Published October 8, 2026 | Version v4

Code, trained PINN models and derived results for: Air Purifier Performance in an Occupied Office: Field CADR and Effectiveness from a Reconstructed Device-Off Condition

  • 1. ROR icon Korea Institute of Machinery & Materials
  • 2. ROR icon Kyung Hee University

Description

Training code, analysis code, trained physics-informed neural network (PINN) weights for thirty paired CO2 and PM2.5 networks, fitted input scalers, the member list and per-member accuracy, derived per-state results, the synthetic parameter-recovery experiments for both networks, the networks of the structural and humidity sensitivity tests, and the underlying field measurements for the counterfactual evaluation of a portable air purifier in an occupied office. The deposit reproduces the reported air change rate, particle penetration factor, removal rate, field CADR and effectiveness results of the third revision of the manuscript (Building and Environment, under review, BAE-D-26-05957). Version 4 adds the code and outputs of the analyses added in the third revision: the range of the counterfactual inputs, the occupancy sensitivity, and the dynamic effectiveness with the measured device-on concentration; no network was retrained and no value reported in version 3 changed. Version 3 replaced the ensemble of the first revision with thirty network pairs with softplus outputs, all of which are used, corrected the room volume to 71.25 m3 and the temperature input of the PM2.5 networks, and added synthetic PM2.5 recovery tests, a structured removal-rate variant and a humidity sensitivity test. The weights of the first-revision networks remain in version 2. See README.md for the layout, the archives and the scripts.

Files

2026CADR_v3_code.zip

Files (54.6 MB)

Name Size
md5:f7bf74c9e31b4e42df22fdfa79510c3a
140.3 kB Preview Download
md5:b0883c691756dd97bf44ef63e3c2ba0d
3.7 MB Preview Download
md5:2fee4a58a539da62d803fa2915dd2d60
8.0 MB Preview Download
md5:cd6917183634abe52aee46480fa41667
6.5 MB Preview Download
md5:5005f5ee24ff67a6df8f19b2bdf1eddd
7.6 MB Preview Download
md5:5269c1d2c34dc969e0ca55a2b81aedda
5.7 MB Preview Download
md5:1b81e7fb7fc7b98f3f46f557e4e1824c
8.9 MB Preview Download
md5:d790fa27128a2a06ded61509e096f42c
4.3 MB Preview Download
md5:4899c77fe70834a5fc700e9cd7a8cfe3
9.7 MB Preview Download
md5:1b3f16e9aec28507e12bf0b96554d3fe
26.3 kB Preview Download

Additional details

Related works

Is derived from
Journal article: 10.1016/j.buildenv.2024.112249 (DOI)
Journal article: 10.1016/j.buildenv.2025.113038 (DOI)