            "name": "open_office",
            "activity": "work",
            "building": "building1",
            "department": ["department1", "department2", "department3", "department4"],
            "area": 330.0,
            "height": 2.7,
            "capacity": 60,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "it_office",
            "activity": "work",
            "building": "building1",
            "department": ["department4"],
            "area": 52.0,
            "height": 2.7,
            "capacity": 10,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "chief_office_A",
            "activity": "work",
            "building": "building1",
            "department": ["department5", "department6", "department7"],
            "area": 21.0,
            "height": 2.7,
            "capacity": 5,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "chief_office_B",
            "activity": "work",
            "building": "building1",
            "department": ["department5", "department6", "department7"],
            "area": 21.0,
            "height": 2.7,
            "capacity": 5,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "chief_office_C",
            "activity": "work",
            "building": "building1",
            "department": ["department5", "department6", "department7"],
            "area": 24.0,
            "height": 2.7,
            "capacity": 5,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "meeting_A",
            "activity": "meeting",
            "building": "building1",
            "department": ["department1", "department2", "department3", "department5", "department6", "department7"],
            "area": 16.0,
            "height": 2.7,
            "capacity": 6,
            "ventilation": 1.0,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "meeting_B",
            "activity": "meeting",
            "building": "building1",
            "department": ["department1", "department2", "department3", "department5", "department6", "department7"],
            "area": 16.0,
            "height": 2.7,
            "capacity": 6,
            "ventilation": 1.0,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "meeting_C",
            "activity": "meeting",
            "building": "building1",
            "department": ["department1", "department2", "department3", "department5", "department6", "department7"],
            "area": 11.0,
            "height": 2.7,
            "capacity": 4,
            "ventilation": 1.0,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "meeting_D",
            "activity": "meeting",
            "building": "building1",
            "department": null,
            "area": 66.0,
            "height": 2.7,
            "capacity": 24,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "coffee_A",
            "activity": "coffee",
            "building": "building1",
            "department": null,
            "area": 25.0,
            "height": 2.7,
            "capacity": 10,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "coffee_B",
            "activity": "coffee",
            "building": "building1",
            "department": null,
            "area": 55.0,
            "height": 2.7,
            "capacity": 20,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "restroom_A",
            "activity": "restroom",
            "building": "building1",
            "department": null,
            "area": 20.0,
            "height": 2.7,
            "capacity": 4,
            "ventilation": 1.0,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "restroom_B",
            "activity": "restroom",
            "building": "building1",
            "department": ["department1", "department2", "department3", "department4", "department5", "department6"],
            "area": 20.0,
            "height": 2.7,
            "capacity": 4,
            "ventilation": 1.0,
            "recirculated_flow_rate": 0,
            "allow": true
        },
        {
            "name": "lunch",
            "activity": "lunch",
            "building": "building1",
            "department": null,
            "area": 150.0,
            "height": 2.7,
            "capacity": 60,
            "ventilation": 1.5,
            "recirculated_flow_rate": 0,
            "allow": true
        }
    ],
    "people": [{
            "department": "department1",
            "building": "building1",
            "num_people": 16
        },
        {
            "department": "department2",
            "building": "building1",
            "num_people": 16
        },
        {
            "department": "department3",
            "building": "building1",
            "num_people": 16
        },
        {
            "department": "department4",
            "building": "building1",
            "num_people": 7
        },
        {
            "department": "department5",
            "building": "building1",
            "num_people": 2
        },
        {
            "department": "department6",
            "building": "building1",
            "num_people": 2
        },
        {
            "department": "department7",
            "building": "building1",
            "num_people": 1
        }
    ],
    "options": {
        "movement_buildings": true,
        "movement_department": false,
        "number_runs": 1,
        "save_log": true,
        "save_config": true,
        "save_csv": false,
        "save_json": false,
        "return_output": false,
        "directory": null,
        "ratio_infected": 0.05,
        "model": "Colorado",
        "model_parameters": {
            "Colorado": {
                "pressure": 0.95,
                "temperature": 20,
                "CO2_background": 415,
                "decay_rate": 0.62,
                "deposition_rate": 0.3,
                "hepa_flow_rate": 0.0,
                "recirculated_flow_rate": 300,
                "filter_efficiency": 0.20,
                "ducts_removal": 0.10,
                "other_removal": 0.00,
                "fraction_immune": 0,
                "breathing_rate": 0.52,
                "CO2_emission_person": 0.005,
                "quanta_exhalation": 25,
                "quanta_enhancement": 1,
                "people_with_masks": 1.00
            }
        }
    }
}

Outputs

Simulation outputs are stored by default in the results directory. The subfolder with the results of an specific simulation have the date and time of the moment when it was launched as a name in %Y-%m-%d_%H-%M-%S-%f format.

By default, three files are saved after a simulation:

  • config.json stores a copy of the input configuration.
  • people.csv stores every person's state along time.
  • places.csv stores every places's state along time.

archABM offers the possibility of exporting the results in JSON and CSV format. To export in JSON format, use the --save-json parameter when running archABM. By default, the --save-csv parameter is set to true.

