| Title | Using Particle Swarm Optimization method to optimize the carbon sequestration potential of agricultural afforestation in Beijing, China |
|---|---|
| ID_Doc | 43805 |
| Authors | Yao, JT; Kong, XB; Lal, R |
| Title | Using Particle Swarm Optimization method to optimize the carbon sequestration potential of agricultural afforestation in Beijing, China |
| Year | 2018 |
| Published | |
| Abstract | Agricultural afforestation is an important way to mitigate climate change and improve the environmental quality of city system. The major restriction of planning agricultural afforestation programs and optimize the carbon sequestration potential of these programs is the decrease of food productivity. The spatial heterogeneity of both the food productivity and carbon sequestration potential further complicate this problem. In this article, we demonstrate how the particle swarm optimization (PSO) method can be formulated and applied to address this problem. Based on the spatial estimation of food productivity and carbon sequestration potential, we formulated a PSO model to generate the optimal zoning of agricultural afforestation area and optimize the carbon sequestration potential with different scenarios of food productivity decrease ratio in Beijing, China. Results show that our method can be used to optimize the carbon sequestration potential of agricultural afforestation under the restriction of decrease in food productivity. With the application of our method, a significantly higher carbon sequestration potential can be achieved with a small loss of the current food productivity, e.g. 8.80-12.47 Tg C (14.82 - 20.93 % of the maximum carbon sequestration potential) can be sequestrated with 5% loss of current food productivity. This research highlights the application of machine learning at the high level of smart city management to improve the efficacy and intelligence of urban planning. |
No similar articles found.