Estimation of construction waste generation based on an improved on-site measurement and SVM-based prediction model: A case of commercial buildings in China

A comprehensive model for quantifying construction waste in high-rise buildings in India

The construction industry plays a vital role in the economic development of any country. Concurrently, the sector also generates enormous quantities of construction and demolition waste (CDW) that damages the ecology causing environmental pollution and deteriorating human health. Recently, various governments and other organizations realized the importance of implementing construction waste management (CWM) practices to attain sustainability in construction. The current decade can be called a pathway for achieving the 2030 agenda for sustainable development goals in which CWM plays an inevitable role. However, accurately quantifying construction waste is necessary to successfully implement any CDW management plan. A detailed literature review for the current research revealed that limited information on the magnitude of construction waste is available in India. Therefore, the current paper proposes a practically viable model to estimate the waste generation index (construction waste generated per total floor area) of high-rise residential buildings in India. The waste quantification is being done based on the project documents and expert interviews. The methodology is later validated through a high-rise building with G + 18 stories located in Kerala, India. The study indicated that a high-rise concrete framed structure generates 122.3 kg m-2 of waste during construction. It was also noted that, concrete, aggregates and blocks constitute 92% of the total waste generated in the project. The developed model can also be used as a cornerstone for establishing a construction waste database at the regional level.

Investigation of spatial association network features of construction waste in major Chinese urban agglomeration

The illegal dumping of construction waste (CW) poses an increasingly serious environmental pollution problem with the accelerated rate of urbanization. As CW disposal capacity struggles to match municipal needs, some CW is being diverted to higher resource endowment cities rather than recycled. To address this situation, it is necessary to obtain reliable information on the characteristics and evolution of CW generation networks in China. This study combines a modified gravity model with Social Network Analysis (SNA) to analyze the spatial association networks of CW generation in four Chinese urban agglomerations between 2000 and 2020. Results reveal the evolution characteristics of the CW generation network, including increasing density and correlation and decreasing network efficiency. Furthermore, the Quality Assurance Procedure (QAP) indicates that urbanization level and population size are positively correlated with CW generations, whereas distance plays a negative role, but resources are insignificant for network formation. The findings provide insight into current patterns of waste distribution and a theoretical basis for government policy formulation in the future.

Modeling construction and demolition waste quantities in Tanta City, Egypt: a synergistic approach of remote sensing, geographic information system, and hybrid fuzzy neural networks

A waste management strategy needs accurate data on the generation rates of construction and demolition waste (CDW). The objective of this study is to provide a robust methodology for predicting CDW generation in Tanta City, one of the largest and most civilized cities in Egypt, based on socioeconomic and waste generation statistics from 1965 to 2021. The main contribution of this research involves the fusion of remote sensing and geographic information systems to construct a geographical database, which is employed using machine learning for modeling and predicting the quantities of generated waste. The land use/land cover map is determined by integrating topographic maps and remotely sensed data to extract the built-up, vacant, and agricultural areas. The application of a self-organizing fuzzy neural network (SOFNN) based on an adaptive quantum particle swarm optimization algorithm and a hierarchical pruning scheme is introduced to predict the waste quantities. The performance of the proposed models is compared against that of the FNN with error backpropagation and the group method of data handling using five evaluation measures. The results of the proposed models are satisfactory, with mean absolute percentage error (MAPE), normalized root mean square error (NRMSE), determination coefficient, Kling-Gupta efficiency, and index of agreement ranging between 0.70 and 1.56%, 0.01 and 0.03, 0.99 and 1.00, 0.99, and 1.00. Compared to other models, the proposed models reduce the MAPE and NRMSE by more than 92.90% and 90.64% based on fivefold cross-validation. The research findings are beneficial for utilizing limited data in developing effective strategies for quantifying waste generation. The simulation outcomes can be applied to monitor the urban metabolism, measure carbon emissions from the generated waste, develop waste management facilities, and build a circular economy in the study area.

