ESA Summer of Code in Space (SoCiS) 2016 Projects
IMS Project Introduction
The Italian chapter of the Mars Society (IMS) is spearheading the European MaRs Analog Station for Advanced Technologies Integration project (ERAS). ERAS’ main goal is to provide an effective test bed for field operation studies in preparation for human missions to Mars. We are currently working on an immersive virtual reality simulation of the ERAS Station (V-ERAS). The major advantage of such virtualization is that it will be possible to undertake training sessions with a crew that can interact with its future environment before the actual station is built. A relevant part of the software supporting V-ERAS has been developed by students during summer of code events. A key point for the development of the ERAS project is the study of all the Mars phisics parameters and data which can effect the future human missions to Mars and which are included in the V-ERAS environment for the purpose of a more detailed development of the simulated Mars environment.
- IRC #veras channel on Freenode
- ERAS mailing-list
- ERAS repository on bitbucket
- The ERAS software documentation
- ERAS on twitter
- SOCIS 2015
- GSOC 2015
The IRC channel is informal and typically a question will be part of a time-limited conversation. On the mailing-list more users/developers will have a chance to comment on the question and the question will receive more feedback over time.
Before a question is posted to the mailing-list care should be taken to construct a useful question. Simple guidelines for questions on the mailing-list:
1. Limit the scope of the questions.
2. Briefly state what is to be accomplish.
3. Give a small example embedded in the question.
4. Clearly state the question in the context of the simplified problem.
5. It is ok to link original code (or attach) as a reference but it should not be required to answer the question.
Mentors will be in a position to help dig through the project code. To get the highest probability of a timely and useful answer the above recommendation should be used when posting to the mailing-list.
Writing Your socis Application
In writing your application refer to the SOCIS documentation on line :
Programming Domain Knowledge
1. Solar Storms Forecasting Server
DIFFICULTY LEVEL: INTERMEDIATE / HARD
Solar storms can cause problems to satellite communication, and damage space electronic equipments. The storms have to be taken into account also for EVA and habitat maintenance activities, as the higher levels of radiation brought by them have a detrimental effect on the crew member’s health. Prediction of these storms are essential to prevent these damage also in view of a manned exploration of Mars.
A lot of astronomical data is generated on a daily basis, and this could be used in conjunction with machine learning methods like Artificial Neural Networks to predict solar storms.
In this project, the student will be required to:
- Predict solar storms according to a chosen model
- Provide real time information about it on a web page
The first task foreseen for the project is to research on the raw astronomical data available on internet. That source of data has to be chosen which would provide with continuous and reliable data. For this purpose, sources like SWPC (Space Weather Prediction Centre ) at NOAA (National Oceanic and Atmospheric Administration) can be used. Features which would be used for the machine learning approach would also need to be decided at this stage.
These features are for example:
- Radio flux
- SESC spot number
- Sunspot area
- New regions
- X-Ray background flux
Using this astronomical raw data, a machine learning Artificial Neural Network model has to be trained. For this, either TensorFlow or PyBrain can be used to allow the training using the Python language.
The final stage of the project consists in connecting a realtime server with this model, so that once the model has been trained, the predictions can be made in real time.
Interfaces would need to be developed to allow showing historical values also.
Tango servers will also need to be developed to link the model with the ERAS ecosystem.
- Choice of the framework for ANNs and collecting sourcing for raw data
- Analysis of features currentely used for Solar Stomr prediction
- Build and completion of sources modules for all the raw data
- Training of a first model in the chosen framework
- Training of a ANN model using the raw data.
- Optimisation phase of the model
- Project documentation writing
- Building of the Tango module
- Backend information storage by means of Django/Flask
- Display model predictions in real time.
Benefits to ERAS
The new algorithm on solar storm forecast will be used inside ERAS to analyse data on solar storms which could have affect on the mission operations carried out in the ERAS station and in the virtual simulated environment V-ERAS. The realtime information on the solar forecast will be displayed on the ERAS web site.