Determining if something is currently, and also likely to remain, structurally stable is a common engineering task.  Consider this water tower. Clearly it currently is not stable.  Rather, this tower is in free fall.  

<img src="https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/blocks-watertower.png" width="320">

In this Kaggle we will attempt to predict the structural stability of block buildings that I render with Blender and used simulated physics to determine the stability.  The data set is made up of many different buildings, built from a simulated set of wooden building blocks.  Your task is to predict if the building is stable or not.  Consider the following stable building.

<img src="https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/blocks-stable.png">

If I were to run the simulated physics in Blender, the appearance of this building would not change much.  There might be some minor settling; however, there would be no significant shift in the positions of the blocks.  However, not all of my block buildings are stable, consider the following unstable building.

<img src="https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/blocks-unstable.png">

Can you see the source of the instability?  Look closely at the bottom row of blocks and how the four ceiling green blocks are supported.  If we run the physics simulation for a second, look at what happens.

<img src="https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/blocks-falling.png">

Clearly the building is not stable, it would nearly completly collapse.  Can you predict which buildings are stable just from then opening picture?

There are other complexities in the data as well.  Different images will have different angles and lighting of the buildings.

<img src="https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/blocks-samples.png">

Also, not all block structures are the same basic shape.  However, all block structures are built from the same basic types of blocks.