Using ML to predict the weather and climate risk

Опубликовано 19 января 2023, 17:00

Notebook with ⛈️ weather prediction code → goo.gle/3WiqVqV
Article for this episode → goo.gle/3iLYxzT
Notebook with 🛰️ code to connect model back to Earth Engine → goo.gle/3Fg5rWV

Welcome back to People and Planet AI, where we explore how machine learning helps us understand the biological variety and variability on Earth. In this episode, we show how we can use machine learning to predict the weather and analyze climate change. Watch to learn how predictive models, neural networks, and satellite images are used to make weather predictions!

Chapters:
0:00 - Intro
1:04 - The challenge of computing weather modules
1:42 - How does deep learning work?
2:16 - Example of deep learning / neural network
3:21 - MetNet forecasting
4:05 - Google AI for Weather and Climate
5:43 - Designing for inputs (data) and outputs (labels)
7:12 - Combined data set extracted
8:56 - Data stored
9:06 - Model building
10:41 - Training the model in Vertex AI and saving it to Cloud storage
11:07 - What’s next?

Resources:
• 8mins on the ML algorithm we use in our series → goo.gle/3DarY4P
• Google weather project → goo.gle/3GALFpO

Google resources:
• How to start a Google cloud project - $300 free trial link → goo.gle/3WmKUF5
• Earth Engine → goo.gle/3GKk9EG
• Colab (interactive notebooks) → goo.gle/3CTYLJy
• Free course by Google on Data Preparation and Feature Engineering in ML → goo.gle/3tqYwCa
• Data normalization → goo.gle/38SMZCd
• Folium (open source Python library for interactive maps) → goo.gle/3kSHTNi
• Vertex AI → goo.gle/3ks3azx
• Autopackage feature in Vertex AI → goo.gle/3IZHULS
• TensorflowKeras → goo.gle/3CVC2gf
• Cloud Run (web app hosting) → goo.gle/3ZOChpx
• Hosting a website on Google Cloud using Cloud Run → goo.gle/38QoIg8

People and Planet AI playlist → goo.gle/PeopleAndPlanetAI
Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech​

#PeopleAndPlanetAI