The predictive skill of hydrologic variables such as streamflow and soil moisture in North Central Texas has improved substantially over the last decades. However, significant biases may be present during extreme events such as droughts and flooding. In this study, we optimize prediction of drought indices such as the Standardized Precipitation Evapotranspiration Index (SPEI) using Artificial Neural Network (ANN) models for the north Texas region. Improving prediction of drought conditions enables more effective reservoir management in terms of water resource and energy efficiency during regional weather and climate anomalies. Multiple ANN models of different network architectures were trained and tested utilizing data from 1915-2012 and 1950-2012, with 70% of available data used for model training and the remaining for validation. The network architectures with the smallest prediction error were applied further in this study. The input data comprised regional climate variability observations of minimum temperature, maximum temperature, total precipitation, average wind speed, evapotranspiration, and potential evapotranspiration. The global climate indices investigated included the Atlantic Multidecadal Oscillation, the Pacific Decadal Oscillation, the North Atlantic Oscillation, the Bivariate El Niño Southern Oscillation, the Southern Oscillation Index, and other regional indices. These indices were used to evaluate their respective ability to improve predictive skill during climate anomaly extremes, e.g., El Niño and La Niña conditions. The choice of climate indices were varied as input into retrained ANN models of the same network architecture, so that the improvement due to each climate index could be ranked and less-influential climate indices could be excluded. The selected ANN model architecture and chosen input data were then applied to produce 12 month-ahead predictions of monthly drought indices in order to evaluate the overall predictive skill of the generated ANN models.