Predicting carbon peak at the provincial level using deep learning
Assessing carbon peak status is crucial in designing mitigation strategies for provinces to mitigate CO _2 emissions while maintaining economic development. This study proposes a comprehensive research framework to evaluate carbon peak status at the provincial level. The framework involves identifyi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Environmental Research Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2515-7620/adac32 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542873498681344 |
|---|---|
| author | Xiaoyan Tang Kunsheng Fang |
| author_facet | Xiaoyan Tang Kunsheng Fang |
| author_sort | Xiaoyan Tang |
| collection | DOAJ |
| description | Assessing carbon peak status is crucial in designing mitigation strategies for provinces to mitigate CO _2 emissions while maintaining economic development. This study proposes a comprehensive research framework to evaluate carbon peak status at the provincial level. The framework involves identifying the critical emission sources and their primary contribution sectors using the LASSO regression method, predicting the CO _2 emissions of critical sources using recurrent neural networks, and exploring mitigation schemes using scenario analysis. This study uses Guizhou Province as an example and analyzes the CO _2 emissions of 17 energy consumption types and one production process in 47 socio-economic sectors and discovers that: ① Between 1997 and 2005, the most critical sources of CO _2 emissions were the consumption of Raw Coal; ② Between 2006 and 2021, the critical sources of emissions were the consumption of Raw Coal, Other Washed Coal (OWC), and Diesel Oil, and one industry process (Cement Production Process, CPP); ③ Between 2006 and 2021, the primary contribution sector for Raw Coal and OWC emissions is the Production and Supply of Electric Power, Steam, and Hot Water (PSEPSHW) sector. The main contributors to Diesel Oil emissions are the Transportation, Storage, Post and Telecommunication Services (TSPTS), and Other Services (OS) sectors. This study projects that the rising trend in total CO _2 emissions will continue from 2022 to 2040 and that emissions will not yet reach their peak by 2030. Furthermore, CO _2 emissions from Raw Coal consumption and CO _2 emissions from Diesel Oil consumption will continue to increase. These are crucial when designing mitigation schemes for total CO _2 emissions. The scenario analysis presents three mitigation schemes for Raw Coal and Diesel Oil emissions that have the potential to reverse the upward trend in CO _2 emissions. |
| format | Article |
| id | doaj-art-174cb9723f7c465a85377214cb190ed0 |
| institution | Kabale University |
| issn | 2515-7620 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Environmental Research Communications |
| spelling | doaj-art-174cb9723f7c465a85377214cb190ed02025-02-03T13:32:26ZengIOP PublishingEnvironmental Research Communications2515-76202025-01-017202500310.1088/2515-7620/adac32Predicting carbon peak at the provincial level using deep learningXiaoyan Tang0https://orcid.org/0009-0004-3628-5228Kunsheng Fang1https://orcid.org/0009-0008-9478-020XSchool of Applied Economics, Guizhou University of Finance and Economics , Guiyang, People’s Republic of ChinaGuangzhou Tianquan Information Science & Technology Co., Ltd., Guangzhou, People’s Republic of ChinaAssessing carbon peak status is crucial in designing mitigation strategies for provinces to mitigate CO _2 emissions while maintaining economic development. This study proposes a comprehensive research framework to evaluate carbon peak status at the provincial level. The framework involves identifying the critical emission sources and their primary contribution sectors using the LASSO regression method, predicting the CO _2 emissions of critical sources using recurrent neural networks, and exploring mitigation schemes using scenario analysis. This study uses Guizhou Province as an example and analyzes the CO _2 emissions of 17 energy consumption types and one production process in 47 socio-economic sectors and discovers that: ① Between 1997 and 2005, the most critical sources of CO _2 emissions were the consumption of Raw Coal; ② Between 2006 and 2021, the critical sources of emissions were the consumption of Raw Coal, Other Washed Coal (OWC), and Diesel Oil, and one industry process (Cement Production Process, CPP); ③ Between 2006 and 2021, the primary contribution sector for Raw Coal and OWC emissions is the Production and Supply of Electric Power, Steam, and Hot Water (PSEPSHW) sector. The main contributors to Diesel Oil emissions are the Transportation, Storage, Post and Telecommunication Services (TSPTS), and Other Services (OS) sectors. This study projects that the rising trend in total CO _2 emissions will continue from 2022 to 2040 and that emissions will not yet reach their peak by 2030. Furthermore, CO _2 emissions from Raw Coal consumption and CO _2 emissions from Diesel Oil consumption will continue to increase. These are crucial when designing mitigation schemes for total CO _2 emissions. The scenario analysis presents three mitigation schemes for Raw Coal and Diesel Oil emissions that have the potential to reverse the upward trend in CO _2 emissions.https://doi.org/10.1088/2515-7620/adac32carbon peakCO2 emission predictionlasso regressionneural networksscenario analysis |
| spellingShingle | Xiaoyan Tang Kunsheng Fang Predicting carbon peak at the provincial level using deep learning Environmental Research Communications carbon peak CO2 emission prediction lasso regression neural networks scenario analysis |
| title | Predicting carbon peak at the provincial level using deep learning |
| title_full | Predicting carbon peak at the provincial level using deep learning |
| title_fullStr | Predicting carbon peak at the provincial level using deep learning |
| title_full_unstemmed | Predicting carbon peak at the provincial level using deep learning |
| title_short | Predicting carbon peak at the provincial level using deep learning |
| title_sort | predicting carbon peak at the provincial level using deep learning |
| topic | carbon peak CO2 emission prediction lasso regression neural networks scenario analysis |
| url | https://doi.org/10.1088/2515-7620/adac32 |
| work_keys_str_mv | AT xiaoyantang predictingcarbonpeakattheprovinciallevelusingdeeplearning AT kunshengfang predictingcarbonpeakattheprovinciallevelusingdeeplearning |