Hydrological Modeling using Google Earth Engine (LSTM) and Long Short Term Memory (LSTM) ML Model 

🌊📈 Welcome to this tutorial! This training was given by Biplov Bhandari on Aug 10 for the SERVIR Amazonia TensorFlow Training in Peru (Aug 8 - Aug 11) 🇵🇪.
For all the training materials, check out the links: [github.com/SER...] and [developmentsee...]. Now, let's dive into what this tutorial is all about! 💧🔍
In this notebook, we will walk you through a step-by-step example of accessing observed and forcing data for hydrologic modeling. We will also demonstrate how to train a powerful Long-Short-Term Memory (LSTM) model to simulate streamflow. 💧🚀 To do this, we will leverage the capabilities of Google Earth Engine (GEE) to access meteorological data as inputs for our model. 💡🛰️
Our example is inspired by the following paper: "Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks". 📚🌧️ Let"s dive in and get started with the exciting world of hydrologic modeling and LSTM networks! 🌊📊 The notebook was originally developed by Kel Markert and now modified by Biplov Bhandari for this training tutorial.
Access the full notebook here: [nbviewer.org/g...]. Feel free to click "Open in Colab" if you're excited to run it locally. 📑💻
Don't miss out on this opportunity to enhance your skills and understanding! 🌊🔗
#hydrology #googleearthengine #datascience #streamflow #serviramazonia #tensorflow #peru #lstm #ml #servir #machinelearning #eo