Estimation of Construction Waste Generation and Management in Taiwan

Huang, Rong; Yeh, Li Hsu; Chen, Hao Hsien; Lin, Jyh Dong; Chen, Ping Fu; Sung, Po Hsun; Yau, Jyh Tyng

doi:10.4028/www.scientific.net/amr.243-249.6292

Cited by 9 publications

(2 citation statements)

References 5 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning and statistical analysis algorithms that have been employed to predict C&D waste generation include artificial neural networks (ANNs), adaptive neuro-fuzzy inference systems, support vector machines (SVMs), linear regression (LR) analysis, decision trees (DTs), and genetic algorithms (Gas) [ 15 ]. Furthermore, most existing studies on the prediction of C&D waste generation have used machine learning models based on using continuous data as input variables that applied algorithms, such as ANN (Golbaz et al (2019) [ 17 ]; Noori et al (2010) [ 18 ]; and Song et al (2016) [ 19 ]), SVM (Abbasi et al (2013) [ 20 ]; Golbaz et al (2019) [ 17 ]; and Kumar et al (2018) [ 21 ]), LR (Abdoli et al (2011) [ 22 ]; Azadi and Karimijashni (2015) [ 23 ]; Chhay et al (2018) [ 24 ]; and Golbaz et al (2019) [ 17 ]), and DT (Cha et al (2017) [ 25 ]; Huang et al (2011) [ 26 ]; and Kannangara et al (2017) [ 27 ]). However, independent variables, which include continuous data (e.g., building age, GFA) and categorical data (e.g., region [ 28 ], building use [ 29 ], building structure [ 30 ], wall material [ 31 ], and roofing material [ 31 ]), affect C&D waste generation.…”

Section: Introductionmentioning

confidence: 99%

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets

Cha

Moon

Kim

et al. 2020

IJERPH

View full text Add to dashboard Cite

Recently, artificial intelligence (AI) technologies have been employed to predict construction and demolition (C&D) waste generation. However, most studies have used machine learning models with continuous data input variables, applying algorithms, such as artificial neural networks, adaptive neuro-fuzzy inference systems, support vector machines, linear regression analysis, decision trees, and genetic algorithms. Therefore, machine learning algorithms may not perform as well when applied to categorical data. This article uses machine learning algorithms to predict C&D waste generation from a dataset, as a way to improve the accuracy of waste management in C&D facilities. These datasets include categorical (e.g., region, building structure, building use, wall material, and roofing material), and continuous data (particularly, gloss floor area), and a random forest (RF) algorithm was used. Results indicate that RF is an adequate machine learning algorithm for a small dataset consisting of categorical data, and even with a small dataset, an adequate prediction model can be developed. Despite the small dataset, the predictive performance according to the demolition waste (DW) type was R (Pearson’s correlation coefficient) = 0.691–0.871, R2 (coefficient of determination) = 0.554–0.800, showing stable prediction performance. High prediction performance was observed using three (for mortar), five (for other DW types), or six (for concrete) input variables. This study is significant because the proposed RF model can predict DW generation using a small amount of data. Additionally, it demonstrates the possibility of applying AI to multi-purpose DW management.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets

Cha

Moon

Kim

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…For instance, Kofoworola and Gheewala (2009) estimated CW generated by new residential and non-residential construction in Thailand using the floor area indicator. Similarly, Huang et al (2011) and Ding and Xiao (2014) quantified the weight of generated waste (tonnes) per unit floor area (m 2 ) of the constructed or demolished works. In Spain, Villoria Sáez et al (2012) created a model to estimate residential CW based on waste accumulation and built area, while Lage et al (2010) estimated waste based on the regional information on floor area, population, waste composition, and quantity to determine WGRs.…”

Section: A Review Of Methods and Relevant Indicators In Estimating Cwmentioning

confidence: 99%

Estimating construction waste in New Zealand: a focus on urban areas, residential and non-residential building activities

Albsoul,

Doan,

GhaffarianHoseini

2024

Environ. Res. Commun.

View full text Add to dashboard Cite

This paper examines the significant increase in construction waste (CW) due to urbanisation and population growth in New Zealand and worldwide. The aim is to estimate CW using available data in New Zealand and identify relevant indicators to employ estimation methods. Various methods and models for estimating CW at the urban level and from building activities are reviewed. According to the best available data, the paper uses the per-capita multiplier and waste generation rate methods to estimate CW in New Zealand. New Zealand's per-capita multiplier for CW is 943.46 kg/per capita. The waste generation method using the floor area indicator is applied at residential and non-residential building levels. The estimated CW in 2021 was 531,109 tonnes for residential and non-residential buildings using the floor area indicator. The findings reveal a positive relationship between residential building activity and population growth, with Auckland generating the highest rate of CW. Because of the limitations of the available data and estimation methods, the paper highlights the need for standardised data collection systems and outreach programs to improve CW estimation practices. Further research is recommended to enhance waste reduction strategies and identify high-waste-generating materials and methods. It is vital to have accurate CW estimations to support project waste management plans and sustainable construction practices and to inform waste management policies and regulations at the regional or national level.

show abstract

Web-based construction waste estimation system for building construction projects

Zhang

2013

Automation in Construction

View full text Add to dashboard Cite

Estimation of Construction Waste Generation and Management in Taiwan

Cited by 9 publications

References 5 publications

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets

Estimating construction waste in New Zealand: a focus on urban areas, residential and non-residential building activities

Web-based construction waste estimation system for building construction projects

Contact Info

Product

Resources

About