[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125150-en":3,"doc-seo-125150-105":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},125150,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","ML-AMPSIT - Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool","Accurate calibration of parameters in atmospheric and Earth system models is essential yet difficult because complex input–output relationships involve multiple interactions, limiting the effectiveness and reproducibility of simple sensitivity analyses. ML-AMPSIT provides a simple, flexible framework to estimate parameter sensitivity and importance in complex numerical weather prediction models. It combines regression-based and probabilistic machine learning methods to build computationally inexpensive surrogate models that predict output impacts while substantially reducing high-fidelity runs. Case study results with WRF coupled with Noah-MP demonstrate efficient multi-method comparisons using relatively few simulations.","Geosci. Model Dev., 18, 433–459, 2025  \n[https://doi.org/10.5194/gmd-18-433-2025](https://doi.org/10.5194/gmd-18-433-2025)[ ](https://doi.org/10.5194/gmd-18-433-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nML-AMPSIT: Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool  \nDario Di Santo 1 , Cenlin He2 , Fei Chen3 , and Lorenzo Giovannini 1  \n1Department of Civil, Environmental and Mechanical Engineering, University of Trento, Trento, Italy  \n2NSF National Center for Atmospheric Research (NCAR), Boulder, CO, USA  \n3Division of Environment and Sustainability, Hong Kong University of Science and Technology, Hong Kong SAR, China Correspondence: Dario Di Santo (dario.disanto@unitn.it)  \nReceived: 22 March 2024 – Discussion started: 18 April 2024  \nRevised: 10 November 2024 – Accepted: 14 November 2024 – Published: 27 January 2025  \nAbstract. The accurate calibration of parameters in atmospheric and Earth system models is crucial for improving their performance but remains a challenge due to their inherent complexity, which is reflected in input–output relationships often characterised by multiple interactions between the parameters, thus hindering the use of simple sensitivity analysis methods. This paper introduces the Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool (ML-AMPSIT), a new tool designed with the aim of providing a simple and flexible framework to estimate the sensitivity and importance of parameters in complex numerical weather prediction models. This tool leverages the strengths of multiple regressionbased and probabilistic machine learning methods, including LASSO (see the list of abbreviations in Appendix B), support vector machine, classification and regression trees, random forest, extreme gradient boosting, Gaussian process regression, and Bayesian ridge regression. These regression algorithms are used to construct computationally inexpensive surrogate models to effectively predict the impact of input parameter variations on model output, thereby significantly reducing the computational burden of running high-fidelity models for sensitivity analysis. Moreover, the multi-method approach allows for a comparative analysis of the results. Through a detailed case study with the Weather Research and Forecasting (WRF) model coupled with the Noah-MP land surface model, ML-AMPSIT is demonstrated to efficiently predict the effects of varying the values of Noah-MP model parameters with a relatively small number of model runs by simulating a sea breeze circulation over an idealised flat domain. This paper points out how ML-AMPSIT can be an effi -  \ncient tool for performing sensitivity and importance analysis for complex models, guiding the user through the different steps and allowing for a simplification and automatisation of the process.  \n1 Introduction  \nOne of the primary sources of error in atmospheric and Earth system models stems from inaccurate parameter values (Clark et al., 2011 ; Li et al., 2018), which can affect different physical parameterisations. Although model parameter tuning can help to alleviate this issue, determining optimal values is highly dependent on model structures and how input parameters influence model outputs. Sensitivity analysis is commonly used to evaluate these input–output relationships and parameter importance, but traditional one-at-a-time (OAT) methods yield varying results depending on the interdependence of parameters, particularly within complex models, leading to issues of poor reproducibility and an inability to generalise results. Consequently, more advanced variancebased techniques like the Sobol method, in the context of global sensitivity analysis (GSA, Saltelli et al., 2008), exhibit superior performance in such tasks, albeit being computationally intensive (Herman et al., 2013) and sometimes infeasible, especially when dealing with co","cbCaimT0BV9pxN68","https://ap.wps.com/l/cbCaimT0BV9pxN68","pdf",6412667,1,27,"English","en",105,"# Abstract\n# Introduction\n## Parameter uncertainty and sensitivity analysis challenges\n## Surrogate models and machine-learning-based emulation\n## Feature importance in geoscience applications","[{\"question\":\"Why is calibrating parameters in atmospheric and Earth system models challenging?\",\"answer\":\"Because model complexity leads to multi-interaction input–output relationships, making simple sensitivity analysis difficult to apply reliably and consistently.\"},{\"question\":\"How does ML-AMPSIT estimate parameter sensitivity and importance?\",\"answer\":\"It builds computationally inexpensive surrogate models using a multi-method set of regression-based and probabilistic machine learning algorithms, then predicts how input parameter variations affect model outputs.\"},{\"question\":\"What computational advantage does ML-AMPSIT provide for sensitivity analysis?\",\"answer\":\"By using surrogate models to avoid many high-fidelity model runs, it significantly reduces the computational burden required for sensitivity and importance assessment.\"}]","ML-AMPSIT - Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool | PDF",1785896986,68,{"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},"ml-ampsit-machine-learning-based-automated-multi-method-parameter-sensitivity-and-importance-analysis-tool","",{"@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/ml-ampsit-machine-learning-based-automated-multi-method-parameter-sensitivity-and-importance-analysis-tool/125150/",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},"Why is calibrating parameters in atmospheric and Earth system models challenging?","Question",{"text":75,"@type":76},"Because model complexity leads to multi-interaction input–output relationships, making simple sensitivity analysis difficult to apply reliably and consistently.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ML-AMPSIT estimate parameter sensitivity and importance?",{"text":80,"@type":76},"It builds computationally inexpensive surrogate models using a multi-method set of regression-based and probabilistic machine learning algorithms, then predicts how input parameter variations affect model outputs.",{"name":82,"@type":73,"acceptedAnswer":83},"What computational advantage does ML-AMPSIT provide for sensitivity analysis?",{"text":84,"@type":76},"By using surrogate models to avoid many high-fidelity model runs, it significantly reduces the computational burden required for sensitivity and importance assessment.","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"]