Title: Matrix completion-based prediction analysis in carbon emissions

Authors: Wei Huang; Danqing Wei; Cheng Wang; Chongze Lin

Addresses: Zhejiang Economic Information Center, Hangzhou, 310006, Zhejiang, China ' Zhejiang Economic Information Center, Hangzhou, 310006, Zhejiang, China ' Zhejiang Economic Information Center, Hangzhou, 310006, Zhejiang, China ' Zhejiang Economic Information Center, Hangzhou, 310006, Zhejiang, China

Abstract: China's carbon emissions data at this stage are mainly concentrated at the provincial and national levels. As a major area for the implementation of carbon emission reduction measures, cities have not had a complete carbon inventory for a long time due to the lack of basic data. In order to solve this problem, this paper constructs a set of prefecture-level CO₂ emission forecasting methods to study the carbon emissions of 11 urban areas in Zhejiang Province. The two-dimensional matrix is formed by one-to-one correspondence between city and time. Through the analysis of the historical data of carbon emissions, the intrinsic relationship is found, and the missing data is predicted by the method of matrix completion. Experiments show that compared with Zhejiang's actual carbon emissions statistics data, the difference is found to be within 1%, and can achieve 69.3% higher than the latest method.

Keywords: carbon emissions; carbon inventory; matrix completion.

DOI: 10.1504/IJES.2021.113806

International Journal of Embedded Systems, 2021 Vol.14 No.2, pp.143 - 148

Received: 20 Dec 2019
Accepted: 24 Dec 2019
Published online: 31 Mar 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article