Solid Waste Classification Research Articles

Waste material classification using performance evaluation of deep learning models

Abstract Waste classification is the issue of sorting rubbish into valuable categories for efficient waste management. Problems arise from issues such as individual ignorance or inactivity and more overt issues like pollution in the environment, lack of resources, or a malfunctioning system. Education, established behaviors, an improved infrastructure, technology, and legislative incentives to promote effective trash sorting and management are all necessary for a solution to be implemented. For solid waste management and recycling efforts to be successful, waste materials must be sorted appropriately. This study evaluates the effectiveness of several deep learning (DL) models for the challenge of waste material classification. The focus will be on finding the best DL technique for solid waste classification. This study extensively compares several DL architectures (Resnet50, GoogleNet, InceptionV3, and Xception). Images of various types of trash are amassed and cleaned up to form a dataset. Accuracy, precision, recall, and F1 score are only a few measures used to assess the performance of the many DL models trained and tested on this dataset. ResNet50 showed impressive performance in waste material classification, with 95% accuracy, 95.4% precision, 95% recall, and 94.8% in the F1 score, with only two incorrect categories in the glass class. All classes are correctly classified with an F1 score of 100% due to Inception V3’s remarkable accuracy, precision, recall, and F1 score. Xception’s classification accuracy was excellent (100%), with a few difficulties in the glass and trash categories. With a good 90.78% precision, 100% recall, and 89.81% F1 score, GoogleNet performed admirably. This study highlights the significance of using models based on DL for categorizing trash. The results open the way for enhanced trash sorting and recycling operations, contributing to an economically and ecologically friendly future.

Prediction of carbon emissions from municipal solid waste treatment in 31 provinces and cities in China under the shared socio-economic pathways

In order to reduce greenhouse gas (GHG) emissions from the municipal solid waste (MSW) sector, it is essential to describe its greenhouse gas emission patterns and propose appropriate mitigation measures. Therefore, this study predicts the greenhouse gas emissions of urban domestic waste treatment by combining the Intergovernmental Panel on Climate Change (IPCC), shared socio-economic pathways and in-depth learning model. Under the hypothetical policy scenario and the shared socio-economic pathways (SSPs), the greenhouse gas emissions from municipal solid waste treatment in 31 provinces and cities in China by 2030 are analyzed. Combined with the model comparison results, the bidirectional long and short-term memory neural network model has better prediction accuracy than the other models, with an average mean absolute percentage error of 9.68% for 31 provinces and cities, indicating good applicability. Scenario analysis shows that greenhouse gas emissions from municipal solid waste disposal can be significantly reduced only after the implementation of municipal solid waste classification. Scenario 3 (S3) of waste segregation will produce the most GHG emissions, and switching to Scenario 5 (S5) of waste segregation will produce significantly less GHG emissions. Finally, the paper makes policy recommendations on the priority areas of urban domestic waste classification, waste source classification and recycling, and the structure of urban municipal solid waste treatment.

Classification of Urban Solid Waste Collected with the Use of Ecobarriers in Watercourses in the Municipality of Caçapava do Sul, RS

Urban solid waste is a serious problem in cities when disposed in inappropriate places or when there is a deficiency in its collection, which can cause several environmental problems. In periods of rain, these problems become more evident when these residues are transported to drainage networks and water courses, accumulating and creating obstacles to the flow, causing floods, floods, etc. In this regard, this work aimed to collect and classify urban solid waste in two water courses in the municipality of Caçapava do Sul, an ecological barrier made with recyclable materials called Ecobarrier, placed across water courses in order to retain floating waste that is transported by water. As a result, the vast majority of residues retained in the eco-barriers correspond to the category of organic matter, this is due to the vegetation around the water bodies studied, followed by the plastic, metal and textile category respectively. Thus, it can be seen that the presence of floating garbage in the water courses of the municipality partially reflects the lack of concern on the part of the population and governments with its effects on human and environmental health. It is in this context, to avoid the generation of floating waste, that the integration of public policies can play a fundamental role, with the help of environmental education.

