OCEAN SURFACE AIR-TEMPERATURE DERIVED FROM MULTIPLE DATA SETS AND ARTIFICIAL NEURAL NETWORKS

This paper presents a new method to derive monthly averaged surface ai r temperature, T-a, from multiple data sets. Sea Surface Temperature ( SST) from the National Centers for Environmental Prediction (NCEP) and total precipitable water (W) from the SSM/I sensor are used as inputs to Artificial Neural Networks (ANN). Surface air temperature (T-a) me asurements from the Surface Marine Data (SMD) are used to develop and evaluate the methodology. When globally evaluated with SMD data, the b ias of the new method is small (0.050 degrees C +/- 0.26 degrees C), a nd the accuracy expressed as root-mean square (rms) differences has a small global mean (0.73 degrees C +/-. 0.37 degrees C). These biases a nd rms differences are smaller than those obtained using NCEP reanalys es and TIROS Operational Vertical Sounder (TOVS) data products. When e valuated with the TOGA-TAO array measurements over the tropical Pacifi c, the ANN mean bias and rms differences have similarly small values: 0.37 degrees C and 0.61 degrees C, respectively.