Analysis of the waste selective collection at drop-off systems: Case study including the income level and the seasonal variation

Artificial intelligence applications for sustainable solid waste management practices in Australia: A systematic review

Solid waste generation and its impact on human health and the environment have long been a matter of concern for governments across the world. In recent years, there has been increasing emphasis on resource recovery (reusing, recycling and extracting energy from waste) using more advanced approaches such as artificial intelligence (AI) in Australia. AI is a powerful technology that is increasingly gaining popularity and application in various fields. The adoption of AI techniques offers alternative innovative approaches to solid waste management (SWM). Although there are previous studies on AI technologies and SWM, no study has assessed the adoption of AI applications in solving the diverse SWM problems for achieving sustainable waste management in Australia. Moreover, there are inconsistencies and a lack of awareness on how AI technologies function in relation to their application to SWM. This study examines the application of AI technologies in various areas of SWM (generation, sorting, collection, vehicle routing, treatment, disposal and waste management planning) to enhance sustainable waste management practices in Australia. To achieve the aims of this study, prior studies from 2005 to 2021 from various databases are collected and analyzed. The study focuses on the adoption of AI applications on SWM, compares the performance of AI applications, explores the benefits and challenges, and provides best practice recommendations on how resource efficiency can be optimized to improve economic, environmental and social outcomes. This study found that AI-based models have better prediction abilities when compared to other models used in forecasting solid waste generation and recycling. Findings show that waste generation in Australia has been steadily increasing and requires upgraded and improved recovery infrastructure and the appropriate adoption of AI technologies to enhance sustainable SWM. Australia's adoption of AI recycling technologies would benefit from a national approach that seeks consistency across jurisdictions, while catering for regional differences. This study will benefit researchers, governments, policy-makers, municipalities and other waste management organizations to increase current recycling rates, eliminate the need for manual labor, reduce costs, maximize efficiency, and transform the way we approach the management of solid waste.

Modeling the Amount of Waste Generated by Households in the Greater Accra Region Using Artificial Neural Networks

Waste can be defined as solids or liquids unwanted by members of the society and meant to be disposed. In developing countries such as Ghana, the management of waste is the responsibility of the metropolitan authorities. These authorities do not seem to have effective management of the waste situation, and therefore, it is not unusual to see waste clog the drains and litter the streets of the capital city, Accra. The impact of waste on the environment, along with its associated health-related problems, cannot be overemphasized. The Joint Monitoring Programme report in 2015 ranked Ghana as the seventh dirtiest country in the world. The lack of effective waste management planning is evident in the large amount of waste dumped in open areas and gutters that remains uncollected. In planning for solid waste management, reliable data concerning waste generation, influencing factors on waste generation, and a reliable forecast of waste quantities are required. This study used two algorithms, namely, Levenberg-Marquardt and the Bayesian regularization, to estimate the parameters of an artificial neural network model fitted to predict the average monthly waste generated and critically assess the factors that influence solid waste generation in some selected districts of the Greater Accra region. The study found Bayesian regularization algorithm to be suitable with the minimum mean square error of 104.78559 on training data and 217.12465 on test data and higher correlation coefficients (0.99801 on training data, 0.99570 on test data, and 0.99767 on the overall data) between the target variables (average monthly waste generated) and the predicted outputs. House size, districts, employment category, dominant religion, and house type with respective importance of 0.56, 0.172, 0.061, 0.027, and 0.026 were found to be the top five important input variables required for forecasting household waste. It is recommended that efforts of the government and its stakeholders to reduce the amount of waste generated by households be directed at providing bins, increasing the frequency of waste collection (especially in highly populated areas), and managing the economic activities in the top five selected districts (Ledzekuku Krowor, Tema West, Asheidu Keteke, Ashaiman, and Ayawaso West), amongst others.

