ABSTRACT
Global warming, caused by greenhouse gas emissions, is a major challenge for all human societies. To ensure that ambitious carbon neutrality and sustainable economic development goals are met, regional human activities and their impacts on carbon emissions must be studied. Guizhou Province is a typical karst area in China that predominantly uses fossil fuels. In this study, a backpropagation (BP) neural network and extreme learning machine (ELM) model, which is advantageous due to its nonlinear processing, were used to predict carbon emissions from 2020 to 2040 in Guizhou Province. The carbon emissions were calculated using conversion and inventory compilation methods with energy consumption data and the results showed an "S" growth trend. Twelve influencing factors were selected, however, five with larger correlations were screened out using a grey correlation analysis method. A prediction model for carbon emissions from Guizhou Province was established. The prediction performance of a whale optimization algorithm (WOA)-ELM model was found to be higher than the BP neural network and ELM models. Baseline, high-speed, and low-carbon scenarios were analyzed and the size and time of peak carbon emissions in Liaoning Province from 2020 to 2040 were predicted using the WOA-ELM model.
Subject(s)
Neural Networks, Computer , China , Carbon/analysis , Global Warming , Humans , Algorithms , Machine LearningABSTRACT
By the methods of classical statistics and geostatistics, this paper studied the spatial heterogeneity of surface soil (0-20 cm layer) moisture and salt contents under three kinds of artificial vegetation in coastal salt land in Chongming Dongtan of Shanghai. The soil moisture content in different plots was in order of Cynodon dactylon > Taxodium distichum > Nerium indicum, and the coefficient of variation was 13.9%, 13.4% and 12.9%, respectively. The soil electric conductivity was in the order of N. indicum > C. dactylon > T. distichum, and the coefficient of variation was 79.2%, 55.4% and 15. 9%, respectively. Both the soil moisture content and the salt content were in moderate variation. The theoretical models of variogram for the soil moisture and salt contents in different plots varied, among which, the soil electric conductivity fitted better, with R2 between 0.97 and 0.99. When the artificial vegetation varied from N. indicum to T. distichum and then to C. dactylon, the spatial heterogeneity of soil moisture content changed from weak to strong, in which, the variability was random under N. indicum. When the vegetation varied from C. dactylon to T. distichum and to N. indicum, the spatial heterogeneity of soil electric conductivity changed from moderate to strong. Under different vegetations, the soil electric conductivity was mostly in positive correlation, whereas the soil moisture content was in negative correlation. The spatial pattern of soil moisture and salt contents under T. distichum was in striped distribution, that under C. dactylon was in large plaque and continuous distribution, whereas under N. indicum, the spatial pattern of soil moisture content was in small breaking plaque distribution, and that of soil salt content was in striped distribution.
