{"id":1726,"date":"2016-11-20T05:00:09","date_gmt":"2016-11-20T05:00:09","guid":{"rendered":"http:\/\/www.rsoftsolution.com\/blog\/how-data-science-and-rocket-science-will-get-humans-to-mars.html"},"modified":"2016-11-20T05:00:09","modified_gmt":"2016-11-20T05:00:09","slug":"how-data-science-and-rocket-science-will-get-humans-to-mars","status":"publish","type":"post","link":"https:\/\/www.rbsitsoftwaresolution.in\/blog\/how-data-science-and-rocket-science-will-get-humans-to-mars.html","title":{"rendered":"How data science and rocket science will get humans to Mars"},"content":{"rendered":"


\n<\/p>\n

In a recent\u00a0op-ed<\/a> to CNN, President Obama re-affirmed America\u2019s commitment to sending a manned mission to Mars. Think your data science challenges are too complicated? Imagine the difficulties involved in mining data to understand the health impacts of an expedition to Mars.<\/p>\n

What happens to astronauts\u2019 muscle tone or lung capacities after several years in space? How much weight can they safely lose? How much CO2 should be in the crew vehicle? How many sensors are needed to calculate joint flexibility in each individual space suit?<\/p>\n

When sending humans \u201cwhere no one has gone before,\u201d there are a multitude of variables to consider, and NASA is hard at work researching the health and safety risks<\/a> of a future Mission to Mars. Understanding these risks is critical, as they impact a number of decisions that need to be made when planning the journey \u2014 spanning everything from how potential crew members are evaluated to equipment engineering, mission logistics and the determination of needed fuel loads.<\/p>\n

The stakes are high, but NASA realized from the get-go that it needed to focus less on developing the perfect analytic model and more on building a data science process<\/em> that empowers decision-makers to use analytics to answer a multitude of continually changing questions. But you don\u2019t have to be dealing with rocket science to learn from NASA\u2019s analytic approach. Here are several key takeaways from NASA\u2019s project that are useful for any organization about to embark \u2014 or that\u2019s stuck \u2014 on a big data analytics initiative.<\/p>\n

Stop making it so complicated<\/h2>\n

Simply put, data science shouldn\u2019t be as complicated as rocket science. (See what I did there?) Yes, analyzing big data has challenges, and yes, your approach may vary depending on what kinds of insights you hope to obtain, but there\u2019s no need to make things more complex than the situation calls for.<\/p>\n

All too often, organizations end up spending endless cycles attempting to move data in order to analyze it when they should instead be focusing on bringing the analytics to the data. Big data, by definition, is very tough, if not impossible, to move around. This is why distributed storage and processing frameworks like Hadoop exist \u2014 data in the cloud is far more scalable than data in a silo.<\/p>\n

For the Mars project, there are so many levels of data to look at, ranging from health data collected from astronauts like Scott Kelly<\/a> who have completed previous space missions, to non-astronaut test studies, to studies done in simulated space environments like the Human Exploration Research Analog<\/a> (HERA) at Johnson Space Center in Houston.<\/p>\n

Getting all the data in one place is the critical first step. For this reason, NASA is using the Collaborative Advanced Analytics and Data Sharing<\/a> platform developed by Lockheed Martin and several analytic partners, such as Alpine Data, to analyze data at its source. Because there\u2019s no waiting to download data into a separate analytic environment to work with it, researchers can focus their time and energy on asking questions and getting the answers that will help them plan a mission to Mars.<\/p>\n

The launch is just the beginning<\/h2>\n

A successful rocket launch is only step one in a multi-year expedition to Mars. Based on past experiences, NASA expects to encounter and address numerous challenges along the way. The same holds true for data analytics projects. Simply deploying a model doesn\u2019t mean the project is done. In fact, the most valuable analytics initiatives are those where models are continually refined and iterated on an ongoing basis.<\/p>\n

Like the scientific method, getting the most out of analytics requires experimentation, testing, learning from failures and testing again. NASA wants to be able to quickly query the large volumes of data at its disposal, then funnel insights back into new models capable of building on what came before. That\u2019s why the data science process for this initiative resembles a \u201cpendulum,\u201d where the forward swing focuses on rapidly driving insights out to researchers and the backward swing focuses on measuring, evaluating results, refining the model and then swinging again.<\/p>\n

Work with the data you have, not the data you wish you had<\/h2>\n

An ability to quickly and easily refine analytic models is especially valuable when your data sets aren\u2019t perfect. (And really, is any data set perfect?)<\/p>\n

For NASA, the biggest data challenge is that the astronaut sample size is small \u2014 only 300 individuals have been\u00a0accepted\u00a0to NASA\u2019s Astronaut Corps. Researchers have to mine the heck out of the data collected from this small sample and extrapolate.<\/p>\n

For example, based on how a 35-year-old female with a starting weight of 120 pounds responded to a five-month trip in space, how would a 32-year-old weighing 123 respond to two years? What about a 30-year-old weighing 118? Furthermore, since an astronaut has yet to step foot on the Red Planet, there\u2019s no data about the health impacts of actually living on Mars (Matt Damon doesn\u2019t count).<\/p>\n

But what can NASA learn from astronauts who have gone to the Moon, or spent a year in the International Space Station? What happens when data from test subjects living in simulated space environments is plugged into a predictive model? With analytic tools that support rapid model deployment and refinement, organizations can keep trying different ways to extract insight from the data they do<\/em> have to make better predictions, even when key information is missing.<\/p>\n

Break the metaphorical black box<\/h2>\n

With the Mars Mission, NASA is not only putting billions of invested taxpayer dollars on the line, but also the lives of its astronauts, who risk their health and safety in the name of science and exploration.<\/p>\n

Like any consumer of analytics, NASA needs to be able to trust in the recommendations that are being generated, but this is hard to do if predictions are computed in a \u201cblack box\u201d that only data science experts can manipulate or understand.<\/p>\n

For a project like this, empowering analytic consumers who aren\u2019t necessarily data science PhDs (such as the health researchers, equipment engineers and others planning the mission) to actually build and launch queries and use the data on their own is key. This requires tight collaboration between business and IT stakeholders, modeling tools that are simple to use and modify and the ability to push insights to the people who need them. This is why NASA has chosen a collaborative analytic platform that includes tools that extend outputs directly into the systems and applications that are used by the scientists and decision-makers working on the Mars Mission.<\/p>\n

Large and complex data sets pose challenges for any organization about to embark on an analytics deployment. But NASA\u2019s example of harnessing data to plan the most complicated of journeys \u2014 an expedition to Mars \u2014 proves that the challenges are not insurmountable. With the right tools and, most importantly, a consistent and well-planned approach, data science doesn\u2019t have to be as daunting as rocket science.<\/p>\n

Note: Lockheed Martin Information Systems Global Solutions is now a part of Leidos Holdings, Inc.<\/em><\/p>\n

<\/p>\n

Featured Image: Atomic Imagery<\/a>\/Getty Images<\/small><\/p>\n

Article source: http:\/\/feedproxy.google.com\/~r\/techcrunchIt\/~3\/QpVGdaEGMoY\/<\/p>","protected":false},"excerpt":{"rendered":"

In a recent\u00a0op-ed to CNN, President Obama re-affirmed America\u2019s commitment to sending a manned mission to Mars. Think your data science challenges are too complicated? Imagine the difficulties involved in <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[19],"tags":[25],"class_list":["post-1726","post","type-post","status-publish","format-standard","hentry","category-enterprise-software","tag-enterprise"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t