摘要：Climate models and/or their output are usually bias-corrected for climate impact studies. The underlying assumption of these corrections is that climate biases are essentially stationary between historical and future climate states. Under very strong climate change, the validity of this assumption is uncertain, so the practical benefit of bias corrections remains an open question. Here, this issue is addressed in the context of bias correcting the climate models themselves. Employing the ARPEGE, LMDZ and CanAM4 atmospheric models, we undertook experiments in which one centre's atmospheric model takes another centre's coupled model as observations during the historical period, to define the bias correction, and as the reference under future projections of strong climate change, to evaluate its impact. This allows testing of the stationarity assumption directly from the historical through future periods for three different models. These experiments provide evidence for the validity of the new bias-corrected model approach. In particular, temperature, wind and pressure biases are reduced by 40-60% and, with few exceptions, more than 50% of the improvement obtained over the historical period is on average preserved after 100 years of strong climate change. Below 3 C global average surface temperature increase, these corrections globally retain 80% of their benefit. Empirical bias corrections in climate models based on historical data improve future projections of climate change, even in strong change over 100 years, suggest experiments with three climate models.
