The result of the comparison of two images showing different levels of contamination. The brightest parts are where it shows differences. This image corresponds to Central and part of South America, perhaps in some parts the contamination levels are not so evident since the industrial activity is not so big and just for that reason high levels should be avoided.
What was your approach to developing this project?
The main focus was the problem of pollution levels in Latin America, since the region has a high level of NO2. The data from the special agency was used to take the images as a sample using artificial intelligence to compare the images
- What tools, coding languages, hardware and software did you use to develop your project?
We used NASA and ESA data specifically from the Sentinel-5p satellite.
For image analysis, Python programming language and cv2 library
In our research we can provide a number of possible solutions such as:
Implement the measures for the use of SCR catalysts in diesel engines in a mandatory way to all the automotive industry, propose it to the OAS and have it implemented by the different environmental institutions of the governments, so that at the end of the pandemic we can reduce the emissions. An SCR catalyst is a device located in the exhaust systems of cars and when the gases produced by combustion reach this area, a series of chemical reactions occur, after these reactions water (H2O), nitrogen and some carbon dioxide (CO2) are produced, as we can imagine this catalysts are not new were developed in 1957 and new studies by the European Commission have led to improvements in them which has led to demonstrate that this technology if used in the right conditions is an effective tool in combating harmful emissions.
By means of an indicator, we can make mathematical models with linear regression which would create a time line where the production of these agents is graphed and we can look for optimal solutions in each region. For this, an AI-based algorithm will be used for this analysis.
- How did you use the space agency data in your project?
As we know because of covid-19 there are many changes that happened on the planet, but some changes are not visible to the naked eye we found it very difficult to verify images and know for sure if there were changes so we decided to implement simple programming to know if the images really had changes and we used Python programming language specifically the CV2 library to compare images and look for the minimum change and create a new image with only the changes that have between them with this we know for sure if the image has changes even if they are minimal imperceptible to the eye this is achieved because this library of Python can subtract pixels and can detect any change between images that we would normally take longer to decipher thanks to this we could see changes easily.
What inspired your team to choose this challenge?
The constant worry and anxiety that we lived day by day seeing how the planet earth in which is our home battles with the constant pollution produced in a great majority by us humans.
That is why the initiative to create possible solutions to this chaos was born, relying on data provided by different entities maps of tropospheric concentrations, so that based on different observations made by satellites to determine the regions that by the nature of their industries and others are more likely to produce substances such as carbon dioxide adversely affecting our environment.
- What problems and achievements did your team have?
One of the biggest problems that we did not know the magnitude and different types of data that we had to analyze, was not knowing where to start, the ignorance of not knowing how to handle the different platforms and libraries to be able to give a good analysis to the data provided by different entities. Another point that caused us quite a lot of trouble was to choose a topic that we didn't know in part because we were trying to find or devise some compound to inhibit NO2 substances, something that we couldn't do in such a short time and even less without advanced knowledge in chemistry so we gave a twist to the possible solution, trying to find laws that regulate countries that are more likely to pollute the environment through their industries and so on.
The time factor cannot be left behind since it was one of the biggest causes of despair in our group, causing us not to advance at a good pace.
One of the biggest achievements for us as a team was to agree on a theme to move forward, to improve communication as a team, because thanks to that all team members managed to see the same goal, and looking for the same solutions to our problems.
Another achievement was to enrich ourselves in the subject, achieving a better understanding of the factors that most influenced the pollution and from that point on we could then provide solutions to our problems.
As we know because of covid-19 there are many changes that happened on the planet, but some changes are not visible to the naked eye we found it very difficult to verify images and know for sure if there were changes so we decided to implement simple programming to know if the images really had changes and we used Python programming language specifically the CV2 library to compare images and look for the minimum change and create a new image with only the changes that have between them with this we know for sure if the image has changes even if they are minimal imperceptible to the eye this is achieved because this library of Python can subtract pixels and can detect any change between images that we would normally take longer to decipher thanks to this we could see changes easily.
MAP EASA