The synchronicity effect between the financial market and online response for time-series forecasting is an important task with wide applications.This study combines data from the Baidu index(BDI),Google trends(GT),an...The synchronicity effect between the financial market and online response for time-series forecasting is an important task with wide applications.This study combines data from the Baidu index(BDI),Google trends(GT),and transfer entropy(TE)to forecast a wide range of futures prices with a focus on China.A forecasting model based on a hybrid gray wolf optimizer(GWO),convolutional neural network(CNN),and long short-term memory(LSTM)is developed.First,Baidu and Google dual-platform search data were selected and constructed as Internetbased consumer price index(ICPI)using principal component analysis.Second,TE is used to quantify the information between online behavior and futures markets.Finally,the effective Internet-based consumer price index(ICPI)and TE are introduced into the GWO-CNN-LSTM model to forecast the daily prices of corn,soybean,polyvinyl chloride(PVC),egg,and rebar futures.The results show that the GWO-CNN-LSTM model has a significant improvement in predicting future prices.Internet-based CPI built on Baidu and Google platforms has a high degree of real-time performance and reduces the platform and language bias of the search data.Our proposed framework can provide predictive decision support for government leaders,market investors,and production activities.展开更多
Greenhouse gas(GHG)emissions from China’s food system are a major environmental concern;however,studies quantifying their drivers and future projections remain limited.This study uses structural decomposition analysi...Greenhouse gas(GHG)emissions from China’s food system are a major environmental concern;however,studies quantifying their drivers and future projections remain limited.This study uses structural decomposition analysis and growth curve models to assess food-related GHG trends from 1961 to 2020,identify key drivers and their contributions,and project emissions for 2050 under six economic and population scenarios.It also proposes reduction pathways to help China achieve its 2060 carbon neutrality goal.Animal and plant foods are categorized into 14 groups based on the similarity of their emission coefficients.China’s total food related GHG emissions rose tenfold,from 351.7 to 3719.8 million tons CO_(2)-equivalent(CO_(2)e)/year,between 1961 and 2020.Per-capita emissions increased from 532.1 to 2584.4 kg CO_(2)e/year.Emissions from plant based foods grew from 435.0 to 824.6 kg CO_(2)e/year,while animal-based emissions surged from 97.1 to 1759.8 kg CO_(2)e/year,with animal products contributing more owing to their higher emission coefficients.Key drivers include rising food intake,increasing demand for animal-based foods(especially red meat),and population growth.Scenario analyses predict that emissions will peak at 3826.2 million tons CO_(2)e/year in 2031(low economy-low population)and 3971.0 million tons CO_(2)e/year in 2039(high economy-medium population).Compared with Australian,Indian,and Japanese diets,Chinese diets exhibit lower per-capita emissions than Australia and India but have higher emissions than in Japan.Adhering to China’s national dietary guidelines could reduce Chinese per-capita food-related GHGs by 31.5%,and optimized diets could lower them by 45.3%.This study provides valuable insights for Chinese policymakers to reduce food-related GHG emissions,refine national dietary guidelines,and raise public awareness regarding the food system’s environmental impact,thus encouraging people to follow sustainable diets.展开更多
Methane,a potent greenhouse gas with a global warming potential significantly higher than carbon dioxide,plays a critical role in climate change.Accurate predictions of its future concentrations are vital for understa...Methane,a potent greenhouse gas with a global warming potential significantly higher than carbon dioxide,plays a critical role in climate change.Accurate predictions of its future concentrations are vital for understanding and mitigating its environmental impact.For this reason,this paper presents a comparative analysis of deep learning models—Long Short-Term Memory(LSTM),Gated Recurrent Unit(GRU),CNN(Convolutional Neural Network)-GRU,and CNN-LSTM—for forecasting atmospheric methane concentrations through 2050.Leveraging historical data,each model's performance was evaluated using key metrics,including Mean Absolute Error(MAE)and