Here are three files I used during Planet Kaggle Competition. I tuned VGG19 to predict labels in the Planet dataset. I competed solo and scored top 20% in this competition (out of 938 teams). Here's the link for the private leaderboard; you can download the dataset from there too.
https://www.kaggle.com/c/planet-understanding-the-amazon-from-space/leaderboard
Download the dataset from the Kaggle website.
Then, run VGG19_initial.py. A submission file will be produced. Example submission file predictions.csv is also included.
Every minute, the world loses an area of forest the size of 48 football fields. And deforestation in the Amazon Basin accounts for the largest share, contributing to reduced biodiversity, habitat loss, climate change, and other devastating effects. But better data about the location of deforestation and human encroachment on forests can help governments and local stakeholders respond more quickly and effectively.
Planet, designer and builder of the world’s largest constellation of Earth-imaging satellites, will soon be collecting daily imagery of the entire land surface of the earth at 3-5 meter resolution. While considerable research has been devoted to tracking changes in forests, it typically depends on coarse-resolution imagery from Landsat (30 meter pixels) or MODIS (250 meter pixels). This limits its effectiveness in areas where small-scale deforestation or forest degradation dominate.
Furthermore, these existing methods generally cannot differentiate between human causes of forest loss and natural causes. Higher resolution imagery has already been shown to be exceptionally good at this, but robust methods have not yet been developed for Planet imagery.
In this competition, Planet and its Brazilian partner SCCON are challenging Kagglers to label satellite image chips with atmospheric conditions and various classes of land cover/land use. Resulting algorithms will help the global community better understand where, how, and why deforestation happens all over the world - and ultimately how to respond.
To dig into/explore more Planet data, sign up for a free account.
And if you're interested in building applications on Planet data, check out our Application Developer Program.
Getting Started
Review the data page, which includes detailed information about the labels and the labeling process. Download a subsample of the data to get familiar with how it looks. Explore the subsample on Kernels. We’ve created a notebook for you to get started.
https://www.kaggle.com/c/planet-understanding-the-amazon-from-space