An optimal solid waste management using red fox optimization and hybrid DenseNet-BiLSTM model.

Municipal solid waste is considered to eliminate the problem of dumping and spreading in rural and urban areas of developing countries. Accumulation of solid wastes in open spaces receives greater concern in solid waste management systems because it leads to environmental hazards and health issues. To build a clean environment, it is essential to construct an advanced and intelligent waste management system to handle different compositions of waste materials. The significant step of waste management is the separation of waste components, which is normally carried out by manual operation. As a result, it can generate improper disposal of waste materials, to simplify the separation process mechanically, a novel automated Dense Net- BiLSTM-based red fox (DNBiLSTM-RF) approach is proposed in this paper. The proposed solid waste classification framework is analyzed by using waste data which is gathered from the Tehran waste management organization. The input waste data is preprocessed initially to transform raw amorphous data into appropriate data structures and extract the most significant dense and latent data features. The abnormal variations in waste patterns generate outliers which are effectively removed by applying the interquartile range (IQR) filtering process. Finally, the proposed DNBiLSTM-RF classifier accurately discriminates municipal waste materials into six different categories such as wood waste, textiles, food residues, rubber, paper, and plastics. The hyperparameters of the DenseNet-BiLSTM model are fine-tuned using a red fox (RF) optimization algorithm to enhance the classification performance of the model. The effectiveness of the DNBiLSTM-RF approach is evaluated using performance indicators namely root mean square error (RMSE), mean absolute error (MAE), the ratio of RMSE to the standard deviation (SD), Nash-Sutcliffe efficiency, coefficient of determination, recall, precision, F-measure, and accuracy. The analytic result demonstrates the feasibility of the proposed DNBiLSTM-RF approach in classifying waste materials into respective categories precisely with an accurate rate of about 98.9% over other state-of-the-art approaches.

Application of Machine learning techniques in environmental governance: A review

In recent years, based on the continuous improvement of computer hardware performance, machine learning (ML) technology has made rapid development. Due to the strong ability of ML methods to find complex functions between associated data and the low cost of human and material resources, they are increasingly favored by environmental governance practitioners. Current research has confirmed that the application of ML technology to the field of environmental governance is of great significance in overcoming the difficulties of analysis and practice in traditional environmental work, and can greatly promote the long-term development of such directions as air quality prediction, solid waste classification, pollutant distribution mapping, and intelligent management of water environment. Therefore, by organizing the representative literature in the past five years, this paper describes the current status of the application of ML technology in four different elements of environmental governance, namely, atmosphere, water, soil, and solid waste, and aims to summarize the possible directions of the future development of ML technology and the new development brought to the field of environmental governance by exploring the basic concepts of ML, the advantages and disadvantages of the model and the constraints and other issues.

Cognitive Study on the Classification Policy of Domestic Waste among Residents in Nanning City

Nanning is one of the 46 key cities in China to establish a municipal solid waste classification system before the end of 2020, and the garbage classification work ranks in the top in many quarters. At the same time, it still faces some difficulties in the implementation of waste classification policy. Exploring people's understanding of domestic waste classification is of great significance to the improvement of waste classification policy and the implementation of waste classification work. Based on the data obtained from the field survey and questionnaire survey of Nanning residents, this paper obtains the residents' cognition of domestic waste classification policy, and obtains the influencing factors of residents' cognition of domestic waste classification policy through empirical analysis. The results show that the factors affecting residents' cognition are government regulation, publicity and education, incentive mechanism, public participation and supporting facilities, while individual wishes and behaviors, charging mechanism and community management have no significant impact on the domestic waste classification policy. According to the analysis results, this paper discusses the problems and reasons existing in the cognition of urban residents' domestic waste classification policy, and puts forward some suggestions for improvement and optimization. First, strengthen publicity and education to promote residents' cognition; The second is to strengthen government control and improve detailed policies and regulations; Third, pay attention to the supervision and implementation of reward and punishment measures, and promote the standardized implementation of classification behavior; The fourth is to build and improve the garbage classification and treatment system; Fifth, broaden the channels of public participation.

