Application of artificial neural networks in global climate change and ecological research: An overview

Fields that employ artificial neural networks (ANNs) have developed and expanded continuously in recent years with the ongoing development of computer technology and artificial intelligence. ANN has been adopted widely and put into practice by researchers in light of increasing concerns over ecological issues such as global warming, frequent El Niño-Southern Oscillation (ENSO) events, and atmospheric circulation anomalies. Limitations exist and there is a potential risk for misuse in that ANN model parameters require typically higher overall sensitivity, and the chosen network structure is generally more dependent upon individual experience. ANNs, however, are relatively accurate when used for short-term predictions; despite global climate change research favoring the effects of interactions as the basis of study and the preference for long-term experimental research. ANNs remain a better choice than many traditional methods when dealing with nonlinear problems, and possesses great potential for the study of global climate change and ecological issues. ANNs can resolve problems that other methods cannot. This is especially true for situations in which measurements are difficult to conduct or when only incomplete data are available. It is anticipated that ANNs will be widely adopted and then further developed for global climate change and ecological research.     

Meta-analysis and its application in global change research

Meta-analysis is a quantitative synthetic research method that statistically integrates results from in- dividual studies to find common trends and differences. With increasing concern over global change, meta-analysis has been rapidly adopted in global change research. Here, we introduce the methodolo- gies, advantages and disadvantages of meta-analysis, and review its application in global climate change research, including the responses of ecosystems to global warming and rising CO2 and O3 concentrations, the effects of land use and management on climate change and the effects of distur- bances on biogeochemistry cycles of ecosystem. Despite limitation and potential misapplication, meta-analysis has been demonstrated to be a much better tool than traditional narrative review in synthesizing results from multiple studies. Several methodological developments for research synthe- sis have not yet been widely used in global climate change researches such as cumulative meta-analysis and sensitivity analysis. It is necessary to update the results of meta-analysis on a given topic at regular intervals by including newly published studies. Emphasis should be put on multi-factor interaction and long-term experiments. There is great potential to apply meta-analysis to global climate change research in China because research and observation networks have been established (e.g. ChinaFlux and CERN), which create the need for combining these data and results to provide support for governments’ decision making on climate change. It is expected that meta-analysis will be widely adopted in future climate change research.     

Impacts of changed litter inputs on soil CO2 efflux in three forest types in central south China

Climate change is expected to cause the alteration of litter production in forests,which may result in substantial changes in soil CO2 efflux (FCO2) process as litter represents a major pathway of carbon from vegetation to the soils.In this study,we conducted an aboveground litter manipulation experiment to examine the influence of litter addition and exclusion on soil FCO2 in Camphor tree,Masson pine,and mixed Camphor tree and Masson pine forests in central south China.Litter input manipulation included three treatments:non-litter input (litter exclusion),double litter input (litter addition),and natural litter input (control).On average,litter exclusion significantly reduced soil FCO2 rate by approximately 39%,24% and 22% in Camphor tree forests,the Mixed forests,and Masson pine forests,respectively.On a yearly basis,double litter addition significantly increased soil CO2 by 12% in the Mixed forests (P=0.02) but not in both Camphor tree and Masson pine forests (P>0.05),when compared with their corresponding control treatments.However,litter addition increased soil FCO2 rates in the months of June-August in Camphor tree and Masson pine forests,coinciding with high soil temperature of summer conditions.Litter exclusion reduced soil FCO2 more than litter addition increased it in the study sites.Responses of soil respiration to litter input treatments varied with forest types.Litter input treatments did not alter the seasonal patterns of soil temperature and soil water content.Our results indicated that changes in aboveground litter as a result of global climate change and/or forest management have a great potential to alter soil respiration and soil carbon balance in forest ecosystems.     

Soil respiration dynamics in <Emphasis Type="Italic">Cinnamomum camphora</Emphasis> forest and a nearby <Emphasis Type="Italic">Liquidambar formosana</Emphasis> forest in Subtropical China

Climate change can significantly affect carbon cycling of forest ecosystems.The diurnal and seasonal dynamics of soil respiration (Rs) in Cinnamomum camphora and Liquidambar formosana forests were investigated by using infrared gas exchange analyzer of Li-Cor 6400-09 each month in 2006.Soil temperature and moisture were also measured.Diurnal variations in Rs varied with daily soil temperature in the two forests.Across the growing season,soil respiration peaked on July 28 due to higher soil temperature and m...