Van Veen

Sao Jose dos Campos, Sao Paulo State | Measuring the Value of Earth Observations

Machine Earthing

High-Level Project Summary

Decisions made based on satellite data affect our lives daily, from farming to weather forecasting, but how can we tell how beneficial these decisions are? We propose a machine learning algorithm that will judge how beneficial they can be. It will be able to learn which factors are most relevant for each situation. After assisted training, the algorithm will evaluate the decision on a scale from 1 to 5, and based on previous data will define how beneficial the action was. The importance remains on the self-learning factor, which after training, allows it to establish relationships between factors that are not always considered in the human evaluation due to their complexity.

Link to Project "Demo"

https://linktr.ee/VanVeen

Link to Final Project

https://yasminmarrie8.wixsite.com/hackathon-van-veen

Detailed Project Description

Through much effort, dedication, and specific knowledge, experts in many different fields interpret satellite data daily to make decisions that benefit our society. However, due to the enormous amount of types, sources, and variables in this data, judging how beneficial an action is can be extremely complex. That’s due to many factors that influence this analysis may not be considered in a human evaluation. A machine, meanwhile, after a supervised training process and many tests, may find a connection between the relative humidity of the air and combating deforestation, for example.

We propose an algorithm that will be trained to have an accurate perception of which distinct factors characterize a successful decision, regardless of which category belongs to or which variables are included in the process. To accomplish this, it will need to be submitted to the training process, which consists of having access to the database used to make the decision and a score given by professionals for the same action. During the training phase, the algorithm will identify which factors are most relevant for a successful action. Once will be capable of measuring how beneficial a decision was without the use of external sources. We intend to use ‘’Python’’ combined with libraries like “Pytorch” to build the algorithm.

Space Agency Data

We used mainly the data provided in NASA's open database, learn more about the amount and diversity of data that is collected by means of satellites and the various fields that are covered. Also, based on the ESA and INPE, where we could see the similarities between different institutions and space agencies and how our proposal could be of great help to them. Through the analysis between them, it was possible to identify and choose how we would act to solve the proposed challenge.

Due to the analysis of data from satellites that are available in open databases and academic articles that used the same sources, it became possible for us to develop our proposal: the best way to measure how efficiently the satellite data were used. We primarily used global surveys and data that worked in different fields, from agriculture, health, security, and economics. We found that several factors influence the data capture and that due to data complexity and extension, without the use of a method that guarantees veracity and practicality, it could be unfeasible. Our proposal it’s developing an algorithm based on machine learning technology capable of adapting in different areas found on NASA databases, consequently, evaluate the actions taken based on the data collected.

Hackathon Journey

We believe that the opportunity to participate in Space Apps was something unique and innovative for everyone. The long hours of teamwork, as well as the stages we had to go through as a team, made us all different people by the end of the hackathon. We learned about perseverance, teamwork, dedication, and we believe these are essential qualities for both a person and a professional. The challenge in question is a topic that we as a team have an avid interest in, first, because of its high potential of being able to act on global issues in different ways, such as the environment. We decided to base on the difficulties that different institutions could share between them, through the analysis, we could notice a certain lack in a particular field and we were able to develop our proposal in response to the challenge.

The setbacks and challenges were only possible to be solved through a long time of dedication and communication between the team members, the essential help of the mentors who were always available, supporting and encouraging us during the whole process. We would like to express our gratitude to everyone, especially to the mentors, who advised us where possible, and to our colleagues through the exchange of experiences that made it possible to complete the Space Apps Challenge.