With a scientific foundation spanning multidisciplinary areas like Machine Learning, Deep Learning, Neural Networks, Computational Mathematics, and Optimization, my objective is to leverage these methodologies to tackle real-world challenges, providing effective and practical solutions. I've applied my expertise across diverse domains, ranging from data-driven weather forecasting, precipitation nowcasting, learning solutions to dynamical systems and brain decoding. My contributions have encompassed tasks like, nonlinear system identification, parameter estimation, image/video segmentation, learning from partially labeled streaming data, domain adaptation, transfer learning, as well as various forms of supervised, unsupervised and semi-supervised learning. Primarily, my focus has been on pioneering advanced deep machine learning models which hold immense potential for widespread application across sectors such as Weather, Climate, Energy, Health, Robotics, Neuroscience, and beyond.