Yapay Sinir Ağları Kullanılarak Toprak Gazı Radonu ve Toprak Geçirgenliği arasındaki İlişkinin Araştırılması

Abstract

Bu çalışmanın amacı, toprak gazı radon konsantrasyonu (CRn) ile toprak geçirgenliği (k) arasındaki ilişkiyi araştırmaktır. Bunu gerçekleştirmek için, literatürden toplanan 142 toprak gazı CRn ve k ölçümünden bir tek doğrusal regresyon analizi (SLRA) modeli ve bir yapay sinir ağı (YSA) modeli oluşturulmuştur. Her iki model tarafından tahmin edilen toprak gazı CRn değerleri ölçülenlerle karşılaştırıldığında, YSA modeli SLRA modelinden daha iyi performans göstermiştir. Ayrıca, SLRA ve YSA modellerinin tahmin yeteneklerini incelemek için korelasyon katsayısı, kök ortalama kare hatası, bağıl mutlak hata ve ortalama mutlak hata dahil olmak üzere çeşitli performans ölçütleri belirlenmiştir. Elde edilen ölçütler, YSA modelinin SLRA modelinden daha üstün performans sergilediğini ve böylece toprak gazı CRn değerlerinin tahmininde YSA modelinin doğruluğunu ve uygulanabilirliğini göstermiştir. Çalışmanın bulguları, geliştirilen YSA modelinin toprak k değerlerine dayalı olarak toprak gazı CRn değerlerini tahmin etmek için kullanılabileceğini göstermiştir.

Keywords

• Toprak gazı radonu
• Toprak geçirgenliği
• Yapay sinir ağları

Investigating the Relationship between Soil Gas Radon and Soil Permeability by Using Artificial Neural Networks

Abstract

This study aims to explore the relationship between soil gas radon concentration (CRn) and soil permeability (k). To accomplish this, a single linear regression analysis (SLRA) model and an artificial neural network (ANN) model were built from 142 soil gas CRn and k measurements collected from the literature. When soil gas CRn values predicted by both models were compared with those measured, the ANN model outperformed the SLRA model. Furthermore, several performance metrics, including correlation coefficient, root mean square error, relative absolute error, and mean absolute error were determined to examine the prediction capabilities of SLRA and ANN models. The metrics obtained demonstrated that the ANN model exhibited superior performance to the SLRA model, thereby showing the accuracy and applicability of the ANN model for forecasting soil gas CRn values. The study's findings indicated that the developed ANN model may be utilized to forecast soil gas CRn values based on soil k values.

Keywords

• Soil gas radon
• Soil permeability
• Artificial neural networks

References

1. [1] Nuhu, H., Hashim, S., Aziz Saleh, M., Syazwan Mohd Sanusi, M., Hussein Alomari, A., Jamal, M.H., Abdullah, R.A., Hassan, S.A. 2021. Soil Gas Radon and Soil Permeability Assessment: Mapping Radon Risk Areas in Perak State, Malaysia, PLoS One, Vol. 16(7), e0254099.
2. [2] WHO. 2011. Guidelines for drinking water quality. World Health Organization, Copenhagen. 2011 Vol 1. 3rd edition).
3. [3] Alonso, H., Rubiano, J.G., Guerra, J.G., Arnedo, M.A., Tejera, A., Martel, P. 2019. Assessment of Radon Risk Areas in the Eastern Canary Islands using Soil Radon Gas Concentration and Gas Permeability of Soils, Science of The Total Environment, Vol. 664, p. 449–460.
4. [4] Giustini, F., Ciotoli, G., Rinaldini, A., Ruggiero, L., Voltaggio, M. 2019. Mapping the Geogenic Radon Potential and Radon Risk by Using Empirical Bayesian Kriging Regression: A Case Study from A Volcanic Area of Central Italy. Science of The Total Environment, Vol. 661, p. 449–464.
5. [5] ICRP. 2010. Lung Cancer Risk from Radon and Progeny and Statement on Radon. ICRP Publication 115. Ann. ICRP, Vol. 40(1), p. 1–64.
6. [6] UNSCEAR. 2006. Effects of Ionizing Radiation-Volume II: Scientific Annexes C, D and E. United Nations, New York.
7. [7] Sharshir, S.S., Abd Elaziz, M., Elsheikh, A. 2023. Augmentation and Prediction of Wick Solar Still Productivity Using Artificial Neural Network Integrated with Tree–Seed Algorithm, International Journal of Environmental Science and Technology, Vol. 20, p. 7237–7252.
8. [8] Araei, A.A. 2013. Artificial Neural Networks for Modeling Drained Monotonic Behavior of Rockfill Materials. International Journal of Geomechanics, Vol. 14(3), 04014005.

