Earth Observation in Oracle Cloud: Part 3

  Author: Philip Godfrey

 

What is Earth Observation data?

Earth Observation (EO) data, as defined by the EU Science Hub as data that is “used to monitor and assess the status of, and changes in, the natural and manmade environment”

With human civilization having an increasingly powerful influence on the Earth system, now seemed like the perfect time to explore what can be done with EO data in Oracle Cloud.

How is Earth Observation data captured?

The process of gathering observations of the Earth's surface and atmosphere via remote sensing instruments. The data is typically in the form of digital imagery.

There are many ways to gather this type of information, through various remote sensing platforms. Instantly with Earth Observation we think of space, but this isn’t the case. It can be through Drone / Aerial or Satellites.

Using Earth Observation data in Oracle Cloud

In this blog series, we will explore all around the Oracle world in terms of technology and will utilise a number of Oracle platforms:

The first blog focused on loading the data into the ADW, and creating a machine learning model in Oracle Data Science, if you missed it you can read it here. The second blog focused on understanding model performance and how you can improve machine learning model performance, if you missed it you can read it here. 

The third blog of this series will focus on applying the model against unseen data, storing results back in the ADW.

•      Our journey begins in the Autonomous Data Warehouse (ADW) - to store the data 

•      We then move onto Oracle Data Science – to explore the data and utilise Machine Learning with our Earth Observation data

•      We come back into ADW – to store the results back to the ADW database

•      To enable the business to see the results we can present them in Oracle Analytics Cloud (OAC)

We are going to use the Machine Learning model we’ve created and apply this to an image from our ADW database.

This will return a prediction of what class it believes the image belongs to.

 

Apply the model against an image in ADW

 Applying the prediction suggests the image is most likely to be “River”.

 

Write result back to the database

We can then write back to the database directly from Python in Oracle Data Science.

The code chunks below will insert data into a table “images_results” and will insert:

•      IMG_ID          

•      PREDICTED_CLASS

•      PREDICTED_SCORE

 

Now that code chunk has ran, we can jump back into the ADW and query our newly created table (images_results) and original table (images) to see the result saved in the database.

 

Look out for the next blog which will take us through to the end of this exercise, where we view the outputs of the Machine Learning model in OAC.