Nash-Sutcliffe Efficiency(NSE).The results reveal that the CNNLSTM model achieved the highest accuracy,with the lowest MAE of 0.6567 and the highest NSE score of 0.933,indicating its superior capability in capturing the complexities of methane concentration trends.In contrast,the GRU model exhibited the poorest performance,with an MAE of 0.9667 and an NSE score of 0.844.Projections for 2050 indicate significant increases in methane levels,with maximum yearly concentrations expected to reach up to 2199.76 ppb,particularly under the CNN-LSTM model.These findings underscore the potential risks associated with rising methane concentrations,which could exacerbate global warming and its associated impacts.The study highlights the importance of employing advanced predictive models like CNN-LSTM to inform and enhance global climate change mitigation strategies.展开更多
The current and potential impacts of global warming have generated widespread concerns about food security among all sectors of society.Central Asian countries located deep in the interior of Asia with fragile ecologi...The current and potential impacts of global warming have generated widespread concerns about food security among all sectors of society.Central Asian countries located deep in the interior of Asia with fragile ecological environments and lower agricultural technology are particularly more prone to severe threats from climate change.Based on panel data acquired in five Central Asian countries from 1990 to 2019,a C-D-C model was developed to study how climate change affects food security in the region and to predict future trends.The study found that the level of food security has generally increased for these five Central Asian countries over the past 30 years,with Kazakhstan and Tajikistan having the highest and lowest food security levels,respectively.The average annual temperature and precipitation exhibit an inverted U-shaped relationship with the region’s food security,with the most positive effect on the food security of Kazakhstan.Extremely high and low temperatures have significantly affected food security in the studied region,with Turkmenistan experiencing the most significant negative impacts.The number of frost days had no significant effect on food security.An analysis of future climate showed that the temperature and precipitation in Central Asia will continue to increase from 2030 to 2090,which will negatively impact the food security of these countries.It is recommended that the Central Asian countries enhance their understanding of climate risks,strengthen scientific climate research,and develop multiple adaptation strategies in advance.Simultaneously,they are encouraged to consolidate international cooperation,reducing greenhouse gas emissions effectively and maintaining the ability to ensure food security.展开更多
文摘The synchronicity effect between the financial market and online response for time-series forecasting is an important task with wide applications.This study combines data from the Baidu index(BDI),Google trends(GT),and transfer entropy(TE)to forecast a wide range of futures prices with a focus on China.A forecasting model based on a hybrid gray wolf optimizer(GWO),convolutional neural network(CNN),and long short-term memory(LSTM)is developed.First,Baidu and Google dual-platform search data were selected and constructed as Internetbased consumer price index(ICPI)using principal component analysis.Second,TE is used to quantify the information between online behavior and futures markets.Finally,the effective Internet-based consumer price index(ICPI)and TE are introduced into the GWO-CNN-LSTM model to forecast the daily prices of corn,soybean,polyvinyl chloride(PVC),egg,and rebar futures.The results show that the GWO-CNN-LSTM model has a significant improvement in predicting future prices.Internet-based CPI built on Baidu and Google platforms has a high degree of real-time performance and reduces the platform and language bias of the search data.Our proposed framework can provide predictive decision support for government leaders,market investors,and production activities.
基金funded by the General Program of the National Natural Science Foundation of China[Grant No.42171300]the Strategic Research Program of the National Natural Science Foundation of China[Grant No.42542001]+1 种基金Post-funded Project of National Social Science Fund of China[Grant No.25FJYB015]Special Project of Strategic Research and Decision Support System of the Chinese Academy of Sciences[Grant No.GHJ-ZLZX-2025-48].
