Atomospheric Deep Learning
Input -> Bootstraping samples -> training -> Post processing -> Output
In the post processing step, the author utilized:
- local boundary effect
- test time augumentation
- Gaussian smoothing
which derived from Kaggle competition (3rd place)
Deep Learning in general
What Do We Understand About Convolutional Networks?
94 pages overview of Convolutional Nerual Network: from technologies to research scope.
Deep learning in SPPs
Sadeghi, M., A.A. Asanjan, M. Faridzad, P. Nguyen, K. Hsu, S. Sorooshian, and D. Braithwaite, 2019: PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks. J. Hydrometeor., 20, 2273–2289, https://doi.org/10.1175/JHM-D-19-0110.1
Author used CNN to train GOES satellite to map the precipitation from IR band and water vapor channel.
Interepretable Machine Learning/Deep Learning
McGovern, A., R. Lagerquist, D. John Gagne, G. E. Jergensen, K. L. Elmore, C. R. Homeyer, and T. Smith, 2019: Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning. Bull. Amer. Meteor. Soc., 100, 2175–2199, https://doi.org/10.1175/BAMS-D-18-0195.1.
In this article, the authors emphasized the ways of interpretating “black box” model in atmospheric predictions to strengthen descision making.
Deep Learning in Hydrology
A nice review paper, introducing concepts of deep learning and machine learning and also their applications in hydrologic fields.