[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117272-en":3,"doc-seo-117272-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},117272,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Better, Not Just More - Data-Centric Machine Learning for Earth Observation","Recent developments in modern machine learning have improved geospatial outcomes, yet many deep learning methods are trained on benchmark datasets with limited real-world relevance, leading to performance saturation. This work argues for shifting from a model-centric mindset to a data-centric perspective across the full machine learning cycle, from problem definition through data creation and curation to deployment with feedback. It provides a precise categorization and overview of automated data-centric learning approaches in geospatial settings, supported by representative experiments and concrete implementation steps for reliable performance in unforeseen conditions.","arXiv :2312 .05327v2 [ cs .LG] 22 Jun 2024  \nBetter, Not Just More: Data-Centric Machine Learning for Earth Observation  \nRibana Roscher∗†, Marc Rußwurm‡, Caroline Gevaert§ , Michael Kampffmeyer¶ , Jefersson A. dos Santos ∥ , Maria Vakalopoulou∗∗ , Ronny Hnsch††, Stine Hansen¶ , Keiller Nogueira‡‡, Jonathan Prexlx , Devis Tuiaxi  \n∗Data Science for Crop Systems Group, Forschungszentrum J¨ulich GmbH  \n†Remote Sensing Group, University of Bonn  \n‡Laboratory of Geo-information Science and Remote Sensing, Wageningen University  \n§Department of Earth Observation Science, Faculty ITC, University of Twente ¶Department of Physics and Technology, UiT The Arctic University of Norway ∥Department of Computer Science, University of Sheffield  \n∗∗MICS Laboratory, CentraleSuplec, Paris-Saclay University ††Microwaves and Radar Institute, German Aerospace Center (DLR)  \n‡‡Computing Science and Mathematics, University of Stirling  \nx  \nDepartment of Aerospace Engineering, University of the Bundeswehr Munich xi Environmental Computational Science and Earth Observation Laboratory, Ecole Polytechnique Fdrale de  \nLausanne (EPFL)  \nAbstract—Recent developments and research in modern machine learning have led to substantial improvements in the geospatial field. Although numerous deep learning architecturesand models have been proposed, the majority of them have been solely developed on benchmark datasets that lack strong real-world relevance. Furthermore, the performance of many methods has already saturated on these datasets. We argue that a shift from a model-centric view to a complementary data-centric perspective is necessary for further improvements in accuracy, generalization ability, and real impact on enduser applications. Furthermore, considering the entire machine learning cycle—from problem definition to model deployment with feedback—is crucial for enhancing machine learning models that can be reliable in unforeseen situations. This work presentsa definition as well as a precise categorization and overview of automated data-centric learning approaches for geospatial data. It highlights the complementary role of data-centric learning with respect to model-centric in the larger machine learning deployment cycle. We review papers across the entire geospatial field and categorize them into different groups. A set of representative experiments shows concrete implementation examples. These examples provide concrete steps to act on geospatial data with data-centric machine learning approaches.  \nIndex Terms—data-centric machine learning, data curation, data utilization, data quality.  \nI. INTRODUCTION  \nREMOTE sensing data is a central link between press  \ning global challenges and the possibilities of machine learning methods. To realize its full potential, a deep understanding of the data and its utilization possibilities is essential. Generally, data plays a fundamental role in the machine learning (ML) cycle with steps from informing (1) problem definition, (2) data creation, (3) data curation, enabling (4) model training, and (5) evaluation to (6) the eventual model deployment that feeds back to modifying the problem definition. We show this cycle in Fig. 1 where each node is  \ncolored by its focus of being problem-centric (dark gray), data-centric (blue), or model-centric (dark green) . Yet, current research in machine learning is predominantly model-centric and focuses on model design and evaluation (Step 4) . This primarily emphasizes optimizing the accuracy and efficiency of the models themselves [1]–[3] and considers the dataset rather as a static benchmark than a dynamic representation of the application. Even in applied machine learning areas such as geospatial data analysis, the research towards integrating new machine learning methods has recently largely focused on refining the algorithms and fine-tuning the model parameters [4] . Data-centric aspects like data acquisition (Step 1) and curation (Step 2) are done manually to a lar","cbCaifez2p2iky47","https://ap.wps.com/l/cbCaifez2p2iky47","pdf",6026489,1,18,"English","en",105,"# Introduction\n## Machine learning cycle in remote sensing\n## Model-centric vs data-centric research directions\n# Data-centric learning approaches\n## Automated categorization overview\n## Representative experiments and implementation steps","[{\"question\":\"Why does the paper argue against a purely model-centric approach in earth observation ML?\",\"answer\":\"It notes that many methods rely on benchmark datasets with weak real-world relevance and that performance often saturates there. The paper argues that further accuracy and generalization gains require focusing on data-centric aspects and the broader pipeline.\"},{\"question\":\"What machine learning cycle steps are emphasized for reliable geospatial models?\",\"answer\":\"The paper highlights a cycle from problem definition and data creation to data curation, then model training and evaluation, followed by model deployment with feedback that modifies problem definition.\"},{\"question\":\"What does the paper contribute besides advocating data-centric learning?\",\"answer\":\"It presents a definition, a precise categorization, and an overview of automated data-centric learning approaches for geospatial data. It also includes representative experiments with concrete implementation examples.\"}]",1785674913,45,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"better-not-just-more-data-centric-machine-learning-for-earth-observation","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/better-not-just-more-data-centric-machine-learning-for-earth-observation/117272/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why does the paper argue against a purely model-centric approach in earth observation ML?","Question",{"text":74,"@type":75},"It notes that many methods rely on benchmark datasets with weak real-world relevance and that performance often saturates there. The paper argues that further accuracy and generalization gains require focusing on data-centric aspects and the broader pipeline.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What machine learning cycle steps are emphasized for reliable geospatial models?",{"text":79,"@type":75},"The paper highlights a cycle from problem definition and data creation to data curation, then model training and evaluation, followed by model deployment with feedback that modifies problem definition.",{"name":81,"@type":72,"acceptedAnswer":82},"What does the paper contribute besides advocating data-centric learning?",{"text":83,"@type":75},"It presents a definition, a precise categorization, and an overview of automated data-centric learning approaches for geospatial data. It also includes representative experiments with concrete implementation examples.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]