Application of artificial neural networks for predicting the physical composition of municipal solid waste: An assessment of the impact of seasonal variation

Sustainable planning of waste management is contingent on reliable data on waste characteristics and their variation across the seasons owing to the consequential environmental impact of such variation. Traditional waste characterization techniques in most developing countries are time-consuming and expensive; hence the need to address the issue from a modelling approach arises. In modelling the complexity within the system, a paradigm shift from the classical models to the intelligent models has been observed. The application of artificial intelligence models in waste management is gaining traction; however its application in predicting the physical composition of waste is still lacking. This study aims at investigating the optimal combinations of network architecture, training algorithm and activation functions that accurately predict the fraction of physical waste streams from meteorological parameters using artificial neural networks. The city of Johannesburg was used as a case study. Maximum temperature, minimum temperature, wind speed and humidity were used as input variables to predict the percentage composition of organic, paper, plastics and textile waste streams. Several sub-models were stimulated with combination of nine training algorithms and four activation functions in each single hidden layer topology with a range of 1-15 neurons. Performance metrics used to evaluate the accuracy of the system are, root mean square error, mean absolute deviation, mean absolute percentage error and correlation coefficient (R). Optimal architectures in the order of input layer-number of neurons in the hidden layer-output layer for predicting organic, paper, plastics and textile waste were 4-10-1, 4-14-1, 4-5-1 and 4-8-1 with R-values of 0.916, 0.862, 0.834 and 0.826, respectively at the testing phase. The result of the study verifies that waste composition prediction can be done in a single hidden-layer satisfactorily.

Determination of the composition and properties of PET bottles: Evidence of the empirical approach from Perm, Russia

Efficient collection systems and information about the characteristics and quality of collected secondary plastic waste flows are of fundamental importance for the development of circular economies. In order to assess the effectiveness of the implementation of separate collection systems for plastic packaging, especially polyethylene terephthalate (PET) bottles, characteristic of the collected PET bottles in street mesh containers were studied in the city of Perm, Russia. The share of extraneous fractions was assessed and differentiation was carried out by volume, type of product, label presence, shape, content of solid and liquid impurities and colour. These results indicate that PET composition in different seasons is very similar, despite the assumption that the consumption of PET bottles in the spring and autumn seasons varies. In the mesh containers, up to 34% of the items were foreign objects, considering that only PET bottles should be collected. In each dimensional flow of PET bottles, the proportion of transparent bottles prevailed; it ranged from 31% to 70%. Based on the results of the experiment, almost all PET bottle categories had a standard shape, except packaging for food products and household chemicals, in which 26-27% of PET bottles had a non-standard shape. The results about charactersitic of source-separated PET bottles are fundamental for goal-oriented design and implementation of collection, recycling technologies, secondary separation facilities, the economics of recycling intitatives and reverse vending machines for collecting materials.

A structured methodology to understand municipal waste generation at local level with minimized effort: development and case study

Understanding municipal solid waste (MSW) generation is a key requirement for designing and optimizing MSW collection services. The present contribution proposes a statistical methodology to identify MSW generation patterns from MSW collection records. The methodology aims at finding statistically distinct household waste generation patterns within the days of the week and within months (seasonal variation). It is based on standard statistical methods (ANOVA complemented by non-parametric tests and cluster analysis). The methodology was applied to a Portuguese neighbourhood to assist in the definition of a waste sampling campaign to support the implementation of a pilot PAYT. The results showed the existence of groups with statistically distinct MSW generation patterns both at the weekly and monthly time scales. Three clusters of days of the week, with high, medium and low generation, and two clusters of months, with high and low generation, were identified. These results allowed to design and implement a customized field waste sampling campaign to estimate the MSW generated at the study site with minimal field work. Instead of implementing a homogeneous sampling campaign (equal number of samples for every day of the week and for every month), the samples were collected from the days and months that showed statistically distinct MSW generation pattern. The systematic procedure can be easily adapted to any given location, thus being a useful tool that combines statistical analysis with field collected data.

