[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122727-en":3,"doc-seo-122727-105":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},122727,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Dynamically weighted ensemble of geoscientific models via automated machine-learning-based classification","Despite progress in geoscientific modeling, combining multiple models to reach benchmark-quality solutions remains difficult across many sub-disciplines. An automated machine-learning-assisted ensemble framework (AutoML-Ens) is introduced to address this gap, with a workflow in which probabilities from a machine-learning classifier are mapped to dynamic weights for ensemble members. A prototype implementation is evaluated using two real-world cases: global soil water retention parameter mapping and remote-sensing cropland evapotranspiration estimation. AutoML-Ens outperforms conventional ensembles across training, testing, and overall sets, improving metrics such as R², Kling–Gupta efficiency, and RMSE, and demonstrates strong potential for uncertainty reduction through dynamic weighting and an AutoML-enabled workflow while combining data-driven learning with physics constraints.","Geosci. Model Dev., 16, 5685–5701, 2023 [https://doi.org/10.5194/gmd-16-5685-2023](https://doi.org/10.5194/gmd-16-5685-2023)[ ](https://doi.org/10.5194/gmd-16-5685-2023)© Author(s) 2023 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nDynamically weighted ensemble of geoscientific models via automated machine-learning-based classification  \nHao Chen 1,2,4 , Tiejun Wang 1,2,3 , Yonggen Zhang 1,2 , Yun Bai5 , and Xi Chen 1,2,3  \n1Institute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin, 300072, China  \n2Tianjin Key Laboratory of Earth Critical Zone Science and Sustainable Development in Bohai Rim, Tianjin University, Tianjin, 300072, China  \n3Tianjin Bohai Rim Coastal Earth Critical Zone National Observation and Research Station, Tianjin University, Tianjin, 300072, China  \n4 State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, 100101, China  \n5Hebei Technology Innovation Center for Remote Sensing Identification of Environmental Change, School of Geographic Sciences, Hebei Normal University, Shijiazhuang, 050024, China  \nCorrespondence: Tiejun Wang ([tiejun.wang@tju.edu.cn](tiejun.wang@tju.edu.cn))  \nReceived: 23 November 2022 – Discussion started: 5 January 2023  \nRevised: 20 August 2023 – Accepted: 7 September 2023 – Published: 12 October 2023  \nAbstract. Despite recent developments in geoscientific (e.g., physics-or data-driven) models, effectively assembling multiple models for approaching a benchmark solution remains challenging in many sub-disciplines of geoscientific fields. Here, we proposed an automated machine-learning-assisted ensemble framework (AutoML-Ens) that attempts to resolve this challenge. Details of the methodology and workflow of AutoML-Ens were provided, and a prototype model was realized with the key strategy of mapping between the probabilities derived from the machine learning classifier and the dynamic weights assigned to the candidate ensemble members. Based on the newly proposed framework, its applications for two real-world examples (i.e., mapping global soil water retention parameters and estimating remotely sensed cropland evapotranspiration) were investigated and discussed. Results showed that compared to conventional ensemble approaches, AutoML-Ens was superior across the datasets (the training, testing, and overall datasets) and environmental gradients with improved performance metrics (e.g., coefficient of determination, Kling–Gupta efficiency, and root-mean-squared error) . The better performance suggested the great potential of AutoML-Ens for improving quantification and reducing uncertainty in estimates due to its two unique features, i.e., assigning dynamic weights for candidate models and taking full advantage of AutoML-assisted workflow. In addition to  \nthe representative results, we also discussed the interpretational aspects of the used framework and its possible extensions. More importantly, we emphasized the benefits of combining data-driven approaches with physics constraints for geoscientific model ensemble problems with high dimensionality in space and nonlinear behaviors in nature.  \n1 Introduction  \nWith improvements to sensing systems and modeling technologies, a wide range of physics-based or data-driven models have been developed in the sub-fields of geosciences, mainly to simulate or predict essential variables for understanding climate, biodiversity, ocean, and geodiversity (Hurrell et al., 2013; Karpatne et al., 2019; Reichstein et al., 2019) . However, significant precision inconsistencies exist among these models due to their own limitations, even for the same process or variable on an identical scale (Steffen et al., 2020) . It is, therefore, not surprising that the corresponding simulations or predictions are often different or even contradictory, particularly with the influence of anthropogenic activities in Earth systems, leading t","cbCaigF2KWSb0vIM","https://ap.wps.com/l/cbCaigF2KWSb0vIM","pdf",6906274,1,17,"English","en",105,"# Introduction\n## Challenges in geoscientific model combination\n## Ensemble approaches and motivation\n## Evapotranspiration products and benchmark datasets","[{\"question\":\"What problem does AutoML-Ens aim to solve in geoscientific modeling?\",\"answer\":\"It addresses the difficulty of effectively assembling multiple geoscientific models to approach benchmark solutions across different sub-disciplines.\"},{\"question\":\"How does AutoML-Ens determine the weights of ensemble members?\",\"answer\":\"It maps probabilities produced by a machine-learning classifier to dynamic weights assigned to candidate ensemble models.\"},{\"question\":\"What applications and performance improvements are reported?\",\"answer\":\"AutoML-Ens is tested on global soil water retention parameter mapping and cropland evapotranspiration estimation, where it shows superior performance over conventional ensembles using metrics like R², Kling–Gupta efficiency, and RMSE.\"}]","Dynamically weighted ensemble of geoscientific models via automated machine-learning-based classification | PDF",1785812556,43,{"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},"dynamically-weighted-ensemble-of-geoscientific-models-via-automated-machine-learning-based-classification","",{"@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/dynamically-weighted-ensemble-of-geoscientific-models-via-automated-machine-learning-based-classification/122727/",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","2026-08-04",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 AutoML-Ens aim to solve in geoscientific modeling?","Question",{"text":75,"@type":76},"It addresses the difficulty of effectively assembling multiple geoscientific models to approach benchmark solutions across different sub-disciplines.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AutoML-Ens determine the weights of ensemble members?",{"text":80,"@type":76},"It maps probabilities produced by a machine-learning classifier to dynamic weights assigned to candidate ensemble models.",{"name":82,"@type":73,"acceptedAnswer":83},"What applications and performance improvements are reported?",{"text":84,"@type":76},"AutoML-Ens is tested on global soil water retention parameter mapping and cropland evapotranspiration estimation, where it shows superior performance over conventional ensembles using metrics like R², Kling–Gupta efficiency, and RMSE.","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"]