|
| Spatiotemporal distribution characteristics and trend prediction of carbon sequestration in farmland ecosystems in Jiangsu Province，China |
| Received:February 16, 2023 |
| View Full Text View/Add Comment Download reader |
| KeyWord:Jiangsu Province;agricultural carbon neutrality;soil carbon fixation;farmland ecological carbon sink;machine learning prediction |
| Author Name | Affiliation | E-mail | | QIU Zijian | School of Environmental Science and Engineering, Nanjing University of Information Science and Technology/Key Laboratory of High Technology Research on Atmospheric Environment Monitoring and Pollution Control in Jiangsu Province/Jiangsu Atmospheric Environment and Equipment Technology Collaborative Innovation Center, Nanjing 210044, China | | | LI Tianling | School of Environmental Science and Engineering, Nanjing University of Information Science and Technology/Key Laboratory of High Technology Research on Atmospheric Environment Monitoring and Pollution Control in Jiangsu Province/Jiangsu Atmospheric Environment and Equipment Technology Collaborative Innovation Center, Nanjing 210044, China | | | SHEN Weishou | School of Environmental Science and Engineering, Nanjing University of Information Science and Technology/Key Laboratory of High Technology Research on Atmospheric Environment Monitoring and Pollution Control in Jiangsu Province/Jiangsu Atmospheric Environment and Equipment Technology Collaborative Innovation Center, Nanjing 210044, China | wsshen@nuist.edu.cn |
|
| Hits: 529 |
| Download times: 355 |
| Abstract: |
| To explore the spatiotemporal distribution characteristics and future carbon sequestration trends of farmland ecosystems in Jiangsu Province, China, the carbon sequestration rate method was used to estimate the carbon sequestration of farmland in Jiangsu Province from 2005—2020, with a focus on analyzing the spatiotemporal distribution characteristics of 2005, 2010, 2015, and 2020. Machine learning methods were used to predict the carbon sequestration of farmland ecosystems in the province from 2021—2060. The results revealed that in terms of time series, the overall carbon sequestration of farmland ecosystems in Jiangsu Province had demonstrated an increasing trend in recent years, with an estimated 2 825 500 t·a-1 （calculated by C, the same below）in 2020, accounting for 20.17% of the total carbon sequestration of terrestrial ecosystems in the province. In terms of spatial distribution, the largest contribution of carbon sequestration was in the northern region of Jiangsu compared to the central and southern regions, owing to high contributions from both fertilizer application and straw returning. According to the importance analysis of machine learning, the amount of straw returned to the field was the most important factor. In the two models, BP neural network had a higher prediction accuracy than that of random forest. The BP neural network predicted that from 2021—2060, the carbon sequestration of farmland ecosystem would continue to increase in the short term but would then entered a more stable platform period. The carbon sequestration would continue to rise and reach a peak of 3 652 600 t · a-1 from 2021—2026, and 3 481 200 t · a-1 by 2060. Studies had revealed that the carbon sequestration capacity of agricultural ecosystems in Jiangsu Province had gradually increased but the growth rate would slow down in the future. It is necessary to further strengthen carbon sequestration measures, with a focus on improving the straw return rate and carbon sequestration efficiency. Meanwhile, existing research methods need to be further optimized. In the future, factors such as organic fertilizer application, green manure return, and rotation should be considered to achieve more accurate and comprehensive carbon sequestration of agricultural ecosystems estimation. |
|
|
|
