首页|New Findings from NASA Goddard Space Flight Center Update Understanding of Machi ne Learning (A Novel Approach To Impact Crater Mapping and Analysis On Enceladus, Using Machine Learning)
New Findings from NASA Goddard Space Flight Center Update Understanding of Machi ne Learning (A Novel Approach To Impact Crater Mapping and Analysis On Enceladus, Using Machine Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting out of Greenbelt, Maryland, by NewsRx editors, research stated, "Impact cratering is one of the most import ant processes shaping planetary surfaces, offering valuable clues about the targ et body's geologic history and composition. However, crater mapping has historic ally been done manually, a process that has proven to be both arduous and time c onsuming." Funders for this research include Data Science Group, NASA Pathways Program at N ASA Goddard Space Flight Center, NASA High-End Computing (HEC) Program through t he NASA Center for Climate Simulation (NCCS) at Goddard Space Flight Center. Our news journalists obtained a quote from the research from NASA Goddard Space Flight Center, "This paper outlines a machine learning crater mapping approach f or bodies with limited elevation data available (Digital Elevation Models). We a pplied a Convolutional Neural Network for the detection and morphometry of impac t craters on Saturn's moon Enceladus using light-shadow labels trained on data f rom the Cassini Imaging Science Subsystem. Our algorithm identified a total of 5 ,240 features which were used to quantify crater distribution; this included the highest number of small craters (<1-2 km in diameter) reco rded on Enceladus by any previous published study. The pool of features was late r down-selected to craters between 0 and 30 degrees N (latitude) imaged at high incidence (>60 degrees) and phase angles (> 26 degrees). The down selection was necessary to accurately perform diameter mea surements and derive depths from shadow estimation techniques to calculate depth -diameter ratios (d/D); a well-studied relationship used to constrain planetary surface properties. Results show that the d/D ratio of craters in the equatorial region of Enceladus range from similar to 0.06 to 0.37, with a median of 0.19. Our results will inform efforts to constrain the surface properties of this regi on of Enceladus, potentially also supporting future mission concept design for t he Saturnian moon."
GreenbeltMarylandUnited StatesNort h and Central AmericaCyborgsEmerging TechnologiesMachine LearningNASA Go ddard Space Flight Center
NETL
NSTL