Formal and informal waste selective collection in developing megacities: Analysis of residents' involvement in Bolivia

The implementation of waste selective collection (SC) schemes in low-income countries is a challenge although it is one important way for improving environmental sustainability. The inclusion of the population is necessary for gaining effective results, and social surveys are support methods for understanding citizens' involvement and behaviour. The aim of the research is to assess the support of the citizens concerning the formal and informal recycling in a low-middle income country. The study presents a questionnaire survey conducted in 2018 in La Paz, Bolivia, where 774 citizens were interviewed for evaluating their support to the formal and informal SC systems. Two questionnaires were submitted to two different users' categories: users of the formal recyclable waste gathering points; and citizens of the neighbourhoods. Evidence of the survey shows that about 8% of the population supports the formal SC while about 48% are used to selecting their waste at home. About 79.2% of them bring the waste to the informal recycling shops or provide it to waste pickers, throwing the waste into or nearby the mixed containers in order to facilitate their collection. This research demonstrates how social inclusion is important for planning recycling systems within a developing big city, starting from the SC. Results suggest that the informal sector can be an effective means for improving the recycling behaviour of the citizens. The study can be of interest to stakeholders involved in introducing recycling policies in developing cities where the SC rate is still low, and informal waste collection exists.

Quantification and characterization of the municipal solid waste for sustainable waste management in newly formed municipalities of Nepal

This study was conducted to set up a new reference line for municipal solid waste quantification and characterization in the least urbanized cities of a developing nation. A survey was run to collect baseline data from 60 new municipalities of Nepal. The study covered a sample size of 3300 households, 600 institutions and 600 commercial establishments in those municipalities. The municipalities were further stratified according to geographical location, the degree of urbanization, household expenditure and population size to assess the influence on waste generation. The results indicated that the average per capita household waste generation is 115 g day^-1 while the average total municipal waste generation was estimated to be 180 g day^-1 per capita.The study also revealed that size of municipal population, geographic location, household expenditure and degree of urbanization were found to have a significant influence on the unit waste generation. The larger the size of municipal population the higher the per capita household waste generation, degree of urbanization and per capita waste production. Increasing household expenditure revealed an increase in the unit waste generation. The waste categories included organic waste, plastics, paper and paper products, textiles, rubber and leather, metals, glass, and others. The results indicated that organic waste dominated the characterization (62%), followed by plastics (12%) and paper/paper products (11%).

Selective collection of recyclable waste in Universities of low-middle income countries: Lessons learned in Bolivia

The implementation of solid waste selective collection (SC) systems is quite difficult in low-middle income countries. Lack of awareness, infrastructure, administrative support and knowledge about recycling are the main barriers for its operation, reducing the possibility of successes. This paper introduces the methodological approach for assessing a recyclable waste SC project in a Bolivian public University. The waste fractions generated before (2016) and after (2019) the action were assessed, as well as the opinion and knowledge of the students, providing reliable indicators of the improvements and benefits obtained. Results of the waste characterization analysis reported that, after one month of implementation of the system, about 15 kg of plastic and 37.1 kg of paper and cardboard were collected, about 8 wt% and 42.9 wt% of the recyclable waste produced. At the same time, the questionnaire survey allows demonstrating that the SC behavior of the students improved considerably from 2018 to 2019, (t_[608] = -7.654, p < 0.05^***), as well as the satisfaction about the waste collection service provided (t_[608] = -6.6224, p < 0.05^***) and about the diffusion of information with awareness campaigns (t_[608] = -8.708, p < 0.05^***). The project and the phases followed for its implementation can be of reference for other local and international stakeholders, for replicating the study in other Universities and public areas. The novelty of the study is the introduction of a step by step methodology for assessing the SC of recyclable waste for supporting the recycling policies of developing cities in low-middle income countries and for boosting sustainable development according to the principle of the circular economy.

The impact of collection portfolio expansion on key performance indicators of the Dutch recycling system for Post-Consumer Plastic Packaging Waste, a comparison between 2014 and 2017

The recycling network of post-consumer plastic packaging waste (PCPPW) was studied for the Netherlands in 2017 with material flow analysis (MFA) and data reconciliation techniques. In comparison to the previous MFA of the PCPPW recycling network in 2014, the predominant change is the expansion of the collection portfolio from only plastic packages to plastic packages, beverage cartons and metal objects. The analysis shows that the amounts of recycled plastics products (as main washed milled goods) increased from 75 to 103 Gg net and the average polymeric purity of the recycled products remained nearly constant. Furthermore, the rise in the amounts of recycled products was accompanied with a rise in the total amount of rejected materials at cross docking facilities and sorting residues at the sorting facilities. This total amount grew from 19 Gg in 2014 to 70 Gg gross in 2017 and is over-proportional to the rise in recycled products. Hence, there is a clear trade-off between the growth in recycled plastics produced and the growth in rejects and residues. Additionally, since the polymeric purity of the recycled plastics did not significantly improve during the last years, most of the recycled plastics from PCPPW are still only suited for open-loop recycling. Although this recycling system for PCPPW is relatively advanced in Europe, it cannot be considered circular, since the net recycling yield is only 26 ± 2% and the average polymeric purity of the recycled plastics is 90 ± 7%.

