Waste managementPub Date : 2025-01-15Epub Date: 2024-12-01DOI: 10.1016/j.wasman.2024.11.025
Yali Hou, Qunwei Wang, Tao Tan
{"title":"Evaluating drivers of PM<sub>2.5</sub> air pollution at urban scales using interpretable machine learning.","authors":"Yali Hou, Qunwei Wang, Tao Tan","doi":"10.1016/j.wasman.2024.11.025","DOIUrl":"10.1016/j.wasman.2024.11.025","url":null,"abstract":"<p><p>Reducing urban fine particulate matter (PM<sub>2.5</sub>) concentrations is essential for China to achieve the Sustainable Development Goals (SDGs). Identifying the key drivers of PM<sub>2.5</sub> will enable the development of targeted strategies to reduce PM<sub>2.5</sub> levels. This study introduces a machine-learning model that combines CatBoost and the Tree-Structured Parzen Estimator (TPE) to analyze PM<sub>2.5</sub> concentration across 297 cities between 2000 and 2021. SHapley Additive exPlanations (SHAP) were employed to identify the primary factors influencing urban PM<sub>2.5</sub> concentrations. The study revealed that the proposed model has high accuracy in predicting urban PM<sub>2.5</sub> concentrations, achieving a coefficient of determination (R<sup>2</sup>) score of 96.44%. Socioeconomic and industrial activity are key drivers of PM<sub>2.5</sub> concentrations. This study not only quantifies the primary factors exacerbating or alleviating pollution for each city or province during the 2000-2021 period but also evaluates the influence of operational factors such as technological and public financial expenditures. In 2000, the main contributors to pollution in four heavily polluted cities included substantial nitrogen oxide emissions, inadequate technology investments, and excessive population density and liquefied gas consumption. Due to the rapid reduction in nitrogen oxide emissions, pollution levels in these cities have improved substantially. In the future, the most effective strategies for pollution reduction in these cities will focus on controlling population density and slowing down mining development. The proposed framework serves as a robust evaluation tool and can propose tailored strategies to control PM<sub>2.5</sub> concentrations effectively in each city.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"192 ","pages":"114-124"},"PeriodicalIF":7.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142772820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-18DOI: 10.1016/j.wasman.2024.12.013
A S Varling, V Chrysochoidis, V Bisinella, B Valverde-Pérez, T H Christensen
{"title":"Climate change impacts of biological treatment of liquid digestate from the anaerobic digestion of food waste.","authors":"A S Varling, V Chrysochoidis, V Bisinella, B Valverde-Pérez, T H Christensen","doi":"10.1016/j.wasman.2024.12.013","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.013","url":null,"abstract":"<p><p>The liquid fraction of digestate (LFD) from anaerobic digestion of food waste contains high nitrogen concentrations, and in some countries, the LFD is treated as wastewater. We modelled alternative LFD treatments, including pretreatment with the partial nitritation Anammox (PNA) process. The PNA effluent is discharged to the sewers to undergo further treatment by conventional nitrification and (post- or pre-) denitrification. Life-cycle inventories were developed for the LFD treatment alternatives, including N<sub>2</sub>O emissions and electricity consumption estimates. The climate change (CC) impact was estimated using life cycle assessment in three different energy systems ranging from fossil-based to fully renewable. In the fossil energy system, pretreatment with PNA was attractive, while in the more renewable energy systems, the PNA process did not improve the CC account due to high N<sub>2</sub>O emissions. Pre-denitrification is the most attractive LFD treatment technology in a fully renewable energy system. Linking the LFD treatment to the anaerobic digestion of food waste showed that LFD treatment is a significant contributor to the overall CC account. As we move towards less fossil-based electricity, the anaerobic digestion of food waste constitutes a CC load of 350-450 kg CO<sub>2</sub>-eq/tonne biowaste, of which up to a third can be attributed to the LFD treatment. The N<sub>2</sub>O emissions are the main contributor, constituting up to 50 % in a fossil-based energy system and even higher in a renewable energy system. We conclude that the LFD treatment must be addressed in assessing anaerobic digestion when the LFD is discharged to the sewer. Our study also points to the need to find alternative ways of managing the LFD.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"339-349"},"PeriodicalIF":7.1,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142865561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-18DOI: 10.1016/j.wasman.2024.12.020
Jonathan Cohen, Jorge Gil, Leonardo Rosado