A cross-jurisdictional comparison on residential waste collection rates during earlier waves of COVID-19

There is currently a lack of studies on residential waste collection during COVID-19 in North America. SARIMA models were developed to predict residential waste collection rates (RWCR) across four North American jurisdictions before and during the pandemic. Unlike waste disposal rates, RWCR is relatively less sensitive to the changes in COVID-19 regulatory policies and administrative measures, making RWCR more appropriate for cross-jurisdictional comparisons. It is hypothesized that the use of RWCR in forecasting models will help us to better understand the residential waste generation behaviors in North America. Both SARIMA models performed satisfactorily in predicting Regina's RWCR. The SARIMA D_CV model's performance is noticeably better during COVID-19, with a 15.7% lower RMSE than that of the benchmark model (SARIMA B_CV). The skewness of overprediction ratios was noticeably different between jurisdictions, and modeling errors were generally lower in less populated cities. Conflicting behavioral changes might have altered the residential waste generation characteristics and recycling behaviors differently across the jurisdictions. Overall, SARIMA D_CV performed better in the Canadian jurisdiction than in U.S. jurisdictions, likely due to the model's bias on a less variable input dataset. The use of RWCR in forecasting models helps us to better understand the residential waste generation behaviors in North America and better prepare us for a future global pandemic.

Construction and demolition waste generation prediction and spatiotemporal analysis: a case study in Sichuan, China

The rapidly increased generation of construction and demolition (C&D) waste hinders the sustainable development of cities. Establishing an effective C&D waste management system is of great importance for achieving sustainable development goals. The quantification and prediction of C&D waste, forming the basis of waste management, are worthy of further exploration. C&D waste generation is time series data in which future waste generation is closely correlated with past ones. This study proposes a time-series waste prediction framework to predict C&D waste generation with less data volume by coupling generation rate calculation (GRC) and autoregressive integrated moving average (ARIMA) model. It is demonstrated in Sichuan, China, as a case study. The prediction result reveals that C&D waste generation in Sichuan shows an overall increasing trend, and the waste is mainly generated in the central of Sichuan. Chengdu accounts for over 40% of the total generation in the province, followed by Luzhou, Nanchong, and Mianyang. C&D waste generation shows a significant continual rise in Yibin and Zigong. Overall, most cities in Sichuan have issued related policies and tried to strengthen control over the transportation phase. This study provides an alternative to predict and analyze C&D waste generation from spatiotemporal perspectives. It enriches the C&D waste generation data and provides quantification support for C&D waste management at the regional level.

Design and development of smart Internet of Things-based solid waste management system using computer vision

Municipal solid waste (MSW) management currently requires critical attention in ensuring the best principles of socio-economic attributes such as environmental protection, economic sustainability, and mitigation of human health problems. Numerous surveys on the waste management system reveal that approximately 90% of the MSW systems are improperly disposing the wastages in open dumps and landfills. Classifying the wastages into biodegradable and non-biodegradable helps converting them into usable energy and disposing properly. The advancements of effective computational approaches like artificial intelligence and image processing provide wide range of solutions for the present problem identified in MSW management. The computational approaches can be programmed to classify wastes that help to convert them into usable energy. Existing methods of waste classification in MSW remain unresolved due to poor accuracy and higher error rate. This paper presents an experimented effective computer vision-based MSW management solution with the help of the Internet of Things (IoT), and machine learning (ML) techniques namely regression, classification, clustering, and correlation rules for the perception of solid waste images. A ground-up built convolutional neural network (CNN) and CNN by the inception of ResNet V2 models trained through transfer learning for image classification. ResNet V2 supports training large datasets in deep neural networks to achieve improved accuracy and reduced error rate in identity mapping. In addition, batch normalization and mixed hybrid pooling techniques are incorporated in CNN to improve stability and yield state of art performance. The proposed model identifies the type of waste and classifies them as biodegradable or non-biodegradable to collect in respective waste bins precisely. Furthermore, observation of performance metrics, accuracy, and loss ensures the effective functions of the proposed model compared to other existing models. The proposed ResNet-based CNN performs waste classification with 19.08% higher accuracy and 34.97% lower loss than the performance metrics of other existing models.

