AN APPLICATION OF MACHINE LEARNING FOR PREDICTING AIRBORNE CHLORIDE IN COASTAL AREAS

被引：0

作者：

Sakihara, Kohei ^{[1
]}

Taki, Yuta ^{[2
]}

Nakamura, Fuminori ^{[3
]}

Ukemasu, Kei ^{[4
]}

机构：

[1] School of Engineering, Faculty of Engineering, University of the Ryukyus

[2] IoE Business Dept., KOZO Keikaku Engineering Inc.

[3] Dept. of Civil and Environmental Engineering, Faculty of Engineering, Nagaoka University of Technology

[4] Sekisui House, Ltd.

来源：

Journal of Structural and Construction Engineering | 2024年 / 89卷 / 822期

关键词：

Airborne Chloride; ArtificialIntelligence; Chloride Attack; Durability; Machine Learning; Random Forest;

D O I：

10.3130/aijs.89.818

中图分类号：

学科分类号：

摘要：

In this study, a machine learning approach using the Isolation Forest, one of the anomaly detection machine learning algorithms, was proposed to exclude anomalous values from the training data. In addition, the influences of the modified training data on the prediction of airborne chloride were investigated. Therefore, it was found that combining statistical processing with the Isolation Forest improves the accuracy of predicting airborne chloride. Furthermore, it was revealed that the most contributing feature importance to the prediction of airborne chloride is the significant wave height. © 2024 Architectural Institute of Japan. All rights reserved.

引用

页码：818 / 829

页数：11

共 22 条

[1]

Uda T., Omata A., Konishi M., Kaigankarano-hiraienbunryounokeisanmoderu (A Model of Calculating the Amount of Airborne Chloride in Coastal Ares), Proceedings of Coastal Engineering, 39, pp. 1051-1055, (1992)

[2]

Kokubo S., Hajime O., Calculation Model for Airborne Chloride Ion Based on Seawater Particle Generation, Transactions of JSCE), 65, 4, pp. 259-268, (2009)

[3]

Yamada Y., Oshiro T., Masuda Y., Analytical Study on Airborne Chloride-Ions Near Coastal Area (Transactions of AIJ), 63, 514, pp. 21-26, (1998)

[4]

Tomiyama J., Konkuritokyojoubukonifuchakusuruhiraienbunnikansurusuchikaisekitekikento (A Numerical Analysis Study on Airborne Chloride Deposition on Concrete Bridge Superstructures), Proceedings of the Japan Concrete Institute, 36, 1, pp. 874-879, (2014)

[5]

Tomiyama J., Habuchi T., Miyazato S., Nakabayashi Y., Konkuritokyojoubukonifuchakusuruenbunryobunpunikansurusuchijik ken (A Numerical Experiments on the Distribution of Chloride Deposition on Concrete Bridge Superstructures), Proceedings of the Japan Concrete Institute, 37, 1, pp. 769-774, (2015)

[6]

Nakamura F., OTGONBILRG C., Masuda T., Kanda K., Shimomura T., Field Observations of Sea Salt Spray at The Hokuriku and Tohoku Area and Effects of Environmental Conditions, Transactions of JSCE), 77, 2, pp. I445-I450

[7]

Nakamura F., Ohara R., Yamaguchi T., Shimomura T., Quantitative Estimation of Surface Chloride Concentration of Concrete Combined with Coastal Geographical Conditions, Transactions of JSCE), 76, 3, pp. 189-208, (2020)

[8]

Ukemasu K., Sakihara K., Nakamura F., Taki Y., Tyokikansokudetanimotozukuokinawahontokaiganfukinnohiraienbunyosokuniokeru kikaigakushunotekiyo (An Application of Machine Learning to the Prediction of Airborne Chloride Along the Coast of Okinawa Island Based on Long-Term Observation Data), Proceedings of the Japan Concrete Institute, 43, 1, pp. 544-549

[9]

Ukemasu K., Sakihara K., Nakamura F., Tomiyama J., Taki Y., Prediction Airborne Chloride by Machine Learning Considering the Environmental Effects of Each Region, Proceedings of the Concrete Structure Scenarios, JSMS, 21, pp. 301-306

[10]

Liu F. T., Et al., Isolation Forest, 2008 Eighth IEEE International Conference on Data Mining, pp. 413-422, (2008)

← 1 2 3 →