An integrated approach ofIoTandWSNusing wavelet transform and machine learning for the solid waste image classification in smart cities

AbstractSolid waste management is one of the utmost vital issues allied with the smart city, which harms our society's health and the environment. Solid waste management has been a significant hurdle in developing smart cities, impacting the community's living standards. Sustainability is the circumstances that help to achieve natural and social development simultaneously in a prolific accord. We can allege that sustainable growth brings out stability in the necessities of the environment. It helps to preserve resources available for the coming generations. Waste management is also a concern for many authorities; researchers have started focusing on this area. This research article presents a unique method for waste management by employing internet of things for waste monitoring, a wireless sensor network for data communication and discrete wavelet transforms, image processing, and machine learning for image categorization. Implementing machine learning for image categorization has gained attention in the research area of artificial intelligence. The paper presents a way to classify waste images into different Classes such as domestic waste, e‐waste, and medical waste. The input image is down‐sampled, and channels are split to extract the color moments for minimal processing time. We have created a convolution neural network (CNN) trained using pre‐processed data for feature extraction and classification. We have used K‐nearest neighbor classifier (KNN) as another classifier to compare the results obtained by the proposed methodology. The findings demonstrate that, compared to the KNN, the suggested model shortens the processing time and achieves a high accuracy rate. The paper presents a novel approach for Solid waste classification by using pre‐processed image data for image processing and CNN for waste image classification, for the sake of proving the efficiency of the proposed method we have compared the results with the KNN classifier and found that the accuracy of classification is better in proposed method than the KNN classifier.

Modified rat swarm optimization with deep learning model for robust recycling object detection and classification

Biomass residues consist of sewage effluents and sludges, crop wastes, non-recyclable municipal solid waste industrial and domestic greywater, and much more. Recycling is regarded as one such significant disposal technique. Considering the intelligent classification and detection of solid waste as an essential factor in consumption and recycling, multi-object solid waste identification and classification methodology on the basis of transfer learning (TL) are presented. This study develops a Modified Rat Swarm Optimization with Deep Learning for Robust Recycling Object Detection and Classification (MRSODL-RODC) model. Primarily, fully convolutional network (FCN) is applied for the identification of waste objects. Moreover, MRSO with deep belief network (DBN) model is applied for object detection process. The design of the MRSO algorithm for the DBN technique, showing the novelty of our work. The performance validation of the MRSODL-RODC model can be executed with the help of the benchmark dataset from Kaggle repository. The experimental outcomes demonstrated the better performance of the MRSODL-RODC model over recent approaches with higher accuracy of 99.20%.

Policy reinvention in diffusion: Evidence from municipal solid waste classification policy in China

AbstractWhile research on policy diffusion has gained significant interest among scholars worldwide, little attention has been given to policy reinvention in diffusion. This study aims to investigate the influencing factors and combination paths of policy reinvention in the Municipal Solid Waste Classification Policy (MSWCP). To achieve this, a theoretical framework encompassing internal factors, intergovernmental relations, and external influence has been constructed. Empirical analysis has been conducted on the MSWCP of 31 large‐ and medium‐sized cities in China using Qualitative Comparative Analysis. Through this analysis, several combination paths that prompted local governments to reinvent policies have been identified. Furthermore, the study has clarified the various roles of six conditions—financial resources, government attention, policy experience, peer competition, organizational learning, and social demand—in achieving policy reinvention. These findings are expected to provide new theoretical and practical insights into the field of policy reinvention research.

