Forecasting global plastic production and microplastic emission using advanced optimised discrete grey model.

Area of Science:

• Environmental Science
• Pollution Studies
• Predictive Modeling

Background:

• Plastic pollution, particularly microplastics in freshwater, poses significant environmental and public health risks.
• The accumulation of microplastics necessitates accurate forecasting of production and emission levels.
• Understanding these trends is crucial for developing effective mitigation strategies.

Purpose of the Study:

• To forecast global plastic production and microplastic emissions.
• To compare the accuracy of four enhanced grey prediction models: EGM (1,1, α, θ), DGM (1,1), EGM (1,1), and DGM (1,1, α).
• To identify the most suitable model for predicting microplastic emission and plastic production.

Main Methods:

• Utilized enhanced grey prediction models, including EGM (1,1, α, θ) and DGM (1,1, α).
• Compared model accuracy using metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE).
• Applied the most accurate models to predict future plastic production and microplastic emission trends.

Main Results:

• The DGM (1,1, α) model demonstrated higher accuracy in predicting microplastic emission.
• The EGM (1,1, α, θ) model showed slightly better accuracy for forecasting global plastic production.
• Microplastic emission is projected to reach 1,084,018 tons by 2030 based on the DGM (1,1, α) model.

Conclusions:

• Enhanced grey prediction models are effective tools for forecasting plastic production and microplastic emissions.
• The DGM (1,1, α) model is recommended for microplastic emission prediction, while EGM (1,1, α, θ) is suitable for plastic production.
• Findings offer critical insights for policymakers to address plastic pollution and its environmental impacts.