Collection behaviour of lightweight packaging waste by individual households and implications for the analysis of collection schemes

The separate collection behaviour of 21 Dutch households was explored. Their lightweight packaging waste (LWP) and mixed municipal solid waste (MSW) was studied twice in detail. The derived net collection yields for plastic packages and beverage cartons were high (mostly between 80 and 100%). A detailed analysis revealed that several packaging types were almost completely separate collected by these households. This observation led to the hypothesis that several packaging types will always be completely separate collected by participating civilians. Five indicator items were chosen and their concentrations in mixed MSW and LWP were used to calculate the minimal participation rate (PR_min) for collection areas. This PR_min is an underestimation of the true participation rate since the population within a collection area will also contain non-ideal separating individuals. Analysis of 15 different municipalities with this new methodology revealed that the PR_min varied strongly from roughly 30% for a municipality with a drop-off collection scheme for only plastic packaging and no PAYT financial trigger to almost 90% for municipalities with a kerbside collection scheme for LWP and a PAYT financial trigger. Surprisingly, participating civilians in all collection schemes kept roughly the same share of desired plastic packages (DPP) separate (73 ± 11%) in all collection schemes. This share is derived from the PR_min and hence a slight over-estimation. The latter was named the maximum selection rate for desired plastic packages (SR_max^DPP). The PR_min and SR_max^DPP form the basis of a new set of technical performance indicators for separate collection schemes of LWP.

Environmental policies for drinks packaging in Georgia: A mini-review of EPR policies with a focus on incentive compatibility

The paper investigates various approaches to an environmental policy regarding drinks containers in Georgia. Currently, most of the waste containers are landfilled or pollute the environment through littering, and separate collection and recycling of drinks containers are almost nonexistent. The Association Agreement with the EU, which entered into force in July 2016, stipulates the development of up-to-date waste management activities in this transition country. In accordance with the legal framework, this mini-review proposes an EPR policy for Georgia, based on the waste hierarchy. Various approaches for such an EPR policy are reviewed as regards their feasibility for a transition country, but in particular with regard to incentive compatibility: the policy should guide producers and consumers to comply with the regulations. Some cost estimates demonstrate the financial feasibility of the recommended solution. Practical experiences from Austria, Bulgaria, France and Germany provide a European context.

Current status of waste management in Botswana: A mini-review

Effective waste management practices are not all about legislative solutions, but a combination of the environmental, social, technical, technically skilled human resources, financial and technological resources, resource recycling, environmental pollution awareness programmes and public participation. As a result of insufficient resources, municipal solid waste (MSW) in transition and developing countries like Botswana remains a challenge, and it is often not yet given highest priority. In Botswana, the environment, public health and other socio-economic aspects are threatened by waste management practices due to inadequate implementation and enforcement mechanisms of waste management policy. This mini-review paper describes the panorama of waste management practices in Botswana and provides information to competent authorities responsible for waste management and to researchers to develop and implement an effective waste management system. Waste management practices in Botswana are affected by: lack of effective implementation of national waste policy, fragmented tasks and overlapping mandates among relevant institutions; lack of clear guidelines on the responsibilities of the generators and public authorities and on the associated economic incentives; and lack of consistent and comprehensive solid waste management policies; lack of intent by decision-makers to prepare national waste management plans and systems, and design and implement an integrated sustainable municipal solid waste management system. Due to these challenges, there are concerns over the growing trend of the illegal dumping of waste, creating mini dumping sites all over the country, and such actions jeopardize the efforts of lobbying investors and tourism business. Recommendations for concerted efforts are made to support decision makers to re-organize a sustainable waste management system, and this paper provides a reference to other emerging economies in the region and the world.