气候变化
碳纤维
自回归积分移动平均
可持续发展
环境经济学
环境科学
碳捕获和储存(时间表)
价值(数学)
全球变暖
电流(流体)
工程类
减缓气候变化
温室气体
计算机科学
光学(聚焦)
遗传算法
环境资源管理
情景分析
碳通量
极限学习机
碳循环
环境工程
碳排放税
建筑业
生命周期评估
碳价格
多目标优化
最优化问题
优化算法
稳健优化
自然资源经济学
作者
Zhangzheng Chen,Xinsheng Zhang,Chunyang Wu
摘要
ABSTRACT Accurately predicting carbon emissions from the construction industry is crucial for sustainable social development and combating climate change. However, current methods primarily focus on qualitative analysis and factors that affect carbon emissions, resulting in imprecise and inaccurate predictions. The study presents an improved whale optimization algorithm (IWOA) for optimizing the extreme learning machine (ELM). The results show that IWOA-ELM outperforms ELM, BP (Back Propagation), and ARIMA (Autoregressive Integrated Moving Average) in analyzing the carbon emissions of China's construction industry. Given the influence of environmental protection policies and the current state of the construction industry, we have developed nine different scenarios to identify trends in the peak carbon value of the industry. We propose optimization strategies that will aid in achieving China's peak carbon goal sooner. These strategies are of practical significance and engineering value for low-carbon sustainable development.
科研通智能强力驱动
Strongly Powered by AbleSci AI