Düşük Plastisiteli Killi Zeminlerin Kıvam Özelliklerinin Tahmininde Rastgele Orman Yöntemi

Year 2021, Volume: 21 Issue: 3, 668 - 680, 30.06.2021

Zülal Akbay Arama , Seyidcem Karakaş , Said Enes Nuray , Oğuzhan Alten , Muhammed Selahaddin Akın , Hazal Berrak Gençdal

https://doi.org/10.35414/akufemubid.856192

Abstract

Bu çalışma kapsamında, düşük plastisiteli killi zeminlerin kıvam özelliklerinin tahmininde Rastgele Orman yönteminin uygulanabilirliği değerlendirilmiştir. Bu amaçla, Birleştirilmiş Zemin Sınıflandırma Sistemi’ne göre düşük plastisiteli kil sınıfında yer alan 665 adet zeminin likit, plastik limit ve su muhtevası deney sonuçları derlenerek bir veri seti oluşturulmuştur. Python yazılımı kullanılarak yapılan tek ve çok değişkenli regresyon analizlerinde likit limit, derinlik, su muhtevası ve doğal birim hacim ağırlığı değerleri bireysel veya gruplar halinde girdi parametreleri olarak değerlendirilmiş ve plastisite indisi tahminindeki etkinlikleri araştırılmıştır. Aynı zamanda, laboratuvar verilerinin tutarsızlık durumları veya belirli bir eğilim izlememesi sebebi ile ortaya çıkan tahmin oranı azalmasına dikkat çekilerek, bu oranlarının Rastgele Orman yöntemi ile nasıl yükseltilebileceği konusu da incelenmiştir. Sonuçlar, Rastgele Orman yönteminin düşük plastisiteli kil zeminlerin plastisite indisi değerinin tahmininde kullanılabilir nitelikte olduğunu göstermektedir.

Keywords

Düşük plastisiteli killer, Rastgele orman yöntemi, Karar ağaçları, plastisite indisi, likit limit

Supporting Institution

İstanbul Üniversitesi-Cerrahpaşa

Project Number

FBA-2020-34051

Thanks

Bu çalışma, İstanbul Valiliği (YİKOB) ve İstanbul Üniversitesi-Cerrahpaşa Bilimsel Araştırma Projeleri Birimi tarafından BYP-2020-34856 ve FBA-2020-34051 projeleri ile desteklenmektedir.

The Random Forest Method to Predict the Consistency Characteristics of Low Plastic Clayey Soils

Abstract

Within the scope of this study, the applicability of the Random Forest Method in the prediction process of the consistency properties of low plastic clayey soils was evaluated. For this purpose, a data set was created by compiling the liquid limit, plastic limit, and water content test results of 665 soils. These soils were classified as low plastic clayey soils according to the Unified Soil Classification System. Univariate and multivariate regression analyzes were performed using Python software. The liquid limit, depth, water content, and natural unit weight values were evaluated individually or in groups as input parameters and their effectiveness in plasticity index estimation was investigated. At the same time, by drawing attention to the decrease in the estimation rate caused by the inconsistency of the laboratory data or not following a certain trend, the issue of how these rates can be increased by the Random Forest method was also examined. Consequently, it is shown that the Random Forest method can be used for the estimation of the consistency properties of low plastic clayey soils.

Keywords

Low plastic clays, Random forest method, Decision trees, plasticity index, liquid limit

