Back to All Events

Webinar: Machine Learning for filling missing Hydrological Data with Python, Keras y Tensorflow - Free - March 26 2019

FillMissingPrecipitationDatawithMachineLearningwithPythonandKeras.png

Registration available till March 25 at 5pm ET (New York time)

Evaluation of hydrological processes as evapotranspiration, runoff, stream routing and infiltration require data as precipitation, flow, temperature and radiation on a daily or hourly basis. Required data for a hydrological model need to be accurate and must be completed over the period of study in order to perform the simulations. Sometimes precipitation data from a station is incomplete in several parts, however it is possible to fill the missing hydrological data with numerical methods from artificial intelligence.

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.

Content

The webinar has the following content:

  • Introduction to Python and Neural Networks.

  • Import precipitation data as Pandas dataframe.

  • Representation of historical data.

  • Generate discrete time series as input data.

  • Correlation analysis with Seaborn.

  • Scaling precipitation series with Sklearn.

  • Create neural network with Keras and Tensorflow.

  • Analysis of predicted and registered values

  • Fill missing precipitation data.

Schedule

The webinar will be perfomed held at:

March 26 at 11 am ET (New York time)

Estimated duration: 1h 45m.


About the speaker

Saul Montoya M.Sc.

Mr. Montoya is a Civil Engineer graduated from the Catholic University in Lima with postgraduate studies in Management and Engineering of Water Resources (WAREM Program) from Stuttgart University – Germany with mention in Groundwater Engineering and Hydroinformatics. Mr Montoya has a strong analytical capacity for the interpretation, conceptualization and modeling of the surface and underground water cycle and their interaction. 

He is in charge of numerical modeling for contaminant transport and remediation systems of contaminated sites. Inside his hydrological and hydrogeological investigations Mr. Montoya has developed an holistic comprehension of the water cycle, understanding and quantifying the main hydrological dynamic process of precipitation, runoff, evaporation and recharge to the groundwater system. 


Participation

The webinar is free and will be held trough a private Youtube streaming. Questions on text can be written on the video chat, and voice questions will done trough Whatsapp.

Level: Beginner. No prior knowledge is required.

To participate, complete the following two requirements:

1. Fill in the form at the bottom

2. Send the screenshots to saulmontoya@hatarilabs.com , as indicated in this video:

Download Anaconda 3: https://www.anaconda.com/distribution/


Registration

Name *
Name