Prediction of agricultural carbon emissions in China based on a GA-ELM model

Abstract

Introduction: Strengthening the early warning of greenhouse gas emissions from agriculture is an important way to achieve Goal 13 of the Sustainable Development Goals. Agricultural carbon emissions are an important part of greenhouse gases, and accelerating the development of green and low-carbon agriculture is of great significance for China to achieve high-quality economic development and the goal of “carbon neutrality in peak carbon dioxide emissions”.Methods: By measuring the total agricultural carbon emissions in China and seven administrative regions from 2000 to 2021, the paper analyzes the influencing factors of agricultural carbon emissions in China by using STIRPAT environmental pressure model, and on this basis, predicts the peak trend of agricultural carbon emissions in China under different development scenarios by using the extreme learning machine model optimized by genetic algorithm.Results: The results showed that the extreme learning machine model improved by the genetic algorithm can overcome the shortcoming that the extreme learning machine model is easy to fall into the local optimal solution, thus obtaining higher prediction accuracy. At the same time, from 2000 to 2021, the total agricultural carbon emissions in China showed a continuous fluctuation trend, and due to the constraints of the agricultural economic level, agricultural industrial structure, and agricultural human capital, the agricultural carbon emissions showed spatial differentiation. It is worth noting that, in the context of green development, the agricultural carbon emissions of the seven regions in China all have the potential to achieve the “peak carbon dioxide emissions” goal in 2030, with only a slight difference at the peak.Discussion: The research results of this paper provide evidence for the government to formulate flexible, accurate, reasonable and appropriate agricultural carbon reduction policies, which is helpful to strengthen the exchanges and cooperation of regional agricultural and rural carbon reduction and fixation, and actively and steadily promote China's agriculture to achieve the goal of “peak carbon dioxide emissions carbon neutrality”.

Application of extreme learning machine (ELM) forecasting model on CO2 emission dataset of a natural gas-fired power plant in Dhaka, Bangladesh

“…The graph shows a decrease in CO 2 emissions over time, with a sharp decrease starting in 2022. The ELM model can only "learn" from the data it's trained on, and if the training data does not capture all the real-world factors influencing CO 2 emissions, the forecast may not perfectly reflect reality [ 5 ].

Fig.

…”

Impact on green finance and environmental regulation on carbon emissions: evidence from China

“…At the same time, with the continuous acceleration of urbanization, the carbon emissions between neighboring provinces are spatially dependent. In view of this, referring to the research results of China Physical Geography and Guo et al (2023), this paper divides the geographical region of China into eastern region, central region, western region and northeast region, so as to further investigate the differences in the impact of green finance on carbon emissions. Among them, each region contains provinces as shown in the table 8.…”

Forecasting Carbon Emissions from Planting Industry in China Based on BO-LightGBM and SHAP

“…Qi et al used the PCA-GS-KNN model to predict agricultural carbon emissions in Zhejiang Province, China, and the results showed that the model can accurately predict regional agricultural carbon emissions 11 . Guo et al used the genetic algorithm optimisation and the extreme learning machine model to construct the Chinese agricultural carbon emissions prediction model to predict the peak trend of China's agricultural carbon emissions 12 .As interpretable machine learning has become increasingly popular, machine learning methods can extract unique insights from large datasets with a large number of feature variables [13][14] .Luo et al proposed a prediction model based on interpretable machine learning with Extra Tree Regression and SHAP to predict carbon emissions in the Yangtze River Delta region. The results showed that the overall areas of plowland, woodland, and grassland have a negative influence on carbon emissions, whereas the area of wave has an overall positive impact on carbon emissions 15 .…”