摘要：Net heat flux (Qnet) and its components from four reanalysis (NCEP‐2, CFSR, ERA5, and MERRA) and two blended products (OAFlux & TropFlux) are compared with in situ observation (two Research Moored Array for African‐Asian‐Australian Monsoon Analysis and Prediction buoys and one Woods Hole Oceanographic Institution buoy) over the north Indian Ocean to quantify their uncertainties in daily, seasonal, and annual scales. These comparisons provide the present status of Qnet error in most state of the art reanalysis/blended products. The root‐mean‐square error (RMSE) remains similar to the RMSE a decade earlier, despite more observation and improved models and reanalysis methods. However, there is a clear separation of flux quality from the older generation of reanalysis (NCEP‐2) to the newer production of reanalysis (MERRA, CFSR, and ERA5). While individually ERA5 provides the best estimate, the ensemble mean (i.e., average of ERA5, CFSR, MERRA, TropFlux, and OAFlux) is very close to ERA5 both in terms of correlations and RMSE and provides the most reliable estimate by virtue of removal of some of the uncertainties in estimation of flux by each of the flux products. A significant reduction of RMSE in Qnet estimates from 100 W/m 2 (in NCEP‐2) to 45 W/m 2 (in the ensemble mean) is considerable progress. It is noteworthy that all the recent flux products estimate the increasing trend of Qnet in the north Bay of Bengal and subseasonal fluctuations with significant fidelity. Also, in the south of equator location vigorous subseasonal fluctuations in boreal winter are well captured. We believe that this is significant progress in the estimation of Qnet over the Indian Ocean.
