This new preprint led by Andrew Brettin introduces a machine-learning framework to better quantify uncertainty in extreme climate events. The proposed ReLU-bias loss quantile neural network (RBLQNN) improves the accuracy and stability of predicted uncertainty ranges, especially for nonlinear and non-Gaussian processes. Tested on synthetic data, temperature extremes from over 1,500 NOAA weather stations, and satellite-observed precipitation, the method outperforms standard approaches and captures complex dependencies that simpler models miss. This work highlights RBLQNN as a powerful, flexible tool for assessing climate hazards and extremes.