Accurate water level forecasts are of vital importance along the Texas coast as the waterways of the northern Gulf of Mexico play a critical economic role for a number of industries including shipping, oil and gas, tourism, and fisheries. While astronomical forcing tides are well tabulated, water level changes along the Gulf coast are often dominated by meteorological factors which impact is often larger than the tidal range itself and unaccounted for in present forecasts. In particular, wind forcing was identified as the principal input absent in the current prediction models. As part of a collaborative effort between the National Weather Service Corpus Christi office, Texas A&M University-Corpus Christi, and Texas A&M University-College Station, data from the NCEP MesoEta model is obtained and used as part of the input to a neural network based prediction model. The neural network model predicts short-term, up to 48 hours, water levels along the coast of Texas based on previous water levels, wind speeds and barometric pressure as well as forecast data from the NCEP MesoEta. The neural network model was successfully tested using historical data for the inlet of Galveston Bay, Texas and the Corpus Christi Ship Channel near Port Aransas, Texas. By the end of 2002, it is expected that the model will produce real-time water level forecasts with dissemination via the World Wide Web. Examples will be presented which illustrate the performance of the neural network model, including a comparison to data from tide tables and a simple linear model.