Valuation of Plastic Waste as a Community Circular Economy Strategy in the Municipality of Choco–Colombia

A business solution is proposed for the accumulation of waste in the Municipality of Choco without prior treatment through the establishment of a center for the reception, classification, recovery and use of solid plastic waste in the Municipality of Quibdo, which would optimize and expand the management of plastic waste. In this study, the basic diagnosis of the practices that are currently carried out in Quibdo is evaluated with the appropriation of the knowledge of the population, the technical structuring of the conditions of production of plastic wood is carried out from the management of plastic waste, recognition of the market for waste generated as an alternative for development and sustainable growth and the financial feasibility of the project and the profitability of each of the investment plans for its implementation. The results of the investigation include the identification of weaknesses and opportunities in waste management practices and the proposal of two investment plans for the establishment of the center. It is concluded that investment plan 2 would require 46,590.50 USD less than investment plan 1, equivalent to a 2.21% return compared to investment plan 1.

Assessment of the Multidimensional Performances of Food Waste Utilization Technologies in China

In recent years, China has made great efforts to carry out source-separation in municipal solid waste management; in particular, the utilization of food waste has received increasing attention. Food waste-utilizing technologies, including anaerobic digestion, aerobic biological treatment, and insect feed conversion, are currently applied in China. However, in the existing cases, there were several disadvantages, such as a low rate of utilization, significant environmental impacts, poor economic benefits, etc., as well as a lack of systematic analysis and comprehensive assessment of the performances of food waste utilization technologies. In this study, a four-dimensional performance assessment method (resource efficiency, environmental impact, economic feasibility, and social effect, with 21 indicators) was established for assessing the life cycle process of food waste utilization technologies. We collected detailed information of 14 typical food waste utilization cases in China, and the results showed that the average scores of anaerobic digestion and insect feed conversion were 58.39 and 59.65, higher than those of the aerobic biological treatment (49.16). The highest scores among all subdivision technologies were centralized black soldier fly conversion and mesophilic wet anaerobic digestion, which were 67.14 and 60.82, respectively. With respect to the technologies of different treatment capacities and distribution modes, i.e., centralized and decentralized technologies, the resource efficiency and economic benefit scores of the former were 13% and 62% higher than those of the latter, whereas the environmental impacts and social effect scores of the latter were 8% and 34% greater than those of the former, respectively. In practice, the utilization technology of food waste should be chosen according to local conditions, such as the physical and chemical properties of food waste, the classification of municipal solid waste, financial affordability, collection and transportation distance, etc.

Influence of the Classification of Municipal Solid Wastes on the Reduction of Greenhouse Gas Emissions: A Case Study of Qingdao City, China

The municipal solid waste (MSW) sector is an important source of greenhouse gas (GHG) emissions. MSW classification can achieve waste reduction and improve resource utilization. However, few studies have investigated the effects of MSW classification on GHG emission reduction. Therefore, the GHG emissions under different MSW disposal modes before and after classification were studied based on the life cycle assessment method in the four districts of Qingdao City. The results showed that MSW classification could significantly reduce the GHG emissions during the whole MSW treatment process. The net carbon emissions(in CO2/MSW)during the whole process of waste treatment for mode 1 (mixed collection+landfill), mode 2 (mixed collection+incineration), mode 3 (waste classification+anaerobic digestion of food waste and other incineration), and mode 4 (waste classification+anaerobic digestion of food waste, recycling of recyclable waste, and other incineration) were 686.39, -130.12, -61.88, and -230.17 kg·t-1, respectively. Improving the classification efficiency of food waste had no significant impact on carbon emissions. The reduction in carbon emissions increased linearly with the improvement of waste recycling efficiency. For every 10% increase in the recovery efficiency of recyclable waste, the net carbon emission decreased by 26.6%(16.5 kg·t-1). Appropriate separation of food waste, improving the recycling efficiency of recyclable waste, and reducing the leakage rate of biogas from anaerobic digestion are feasible strategies to reduce carbon emissions from MSW disposal units through the classification of MSW.

