Webinar: Machine Learning for filling missing Hydrological Data with Python, Keras y Tensorflow - Free - March 26 2019
Keras is a high level platform for neural networks in Python. This platform is focused on fast experimentation on input data. Keras supports convultional networks, recurrent networks and their combination. In addition, Keras runs seamlessly on CPUs, GPUs and andavanced multiprocessor computers.
The advantage of machine learning libraries as Keras in Python scripts is the practical way to manage the data, the configuration options, the processing capacity and the input/output representation from huge datasets.
This webinar shows the complete process to create a neural network in Keras with a Tensorflow backend done to fill missing precipitation data for a station based on the records from neighboring stations. The scripting is done with Python 3, Keras and Tensorflow on a Jupyter Notebook. The webinar describes Keras commands for the creation, trainning and prediction of a neural netowork, as well as tools in Python for data import and analysis.