{"title":"Exploring urban scenarios of individual residential waste sorting using a spatially explicit agent-based model.","authors":"Jonathan Cohen, Jorge Gil, Leonardo Rosado","doi":"10.1016/j.wasman.2024.12.020","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.020","url":null,"abstract":"<p><p>Managing the diverse waste fractions generated by households presents a significant environmental and logistical challenge. One widely adopted solution is waste sorting at the source, where residents are required to separate their waste into designated containers. The success of this strategy depends on the extent of adoption and the behaviour of residents. Waste separation is a complex activity influenced by various interrelated factors. While the Theory of Planned Behaviour (TPB) has been effectively applied to characterise waste-sorting behaviour, it primarily focuses on internal psychological mechanisms, often overlooking environmental factors such as the placement of waste bins or the condition of sorting stations-critical elements for spatial planning. To bridge this gap, this study presents an agent-based model (ABM) that simulates residential waste sorting in urban scenarios, incorporating TPB for the agents' behavioural architecture (residents). Three features distinguish this ABM from previous efforts: (i) Agents in the model are residents and not aggregated households, allowing for a one-to-one integration with TPB; (ii) the ABM bridges the gap between individual waste sorting behaviour extracted by TPB and outcomes quantifiable through waste sorting metrics; and (iii) the ABM is spatially explicit, enabling the exploration of various urban scenarios. The ABM was applied to two urban areas with differing population densities, demonstrating that changes in bin placement impacts sorting behaviour, and proximity to recyclable waste bins influences the correct sorting of residual waste. This study illustrates how modelling the interaction between the urban environment and waste sorting behaviour can reveal the impact of individual residents' actions on overall waste sorting performance.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"350-362"},"PeriodicalIF":7.1,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142865566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-17DOI: 10.1016/j.wasman.2024.12.002
Joshua T Grassel, Adolfo R Escobedo, Rajesh Buch
{"title":"Predicting the composition of solid waste at the county scale.","authors":"Joshua T Grassel, Adolfo R Escobedo, Rajesh Buch","doi":"10.1016/j.wasman.2024.12.002","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.002","url":null,"abstract":"<p><p>The primary goals of this paper are to facilitate data-driven decision making in solid waste management (SWM) and to support the transition towards a circular economy, by providing estimates of the composition and quantity of waste. To that end, it introduces a novel two-phase strategy for predicting municipal solid waste (MSW). The first phase predicts the waste composition, the second phase predicts the total quantity, and the two predictions are combined to give a comprehensive waste estimate. This novel approach overcomes limitations of existing methods that rely on material-specific quantity data, facilitating the prediction of dozens of waste material streams; existing methods typically classify MSW into no more than 10 categories, and often reduce it to a single aggregate total. To implement this strategy, the proposed study utilizes publicly available data encompassing demographic, economic, and spatial predictors, in conjunction with waste sampling reports. In addition, it develops a Least Absolute Shrinkage and Selection Operator (LASSO) regression model to estimate the MSW composition across 43 comprehensive material categories. The LASSO model is designed to predict MSW composition distinctly from quantity. The model's capability is demonstrated through case studies, showcasing its potential to provide detailed waste estimates at the U.S. county level.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"293-306"},"PeriodicalIF":7.1,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142855337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-17DOI: 10.1016/j.wasman.2024.12.008
Sabrina L Bradshaw, Horacio A Aguirre-Villegas, Suzanne E Boxman, Craig H Benson
{"title":"Material Recovery Facilities (MRFs) in the United States: Operations, revenue, and the impact of scale.","authors":"Sabrina L Bradshaw, Horacio A Aguirre-Villegas, Suzanne E Boxman, Craig H Benson","doi":"10.1016/j.wasman.2024.12.008","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.008","url":null,"abstract":"<p><p>An analysis was conducted using nationwide survey data to evaluate how material recovery facilities (MRFs) operations vary regionally and with scale. The survey characterized materials, processes, and energy use involved with operations, and revenue for recyclables. This is the first nationwide analysis of MRFs in the US that accounts for mass processed, energy consumed, and revenue. Of a population of 521 MRFs, 48 responses representing MRFs from five US regions were received and analyzed (9.2 % response rate). Responses were analyzed by size according to yearly mass of inbound materials (small: <1,000 Mg/year, medium: 1,000-10,000 Mg/year, and large: >10,000 Mg/year). Most MRFs identify as single-stream; source from residences; utilize tipping floors, picking lines, baling and warehousing; and are powered by electricity. Most revenue and inbound mass (>50 %) came from fiber (cardboard and paper). Glass had little revenue, and plastics were difficult to transition to market. Percent residue ranged from 1-39 %, averaged < 20 %, and increased as the mass of inbound material increased. Large MRFs reported more sources of material, employed advanced sorting technology, had greater plastics revenue (33 % versus 5 % for small MRFs), and had more market access for plastics compared to small MRFs. Large MRFs had two orders of magnitude less annual electricity consumption per Mg recyclables than small MRFs (5-90 kWh/Mg versus ∼ 300-550 kWh/Mg). Results demonstrate environmental and economic benefits of larger-scale MRFs, which could be implemented more broadly in the US through regional hub-and-spoke arrangements for collecting and processing recyclables, lowering energy consumption and increasing revenue for recyclables.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"317-327"},"PeriodicalIF":7.1,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142855256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-17DOI: 10.1016/j.wasman.2024.12.018
