[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119963-en":3,"doc-seo-119963-105":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":20,"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},119963,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Machine-Learning Based Observational Cloud Products for Process-Oriented Climate Model Evaluation - Doctoral Dissertation","Clouds strongly regulate Earth’s energy balance and moisture/heat distributions, making their representation critical for understanding anthropogenic climate change. Uncertainty in how global climate models (GCMs) simulate clouds is a major driver of spread between model projections. This doctoral thesis develops machine-learning and neural-network methods to characterize clouds from space, producing satellite products designed to be objectively interpretable and consistently comparable with GCM output. The work improves cloud-class interpretability, creates a new Cloud Class Climatology dataset, and enables generative domain adaptation to synthesize satellite-like observations from GCM simulations.","Machine-Learning Based Observational Cloud Products for Process-Oriented Climate Model  \nEvaluation  \nDoctoral Dissertation of  \nArndt Kaps  \nDecember 2023  \nUniversity of Bremen  \nInstitute of Environmental Physics (IUP)  \nMachine-Learning Based Observational Cloud Products for Process-Oriented Climate Model  \nEvaluation  \nDoctoral Dissertation of  \nArndt Kaps  \nA thesis submitted in fulfillment of the requirements for the degree Doktor der Naturwissenschaften (Dr. rer. nat.)  \nPrimary Examiner: Prof. Dr. Veronika Eyring  \nSecondary Examiner: Prof. Dr. Hartmut B¨osch  \nSubmission: 11 December 2023  \nAbstract  \nThe importance of clouds in regulating the Earth’s energy balance as well as moisture and heat distributions cannot be overstated. Consequently, clouds have a considerable influence on the trajectory of anthropogenic climate change, of which possible scenarios are being studied with global climate models (GCMs) . Uncertainties from the representation of clouds in GCMs have been identified as a leading cause of inter-model spread in climate projections. Our current understanding of clouds and the processes relevant to their formation and effect on climate is informed partly by observations from remote sensing instruments aboard orbital satellites. This thesis introduces new methods of characterizing clouds from space with the help of machine learning and neural networks. The purpose of these methods is to improve the understanding of and reduce the uncertainties in climate projections by providing satellite products that are objectively interpretable and consistently comparable to GCM output.  \nIn a first study, the lack of interpretability in existing products is addressed with a newly developed framework to assign cloud classes to satellite data and GCM output. A neural network and a Random Forest are combined and trained on observations from both active and passive satellite sensors to infer cloud class distributions from low-resolution cloud property data. During training, the models use cloud properties from the Moderate Resolution Imaging Spectroradiometer (MODIS) as inputs. The ground truth classes-eight cloud types defined to be similar to those established by the World Meteorological Organization (WMO) - are obtained from CloudSat radar and Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) lidar measurements. The generalization performance of the framework is assessed using the European Space Agency (ESA) Climate Change Initiative cloud dataset (Cloud cci) . Throughout all stages of machine learning, the predicted cloud-type distributions are physically consistent with the WMO definitions and comparable to those of the ground truth dataset. This allows cloud-related data to be presented in the phase space of cloud classes, which makes the data more easily interpretable and usable for GCM evaluation. Based on this, the trained framework was used to create a new Cloud Class Climatology (CCClim) from the complete ESA Cloud cci AVHRR-PMv3 (ESA-CCI) dataset. CCClim contains daily mean values of the cloud properties from ESA-CCI and the predicted cloudtype distributions globally at 1◦ resolution over 35 years. Compared to existing cloud-type datasets, CCClim provides comparable or better resolution and coverage and as it is based on active sensor data, allows for more objective downstream studies. Applying the machinelearning framework to the output of GCM and comparing the simulated to observed cloud-type  \ndistributions is demonstrated as one of the use cases of CCClim using output from a simulation of the Icosahedral Nonhydrostatic Atmosphere model (ICON-A) climate model. CCClim acts as a new basis for process-based analysis of clouds and can be valuable for evaluating similar cloud class distributions in GCMs.  \nThe limited comparability between GCMs and observations is addressed in a third study by employing neural-network-based generative domain adaptation, tailored specifically to sate","cbCaijFxZCdncr1B","https://ap.wps.com/l/cbCaijFxZCdncr1B","pdf",24532657,1,166,"English","en",105,"# Introduction\n## Motivation\n## Central Scientific Questions\n## Content and Structure of this Thesis","[{\"question\":\"Why are clouds central to climate model evaluation in this thesis?\",\"answer\":\"Clouds regulate Earth’s energy balance and moisture/heat distribution, so inaccuracies in cloud representation in GCMs create major uncertainty in climate projections. The thesis targets this uncertainty directly through new observational products and methods.\"},{\"question\":\"How does the thesis improve interpretability of satellite-derived cloud information?\",\"answer\":\"It introduces a framework that assigns cloud classes to both satellite data and GCM output. A neural network combined with a Random Forest is trained on cloud properties using MODIS inputs, with ground truth cloud-type distributions derived from CloudSat and CALIPSO measurements.\"},{\"question\":\"What role does generative domain adaptation play?\",\"answer\":\"A cycle-consistent GAN (CycleGAN) is trained to translate ICON-A model scenes into ESA-CCI-like satellite observations and vice versa. This produces synthetic observations similar to instrument simulators, supporting more comparable evaluation between models and observations.\"}]","Machine-Learning Based Observational Cloud Products for Process-Oriented Climate Model Evaluation - Doctoral Dissertation | PDF",1785727249,418,{"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},"machine-learning-based-observational-cloud-products-for-process-oriented-climate-model-evaluation-doctoral-dissertation","",{"@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/machine-learning-based-observational-cloud-products-for-process-oriented-climate-model-evaluation-doctoral-dissertation/119963/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are clouds central to climate model evaluation in this thesis?","Question",{"text":75,"@type":76},"Clouds regulate Earth’s energy balance and moisture/heat distribution, so inaccuracies in cloud representation in GCMs create major uncertainty in climate projections. The thesis targets this uncertainty directly through new observational products and methods.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis improve interpretability of satellite-derived cloud information?",{"text":80,"@type":76},"It introduces a framework that assigns cloud classes to both satellite data and GCM output. A neural network combined with a Random Forest is trained on cloud properties using MODIS inputs, with ground truth cloud-type distributions derived from CloudSat and CALIPSO measurements.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does generative domain adaptation play?",{"text":84,"@type":76},"A cycle-consistent GAN (CycleGAN) is trained to translate ICON-A model scenes into ESA-CCI-like satellite observations and vice versa. This produces synthetic observations similar to instrument simulators, supporting more comparable evaluation between models and observations.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]