Proceedings of the 2025 7th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2025)

<Previous Article In Volume
Next Article In Volume>

Research on the Enaemble Method of Mechanism Sand and Natural Sand Based on Machine Learning

Authors
Lei Wang1, Junmao Hu1, Jie He2, Min Liu2, Jinpeng Dai2, Qicai Wang2, *
1China Railway 21st Bureau Group Fourth Engineering Co., Ltd., Qinghai, Xining, 811600, China
2Lanzhou Jiaotong University, Gansu, Lanzhou, 730070, China
*Corresponding author. Email: wangqc@mail.lzjtu.cn
Corresponding Author
Qicai Wang
Available Online 16 December 2025.
DOI
10.2991/978-94-6463-902-5_15How to use a DOI?
Keywords
Mechanized sand; Natural sand; Machine learning; Feature engineering; Ensemble learning; SHAP analysis
Abstract

Accurate classification of manufactured and natural sand, a key natural sand substitute, is vital for controlling concrete performance. This study proposes a machine - learning - based sand classification method. By extracting sand particles’ morphological features (length /width ratio × roundness), a multi - dimensional feature engineering system is built. An ensemble learning model (combining Gradient Boosting, XGBoost, LightGBM) is used to distinguish manufactured (class 0) and natural (class 1) sand. It achieves an F1 score of 0.6211 and an ROC - AUC of 0.7105. SHAP analysis shows the “Length/width ratio×Roundness” interaction feature most impacts results, aiding sand classification mechanism study. This method helps rapid construction sand identification and concrete quality control.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2025 7th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2025)
Series
Advances in Engineering Research
Publication Date
16 December 2025
ISBN
978-94-6463-902-5
ISSN
2352-5401
DOI
10.2991/978-94-6463-902-5_15How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Lei Wang
AU  - Junmao Hu
AU  - Jie He
AU  - Min Liu
AU  - Jinpeng Dai
AU  - Qicai Wang
PY  - 2025
DA  - 2025/12/16
TI  - Research on the Enaemble Method of Mechanism Sand and Natural Sand Based on Machine Learning
BT  - Proceedings of the 2025 7th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2025)
PB  - Atlantis Press
SP  - 140
EP  - 154
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-902-5_15
DO  - 10.2991/978-94-6463-902-5_15
ID  - Wang2025
ER  -