Part-1: Detecting, classifying and characterizing weather and climate patterns is a fundamental requirement to improve our understanding of extreme events, their formation and how they may change with global warming. These tasks, however, remain challenging across all classes of weather and climate pattern, and especially for extreme events. Deep Learning has revolutionized solutions to pattern recognition problems resulting in tremendous advances in computer vision, speech recognition, robotics and control systems. In this presentation we show how deep learning is similarly impactful in climate science, especially in recognizing complex weather and climate patterns. We present results on the methodology, performance and scaling and lessons learned both on the science and the computations. We also highlight some grand challenges and opportunities.
Part-2: Predictive modeling of complex, nonlinear, high-dimensional dynamical systems such as atmospheric convection are crucial for building reliable and accurate weather and climate models. Deep generative models have recently been successful in learning the underlying statistics of complex physical processes from large amounts of data. However, their success in predicting physical systems have been limited, primarily because they do not require physical consistency. By integrating physics constraints and desirable statistical properties into an emerging class of deep generative model called Generative Adversarial Networks (GANs), we develop a new paradigm for modeling complex dynamical systems. We present preliminary results on the methodology and performance of this model from simple test cases to complex chaotic processes of relevance to weather and climate modeling.