{"667605":{"#nid":"667605","#data":{"type":"news","title":"New Algorithm Perseveres in Search for Data Anomalies on Mars","body":[{"value":"\u003Cp\u003ESearching for evidence of life on Mars is making an impact here on Earth. One way this is being achieved is through development of data science tools successfully tested on the Mars Perseverance rover, which could be applied to interpret large, complex datasets on our own planet.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn\u0026nbsp;\u003Ca href=\u0022https:\/\/arxiv.org\/abs\/2302.07187\u0022\u003Ea recent paper\u003C\/a\u003E, a collaborative team of School of Computational Science and Engineering (CSE) researchers and NASA Jet Propulsion Laboratory (JPL) scientists introduce a design methodology, called ISHMAP, to develop new data anomaly detection models.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThough implemented on the Perseverance rover as it explores for new discoveries on the Red Planet, ISHMAP\u2019s greater impact will be its applicability for terrestrial life here at home who work in the rocketing field of scientific data science.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cWe have shown that collaboratively framing a data science problem with the relevant domain experts may be much more important than the actual data modeling when it comes to the ultimate impact of a model,\u201d said\u0026nbsp;\u003Ca href=\u0022https:\/\/www.austinpwright.com\/\u0022\u003E\u003Cstrong\u003EAustin Wright\u003C\/strong\u003E\u003C\/a\u003E, a School of CSE Ph.D. student. \u201cThat is to say, really working hard to precisely form the right question is, in many ways, more important than the model used to try and answer it.\u201d\u003C\/p\u003E\r\n\r\n\u003Cp\u003EISHMAP stands for Iterative Semantic Heuristic Modeling of Anomalous Phenomena. In essence, ISHMAP is a process for scientists and researchers to produce natively interpretable anomaly detection models.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe framework is the culmination of more than 30 months of collaborative research between CSE and JPL through Wright\u2019s internship.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHere, the ISHMAP group partnered with the NASA team that manages Perseverance\u2019s Planetary Instrument for X-Ray Lithochemistry (PIXL) instrument, a fluorescence spectrometer that studies elemental composition data of the Martian surface.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe highlight of ISHMAP\u2019s development is a highly accurate spectral anomaly algorithm that resulted in a 93.4% accuracy rate when detecting diffraction anomalies. What started as a yearlong field deployment of the toolkit is now a regular component of the PIXL team\u2019s workflow.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn fact, more than 97 NASA and NASA-affiliated scientists around the globe currently use a visualization tool embedded with the algorithm, thus proving itself as a key contributor in finding discoveries on Mars and elsewhere in our galaxy.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cISHMAP can provide a strong structure to make sure scientists know what the model is doing and is guaranteed to be addressing something that they are interested in,\u201d Wright said. \u201cBy contributing through the whole process, they have built-in levels of trust and ownership rather than just having some extra feature foisted upon them.\u201d\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cimg alt=\u0022ISHMAP2\u0022 height=\u0022478\u0022 src=\u0022https:\/\/www.cc.gatech.edu\/sites\/default\/files\/images\/general\/2023\/ISHMAP%20Flowchart%20copy.png\u0022 width=\u0022323\u0022 \/\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EOverview of how ISHMAP is used to assist in the PIXL science mission. Using this collaborative process, researchers were able to develop a novel interpretable anomaly detection model and deploy interactive visualizations within the widely used PIXLISE visual analytics program. This deployment proved to provide key insights in ongoing major scientific findings.\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe ISHMAP team joining Wright includes his advisor, School of CSE Associate Professor\u0026nbsp;\u003Ca href=\u0022https:\/\/poloclub.github.io\/polochau\/\u0022\u003E\u003Cstrong\u003EPolo Chau\u003C\/strong\u003E\u003C\/a\u003E, as well as\u0026nbsp;\u003Cstrong\u003EAdrian Galvin\u003C\/strong\u003E\u0026nbsp;and\u0026nbsp;\u003Cstrong\u003EScott Davidoff\u003C\/strong\u003E\u0026nbsp;from JPL.\u0026nbsp;\u003Cstrong\u003EPeter Nemere\u003C\/strong\u003E, a programmer at Queensland University of Technology, also co-authored the paper.