Estimating the air exchange rates in naturally ventilated cattle houses using Bayesian-optimized GBDT

It is challenging to estimate the air exchange rate(AER)dynamically in naturally ventilated livestock buildings such as dairy houses due to the influence of complex and variable outdoor environmental factors,large opening ratios,and the confusion of inflow and outflow at openings.This makes it difficult to efficiently regulate the opening ratio to meet the ventilation requirements in naturally ventilated livestock buildings.In this study,the air exchange rates of naturally ventilated cattle houses(NVCHs)in different seasons and opening ratios were obtained through field measurements and computational fluid dynamics(CFD)simulations.A fast and efficient machine learning framework was proposed and examined to predict AER based on the gradient boosting decision tree(GBDT)combined with Bayesian optimization.Compared with commonly used machine learning models such as multilayer perceptrons(MLPs)and support vector machines(SVMs),the proposed GBDT model has higher prediction accuracy and can avoid falling easily into local optima.Compared with the existing mechanical model based on the Bernoulli equation,the proposed GBDT model showed a slightly higher prediction than the mechanistic model and was much easier to use in AER estimation when inputting easily collected environmental factors in practical applications.Using Bayesian optimization could dramatically reduce the computing time when determining the optimal hyperparameter for establishing the GBDT model,dramatically saving on computing resources.Based on the Bayesian optimized GBDT model,the desirable opening ratio of the side curtain can be determined for automatically regulating the AER of cattle houses in future applications.

Measurement of air exchange rates in different indoor environments using continuous CO_2 sensors

A new air exchange rate （AER） monitoring method using continuous CO2 sensors was developed and validated through both laboratory experiments and field studies. Controlled laboratory simulation tests were conducted in a 1-m3 environmental chamber at different AERs （0.1-10.0 hr-1）. AERs were determined using the decay method based on box model assumptions. Field tests were conducted in classrooms, dormitories, meeting rooms and apartments during 2-5 weekdays using CO2 sensors coupled with data loggers. Indoor temperature, relative humidity （RH）, and CO2 concentrations were continuously monitored while outdoor parameters combined with on-site climate conditions were recorded. Statistical results indicated that good laboratory performance was achieved： duplicate precision was within 10%, and the measured AERs were 90%-120% of the real AERs. Average AERs were 1.22, 1.37, 1.10, 1.91 and 0.73 hr-l in dormitories, air-conditioned classrooms, classrooms with an air circulation cooling system, reading rooms, and meeting rooms, respectively. In an elderly particulate matter exposure study, all the homes had AER values ranging from 0.29 to 3.46 hr-1 in fall, and 0.12 to 1.39 hr-1 in winter with a median AER of 1.15.

Assessment of SARS-CoV-2 airborne infection transmission risk in public buses

Public transport environments are thought to play a key role in the spread of SARS-CoV-2 worldwide.Indeed,high crowding indexes(i.e.high numbers of people relative to the vehicle size),inadequate clean air supply,and frequent extended exposure durations make transport environments potential hotspots for transmission of respiratory infections.During the COVID-19 pandemic,generic mitigation measures(e.g.physical distancing)have been applied without also considering the airborne transmission route.This is due to the lack of quantified data about airborne contagion risk in transport environments.In this study,we apply a novel combination of close proximity and room-scale risk assessment approaches for people sharing public transport environments to predict their contagion risk due to SARS-CoV-2 respiratory infection.In particular,the individual infection risk of susceptible subjects and the transmissibility of SARS-CoV-2(expressed through the reproduction number)are evaluated for two types of buses,differing in terms of exposure time and crowding index:urban and long-distance buses.Infection risk and reproduction number are calculated for different scenarios as a function of the ventilation rates(both measured and estimated according to standards),crowding indexes,and travel times.The results show that for urban buses,the close proximity contribution significantly affects the maximum occupancy to maintain a reproductive number of<1.In particular,full occupancy of the bus would be permitted only for an infected subject breathing,whereas for an infected subject speaking,masking would be required.For long-distance buses,full occupancy of the bus can be maintained only if specific mitigation solutions are simultaneously applied.For example,for an infected person speaking for 1 h,appropriate filtration of the recirculated air and simultaneous use of FFP2 masks would permit full occupancy of the bus for a period of almost 8 h.Otherwise,a high percentage of immunized persons(>80%)would be needed.

An indoor air aerosol model for outdoor contaminant transmission into occupied rooms

The paper presents a simple model for outdoor air contaminant transmission into occupied rooms. In the model, several factors such as filtration, ventilation, deposition, re-emission, outdoor concentration and indoor sources are included. The model results show that the air exchange rate plays an important role in the transmission of outdoor contaminants into the indoor environment. The model shows that increasing the value of the filtration efficiency decreases the mass concentration of indoor particles. In addition, if outdoor aerosol particles have a periodic behaviour, indoor aerosol particles also behave periodically but smoother. Indoor sources are found to be able to increase indoor concentrations greatly and continuously.