Nonlinear Dynamic Response Analysis of a Three-Stage Gear Train Based on Lightweight Calculation for Edge Equipment

Bevel gears are widely used in aerospace transmission systems as well as modern mechanical equipment. In order to meet the needs and development of aerospace, high-speed dynamic vehicles, and various defense special equipment, higher and higher requirements are made for the high precision and stability of gear transmission systems, as well as the prediction and control of noise and vibration. Considering the nonlinear factors such as comprehensive gear error and tooth side clearance, a dynamic model of the three-stage gear transmission system is established. The relevant physical parameters, geometric parameters, and load parameters in the gear system are considered random variables to obtain the stochastic vibration model. When the random part of the random parameters is much smaller than the deterministic part, the vibration differential equation is expanded into a first-order term at the mean of the random parameter vector according to the Taylor series expansion theorem, and the ordering equation is solved numerically. Based on the improved stochastic regression method, the nonlinear dynamic response analysis of the three-stage gear train is carried out. This results in a relatively stable system when the dimensionless excitation frequency is in the range of 0.716 to 0.86 and the magnitude of the dimensionless integral meshing error is < 1.089.

Construction waste landfill volume estimation using ground penetrating radar

Underground landfill, the primary disposal method of construction waste in several areas, negatively affects the surrounding environments. Suitably locating and estimating waste volume in an underground landfill are vital for adequate disposal and recycling of construction wastes. In this study, we investigated the applicability of ground penetrating radar (GPR) technology to estimate waste depth and volume of a construction waste landfill. The results revealed the following. (1) The GPR technology effectively delineated boundaries between underground waste and the surrounding strata; the topographic structure obtained from the analysis of the associated images was consistent with the actual topography. (2) Layer information from GPR images and electromagnetic wave velocity calculated using the complex refractive index model for construction waste burial depth inversion produced highly accurate results. Waste depth in the landfill was estimated using the GPR inversion results and spatial interpolation. Kriging interpolation exhibited the highest accuracy. (3) The trapezoid, Simpson and Simpson 3/8 rules were suitable for estimating construction waste volume. A three-dimensional model created using the spatial interpolation grid precisely depicted the structure of the buried landfill. Our study provides references for the management, recycling and environmental impact assessment of construction waste.

Estimating construction waste generation in the Greater Bay Area, China using machine learning

Reliable construction waste generation data is a prerequisite for any evidence-based waste management effort, but such data remains scarce in many developing economies owing to their rudimentary recording systems. By referring to several models proposed for estimating waste generation, this study aims to develop a reliable and accessible method for estimating construction waste generation based on limited publicly available data. The study has two objectives. Firstly, it aims to estimate construction waste generation by focusing on the Greater Bay Area (GBA) in China, one of the world's most thriving regions in terms of construction activities. Secondly, it aims to compare the strengths and weaknesses of various waste quantification models. 43 sets of annual socio-economic, construction-related and C&D waste generation data ranging from 2005 to 2019 were collected from the local government authorities. By analyzing the data using four types of machine learning models, namely multiple linear regression, decision tree, grey models, and artificial neural network, it is found that all calibrated models, with their respective strengths and weaknesses, can produce acceptable results with the testing R² ranging from 0.756 to 0.977. This study also reveals that the 11 cities in the GBA produced a total of about 364 million m³ of construction waste in 2018. The result can be used for monitoring the urban metabolism, quantifying carbon emission, developing a circular economy, valorizing recycled materials, and strategic planning of waste management facilities in the GBA. The research findings also contribute to the methodologies for estimating waste generation using limited data.