Assessment of ANN Algorithms for the Concentration Prediction of Indoor Air Pollutants in Child Daycare Centers

Modeling, quality assessment, and Sobol sensitivity of water resources and distribution system in Shiraz: A probabilistic human health risk assessment

Given water's vital role in supporting life and ecosystems, global climate change and human activities have significantly diminished its availability and quality. This study explores the health risks of drinking water consumption in the shiraz county water resources and distribution system. The result showed that the water was slightly alkaline. However, the average pH values during the study were within the permissible range. The area's abundance of total hardness and calcium was due to the high concentration of minerals in rocks and soils. The nitrate and fluoride concentrations in drinking groundwater varied from 0.02 to 116.70 mg/L and 0.10-1.85 mg/L, respectively. Although the water quality index indicated that 52.63, 45.03, and 20.3 percent of samples were of excellent, good, and poor quality in 2020, those percentages obtained 46.05, 52.09, and 14.0 percent in 2021. The regression values of training, testing, validation, and the proposed artificial neural network model were 0.93, 0.92, 0.85, and 0.92. The maximum levels of hazard quotient of nitrate and fluoride (except for adults) were higher than 1 in all age groups, indicating a high non-carcinogenic risk by exposure to nitrate. Furthermore, according to the Monte Carlo simulation, the 95th percentile hazard index in all groups was more than 1. Children and infants were more inclined towards risk than teens and adults based on the intake of nitrate and fluoride from drinking water. The Sobol sensitivity reflected that the nitrate concentration and ingestion rate are vital parameters that influence the outcome of the oral exposure model for all age groups. The interaction of ingestion rate with a concentration of nitrate and fluoride is an important parameter affecting the health risk assessment. In conclusion, these findings suggest that precise measures can reduce health risks and guarantee safe drinking water for residents of Shiraz County.

Achieving better indoor air quality with IoT systems for future buildings: Opportunities and challenges

With the development of IoT technology and low-cost indoor air quality (IAQ) sensors, the IoT-based IAQ monitoring platform has garnered significant research interest and demonstrated its potential in enhancing IAQ management. This study presents a comprehensive review of previous research on the development and application of IoT-based IAQ platforms in different built environments. It offers detailed insights into the design and implementation of recent IoT-based IAQ platforms. The findings indicate that the IoT-based IAQ platforms are able to provide reliable information for IAQ monitoring. To ensure quality control of the IoT-based IAQ platform, it is suggested to replace the sensors every 4-6 months for reliable monitoring. In another aspect, integrating data-driven technology into the platform is crucial for IAQ prediction and efficient control of ventilation systems, leveraging the wealth of data available from the IoT platform. According to recent studies that applied data-driven algorithms for IAQ management, it can be confirmed that the data-driven algorithms are able to prompt IAQ by providing either more information or a control strategy. However, it should be noted that only 9.1 % of the developed platforms integrated data-driven models for IAQ management. Based on our findings, current challenges and further opportunities are discussed. Future studies should focus on integrating data-driven algorithms into IoT-based IAQ platforms and developing digital twins that can be used for real building IAQ management. However, there is obvious tension between controlling ventilation for energy efficiency versus better air quality. It is important to make a balance between energy efficiency and better air quality according to the current situations of specific built environments. Also, the next generation of IoT-based IAQ platforms should include occupants in the loop to create a more occupant-centric IAQ management approach.

A Review of Artificial Neural Network Models Applied to Predict Indoor Air Quality in Schools

BACKGROUND

Indoor air quality (IAQ) in schools can affect the performance and health of occupants, especially young children. Increased public attention on IAQ during the COVID-19 pandemic and bushfires have boosted the development and application of data-driven models, such as artificial neural networks (ANNs) that can be used to predict levels of pollutants and indoor exposures.

METHODS

This review summarises the types and sources of indoor air pollutants (IAP) and the indicators of IAQ. This is followed by a systematic evaluation of ANNs as predictive models of IAQ in schools, including predictive neural network algorithms and modelling processes. The methods for article selection and inclusion followed a systematic, four-step process: identification, screening, eligibility, and inclusion.

RESULTS

After screening and selection, nine predictive papers were included in this review. Traditional ANNs were used most frequently, while recurrent neural networks (RNNs) models analysed time-series issues such as IAQ better. Meanwhile, current prediction research mainly focused on using indoor PM2.5 and CO2 concentrations as output variables in schools and did not cover common air pollutants. Although studies have highlighted the impact of school building parameters and occupancy parameters on IAQ, it is difficult to incorporate them in predictive models.

CONCLUSIONS

This review presents the current state of IAQ predictive models and identifies the limitations and future research directions for schools.

Natural Ventilation and Aerosol Particles Dispersion Indoors

Aerosol pollutant particles indoors significantly affect public health. The conventional wisdom is that natural ventilation will alleviate the dispersion of airborne or aerosol particles. However, we show that the problem is far more complex and that natural ventilation should be applied under specific conditions to be effective. We performed several simulations of a simplified (and easily reproducible) room with a window opening and aerosol particles stratified layers. Opening a window can scatter particles present in stratified layers indoors and potentially contribute to the degradation of indoor air quality for a significant period of time. Moreover, we show that thermal instabilities arising from the temperature gradients due to temperature differences between the indoor and outdoor environment spread the particles randomly indoors, adversely affecting air quality and architectural design. Recommendations for more efficient natural ventilation minimizing aerosol pollutant particles dispersed indoors are provided.