[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125080-en":3,"doc-seo-125080-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125080,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Optimized Martian Dust Displacement Detection Using Explainable Machine Learning","ChemCam on NASA’s Curiosity rover performs LIBS geochemical analyses, and the shockwaves from LIBS measurements can shift dust on Mars. This work builds an automatic Dust Displacement Detection (DDD) pipeline using ChemCam RMI image datasets to identify dust displacement on targets. A preprocessing workflow is introduced, followed by two-stage models with VGG16 feature extraction and a Random Forest or SVM binary classifier. The best model uses the first 10 layers of VGG16 plus Random Forest, reaching 92% accuracy, with explainable AI support via Shapley values and guided backpropagation.","This CVPR Workshop paper is the Open Access version, provided by the Computer Vision Foundation.  \nExcept for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.  \nOptimized Martian Dust Displacement Detection Using Explainable Machine  \nLearning  \nAna Lomashvili* Kristin Rammelkamp* Olivier Gasnault† Protim Bhattacharjee* Elise Clav* Christoph H. Egerland* Susanne Schrder* Beg¨um Demir‡ Nina L. Lanza§  \nAbstract  \nThe ChemCam instrument on the Curiosity rover performs geochemical analyses of rocks on Mars using LaserInduced Breakdown Spectroscopy (LIBS) . The shockwaves generated during the LIBS measurements sometimes shift dust from the surface of the target. The study of the Martian dust phenomena in the scope of the ChemCam instrument has the potential to provide insight into the planet’s geology and aid calibration methods for data processing. In this study, we develop a pipeline, named Dust Displacement Detection (DDD), for automatic detection of dust displacement on LIBS targets based on the image dataset acquired by ChemCam. To this end, we introduce a data preprocessing methodology and test two-stage models with apretrained model in the first stage for feature extraction anda Random Forest classifier or a Support Vector Machine asa binary classifier in the second stage. The best performing model was found to consist of the first 10 layers of VGG16 and a Random Forest classifier, achieving 92% accuracy. Additionally, we use Explainable AI (XAI) methods such as Shapley values and guided backpropagation for model optimization. The experiments show potential for model optimization, and the application examples presented encourage discussion of machine learning in the field of Martian dust research.  \n1. Introduction  \nIn 2012, NASA’s Curiosity rover landed on Mars to investigate the Martian surface, geology, and climate, with a particular focus on assessing the planet’s past habitability. The rover has successfully completed its primary mission, finding signs of past habitability. After many years of service,  \n* German Aerospace Center (DLR)  \n†Institut de Recherche en Astrophysique et Plantologie (IRAP)‡Technical University Berlin  \n§ Los Alamos National Laboratory  \nCuriosity is still at work and is now on its fourth extended mission [16, 34, 37] . The rover is equipped with various scientific instruments including the mast-mounted ChemCam (Chemistry and Camera) instrument. ChemCam consists of the first Laser-induced Breakdown Spectrometer (LIBS) in planetary science and a Remote Micro Imager (RMI) [12– 14] . LIBS involves focusing a laser on the surface of the target up to several meters from the rover, creating a luminous micro-plasma that emits characteristic photons from excited atoms, ions, and molecules. Spectral analysis of this light provides spectra with emission lines from species present in the sample, from which elemental composition can be derived [6] . The RMI instrument images through the same telescope as the LIBS providing context to the samples. RMI images are usually taken before and after the LIBS measurements [14] . Until now, the instrument has acquired data from more than 4000 individual targets and collected LIBS spectra from multiple points of each target (5-25 points per target) typically arranged in rasters. The LIBS plasma is accompanied by a shock wave that expands into the thin Martian atmosphere which sometimes leads to dust displacement on the target [22] . The occurrence of dust displacement is often observed in the images taken after the LIBS measurements, as shown in Fig. 1. The left and right images correspond to the RMIs acquired before and after LIBS measurements, respectively; in the ”after” image, dust displacement is marked by an ellipse and the LIBS pits are circled. Investigating whether dust displacement has occurred and whether it is related to specific rock types or local or seasonal conditions","cbCaimqrLPNSPlSo","https://ap.wps.com/l/cbCaimqrLPNSPlSo","pdf",3369059,1,10,"English","en",105,"# Introduction\n## Martian dust and ChemCam RMI investigations\n# Literature review","[{\"question\":\"What problem does the DDD pipeline address in ChemCam LIBS observations?\",\"answer\":\"It detects whether dust displacement occurs on LIBS targets based on RMI images, accounting for shifts caused by shockwaves produced during LIBS measurements.\"},{\"question\":\"How is the dust displacement detection model structured?\",\"answer\":\"The approach uses a two-stage pipeline: preprocessing and feature extraction with a pretrained VGG16 network, followed by a binary classifier such as Random Forest or SVM.\"},{\"question\":\"Which model performed best and what accuracy was achieved?\",\"answer\":\"The best-performing configuration combines the first 10 VGG16 layers with a Random Forest classifier, achieving 92% accuracy.\"}]","Optimized Martian Dust Displacement Detection Using Explainable Machine Learning | PDF",1785896516,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"optimized-martian-dust-displacement-detection-using-explainable-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/optimized-martian-dust-displacement-detection-using-explainable-machine-learning/125080/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the DDD pipeline address in ChemCam LIBS observations?","Question",{"text":75,"@type":76},"It detects whether dust displacement occurs on LIBS targets based on RMI images, accounting for shifts caused by shockwaves produced during LIBS measurements.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the dust displacement detection model structured?",{"text":80,"@type":76},"The approach uses a two-stage pipeline: preprocessing and feature extraction with a pretrained VGG16 network, followed by a binary classifier such as Random Forest or SVM.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performed best and what accuracy was achieved?",{"text":84,"@type":76},"The best-performing configuration combines the first 10 VGG16 layers with a Random Forest classifier, achieving 92% accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]