Ya Wang, Bin Zhang, Xiucai Liu, Jie Bao
{"title":"Balanced water and heat energy recycling by full evaporation of wastewater (FEW) in dry biorefining processes of lignocellulose biomass.","authors":"Ya Wang, Bin Zhang, Xiucai Liu, Jie Bao","doi":"10.1016/j.wasman.2024.12.018","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.018","url":null,"abstract":"<p><p>Lignocellulosic biorefinery technology requires minimum energy consumption and wastewater generation to overcome challenges in industrial applications. This study established a rigorous model and a comprehensive physical property database of dry biorefining process on Aspen Plus platform for production including L-lactic acid, citric acid, sodium sugar acids, amino acid, and ethanol based on the experimental data. Full evaporation of wastewater (FEW) approach was proposed to completely replaced the external steam supply, and significantly reduced the freshwater input by 67% ∼ 85% and wastewater generation by 64% ∼ 89%, depending on the specific products. The carbon-neutral heat energy from lignin residue combustion generates an extra heat output of 1.098 ∼ 4.772 GJ per ton of dry wheat straw (DW) after all the heat energy needs of the biorefinery process and FEW treatments are satisfied, equivalent to a reduction of 0.219 ∼ 0.952 kg CO<sub>2</sub> eq/kg DM emission. This study provided a self-consistent solution for water and energy balance in biorefinery processes.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"307-316"},"PeriodicalIF":7.1,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142855670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-17DOI: 10.1016/j.wasman.2024.11.043
Stoyana Peneva, Quynh Nhu Phan Le, Davi R Munhoz, Olivia Wrigley, Giovana P F Macan, Heidi Doose, Wulf Amelung, Melanie Braun
{"title":"Plastic input and dynamics in industrial composting.","authors":"Stoyana Peneva, Quynh Nhu Phan Le, Davi R Munhoz, Olivia Wrigley, Giovana P F Macan, Heidi Doose, Wulf Amelung, Melanie Braun","doi":"10.1016/j.wasman.2024.11.043","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.11.043","url":null,"abstract":"<p><p>Green and biowaste, processed within large facilities into compost, is a key fertilizer for agricultural and horticultural soils. However, due to improper waste disposal of plastic, its residues often remain or even lead to the formation ofmicroplastics (1 µm - 5 mm, MiPs) in the final compost product. To better understand the processes, we first quantified 'macroplastics' (> 20 mm, MaPs) input via biowaste collection into an industrial composting plant, and, then determined MiP concentrations at five stages during the composting process (before and after shredding and screening processes), and in the water used for irrigation. The total concentrations of MaPs in the biowaste collected from four different German districts ranged from 0.36 to 1.95 kg ton<sup>-1</sup> biowaste, with polyethylene (PE) and polypropylene (PP) representing the most abundant types. The \"non-foil\" and \"foil\" plastics occurred in similar amounts (0.51 ± 0.1 kg ton<sup>-1</sup> biowaste), with an average load of 0.08 ± 0.01 items kg<sup>-1</sup> and 0.05 ± 0.01 items kg<sup>-1</sup>, respectively. Only 0.3 ± 0.1 kg MaP t<sup>-1</sup> biowaste was biodegradable plastic. Compost treatment by shredding tripled the total number of MaPs and MiPs to 33 items kg<sup>-1</sup>, indicating an enrichment of particles during the process and potential fragmentation. Noticeably, a substantial amount of small MiPs (up to 22,714 ± 2,975 particles L<sup>-1</sup>) were found in the rainwater used for compost moistening, being thus an additional, generally overlooked plastic source for compost. Our results highlight that reducing plastic input via biowaste is key for minimizing MiP contamination of compost.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"283-292"},"PeriodicalIF":7.1,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142855218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Differentiating low-carbon waste management strategies for bio-based and biodegradable plastics under various energy decarbonization scenarios.","authors":"Yuxin Huang, Mengqi Han, Zhujie Bi, Nannan Gu, Dungang Gu, Tingting Hu, Guanghui Li, Jiaqi Lu","doi":"10.1016/j.wasman.2024.12.001","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.001","url":null,"abstract":"<p><p>Bio-based and biodegradable (bio-)plastics are heralded as a key solution to mitigate plastic pollution and reduce CO<sub>2</sub> emissions. Yet, their end-of-life treatments embodies complex energy and material interactions, potentially leading to emissions through incineration or recycling. This study investigates the cradle-to-grave, emphasizing the waste management stage, carbon footprint for several types of bio-plastics, leveraging both GWP100a and CO<sub>2</sub> uptake methods to explore the carbon reduction benefits