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe ISHMAP algorithm analyzes\u0026nbsp;\u003Ca href=\u0022https:\/\/www.science.org\/doi\/full\/10.1126\/sciadv.abp9084\u0022\u003Eanomalies in crystal structure\u003C\/a\u003Es. These reveal aspects of geological and geochemical history that indicate suitability of life, such as past presence of water and essential minerals. This is a specific component of the PIXL instrument that searches for elemental traces of ancient microbial life on Mars in datasets collected in surveys, scans, and samples.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAs scientific datasets grow larger and more complex, so too do the methods used to find anomalies. Existing anomaly detection research primarily relies on deep learning methods, but these tend to lack nuance and interpretability, which are vital to scientific inquiry.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EISHMAP bridges methodologies from artificial intelligence (AI) and human-computer interaction (HCI) into a framework for scientific researchers to use in designing more effective and interpretable anomaly detection tools.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAn important early stage in the ISHMAP process was an 18-month-long formative design study between the ISHMAP group and NASA\u2019s PIXL team. This defined the design goals needed to enhance PIXL.\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETo accomplish its mission, PIXL needed an algorithm that focused on raw data over processed data, robustness to operate under a limited amount of ground truth data, and enhanced ability to interpret and differentiate different kinds of anomalies.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EBuy-in from users proved to be a key step in the early stages of the methodology to understand research problems and to integrate with existing model techniques. This way, ISHMAP produces an effective anomaly detection algorithm custom made to meet end-user needs.\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETo help spread the word about ISHMAP and attract more scientific users, Wright represented the group by presenting their research at the 28th Annual Conference on Intelligent User Interfaces (\u003Ca href=\u0022https:\/\/iui.acm.org\/2023\/call_for_papers.html\u0022\u003EIUI 2023\u003C\/a\u003E).\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAn Association for Computing Machinery conference held March 27 \u2013 31 in Sydney, IUI 2023 is a premier international forum reporting outstanding research at the intersection of HCI and AI to further develop user interfaces.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cI think that researchers can consider using ISHMAP simply because these kinds of collaboration between data scientists and domain scientists are difficult,\u201d Wright said. \u201cA resource like ISHMAP can give structure to both parties, and make the whole process easier and more likely to result in good science.\u201d\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EIn\u0026nbsp;\u003Ca href=\u0022https:\/\/arxiv.org\/abs\/2302.07187\u0022\u003Ea recent paper\u003C\/a\u003E, a collaborative team of School of Computational Science and Engineering researchers and NASA Jet Propulsion Laboratory scientists introduce a design methodology, called ISHMAP, to develop new data anomaly detection models.\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"Methodology implemented on Marse Rover will have applications in scientific data science.  "}],"uid":"32045","created_gmt":"2023-05-02 14:36:58","changed_gmt":"2023-05-02 14:40:26","author":"Ben Snedeker","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2023-04-30T00:00:00-04:00","iso_date":"2023-04-30T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"670712":{"id":"670712","type":"image","title":"perserverence_story graphic.v2 copy_0.jpg","body":null,"created":"1683038261","gmt_created":"2023-05-02 14:37:41","changed":"1683038261","gmt_changed":"2023-05-02 14:37:41","alt":"Illustration of Perseverance rover on Mars","file":{"fid":"253624","name":"perserverence_story graphic.v2 copy_0.jpg","image_path":"\/sites\/default\/files\/2023\/05\/02\/perserverence_story%20graphic.v2%20copy_0.jpg","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/2023\/05\/02\/perserverence_story%20graphic.v2%20copy_0.jpg","mime":"image\/jpeg","size":82844,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2023\/05\/02\/perserverence_story%20graphic.v2%20copy_0.jpg?itok=yJ13HFcl"}}},"media_ids":["670712"],"groups":[{"id":"37041","name":"Computational Science and Engineering"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"136","name":"Aerospace"},{"id":"153","name":"Computer Science\/Information Technology and Security"}],"keywords":[],"core_research_areas":[{"id":"39431","name":"Data Engineering and Science"},{"id":"39541","name":"Systems"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine Communications Officer I School of Computational Science \u0026amp; Engineering\u0026nbsp;bryant.wine@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["bryant.wine@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}