Alternatively, archABM can also be configured to yield more detailed information. The app.log file saves the log of the actions and events occurred during the simulation. To export this file, use the --save-log parameter when running archABM.


Citing archABM

If you use ArchABM in your work or project, please cite the following article, published in Building and Environment (DOI...): [Full REF]

@article{
}
Owner
Vicomtech
Applied Research in Visual Computing & Interaction and Artificial Inteligence - Official Github Account - Member of Basque Research & Technology Alliance, BRTA
Vicomtech
This repository contains code to run experiments in the paper "Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers."

Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers This repository contains code to run experiments in the paper "Signal Stre

0 Jan 19, 2022
Neural style transfer in PyTorch.

style-transfer-pytorch An implementation of neural style transfer (A Neural Algorithm of Artistic Style) in PyTorch, supporting CPUs and Nvidia GPUs.

Katherine Crowson 395 Jan 06, 2023
Code for NAACL 2021 full paper "Efficient Attentions for Long Document Summarization"

LongDocSum Code for NAACL 2021 paper "Efficient Attentions for Long Document Summarization" This repository contains data and models needed to reprodu

56 Jan 02, 2023
CBKH: The Cornell Biomedical Knowledge Hub

Cornell Biomedical Knowledge Hub (CBKH) CBKG integrates data from 18 publicly available biomedical databases. The current version of CBKG contains a t

44 Dec 21, 2022
Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations

HierarchicyBandit Introduction This is the implementation of WSDM 2022 paper : Show Me the Whole World: Towards Entire Item Space Exploration for Inte

yu song 5 Sep 09, 2022
Pytorch GUI(demo) for iVOS(interactive VOS) and GIS (Guided iVOS)

GUI for iVOS(interactive VOS) and GIS (Guided iVOS) GUI Implementation of CVPR2021 paper "Guided Interactive Video Object Segmentation Using Reliabili

Yuk Heo 13 Dec 09, 2022
Code for the paper "Controllable Video Captioning with an Exemplar Sentence"

SMCG Code for the paper "Controllable Video Captioning with an Exemplar Sentence" Introduction We investigate a novel and challenging task, namely con

10 Dec 04, 2022
Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

MotionCLIP Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space". Please visit our webpage for mor

Guy Tevet 173 Dec 26, 2022
Flow is a computational framework for deep RL and control experiments for traffic microsimulation.

Flow Flow is a computational framework for deep RL and control experiments for traffic microsimulation. See our website for more information on the ap

867 Jan 02, 2023
An unofficial implementation of "Unpaired Image Super-Resolution using Pseudo-Supervision." CVPR2020

UnpairedSR An unofficial implementation of "Unpaired Image Super-Resolution using Pseudo-Supervision." CVPR2020 turn RCAN(modified) -- xmodel(xilinx

JiaKui Hu 10 Oct 28, 2022
Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" (RSS 2022)

Intro Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" Robotics:Science and

Yunho Kim 21 Dec 07, 2022
Convenient tool for speeding up the intern/officer review process.

icpc-app-screen Convenient tool for speeding up the intern/officer applicant review process. Eliminates the pain from reading application responses of

1 Oct 30, 2021
Catalyst.Detection

Accelerated DL R&D PyTorch framework for Deep Learning research and development. It was developed with a focus on reproducibility, fast experimentatio

Catalyst-Team 12 Oct 25, 2021
Code Release for the paper "TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation"

TriBERT This repository contains the code for the NeurIPS 2021 paper titled "TriBERT: Full-body Human-centric Audio-visual Representation Learning for

UBC Computer Vision Group 8 Aug 31, 2022
Jittor implementation of Recursive-NeRF: An Efficient and Dynamically Growing NeRF

Recursive-NeRF: An Efficient and Dynamically Growing NeRF This is a Jittor implementation of Recursive-NeRF: An Efficient and Dynamically Growing NeRF

33 Nov 30, 2022
Toontown: Galaxy, a new Toontown game based on Disney's Toontown Online

Toontown: Galaxy The official archive repo for Toontown: Galaxy, a new Toontown

1 Feb 15, 2022
Repository for the paper "Exploring the Sensory Spaces of English Perceptual Verbs in Natural Language Data"

Sensory Spaces of English Perceptual Verbs This repository contains the code and collocational data described in the paper "Exploring the Sensory Spac

David Peng 0 Sep 07, 2021
Replication Package for "An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Datasets"

Replication Package for "An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Data

2 Oct 06, 2022
Official repository for CVPR21 paper "Deep Stable Learning for Out-Of-Distribution Generalization".

StableNet StableNet is a deep stable learning method for out-of-distribution generalization. This is the official repo for CVPR21 paper "Deep Stable L

120 Dec 28, 2022
PyTorch implementation of Munchausen Reinforcement Learning based on DQN and SAC. Handles discrete and continuous action spaces

Exploring Munchausen Reinforcement Learning This is the project repository of my team in the "Advanced Deep Learning for Robotics" course at TUM. Our

Mohamed Amine Ketata 10 Mar 10, 2022