SANSA AWS Informal Settlements in South Africa by #ZindiWeekendz
Use high resolution satellite imagery from urban South Africa to identify the locations of informal settlements
Prize
$1,000 USD
Time
Ended over 2 years ago
Participants
77 active ยท 184 enrolled
Helping
South Africa
Computer Vision
Government
Description

During the COVID-19 crisis, it is more critical than ever for governments to be able to identify the locations of informal settlements. Knowing where informal settlements are located will help governments make more appropriate policies and ensure that all people have access to the services they need. Satellite imagery can help do this at scale across the country.

The South African National Space Agency (SANSA) collects high-resolution satellite imagery from a number of international earth observation satellites. A machine learning model trained on this imagery would help SANSA to locate informal settlements more efficiently, providing the South African government with up-to-date information about the location and size of informal settlements.

In this hackathon, you’re invited to use SANSA’s high-resolution satellite imagery to develop a machine learning model to identify whether an image of an area in South Africa contains informal settlements or not. All participants will use Amazon AWS virtual machines (VMs) to access the data and do all their work during the hackathon.

Only 300 data scientists will be able to participate in this hackathon.

The hackathon opens on Friday 12 June 2020 12:00 GMT.

We have removed the secret code so anyone may sign up now and throughout the weekend. Spaces will be filled on a first-come-first-serve basis.

Everyone who registers for this hackathon will receive an email with a unique code and instructions to access their assigned virtual machine on AWS for the weekend. If you have not received this code by 12 June 12:00PM GMT, please email us at zindi@zindi.africa.

This hackathon is sponsored by SANSA and Amazon.

About #ZindiWeekendz

The Zindi community is joining the fight against COVID-19! #ZindiWeekendz are virtual weekend hackathons hosted by Zindi. This series focuses specifically on COVID-19.

In a time of lockdowns, remote work, and general uncertainty, #ZindiWeekendz hackathons offer data scientists the opportunity to continue to develop their skills while contributing to practical, open-source AI solutions to help in the battle against COVID-19.

All winning solutions will be shared as a public good on GitHub. We are committed to supporting partners to implement these solutions and encourage anyone who is interested to reach out to us at zindi@zindi.africa.

About SANSA (sansa.org.za):

The South African National Space Agency promotes cooperation in space-related activities, fosters research in space science, advances science and engineering through human capital development, and works toward an environment conducive to industrial development in space technologies within the framework of national government policy. The intent is to converge and optimise resources and maximise the benefits of space services and applications to society.

SANSA has six thematic areas, namely Earth Observation, Space Operations, Space Science, Space Engineering, Human Capital Development and Science Advancement. The Earth Observation programme focuses on providing and using satellite imagery for societal benefit, and to support key government planning, decision-making, and outcomes. Data from SANSA Earth Observation is also increasingly finding wide applications in environmental issues such as climate change. You can learn more about SANSA at www.sansa.org.za.

About AWS (aws.amazon.com):

For 14 years, Amazon Web Services has been the world’s most comprehensive and broadly adopted cloud platform. AWS offers over 175 fully featured services for compute, storage, databases, networking, analytics, robotics, machine learning and artificial intelligence (AI), Internet of Things (IoT), mobile, security, hybrid, virtual and augmented reality (VR and AR), media, and application development, deployment, and management from 76 Availability Zones (AZs) within 24 geographic regions, with announced plans for nine more Availability Zones and three more AWS Regions in Indonesia, Japan, and Spain. Millions of customers - including the fastest-growing startups, largest enterprises, and leading government agencies - trust AWS to power their infrastructure, become more agile, and lower costs. To learn more about AWS, visit aws.amazon.com.

Rules

Teams and collaboration

You may participate in this competition as an individual or in a team of up to four people. When creating a team, the team must have a total submission count less than or equal to the maximum allowable submissions as of the formation date. A team will be allowed the maximum number of submissions for the competition, minus the highest number of submissions among team members at team formation. Prizes are transferred only to the individual players or to the team leader.

Multiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be disqualified.

Code must not be shared privately outside of a team. Any code that is shared, must be made available to all competition participants through the platform. (i.e. on the discussion boards).

Datasets and packages

The solution must use publicly-available, open-source packages only. Your models should not use any of the metadata provided.

You may use only the datasets provided for this competition. Automated machine learning tools such as automl are not permitted.

Image metadata (Image size, aspect ratio, pixel count, etc) may NOT be used in your solution. Coordinates or other location information may NOT be used in your solution either.

You may use pretrained models as long as they are openly available to everyone.

The data used in this competition is the sole property of Zindi and the competition hosts. You may not transmit, duplicate, publish, redistribute or otherwise provide or make available any competition data to any party not participating in the Competition (this includes uploading the data to any public site such as Kaggle or GitHub).

You may use the data ONLY on your AWS virtual machine. You are strictly prohibited from copying or sharing any of the datasets provided for this competition.

You must notify Zindi immediately upon learning of any unauthorised transmission of or unauthorised access to the competition data, and work with Zindi to rectify any unauthorised transmission or access.

Your solution must not infringe the rights of any third party and you must be legally entitled to assign ownership of all rights of copyright in and to the winning solution code to Zindi.

Submissions and winning

You may make a maximum of 30 submissions per day. Your highest-scoring solution on the private leaderboard at the end of the competition will be the one by which you are judged.

If your solution places 1st, 2nd, or 3rd in the final ranking, you will be required to submit your winning solution code to us for verification and you thereby agree to share your code on GitHub as a public good to the sector. We also encourage all participants to share their solutions on GitHub.

You will have until 17:00 GMT on Wednesday 17 June 2020 to submit your code for review. Submit your code to zindi@zindi.africa with subject line "Challenge name position # - team name or username" Regardless of any public announcement of winners, Zindi reserves the right to disqualify any user, team if the code does not reproduce the winning submission.

Zindi maintains a public leaderboard and a private leaderboard for each competition. The Public Leaderboard includes approximately 50% of the test dataset. While the competition is open, the Public Leaderboard will rank the submitted solutions by the accuracy score they achieve. Upon close of the competition, the Private Leaderboard, which covers the other 50% of the test dataset, will be made public and will constitute the final ranking for the competition.

If you are in the top three at the time the leaderboard closes, we will email you to request your code. On receipt of email, you will have 48 hours to respond and submit your code following the submission guidelines detailed below. Failure to respond will result in disqualification.

If two solutions earn identical scores on the leaderboard, the tiebreaker will be the date and time in which the submission was made (the earlier solution will win).

The winners will be paid via bank transfer, PayPal, or other international money transfer platform. International transfer fees will be deducted from the total prize amount, unless the prize money is under $500, in which case the international transfer fees will be covered by Zindi. In all cases, the winners are responsible for any other fees applied by their own bank or other institution for receiving the prize money. All taxes imposed on prizes are the sole responsibility of the winners.

You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these rules. Entry into this competition constitutes your acceptance of these official competition rules.

Please refer to the FAQs and Terms of Use for additional rules that may apply to this competition. We reserve the right to update these rules at any time.

Evaluation

The evaluation metric for this challenge is Log Loss.

The values can be between 0 and 1, inclusive.

ID        Label
A1BZQJG     0
EAYTGHU     1
MHGWJNO     0
Prizes

1st: $500

2nd: $300

3rd: $200

Timeline

Competition closes on 14 June 2020.

Final submissions must be received by 11:59 PM GMT.

We reserve the right to update the contest timeline if necessary.