摘要：Observations worldwide are providing an increasing amount of atmosphere–ecosystem flux data. Thus, the establishment of a data mining methodology to detect significant trends and attribute changes to specific factors is important. This study examined the possibility of detecting significant trends in observed data at a test site with one of the longest records of flux measurements (Takayama, Japan). Statistical tests using non-parametric methods showed a 'likely' trend (i.e., detected at 66–90% confidence level) of increasing carbon sequestration. To investigate the change in carbon sequestration in relation to biological and environmental factors (ambient CO2, temperature, radiation, precipitation and disturbance), mechanistic and numerical methods were applied. A process-based model was used for the mechanistic attribution of change, and an optimal fingerprinting method in combination with model-based sensitivity simulations was used for numerical attribution. At the study site, local disturbances appeared to exert an impact on the observed carbon sequestration, whereas climatic factors made moderate contributions. These results indicate the feasibility of detection and attribution using current flux measurement data, although more evidence is needed to confirm global coherence.
