AI grey box model for alum sludge as a soil stabilizer : an accurate predictive tool
- Authors: Baghbani, Abolfazl , Nguyen, Minh , Kafle, Bidur , Baghbani, Hasan , Shirani Faradonbeh, Roohollah
- Date: 2023
- Type: Text , Journal article
- Relation: International Journal of Geotechnical Engineering Vol. 17, no. 5 (2023), p. 480-494
- Full Text: false
- Reviewed:
- Description: By using a grey box AI model, a comprehensive study is presented on the behaviour prediction of alum sludge as a soil stabilizer. To creat models for predicting the California bearing rtio (CBR) of alum sludge as a soil stabilizer, the study employs statistical models, including multiple linear regression (MLR) and Partial least squares (PLS), and advanced artificial intelligence, including classificatoin and regression random forests (CRRF) and classification and regression trees (CART). Results show that CRRF and CART models accurately predict CBR values better than MLR and PLS models. For predicting the behaviour of alum sludge in soil stablization, the compaction number of hammer and sludge content were the most significant parameters. Gs and optimum moisture content of soil were the least important parameters. Study results provide valuable insights into alum sludge’s behaviour as a soil stablizer, which could reduce waste and promote sustainable practice. © 2023 Informa UK Limited, trading as Taylor & Francis Group.
Initial state of excavated soil and rock (ESR) to influence the stabilisation with cement
- Authors: Lu, Yi , Xu, Changhao , Baghbani, Abolfazl
- Date: 2023
- Type: Text , Journal article
- Relation: Construction and Building Materials Vol. 400, no. (2023), p.
- Full Text:
- Reviewed:
- Description: This paper investigates the initial state of excavated soil and rock (ESR). These initial states include dry density, organic content, water content (Wc), cement content (Cc), liquid index (LI), dry or wet mixing method. Three ESRs collected from tunnelling projects and kaolin were used in this study to compare. The specimens (i.e., 50 mm in diameter and 100 mm in height) were prepared in the laboratory and cured at 7 and 14 days, and then assessed by the unconfined compressive strength (UCS) test. The analysis shows that the ratio of Wc/Cc is the primary factor to obtain different UCS for high LI ESR and a simple equation is proposed for quick prediction. For ESR with a more general LI, predictive equations are also proposed in terms of artificial neural network (ANN) and genetic programming (GP) for 7-days curing time. The results indicate that the both ANN models with Bayesian Regularization (BR) algorithm outperform ANN with Levenberg-Marquardt (LM) and GP model are accurate to predict UCS of mixtures. © 2023 Elsevier Ltd
Microplastics in terrestrial ecosystems: A scientometric analysis
- Authors: He, Donghui , Bristow, Keith , Filipović, Vilim , Lv, Jialong , He, Hailong
- Date: 2020
- Type: Text , Journal article
- Relation: Sustainability Vol. 12, no. 20 (2020), p. 8739
- Full Text: false
- Reviewed:
- Description: Microplastics, as an emerging contaminant, have been shown to threaten the sustainability of ecosystems, and there is also concern about human exposure, as microplastic particles tend to bioaccumulate and biomagnify through the food chain. While microplastics in marine environments have been extensively studied, research on microplastics in terrestrial ecosystems is just starting to gain momentum. In this paper, we used scientometric analysis to understand the current status of microplastic research in terrestrial systems. The global scientific literature on microplastics in terrestrial ecosystems, based on data from the Web of Science between 1986 and 2020, was explored with the VOSviewer scientometric software. Co-occurrence visualization maps and citation analysis were used to identify the relationship among keywords, authors, organizations, countries, and journals focusing on the issues of terrestrial microplastics. The results show that research on microplastics in terrestrial systems just started in the past few years but is increasing rapidly. Science of the Total Environment ranks first among the journals publishing papers on terrestrial microplastics. In addition, we also highlighted the desire to establish standards/protocols for extracting and quantifying microplastics in soils. Future studies are recommended to fill the knowledge gaps on the abundance, distribution, ecological and economic effects, and toxicity of microplastics.