README for MSLNet Predicted Classes
-----------------------------------

This bundle contains a collection of image classification predictions
for images taken by the Mars Science Laboratory (MSL) mission that
were made by a machine learning model (MSLNet), along with the
posterior probability associated with each prediction.  The images
include observations by the Mastcam and MAHLI instruments on MSL.

Bundle contents
---------------

There is one collection, called 'data'.  Inside the 'data' directory
is a .csv file that contains the predictions for each image product.
Fields include the image filename, its predicted class (as a numeric
index), its predicted class (as a human-readable string), the
posterior probability of the prediction, and the model version that
was used to generate the prediction.

Methods
-------

For information on how the machine learning model (a convolutional
neural network) was trained and evaluated, see reference [1] below.

Citation
--------

If you use the contents of this bundle in your own work, please
include this citation:

Kiri Wagstaff, Steven Lu, Kevin Grimes, Jesse Cai, Raymond Francis,
and Jake Lee. (2020). MSL Predicted Classes (Version 1.0) [Data
set]. http://doi.org/10.17189/5kvw-tp63/

References
----------

1. Mars Image Content Classification: Three Years of NASA Deployment
and Recent Advances.
Kiri Wagstaff, Steven Lu, Emily Dunkel, Kevin Grimes, Brandon Zhao,
Jesse Cai, Shoshanna B. Cole, Gary Doran, Raymond Francis, Jake Lee,
and Lukas Mandrake.
Proceedings of the Thirty-Third Annual Conference on Innovative
Applications of Artificial Intelligence, p. 15204-15213, 2021.
  https://wkiri.com/research/papers/wagstaff-pds-classifier-21.pdf

--------------------------------------------------
Contact: Kiri Wagstaff, Jet Propulsion Laboratory,
kiri.wagstaff@jpl.nasa.gov

Team: Kiri Wagstaff and Steven Lu

Funding: NASA Planetary Data System