Global Plastic Waste Management: Analyzing Trends, Economic and Social Implications, and Predictive Modeling Using Artificial Intelligence DOI Creative Commons

Syed Ali Reza,

Morshed Chowdhury, Saddam Hossain

et al.

Journal of Environmental and Agricultural Studies, Journal Year: 2024, Volume and Issue: 5(3), P. 42 - 58

Published: Dec. 30, 2024

Plastic waste, which is a result of human activities in America, has become one the most critical environmental issues 21st century, and this calls for an urgent prescription strategies at global management level. The pervasiveness plastic modern life created unparalleled surge which, unless adequately managed, poised to pose severe threats ecosystems, health, economy. utmost objective study was perform extensive analysis waste practices USA, with specific concentration on pinpointing economic social implications these practices. This research project therefore intends probe into practice applied different countries understanding various best practices, challenges, areas improvement. also aimed employ AI-driven predictive models, notably, gradient boosting algorithm, linear regression, random forest predict future trends wastes generated. Diverse datasets were used, ensure that comprehensive. Primary data conditions generation obtained through World Bank's database, provides detailed composition, rate, methods disposal many countries. Also, sources indicators OECD reports UNEP publications hidden costs municipal budgets. Data its impact, such as health effects metrics involving pollution, provided by Health Organization studies it conducted along from NGOs Greenpeace. Gradient Boosting model performed relatively high accuracy, followed Logistic Regression Random Forest Classifier. Besides, offered highest Macro Average F1-score, suggests better overall performance balancing precision recall all classes. Predictive insights proposed models are valuable tools expect patterns generation. Advanced analytics machine learning can help volume generated across geographies sectors. Application contexts huge potential about information shaping policy decisions. use historical production, consumption, recycling rates plastics create forecasts define high-risk areas.

Language: Английский

Global Plastic Waste Management: Analyzing Trends, Economic and Social Implications, and Predictive Modeling Using Artificial Intelligence DOI Creative Commons

Syed Ali Reza,

Morshed Chowdhury, Saddam Hossain

et al.

Journal of Environmental and Agricultural Studies, Journal Year: 2024, Volume and Issue: 5(3), P. 42 - 58

Published: Dec. 30, 2024

Plastic waste, which is a result of human activities in America, has become one the most critical environmental issues 21st century, and this calls for an urgent prescription strategies at global management level. The pervasiveness plastic modern life created unparalleled surge which, unless adequately managed, poised to pose severe threats ecosystems, health, economy. utmost objective study was perform extensive analysis waste practices USA, with specific concentration on pinpointing economic social implications these practices. This research project therefore intends probe into practice applied different countries understanding various best practices, challenges, areas improvement. also aimed employ AI-driven predictive models, notably, gradient boosting algorithm, linear regression, random forest predict future trends wastes generated. Diverse datasets were used, ensure that comprehensive. Primary data conditions generation obtained through World Bank's database, provides detailed composition, rate, methods disposal many countries. Also, sources indicators OECD reports UNEP publications hidden costs municipal budgets. Data its impact, such as health effects metrics involving pollution, provided by Health Organization studies it conducted along from NGOs Greenpeace. Gradient Boosting model performed relatively high accuracy, followed Logistic Regression Random Forest Classifier. Besides, offered highest Macro Average F1-score, suggests better overall performance balancing precision recall all classes. Predictive insights proposed models are valuable tools expect patterns generation. Advanced analytics machine learning can help volume generated across geographies sectors. Application contexts huge potential about information shaping policy decisions. use historical production, consumption, recycling rates plastics create forecasts define high-risk areas.

Language: Английский

Citations

1