Project Number

FBA-2020-34051

References

• Ahmed, Z., Mohamed, K., Zeeshan, S., Dong. X., 2020. Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine. Database, 2020, 1-35.
• Akar, Ö., Güngör, O., Akar, A., 2010. Rastgele Orman Sınıflandırıcısı ile arazi kullanım alanlarının belirlenmesi. III. Uzaktan Algılama ve Coğrafi Bilgi Sistemleri Sempozyumu, Gebze, Kocaeli, 1, 142-152.
• Akar, Ö., Güngör, O., 2012. Rastgele Orman Algoritması kullanılarak çok bantlı görüntülerin sınıflandırılması. Jeodezi ve Jeoinformasyon Dergisi, 1, 2, 139-146. DOI: 10.9733/jgg.241212.1t.
• Akbay Arama, Z., Yücel, M., Akın, M.S., Dalyan, İ., 2021. A comparative study on the application of artificial intelligence networks versus regression analysis for the prediction of clay plasticity. Arabian Journal of Geosciences, 14, 534.
• Archer, K.J., 2008. Emprical characterization of Random Forest variable importance measure, computational statistical data analysis. Computational Statistics & Data Analysis, 52, 4, 2249-2260.
• ASTM D-4318. Standard test methods for liquid limit, plastic limit, and plasticity index of soils.
• ASTM D-422. Standard test method for particle-size analysis of soils.
• Breiman, L., 2001. Random Forests, Machine Learning. 2001 Kluwer Academic Publishers, 45, 1, 5-32.
• Çinicioğlu, F., Öser, C., Uzman, E., Kutu, S., Güler, M., 2002. Killerde kıvam parametrelerinin birbirleriyle ilişkilendirilmesi. Zemin Mekaniği ve Temel Mühendisliği Dokuzuncu Ulusal Kongresi, Eskişehir, Türkiye.
• Das, M. D., 2010. Principals of Foundation Engineering. SI Edition, 15-17. Davis, J.A. 1971. Elementary Survey Analysis. Prentice Hall, New Jersey.
• Ermias, B., Vishal, V., 2020. Application of artificial ıntelligence for prediction of swelling potential of clay-rich soils. Geotech Geol Eng, 38, 6189–6205.
• Gislason, P.O., Benediktsson, J. A, Sveinsson, J.R., 2004. Random Forest Classification of multi-source remote sensing and geographic data. IEEE International Geoscienceand Remote Sensing Symposium IGARSS ‘04Proceedings, 2, 1049 – 1052.
• Grömping, U., 2009. Variable importance assessment in regression: linear regression versus Random Forest. Am Stat, 63, 4, 308–319. DOI:10.1198/tast.2009.08199.
• Iyisan, R., 1993. Geoteknik özelliklerin belirlenmesinde sismik ve penetrasyon deney sonuçlarının karşılaştırılması (Doktora Tezi), İstanbul Teknik Üniversitesi, Fen Bilimleri Enstitüsü, Geoteknik Mühendisliği, 255.
• Kandpal, M., Kandpal, A., 2014. Establishing correlation between size estimation metrics and effort-A statistical approach. International Journal of Computer Applications, 95, 21, 1-6.
• Kayabası, A., 2020. Geotechnical properties of fine-grained soils in Ankara/Turkey: an assessment of the existing empirical equations. Environ Earth Sci, 79, 282.
• Laskar, A., Pal, S. K., 2012. Geotechnical characteristics of two different soils and their mixture and relationships between parameters. EJGE, 17, 2821–2832.
• Lewis, C. D., 1982. Industrial and business forecasting methods: a practical guide to exponential smoothing and curve fitting. Butterworths Scientific, London.
• Ly, H., Nguyen, T., Pham, B. T., 2021. Estimation of soil cohesion using machine learning method: A Random Forest approach. Advances in Civil Engineering, 8873993, 14. https://doi.org/10.1155/2021/8873993
• Liaw, A., Wiener, M., 2002. Classification and regression by Random Forest. R News, 2, 3, 18–22.
• Naveena, N., Sanjay, S. J., 2018. Establishing relationship between plasticity ındex and liquid limit by simple linear regression analysis. Int J Res Appl Sci Eng Technol, 6, 6, 1975–1978.
