A suspected lunar volcano identification algorithm based on convolutional neural network by the rapid location of light shadow impacts

摘要

The impact crater is the most common geological unit in the lunar surface, an important objectto study the geological evolution history of theMoon, and the foundational basis for the geologicaldating of the Moon. Thus, the identification of impact craters is of important significance. Asa new field with rapid development for more than ten years, deep learning has received attentionfrom an increasing number of researchers because of its obvious advantages compared withthe superficialmodel in terms of both feature extraction and modeling. To address various defectsof the current method for the identification and feature extraction of impact craters, includingits low efficiency and limited application range, this paper proposes a type of new impactcrater identification using the convolutional neural network based on illumination and shadowquick-positioning. First, we quickly locate the impact crater using the effect of illumination on theimpact crater. Second,we train the impact crater imagesusing the convolutional neural network toperform the feature extraction. Then,we identify impact craters in images. Finally,we classify theidentified impact craters based on the roughness feature and find impact craters with unsmoothbottoms. Compared with the traditional algorithm, the algorithm of this paper breaks away fromthe important index of border but has a high identification rate under the specific resolution rateand can classify the identified impact craters. Such impact craters with unsmooth bottoms mayoverflow and form from the Earth's mantle at the bottom ormay be the remnant of volcanic ventssince ancient times, which are of great research significance.