Artificial neural network modeling of meteorological and geological influences on indoor radon concentration in selected tertiary institutions in Southwestern Nigeria

Oni, Olatunde Michael; Aremu, Abraham Adewale; Oladapo, Olukunle Olaonipekun; Agboluaje, BA; Fajemiroye, Joseph Ademola

doi:10.1016/j.jenvrad.2022.106933

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few literatures on radon levels in buildings are available in developing countries. However, in Nigeria only radon concentration levels in buildings from south-western part of the country were reported (Oni et al, 2012;Okeji et al, 2013;Ademola et al, 2015;Afolabi et al, 2015;Asere and Ajayi 2017;Obed et al, 2018;Sokari, 2018;Usikalu et al, 2018;Akabuogu et al, 2019;Chenko et al, 2019;Avwiri et al, 2020;Oladapo et al, 2020;Olaoye et al, 2020;Ndubisi et al, 2021;Asere et al, 2022;Olowookere et al, 2022). Hence, this work investigates the radon concentration levels in IBB University buildings and its effect on the occupants.…”

Section: Introductionmentioning

confidence: 98%

Indoor radon concentration levels in some selected offices at Ibrahim Badamasi Babangida University, Lapai, Nigeria and its attendant annual effective dose

Bashir,

Suleiman,

Kolo

et al. 2023

SWJ

View full text Add to dashboard Cite

Although radon concentrations in outdoor environments are generally low, the indoor concentrations can become appreciably high thereby affecting the indoor air quality and causing some severe health challenges. Thirty (30) offices from the ground floor and first floor of some buildings within Ibrahim Badamasi Babangida (IBB) University campus, Lapai Nigeria, were randomly selected for indoor radon concentration (CRn) measurement using RAD7 continuous radon monitor. Annual effective dose was also computed to determine the level of public exposure. The results showed that radon concentration values for all the offices on the ground floor ranged between 9.6±2.7 Bqm−3 and 90.7±8.1 Bqm−3, with mean value of 28.5±4.8 Bqm−3 while the range of radon concentration at first floor was 2.5±1.4 Bqm−3 - 80.4±7.5 Bqm−3. All the measured indoor radon concentration levels were less than the 100 Bqm−3 action level proposed by World Health Organization (WHO). Average annual absorbed dose for both ground and first floors were 0.36±0.06 mSvy−1 and 0.24±0.05 mSvy−1 respectively, with corresponding mean annual effective dose of 0.86±0.15 mSvy−1 and 0.58±0.11 mSvy−1 in sequence. These values were below the 1.0 mSvy−1 safety limit set for public. Although the results did not suggest any immediate exposure threat to the public, it is important that the University staffs are adequately informed of indoor radon levels and its attendant health hazards. Improved and adequate ventilation of all the office buildings is highly encouraged in order to keep the radon levels as low as reasonably achievable (ALARA).

show abstract

Section: Introductionmentioning

confidence: 98%

Indoor radon concentration levels in some selected offices at Ibrahim Badamasi Babangida University, Lapai, Nigeria and its attendant annual effective dose

Bashir,

Suleiman,

Kolo

et al. 2023

SWJ

View full text Add to dashboard Cite

show abstract

“…With the advances in computing capacity, the need for improved accuracy, and reduced complexity, machine learning techniques have emerged as a promising horizon. Thus, an increasing tendency toward deep learning has been noticed with a particular interest in Artificial Neural Networks (ANNs), and it was extensively utilized by researchers in a variety of applications (Alardhi et al, 2023; Babu et al, 2022;Bashayreh et al, 2021;Chen et al, 2023;Oni et al, 2022). In the field of hydrology, ANNs derive their strength from their adaptability and ability to perceive complex and intricate connections between the variables, which is essential for simulating the inherent complexity and non-linearity of the hydrological systems (Govindaraju and Rao, 2000; Wu and Chau, 2011).…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approach for Runoff Prediction: Evaluating the Long-Short-Term Memory Neural Network Architectures for Capturing Extreme Discharge Events in the Ouergha Basin, Morocco

Karmouda,

Bouramtane,

TAHIRI

et al. 2023

Ecol. Eng. Environ. Technol.

View full text Add to dashboard Cite

Rainfall-runoff modeling plays a crucial role in achieving efficient water resource management and flood forecasting, particularly in the context of increasing intensity and frequency of extreme meteorological events induced by climate change. Therefore, the aim of this research is to assess the accuracy of the Long-Short-Term Memory (LSTM) neural networks and the impact of its architecture in predicting runoff, with a particular focus on capturing extreme hydrological discharges in the Ouergha basin; a Moroccan Mediterranean basin with historical implications in many cases of flooding; using solely daily rainfall and runoff data for training. For this purpose, three LSTM models of different depths were constructed, namely LSTM 1 single-layer, LSTM 2 bi-layer, and LSTM 3 tri-layer, their window size and hyperparameters were first tuned, and on seven years of daily data they were trained, then validated and tested on two separate years to ensure the generalization on unseen data. The performance of the three models was compared using hydrogram-plots, Scatter-plots, Taylor diagrams, and several statistical metrics. The results indicate that the single-layer LSTM 1 outperforms the other models, it consistently achieves higher overall performance on the training, validation, and testing periods with a coefficient of determination R-squared of 0.92, 0.97, and 0.95 respectively; and with Nash-Sutcliffe efficiency metric of 0.91, 0.94 and 0.94 respectively, challenging the conventional beliefs about the direct link between complexity and effectiveness. Furthermore, all the models are capable of capturing the extreme discharges, although, with a moderate underprediction trend for LSTM 1 and 2 as it does not exceed -25% during the test period. For LSTM 3, even if its underestimation is less pronounced, its increased error rate reduces the confidence in its performance. This study highlights the importance of aligning model complexity with data specifications and suggests the necessity of considering unaccounted factors like upstream dam releases to enhance the efficiency in capturing the peaks of extreme events.

show abstract

Machine Learning for Indoor Air Quality Assessment: A Systematic Review and Analysis

Saini,

Dutta,

Marques

2024

Environ Model Assess

View full text Add to dashboard Cite

Artificial neural network modeling of meteorological and geological influences on indoor radon concentration in selected tertiary institutions in Southwestern Nigeria

Cited by 3 publications

References 22 publications

Indoor radon concentration levels in some selected offices at Ibrahim Badamasi Babangida University, Lapai, Nigeria and its attendant annual effective dose

Indoor radon concentration levels in some selected offices at Ibrahim Badamasi Babangida University, Lapai, Nigeria and its attendant annual effective dose

Deep Learning Approach for Runoff Prediction: Evaluating the Long-Short-Term Memory Neural Network Architectures for Capturing Extreme Discharge Events in the Ouergha Basin, Morocco

Machine Learning for Indoor Air Quality Assessment: A Systematic Review and Analysis

Contact Info

Product

Resources

About