Ochoa-Barragán Rogelio, Munguía-López Aurora Del Carmen, Ponce-Ortega José María
Chemical Engineering Department, Universidad Michoacana de San Nicolás de Hidalgo, Francisco J. Mujica S/N, Ciudad Universitaria, 58060 Morelia, Michoacán México.
Environ Dev Sustain. 2023 May 13:1-20. doi: 10.1007/s10668-023-03354-2.
This paper provides a mathematical optimization strategy for optimal municipal solid waste management in the context of the COVID-19 epidemic. This strategy integrates two approaches: optimization and machine learning models. First, the optimization model determines the optimal supply chain for the municipal waste management system. Then, machine learning prediction models estimate the required parameters over time, which helps generate future projections for the proposed strategy. The optimization model was coded in the General Algebraic Modeling System, while the prediction model was coded in the Python programming environment. A case study of New York City was addressed to evaluate the proposed strategy, which includes extensive socioeconomic data sets to train the machine learning model. We found the predicted waste collection over time based on the socioeconomic data. The results show trade-offs between the economic (profit) and environmental (waste sent to landfill) objectives for future scenarios, which can be helpful for possible pandemic scenarios in the following years.
The online version contains supplementary material available at 10.1007/s10668-023-03354-2.
本文提供了一种在新冠疫情背景下实现城市固体废物优化管理的数学优化策略。该策略整合了两种方法：优化和机器学习模型。首先，优化模型确定城市垃圾管理系统的最优供应链。然后，机器学习预测模型随时间估计所需参数，这有助于为所提出的策略生成未来预测。优化模型用通用代数建模系统编码，而预测模型在Python编程环境中编码。以纽约市为例来评估所提出的策略，其中包括用于训练机器学习模型的大量社会经济数据集。我们根据社会经济数据找到了随时间预测的垃圾收集量。结果显示了未来情景下经济（利润）和环境（送往垃圾填埋场的废物）目标之间的权衡，这可能有助于应对未来几年可能出现的疫情情景。
在线版本包含可在10.1007/s10668-023-03354-2获取的补充材料。