文摘Greenhouse gas(GHG)emissions from China’s food system are a major environmental concern;however,studies quantifying their drivers and future projections remain limited.This study uses structural decomposition analysis and growth curve models to assess food-related GHG trends from 1961 to 2020,identify key drivers and their contributions,and project emissions for 2050 under six economic and population scenarios.It also proposes reduction pathways to help China achieve its 2060 carbon neutrality goal.Animal and plant foods are categorized into 14 groups based on the similarity of their emission coefficients.China’s total food related GHG emissions rose tenfold,from 351.7 to 3719.8 million tons CO_(2)-equivalent(CO_(2)e)/year,between 1961 and 2020.Per-capita emissions increased from 532.1 to 2584.4 kg CO_(2)e/year.Emissions from plant based foods grew from 435.0 to 824.6 kg CO_(2)e/year,while animal-based emissions surged from 97.1 to 1759.8 kg CO_(2)e/year,with animal products contributing more owing to their higher emission coefficients.Key drivers include rising food intake,increasing demand for animal-based foods(especially red meat),and population growth.Scenario analyses predict that emissions will peak at 3826.2 million tons CO_(2)e/year in 2031(low economy-low population)and 3971.0 million tons CO_(2)e/year in 2039(high economy-medium population).Compared with Australian,Indian,and Japanese diets,Chinese diets exhibit lower per-capita emissions than Australia and India but have higher emissions than in Japan.Adhering to China’s national dietary guidelines could reduce Chinese per-capita food-related GHGs by 31.5%,and optimized diets could lower them by 45.3%.This study provides valuable insights for Chinese policymakers to reduce food-related GHG emissions,refine national dietary guidelines,and raise public awareness regarding the food system’s environmental impact,thus encouraging people to follow sustainable diets.
文摘Methane,a potent greenhouse gas with a global warming potential significantly higher than carbon dioxide,plays a critical role in climate change.Accurate predictions of its future concentrations are vital for understanding and mitigating its environmental impact.For this reason,this paper presents a comparative analysis of deep learning models—Long Short-Term Memory(LSTM),Gated Recurrent Unit(GRU),CNN(Convolutional Neural Network)-GRU,and CNN-LSTM—for forecasting atmospheric methane concentrations through 2050.Leveraging historical data,each model's performance was evaluated using key metrics,including Mean Absolute Error(MAE)and Nash-Sutcliffe Efficiency(NSE).The results reveal that the CNNLSTM model achieved the highest accuracy,with the lowest MAE of 0.6567 and the highest NSE score of 0.933,indicating its superior capability in capturing the complexities of methane concentration trends.In contrast,the GRU model exhibited the poorest performance,with an MAE of 0.9667 and an NSE score of 0.844.Projections for 2050 indicate significant increases in methane levels,with maximum yearly concentrations expected to reach up to 2199.76 ppb,particularly under the CNN-LSTM model.These findings underscore the potential risks associated with rising methane concentrations,which could exacerbate global warming and its associated impacts.The study highlights the importance of employing advanced predictive models like CNN-LSTM to inform and enhance global climate change mitigation strategies.
基金This work was supported by the Chinese Academy of Sciences(Grant No.xbzg-zdsys-202217)the Shandong Provincial Special Fund(Grant No.LSKJ202203300).
文摘The current and potential impacts of global warming have generated widespread concerns about food security among all sectors of society.Central Asian countries located deep in the interior of Asia with fragile ecological environments and lower agricultural technology are particularly more prone to severe threats from climate change.Based on panel data acquired in five Central Asian countries from 1990 to 2019,a C-D-C model was developed to study how climate change affects food security in the region and to predict future trends.The study found that the level of food security has generally increased for these five Central Asian countries over the past 30 years,with Kazakhstan and Tajikistan having the highest and lowest food security levels,respectively.The average annual temperature and precipitation exhibit an inverted U-shaped relationship with the region’s food security,with the most positive effect on the food security of Kazakhstan.Extremely high and low temperatures have significantly affected food security in the studied region,with Turkmenistan experiencing the most significant negative impacts.The number of frost days had no significant effect on food security.An analysis of future climate showed that the temperature and precipitation in Central Asia will continue to increase from 2030 to 2090,which will negatively impact the food security of these countries.It is recommended that the Central Asian countries enhance their understanding of climate risks,strengthen scientific climate research,and develop multiple adaptation strategies in advance.Simultaneously,they are encouraged to consolidate international cooperation,reducing greenhouse gas emissions effectively and maintaining the ability to ensure food security.