of recycling over disposal. Our findings indicate that in scenarios characterized by carbon-intensive electricity, using polylactic acid (PLA) as an example, incineration with energy recovery (-1.6316 kg CO<sub>2</sub>-eq/kg, PLA) yields a more favorable carbon footprint compared to chemical recycling (-1.5317 kg CO<sub>2</sub>-eq/kg, PLA). In contrast, in environments with a high proportion of renewable energy, chemical recycling is a superior method, and compared to incineration (-1.4087 kg CO<sub>2</sub>-eq/kg, PLA), the carbon footprint of chemical recycling (-2.0406 kg CO<sub>2</sub>-eq/kg, PLA) are significantly reduced. While mechanical recycling presents considerable environmental benefits, its applicability is constrained by the waste quality, especially in the case of biodegradable plastics like PLA. In addition, the degradation of biodegradable plastics such as PLA was modeled during compost and anaerobic digestion processes. This enables us to quantify the specific biogenic carbon emissions released during these processing steps, revealing the direct emissions with dynamic degradation. This study highlights the importance of tailoring bio-plastic waste management strategies to support global energy decarbonization while understanding their life-cycle carbon metabolism to effectively tackle plastic pollution and climate change.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"328-338"},"PeriodicalIF":7.1,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142855254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-16DOI: 10.1016/j.wasman.2024.12.009
Jude Shalitha Perera, Shanaka Kristombu Baduge, Egodawaththa Ralalage Kanishka Chandrathilaka, Sadeep Thilakarathna, Thilini S Palle, A M Amado, Priyan Mendis
{"title":"Enhancing the Efficiency of Plastic Recovery Facilities: Systematically Integrating Seasonal and Regional Variations of Municipal Solid Recyclable Waste Through Infeed Management.","authors":"Jude Shalitha Perera, Shanaka Kristombu Baduge, Egodawaththa Ralalage Kanishka Chandrathilaka, Sadeep Thilakarathna, Thilini S Palle, A M Amado, Priyan Mendis","doi":"10.1016/j.wasman.2024.12.009","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.009","url":null,"abstract":"<p><p>Plastic Recovery Facilities are typically designed to process a specific, predetermined mix of plastic in the infeed. However, in many cases, the composition of the infeed varies seasonally and regionally. These variations may result in bottlenecks within sorting machines, thereby causing inconsistencies in the quality and quantity of recovered material. While most recovery facilities attempt to mix different bales before feeding them into the sorting line, relying on trial and error based on the material compositions of those bales, there is a lack of a systematic approach to this process. This paper introduces a systematic approach to plastic sorting within a plastic recovery facility, where the entire recovery process flow is dynamically modelled and validated. By identifying bottleneck regions within the system, infeed bales can be premixed to achieve the designed proportions, ensuring that machines and process lines are optimised for maximum efficiency. A pre-waste survey is necessary to achieve premixing, and the cost is justified by the benefits of the final return. To enhance the efficiency, it is crucial to implement a dynamic mixing model adaptable to daily variations in infeed. In this study, the dynamic optimisation model is designed in the form of simple mixing charts, allowing for on-site premix adjustments to bales without the need for additional equipment or tools. The proposed design chart based mixing methodology can be adopted across the globe to increase the output of established plastic recovery facilities.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"261-272"},"PeriodicalIF":7.1,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142847782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste managementPub Date : 2024-12-16DOI: 10.1016/j.wasman.2024.12.014
Junhyeok Son, Yuchan Ahn
{"title":"AI-based plastic waste sorting method utilizing object detection models for enhanced classification.","authors":"Junhyeok Son, Yuchan Ahn","doi":"10.1016/j.wasman.2024.12.014","DOIUrl":"https://doi.org/10.1016/j.wasman.2024.12.014","url":null,"abstract":"<p><p>The export ban on plastic waste by China has brought domestic plastic recycling to the forefront of environmental concerns, with sorting being a crucial step in the recycling process. This study assessed the performance of advanced AI models, Mask R-CNN, and YOLO v8, in enhancing plastic waste sorting. The models were evaluated in terms of accuracy, mean average precision (mAP), precision, recall, F1 score, and inference time, with hyperparameter tuning performed through grid search. Mask R-CNN, with an accuracy of 0.912 and mAP of 0.911, outperformed YOLO v8 in tasks requiring detailed segmentation, despite a longer inference time of 200-350 ms. Conversely, YOLO v8, with an accuracy of 0.867 and mAP of 0.922, excelled in real-time applications owing to its shorter inference time of 80-160 ms. This study underscores the importance of selecting the appropriate model based on specific application requirements.</p>","PeriodicalId":23969,"journal":{"name":"Waste management","volume":"193 ","pages":"273-282"},"PeriodicalIF":7.1,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142847780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}