High-Level Project Summary
This solution brings historical data to life from the outset with additional parameters thanks to algorithms and predictions with additional functions (e.g. adds to the existing data information about the depth of occurrence, correlation and seismic work in one environment of each apparatus on the moon (geological surveys) Equipment, conditions To test gases chemical and geological), as well as objects in the vicinity of the Moon, this solution also allows you to make forecasts, which, after an in-depth analysis of the machine school, predictive algorithms, neural sulfur, i.e. all data indicate the potential presence of minerals in addition to the basic functions indicated in the task.
Link to Final Project
Link to Project "Demo"
Detailed Project Description
This solution revives historical data from the very beginning with additional parameters thanks to algorithms and predictions with additional functions (e.g. adds to the existing data information about the depth of seismic occurrence, correlation and operation in one environment of each apparatus on the Moon (geological research equipment, conditions For the study of chemical and geological gases, as well as objects in the vicinity of the moon, this solution also allows you to make predictions that indicate after an in-depth analysis of all data on the potential occurrence of a given mineral.
It uses advanced machine learning, predictive algorithms and machine learning in Big Data datasets and devices, e.g. thermovision, IoT devices.
We worked on an advanced GIS program supported by AI, ML, DL, BI, which allowed us to connect to databases and work on them using API and Data Warehouses.
The solution easily integrates any type of data and shares this data with AI for planning subsequent lunar missions.
What exactly does it do?
Use the local stations from the Apollo warehouse and send them to Earth.
Our solution is the ability to simultaneously download data from several Apollo stations, thanks to which we can predict shocks over a larger area and obtain data on the Z axis (i.e. depth)
How it's working?
The data collected during the mission was not intended for predictive measurements by other sensors so that such predictions and collaborative activities would cover a larger area. The data has different origins and it has been necessary to codify and standardize it.
Our solution shows in a simple, intuitive way seismic movements on the surface of the moon, regardless of the idea in which times, year they were created, aggregation from a data warehouse, downloading via API
What are its advantages?
It does not generate additional missions, using the already collected data, and in its absence, it is enriched (the depth of the tremors is forecast at the peaks, and these are our data on the Z axis).
What are you hoping to achieve?
Building a unified data set from distant times, as well as using aggregation and machine learning, enriching them with predictions that were not possible a few years ago, which allows for the next mission to create a map of future missions for UAVs.
It is worth considering building a data reading simultaneously in hourly and daily cycles
What tools, coding languages, hardware or software did you use to develop your project?
- ArcGIS Online - Building a 3D model
- ArtGIS PRO - Build a 3D model
- Python 3.7 - Modified Datasets Python 3.7 - Modified data sets, we used advanced algorithms for the purpose, there was a triangulation of data from many points, we diversified the data with Z points, data standardization.
- deep learning
- machine learning
- predictive algorithms for this data
Space Agency Data
• Moon Elevation Surface is from NASA, GSFC, and Arizona State University. It is a digital elevation model (DEM) that is based on data from the Lunar Orbiter Laser Altimeter (LOLA; Smith and others, 2010), an instrument on NASA’s Lunar Reconnaissance Orbiter (LRO) spacecraft (Tooley and others, 2010).
• Moon Imagery (additional ref) is from NASA, GSFC, and Arizona State University. It is a combination of high resolution black and white imagery and colour normalised imagery was tiled to show surface detail of the moon.
• Apollo Mission high-res imagery is from LROC.
• Apollo Missions and Man-made Objects are from Wagner, R. V., Nelson, D. M., Plescia, J. B., Robinson, M. S., Speyerer, E. J., & Mazarico, E. (2017). Coordinates of anthropogenic features on the Moon. Icarus, 283, 92-103. doi:10.1016/j.icarus.2016.05.011.
• Extravehicular Activity is from NASA, GSFC, Arizona State University, LROC, and N.R. Gonzales, M.R. Henriksen, R.V. Wagner, M.S. Robinson (2019) Apollo 11: Where They Were When – A New Spatiotemporal EVA Map, Lunar and Planetary Science Conference 50, abstract #3089.
• Moon Nomenclature is from International Astronomical Union (IAU) Working Group for Planetary System Nomenclature (WGPSN).
• Images are from NASA.
• Icons were made by Esri UK.
Please credit data usage to support the continued access to these breathtaking datasets!
Esri. Esri UK. NASA. GSFC. Arizona State University. International Astronomical Union (IAU) Working Group for Planetary System Nomenclature (WGPSN). Wagner, R. V., Nelson, D. M., Plescia, J. B., Robinson, M. S., Speyerer, E. J., & Mazarico, E. (2017). Coordinates of anthropogenic features on the Moon. Icarus, 283, 92-103. doi:10.1016/j.icarus.2016.05.011. N.R. Gonzales, M.R. Henriksen, R.V. Wagner, M.S. Robinson (2019) Apollo 11: Where They Were When – A New Spatiotemporal EVA Map, Lunar and Planetary Science Conference 50, abstract #3089.
This is the 3D web-scene which underpins Esri UK's History of the Lunar Landings web application. Please feel free to use this webscene and underlying data in your own extra-planetary projects!
The below list contains information about where each of the datasets used in the map were sourced:
Hackathon Journey
We are a group of 2 Engineer's and 1 child :) participating for the first time in the Space App challenge.
As a team we reviewed the list of challenges offered on the Space app website and we felt inclined towards the “Make a Moonquake Map.
We decided to focus our research on the "3D modeling seismology on Moon"
We faced many difficulties since there were topics out of our current understanding, but we were able to work on them by investigating them, and we have problems to good interprete the dataset, but we did it :)
References
- Fig. 1. xa.s11.00.mh1.1969.202.0.a.csv - https://pds-geosciences.wustl.edu/lunar/urn-nasa-pds-apollo_pse/data/xa/continuous_waveform/s11/1969/202/
- Fig. 2. Catalog of Lunar Seismic Datarom Apollo Passive Seismic Experiment on 8-mm Video Cassette (Exabyte) Tapes. - https://nssdc.gsfc.nasa.gov/misc/documents/b53211.pdf/13
- Other is in free use from webside's
Tags
#Moonquake, #Map, #3Dmodeling, #seismology, #Moon, #AI, #ML, #Prediction, #ForecastingSafeAndDangerousZones