9. [9] Khandelwal, M., Singh, T.N. 2009. Prediction of Blast-Induced Ground Vibration Using Artificial Neural Network. International Journal of Rock Mechanics and Mining Sciences, Vol. 46(7), p. 1214-1222.
10. [10] Neznal, M., Neznal, M., Matolin, M., Barnet, I., Miksova, J. 2006. The New Method for Assessing the Radon Risk of Building Sites. Project report. State Office for Nuclear Safety, Prague
11. [11] Cosma, C., Cucoş-Dinu, A., Papp, B., Begy, R., Sainz, C. 2013. Soil and Building Material as Main Sources of Indoor Radon in Băiţa-Ştei Radon Prone Area (Romania), Journal of Environmental Radioactivity, Vol. 116, p. 174-179.
12. [12] Beltrán-Torres, S., Szabó, K.Z., Tóth, G., Tóth-Bodrogi, E., Kovács, T., Szabó, C. 2023. Estimated Versus Field Measured Soil Gas Radon Concentration and Soil Gas Permeability, Journal of Environmental Radioactivity, Vol. 265, 107224.
13. [13] Ünal, H.T., Başçiftçi, F. 2022. Evolutionary Design of Neural Network Architectures: A Review of Three Decades of Research, Artificial Intelligence Review, Vol. 55, p. 1723–1802.
14. [14] Choobbasti AJ, Farrokhzad F, Barari A (2009) Prediction of Slope Stability Using Artificial Neural Network (A Case Study: Noabad, Mazandaran, Iran). Arabian Journal of Science and Engineering, Vol. 2, p. 311–319
15. [15] Guo, Z., Uhrig, R.E. 1992. Use of Artificial Neural Networks to Analyze Nuclear Power Plant Performance, Nuclear Technology, Vol. 99, p. 36–42
16. [16] Goktepe B, Agar E, Lav AH (2004) Comparison of Multilayer Perceptron and Adaptive Neuro-Fuzzy System on Backcalculating the Mechanical Properties of Flexible Pavements ARI: The Bulletin of Istanbul Technical University, Vol. 54, p. 65–77.
17. [17] Erzin, S. 2024. Prediction of the Radon Concentration in Thermal Waters Using Artificial Neural Networks, International Journal of Environmental Science and Technology, Vol. 21(3), p. 7321–732.
18. [18] Uzair, M., Jamil, N. 2020. Effects of Hidden Layers on the Efficiency of Neural networks. 2020 IEEE 23rd International Multitopic Conference (INMIC), 1-6.
19. [19] Gopalakrishnan, K. 2010. Effect of Training Algorithms on Neural Networks Aided Pavement Diagnosis, International Journal of Engineering Science and Technology, Vol. (2), p. 83-92.
20. [20] Erzin, Y., Rao, B.H., Singh, D.N. 2008. Artificial Neural Network Models for Predicting Soil Thermal Resistivity, International Journal of Thermal Sciences, Vol. 47(10), p. 1347–1358.
21. [21] Motahar, S., Sadri, S. 2021. Applying Artificial Neural Networks to Predict the Enhanced Thermal Conductivity of a Phase Change Material with Dispersed Oxide Nanoparticles, International Journal of Energy Resources, Vol. 45, p. 15092–15109.
22. [22] Mahmoud, B., Pete, B., Majid, H., Sahar, H. 2021. Ten-Year Estimation of Oriental Beech (Fagus Orientalis Lipsky) Volume Increment in Natural Forests: A Comparison of An Artificial Neural Networks Model, Multiple Linear Regression and Actual Increment, Forestry: An International Journal of Forest Research, Vol. 94(4), p. 598–609.
23. [23] Muhammad Waseem, A., Monjur, M., Yacine, R. 2017. Trees vs Neurons: Comparison Between Random Forest and ANN for High-Resolution Prediction of Building Energy Consumption, Energy and Buildings, Vol. 147, p. 77-89, ISSN 0378-7788.
24. [24] Kaastra, I., Boyd, M. 1996. Designing a Neural Network for Forecasting Financial and Economic Time Series. Neurocomputing, Vol. 10(3), p. 215-236.
25. [25] Smith, G.N. 1986. Probability and Statistics in Civil Engineering: An Introduction, Collins, London