Hybrid deep learning model for accurate classification of solid waste in the society

Due to the increasing initiatives for urbanization and the development of smart cities, waste generation, segregation, and its management have become fundamental tasks. To provide efficient planning for waste management and its processes, such as collection, sorting, recycling, and disposal, recently, machine learning (ML) approaches have been utilized to assist the authorities. However, the identification of the best ML approach for the prediction of waste is a challenging effort. Finding adequate waste litter measurement is necessary for the ecological characteristics to improve over time. The waste from the trash may divide into organic and recycling types. In this paper, the optimized hybrid deep learning model has been developed for waste classification. This proposed work takes advantage of (i) data collection and preprocessing (ii) feature extraction using CNN (AlexNet) (iii) waste prediction from the urban cities' wastes using DBN, and (iv) hyperparameter optimization using Optuna. This model obtained an R2 score of 0.94, MPE 0.02 than other state-of-the-art approaches. Compared to the individual learners model, this proposed optimized hybrid deep learning model boosts the performance to predict waste generation and classify it with increased accuracy.

Differential game analysis between government and waste incineration plants on the management of municipal solid waste classification

PurposeThe purpose of this paper is to study how the government stimulates incineration plants to participate in waste classification management, and how to adjust the subsidy strategy for them.Design/methodology/approachConsidering that the classification behavior of residents will produce herd effect, and waste classification can reduce the disposal cost of incineration plants, the authors constructed a differential game model between the government and waste incineration plants, and analyzed the input strategy of the government and incineration plants when they cooperate in the management of municipal waste classification.FindingsIncreasing the input level of supervision or raising subsidy price, the government can promote incineration plants to increase the input level of incentive. Moreover, from a long-term perspective, increasing the input level of supervision is more effective. Compared with government supervision, the method of incineration plants incentive can more effectively increase the amount of waste disposal. Furthermore, the government supervision and the incineration plants incentive have a positive interaction effect on improving the amount of waste disposal. Increasing the input level of incineration plants incentive or the level of waste-to-energy technology can increase the amount of waste disposal, and from a long-term perspective, increasing the level of R&D investment is more beneficial to increasing the amount of waste disposal.Originality/valueThe results are helpful to improve the investment in the management of waste classification, and also provide a certain theoretical basis for the government's subsidy policy for incineration plants, so as to reduce the financial pressure of the government.

Municipal solid waste classification and real-time detection using deep learning methods

Waste management has become a significant issue in most developing countries. Municipal solid waste generation has been steadily increasing over the past decade. Recycling is gaining importance because it is the only method to maintain a healthy and sustainable environment. Furthermore, recycling is not a fully autonomous operation; a significant amount of waste must be performed manually. New and innovative procedures must be implemented to deal with the increasing volume of waste products at recycling facilities. It is suggested that effective solid waste management systems have a practical approach to detecting and classifying waste materials. This study presents CNN and Graph-LSTM, two deep-learning techniques that can recognize typical waste products when handled on a belt conveyor in waste collection systems. This convolutional neural network-based solution is trained to use six object classes: cardboard, metal, glass, plastic, paper, and organic waste. The major advantage is the ability to model long-term dependencies, Improved performance, better generalization, and easy access The experimental findings show that the suggested system can achieve 97.5% accuracy in real-world situations, outperforming existing methods identified in the literature.

Multi-agent evolutionary game analysis on the implementation of municipal solid waste classification policy

With the rapid development of economy and the improvement of people's living standard, the domestic waste is greatly increasing. Based on the multi-agent evolutionary game theory, an evolutionary game model among the recycling industry, urban management officer and government is established to address the environmental issues of rising municipal solid waste production and low recycling utilization rates in China. Through numerical example analysis, the relationship between relevant factors on the evolutionary stable state of the system is studied. The findings demonstrate that when the likelihood of severe oversight by the government and of significant enforcement by urban management officers grows, the recycling industry becomes more ready to select waste separation strategy. Additionally, the government is far more affected by the likelihood of significant enforcement by urban management officers than the recycling industries are. In addition, effective acceleration of waste sorting may be achieved by giving the recycling industries the proper government subsidies and increasing the recycling industries' profits from garbage sorting. Moreover, the government's increased fines for the urban management officers can significantly lower the incidence of bribery between the recycling industries and the urban management officers.

