Marine dimethyl sulfide (DMS) is important to climate due to the ability of DMS to alter Earth’s radiation budget. However, a knowledge of the global-scale distribution, seasonal variability, and sea-to-air flux of DMS is needed in order to understand the factors controlling surface ocean DMS and its impact on climate. Here we examine the use of an artificial neural network (ANN) to extrapolate available DMS measurements to the global ocean and produce a global climatology with monthly temporal resolution. A global database of 57,810 ship-based DMS measurements in surface waters was used along with a suite of environmental parameters consisting of lat-lon coordinates, time-of-day, time-of-year, solar radiation, mixed layer depth, sea surface temperature, salinity, nitrate, phosphate, silicate, and oxygen. Linear regressions of DMS against the environmental parameters show that on a global scale mixed layer depth and solar radiation are the strongest predictors of DMS, however, they capture 14% and 12% of the raw DMS data variance, respectively. The multi-linear regression can capture more (29%) of the raw data variance, but strongly underestimates high DMS concentrations. In contrast, the ANN captures ∼61% of the raw data variance in our database. Like prior climatologies our results show a strong seasonal cycle in DMS concentration and sea-to-air flux. The highest concentrations (fluxes) occur in the high-latitude oceans during the summer. We estimate a lower global sea- to-air DMS flux (17.90±0.34 Tg S yr−1) than the prior estimate based on a map interpolation method when the same gas transfer velocity parameterization is used.