首页|Researchers from Indian Institute for Technology Report Recent Findings in Machi ne Learning (Temporal Trends In Asteroid Behaviour: a Machine Learning and n-bod y Integration Approach)
Researchers from Indian Institute for Technology Report Recent Findings in Machi ne Learning (Temporal Trends In Asteroid Behaviour: a Machine Learning and n-bod y Integration Approach)
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 originating from Jharkhand, India, by NewsRx correspondents, research stated, “Asteroids pose significant threats to Earth, necessitating early detection for potential deflection. Leveraging machin e learning (ML), we classify asteroids into near-Earth Asteroids (particularly A tens, Amors, Apollos, and Apoheles) and non-near-Earth asteroids, further catego rizing them based on hazard potential.” Our news journalists obtained a quote from the research from Indian Institute fo r Technology, “Training the seven models on a comprehensive data set of 4687 ast eroids, we achieve high accuracy in prediction. The predictive capability of the se models is critical for informed decision-making in planetary defense strategi es. We apply different regularization techniques to prevent overfitting and vali date the models using a large unseen data set. A rigorous long-term N-body integ ration spanning 1 Myr is executed utilizing the Mercury N-body integrator to ill uminate the evolution of asteroid properties over extended temporal scales. Foll owing this integration process, the best-performing ML model is employed to clas sify asteroids based on their orbital characteristics and hazardous status respe ctively. Our findings highlight the effectiveness of ML in asteroid classificati on and prediction, paving the way for large-scale applications. By dividing a 1 Myr integration into intervals, we uncover temporal trends in asteroid behaviour , revealing insights into hazard evolution and ejection patterns. Notably, initi ally, hazardous asteroids tend to transition to non-hazardous states over time, elucidating key dynamics in planetary defense. We illustrate these findings thro ugh plotted graphs, providing valuable insights into asteroid dynamics.”
JharkhandIndiaAsiaCyborgsEmergin g TechnologiesMachine LearningIndian Institute for Technology
NETL
NSTL