Changes and Future Issues in Policies for the Classification of Municipal Solid Waste in China

Changes and Future Issues in Policies for the Classification of Municipal Solid Waste in China

Assessing the implementation effect of Shanghai's compulsory municipal solid waste classification policy.

Waste treatment is a problem faced by cities all over the world. In recent years, China, as a developing country, regards the municipal solid waste (MSW) classification as one of the important strategies to deal with the MSW problem. The previous MSW classification policies in China were all only advocacy in nature. It was not until January 2019 that the "Regulations on the Management of MSW in Shanghai" was officially promulgated as China's first compulsory MSW classification policy, marking the beginning of an era of compulsory MSW classification in China. How effective is the implementation of Shanghai's compulsory MSW classification policy 18months after its implementation and can developing countries continuously and effectively implement compulsory MSW classification policies? These are important issues of concern to the government, academia, and the public. This paper establishes a three-stage DEA model to evaluate the implementation effect of the compulsory MSW classification policies in Shanghai during the period of February 2019 and July 2020. The study found that the average efficiency of the compulsory MSW classification policy in Shanghai reached 0.906 during the study period, indicating that the policy was executed reasonably well. However, there are only 5months in 18months that the policy was fully effective (reaching efficiency level 1), suggesting that there is still room for improvement. The main reason for not being able to achieve full effectiveness in some months is attributed to scale efficiency. At the same time, the general public budget revenue and expenditure of environmental variables have positive and negative impacts on the policy implementation effect in Shanghai. The research results can provide experience for China to comprehensively implement the compulsory MSW classification policy in the future and can also provide valuable case study information for cities in other developing countries to implement the compulsory MSW classification policy.

Model and method of solid household waste sorting for their effective thermal disposal

The work considers the development of a simulation model and an automated method of sorting solid household waste based on the identification of a portion of the studied raw material with further classification according to accepted groups of characteristic chemical composition. A method of classification of municipal solid waste (MSW) and a method of their identification was proposed, which made it possible to identify groups that produce acid gases. The basis of the method is a simulation model, which is represented by a tabular form of the gross formulas of possible compounds. The identified compounds are identified both qualitatively by the isoenthalpic method and quantitatively by the express gravimetric method. The sequential chain of identification makes it possible to search for substances that form acid gases during further processing by thermal destruction methods. A method of sorting solid household waste has been developed for the possibility of further processing of each group with maximum efficiency and compliance with ecological indicators. The method is based on: technological method of sorting; the method of sorting raw materials-processing in which measuring devices are integrated to ensure the specified characteristics of identification according to the classification features of the simulation model; the principle of using measuring devices depending on the type of identification task by qualitative or quantitative indicator.

Solid waste mapping based on very high resolution remote sensing imagery and a novel deep learning approach

The urbanization worldwide leads to the rapid increase of solid waste, posing a threat to environment and people’s wellbeing. However, it is challenging to detect solid waste sites with high accuracy due to complex landscape, and very few studies considered solid waste mapping across multi-cities and in large areas. To tackle this issue, this study proposes a novel deep learning model for solid waste mapping from very high resolution remote sensing imagery. By integrating a multi-scale dilated convolutional neural network (CNN) and a Swin-Transformer, both local and global features are aggregated. Experiments in China, India and Mexico indicate that the proposed model achieves high performance with an average accuracy of 90.62%. The novelty lies in the fusion of CNN and Transformer for solid waste mapping in multi-cities without the need for pixel-wise labelled data. Future work would consider more sophisticated methods such as semantic segmentation for fine-grained solid waste classification.