# HOW TO PARTICIPATE

To make a submission, complete the [submission form](https://www.kaggle.com/page/environmental-insights-explorer-submission-form). Only one submission will be judged per participant, so if you make multiple submissions we will only review the most recent entry.

**To be valid, a submission must be contained in one or more notebook, and made public on or before the submission deadline. Participants are free to use any datasets in addition to the [official Kaggle dataset](https://www.kaggle.com/c/ds4g-environmental-insights-explorer), but those datasets must also be publicly available on either Earth Engine or Kaggle for the submission to be valid.**

# SUBMISSIONS WILL BE EVALUATED ON THE FOLLOWING

**Documentation** 

* Is the code documented in a way that is easily reproducible (i.e. thorough comments, organized notebook, clear scripts/code)?
* Does the notebook narrative clearly state all assumptions that are factored into the value and the potential impact of fluctuations? (i.e. Which plants / fuel types did the author use for their analysis, and why?)
* Does the notebook contain data visualizations (e.g. time graphs, etc.) that help convey the author’s findings and/or recommendations? 
* Did the author upload and properly cite all files for any supporting datasets that were used for their analysis?


**Recommendation**

* Did the author write a compelling and coherent narrative explaining their rationale for the scalability and accuracy of their model and recommendation?
* Does the recommendation include an explanation of what data/assumptions could be substituted to produce the value for another geospatial area or location?
* Is there documentation about the pros and cons of the model, and the geographic nuances that may have impacted the emissions factor?
* Does the explanation convey why/how this model improves current emissions factors calculations? 
* Does the recommendation indicate other datasets/factors/assumptions (and why) that could be useful to include to make future emissions factor calculation methodologies more robust?


**Accuracy**

* Does the model produce a value for the an annual average historical grid-level electricity emissions factor (based on rolling 12-months of data from July 2018 - July 2019) for the sub-national region?
* Bonus points for smaller time slices of the average historical emissions factors, such as one per month for the 12-month period.
* Bonus points for participants that develop a methodology to calculate a marginal emissions factor for the sub-national region using the provided datasets.