Search

Accurate prediction of carbon price effectively ensures the stability of the carbon trading market and reduces carbon emissions. However, making accurate prediction is challenging because the carbon price is highly nonlinear and nonstationary due to complex influential factors. Thus, we propose a multifactorial hybrid forecasting framework, ET-MVMD-LSTM, to integrate three advanced algorithms for a reliable multi-step ahead prediction of the carbon price. First, extremely randomized tree (ET) is used to determine the optimal input variables for the modeling to follow. Then, multivariate variational mode decomposition (MVMD) is executed to simultaneously decompose the screened input variables into relatively regular sub-modes, which reflect characteristics at different scales. Subsequently, long short-term memory (LSTM) with a stable forecasting ability is employed to model each mode individually to effectively extract the long-term trend and short-term fluctuation features. The final forecast is reconstructed by the ensemble of the predictions of all sub-modes. Last, systematical studies on two European Union Emissions Trading Scheme carbon price datasets indicate that the proposed ET-MVMD-LSTM framework outperforms several advanced baseline models in terms of accuracy and stability, which prove the framework is deemed promising and practical for carbon price prediction. • Propose a novel hybrid framework for multi-step carbon price forecasting. • Consider multiple influential factors for carbon price forecasting. • Use extremely randomized tree for feature selection. • MVMD algorithm decomposes multiple variables simultaneously. • The proposed model outperforms the baseline models in two EU ETS dataset. [ABSTRACT FROM AUTHOR]

Abstract: Increasing atmospheric concentrations of greenhouse gases has caused grievous global warming and associated consequences. Lowering carbon footprint to promote the development of cleaner production demands the immediate attention. In this study, the carbon footprint calculations were performed on five cropping systems in North China Plain from 2003 to 2010. The five cropping systems included sweet potato → cotton → sweet potato → winter wheat–summer maize (SpCSpWS, 4-year cycle), ryegrass–cotton → peanut → winter wheat–summer maize (RCPWS, 3-year cycle), peanut → winter wheat–summer maize (PWS, 2-year cycle), winter wheat–summer maize (WS, 1-year cycle), and continuous cotton (Cont C), established in a randomized complete-block design with three replicates. We used a modified carbon footprint calculation with localized greenhouse gas emissions parameters to analyze the carbon footprint of each cropping system per unit area, per kg biomass, and per unit economic output. Results showed that the lowest annual carbon footprint values were observed in SpCSpWS among the five cropping systems, which were only 27.9%, 28.2% and 25.0% of those in WS rotation system (the highest carbon footprint) in terms of per unit area, per unit biomass, and per unit economic output, respectively. The five cropping systems showed the order of SpCSpWS < Cont C < RCPWS < PWS < WS sorting by their annual carbon footprint calculated by all the three metrics above-mentioned. Results revealed that appropriate diversified crop rotation systems could contribute to decreased carbon footprint compared with conventional intensive crop production system in North China Plain. [Copyright &y& Elsevier]

Available saline-alkali land could be used to plant bioenergy crops for biofuel stocks, retaining productive land for food crops. Sweet sorghum is a promising candidate for bioethanol production due to its ability to tolerate environmental stresses. This study estimated the available saline-alkali land for sweet sorghum planting in northwest China using a multi-factorial analysis, quantified its bioethanol potential, and assessed the carbon footprint of sweet sorghum stalk (SSS)-based bioethanol production on this land using a life cycle assessment. The results revealed 9.33 × 105 ha saline-alkali land available for sweet sorghum planting, or 11.47% of the total saline-alkali land in the study area, with a potential yield of 6.87 × 107 t sweet sorghum stalk, producing 4.29 × 106 t bioethanol. The carbon footprint of SSS-based bioethanol production ranged from 2.21 to 2.25 t CO 2 eq t−1 bioethanol across selected districts. Sweet sorghum cultivation accounted for most of the carbon footprint in each district (40.18–45.30%). Compared to gasoline, the carbon footprint for pure bioethanol (E100) made from SSS in the selected districts declined by 33.42–49.94% with or without reusing the bagasse co-product. The carbon footprint of E10 (10% bioethanol from SSS and 90% gasoline) declined by 2.68–4.49%. Thus, it is possible to cultivate sweet sorghum on the selected saline-alkali land in northwest China for bioethanol production. However, future studies are needed to (1) improve sweet sorghum genotypes and identify optimal agronomic management for feedstock, (2) advance technologies for bioethanol production, (3) develop bioethanol-tolerant yeast and bacteria strains, and (4) stimulate policy support for growers and industrialists to accelerate cleaner production. • The available saline-alkali land for sweet sorghum planting in northwest China was assessed. • Carbon footprint and potential yield of sweet sorghum stalk-based bioethanol was evaluated. • SSS-based bioethanol decreased carbon footprint up to 49.94% compared to gasoline. [ABSTRACT FROM AUTHOR]