长时间大气温度序列的外部变化趋势判别研究

Detection of significant external trend in long-term air temperature records

选取全球历史气候网日值数据集中4个具有长时间大气温度序列的站点并统计其逐月距平值,利用二阶去趋势的涨落分析法分析研究站点不同时段的气温序列长程相关性特征,并计算4站在不同时段的最高气温、最低气温的相对变化趋势.利用傅里叶滤波法生成具有与各站不同时段气温序列相同的长程相关性强度及数据长度相等的代用序列,并估算出其源于系统内部自然变率的"增/降温"范围,经分析可知气温序列内部自然变率导致的趋势变化范围与其长度成反比,而与序列的长程相关性强弱成正比.最后对比实际温度序列的相对变化趋势以及在95%和99%的置信概率下自然变率的趋势范围,除SAGINAW MBS INTL AP站日最高气温序列外,各站点的日最高气温和最低气温长时间序列普遍表现为明显的外部变化趋势,近30年各站最高、最低气温序列的变化趋势则未超自然变率的趋势范围,虽不能排除外部趋势的存在,但与气候系统内部各因子相互作用的影响相比,这种外部趋势并不显著.该方法可判别全球变暖背景下气候因子的变化趋势是否显著地由气候系统外部因子引起,从而能有针对性地对系统外(内)部影响因子展开进一步的研究.

Long-term historical air temperature records of four stations from Global Historical Climatology Network-Daily are analyzed in this study. By applying detrended fluctuation analysis of the second order to the monthly anomalies, different long-term correlations are found in different time periods at both the maximum and minimum temperatures, which indicate the existence of internal stochastic trend. By generating surrogate data with the same long-term correlations and data length, internal stochastic trends are estimated with confidence probability intervals of 95%and 99%provided. We find the longer data length, the shorter confidence probability interval we have; the stronger long-term correlation, the wider confidence probability interval is obtained. By comparing the temperature trends observed from the historical temperature records with the corresponding confidence probability intervals of the internal stochastic trends, significant external trends can be detected. We find that except for the maximum temperature in SAGINAW MBS INTL AP, temperatures from the four stations all show significant external trends when long historical data （＆gt; 100 years） are considered. However, if only the past 30 years are taken into account, the observed trends are still not strong enough to exceed the confidence probability interval. Although we cannot exclude the existence of external trends, considering the possible influence from internal stochastic trends, the external trends are not significant. From this detection method, we can judge, in the context of global warming, whether an observed trend is significantly induced by external forcing. Therefore, it is useful for our further study targeting the internal （external） climatic impact factors.