• Nuray, S. E., Gençdal, H. B., Akbay Arama, Z., 2021. Zeminlerin kıvam ve kompaksiyon özelliklerinin tahmininde Rastgele Orman Regreyonu yönteminin uygulanabilirliği. Journal of Engineering Sciences and Design, 9, 1, 265-281. DOI: 10.21923/jesd.804446.
• Ouedraogo, I., Defourny, P., Vanclooster, M., 2019. Application of Random Forest Regression and comparison of its performance to multiple linear regression in modeling groundwater nitrate concentration at the African Continent scale. Hydrogeology Journal, 27, 1081–1098. https://doi.org/10.1007/s10040-018-1900-5.
• Pal, M., 2003. Random Forest for land cover classification. IEEE International Geoscience and Remote Sensing Symposium, IGARSS ‘03Proceedings, 6, 3510-3512.
• Pham, T.B., Qi, C., Ho, L.S., Thoi, T.N., Ansari, N.A., Nguyen, M.D., Nguyen, H.D., Ly, H.B., Le, H.V., Prakash, I., 2020. A novel hybrid soft computing model using Random Forest and particle swarm optimization for estimation of undrained shear strength of soil. Sustainability, 12, 2218; DOI:10.3390/su12062218.
• Prakash, S., Jain, P.K., 2002. Engineering Soil Testing, Nem Chand & Bros, Roorkee.
• Seed, H. B., Woodward, R.J., Lundgren, R., 1964. Fundamental aspects of the atterberg limits. J Soil Mech Found Div, 90, 6, 75–106.
• Segal, M.R. 2003. Machine Learning Benchmarks and Random Forest Regression. https://escholarship.org/uc/item/35x3v9t4.
• Sen, B., Pal, S. K., 2014. Index properties of soils collected from different locations and correlations of parameters. EJGE, 19, 3443–3452.
• Sharma, B., Sridharan, A., 2018. Liquid and plastic limits of clays by cone method. Geo-Engineering, 9, 22–31.
• Shimobe, S., Spagnoli, G., 2020. Fall cone tests considering water content, cone penetration index, and plasticity angle of fine-grained soils. J Rock Mech Geotech Eng, 12, 1347–1355. https://doi.org/10.1016/j. jrmge.2020.02.005.
• Spagnoli, G., Sridharan, A., Oreste, P., Bellato, D., Matteo, L. D., 2018. Statistical variability of the correlation plasticity index versus liquid limit for smectite and kaolinite. Appl Clay Sci, 156, 152–159.
• Srinath, K.R. 2017. Python – The fastest growing programming language. International Research Journal of Engineering and Technology, Volume 4, Issue 12, 354-357.
• Swamidass, P.M., 2000. Mean absolute percentage error (MAPE). Encyclopedia of Production and Manufacturing Management. Springer, Boston, MA. https://doi.org/10.1007/1-4020-0612-8_580.
• TS 1900-1. Türk Standardı. İnşaat mühendisliğinde zemin laboratuvar deneyleri-fiziksel özelliklerin tayini.
• Waske, B., Heinzel, V., Braun, M., Menz, G., 2007. Random Forests for classifying multi-temporal sar data, Proc. ‘Envisat Symposium Montreux, Switzerland.http://envisat.esa.int/envisatsymposium/proceedings/sessions/3D3/461589wa.pdf.
• Watts J. D., Lawrence R. L., 2008. Merging Random Forest classification with an object-oriented approach for analysis of agricultural lands. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVII(B7).
• Whyte, I. L., 1982. Soil plasticity and strength-a new approach using extrusion. Ground. Eng., 15, 1, 16-24.
• Yogatama, B. A., Tirta, B. A., 2021. Python application in geotechnical engineering practices. Simposium Nasional Teknologi Infrastruktur Abad ke-21.
• Zhang, W., Wu, C., Zhong, H. Li, Y., Wang, L., 2021. Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization. Geoscience Frontiers, 469-477.
• https://veribilimcisi.com/mse-rmse-mae-mape metrikleri-nedir/ (14.07.2017).
• https://medium.com/human-in-a-machine-world/mae-and-rmse-which-metric-is-better-e60ac3bde13d (14.07.2017).