[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125122-en":3,"doc-seo-125122-105":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},125122,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Explainable machine learning for modeling of net ecosystem exchange in boreal forests - Research article","Growing interest in machine-learning approaches for predicting net ecosystem exchange (NEE) using site information and climate drivers is addressed through four models: cubist, random forest, averaged neural networks, and linear regression. The study uses Finnish boreal-forest datasets from Hyytiälä and Värriö to model NEE for the peak growing season and for the full year. Explainable AI identifies key predictors—radiation-related variables and vapor pressure deficit (or air temperature) seasonally, and vapor pressure deficit replaced by soil temperature on a yearly scale. Model scores can be strong, yet results require caution for upscaling due to opposite dependencies among interdependent inputs under future climates.","Biogeosciences, 22, 257–288, 2025  \n[https://doi.org/10.5194/bg-22-257-2025](https://doi.org/10.5194/bg-22-257-2025)[ ](https://doi.org/10.5194/bg-22-257-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nExplainable machine learning for modeling of net ecosystem exchange in boreal forests  \nEkaterina Ezhova 1 ;􀀔 , Topi Laanti2 ;􀀔 , Anna Lintunen1 , Pasi Kolari 1 , Tuomo Nieminen 1 , Ivan Mammarella 1 , Keijo Heljanko2,3 , and Markku Kulmala 1  \n1INAR Physics, University of Helsinki, Helsinki, Finland  \n2Department of Computer Science, University of Helsinki, Helsinki, Finland  \n3Helsinki Institute for Information Technology (HIIT), Helsinki, Finland  \n􀀔 These authors contributed equally to this work.  \nCorrespondence: Ekaterina Ezhova (ekaterina.ezhova@helsinki.fi) and Topi Laanti (topi.m.laanti@helsinki.fi)  \nReceived: 1 November 2023 – Discussion started: 6 December 2023  \nRevised: 29 August 2024 – Accepted: 29 October 2024 – Published: 13 January 2025  \nAbstract. There is a growing interest in applying machine learning methods to predict net ecosystem exchange (NEE) based on site information and climatic variables. We apply four machine learning models (cubist, random forest, averaged neural networks, and linear regression) to predict the NEE of boreal forest ecosystems based on climatic and site variables. We use data sets from two stations in the Finnish boreal forest (southern site Hyytiälä and northern site Värriö) and model NEE during the peak growing season and the whole year. For Hyytiälä, all nonlinear models demonstrated similar results with R2 D 0. 88 for the peak growing season and R2 D 0.90 for the whole year. For Värriö, nonlinear models gave R2 D 0.73–0.76 for the peak growing season, whereas random forest and cubist with R2 D 0.74 were somewhat better than averaged neural networks with R2 D 0.70 for the whole year. Using explainable artificial intelligence methods, we show that the most important input variables during the peak season are photosynthetically active radiation, diffuse radiation, and vapor pressure deficit (or air temperature), whereas, on the whole-year scale, vapor pressure deficit (or air temperature) is replaced by soil temperature. When the data sets from both stations were mixed, soil water content, the only variable clearly different between Hyytiälä and Värriö data sets, emerged as one of the most important variables, but its importance diminished when input variables labeling sites were added. In addition, we analyze the dependencies of NEE on input variables against the existing theoretical understanding of NEE drivers. We show that even though the statistical scores of some models can  \nbe very good, the results should be treated with caution, especially when applied to upscaling. In the model setup with several interdependent variables ubiquitous in atmospheric measurements, some models display strong opposite dependencies on these variables. This behavior might have adverse consequences if models are applied to the data sets in future climate conditions. Our results highlight the importance of explainable artificial intelligence methods for interpreting outcomes from machine learning models, particularly when a set containing interdependent variables is used as a model input.  \n1 Introduction  \nForests play an important role in the global carbon cycle because they remove carbon from the atmosphere through photosynthesis and store it in the wood biomass and forest soil. Recent studies suggest that in the past several decades, thenet carbon uptake of the boreal forest has been increasing and that of the tropical forest has been decreasing, making the boreal forest the largest terrestrial carbon sink on the planet (Tagesson et al., 2020) . The dynamics ofthe forest carbon cycle and its interaction with various climatic drivers are generally well understood; however, the complex responses of forests to climate change and their potential to","cbCaighN9R7xHioE","https://ap.wps.com/l/cbCaighN9R7xHioE","pdf",13264374,1,32,"English","en",105,"# Introduction\n## Motivation and background\n## Machine learning for carbon-flux modeling\n## Functional relationships for NEE prediction","[{\"question\":\"What models are used to predict NEE in boreal forests?\",\"answer\":\"The study applies cubist, random forest, averaged neural networks, and linear regression to predict net ecosystem exchange from site and climatic variables.\"},{\"question\":\"How does model performance compare across the two stations and time scales?\",\"answer\":\"For Hyytiälä, nonlinear models show similar performance with R2 around 0.88 for the peak season and 0.90 for the whole year. For Värriö, nonlinear models yield lower R2 (about 0.73–0.76) for the peak season, while random forest and cubist perform somewhat better than averaged neural networks on the full-year scale.\"},{\"question\":\"Which variables are identified as most important by explainable AI, and how does that change seasonally?\",\"answer\":\"During the peak season, photosynthetically active radiation, diffuse radiation, and vapor pressure deficit (or air temperature) are most important. On the whole-year scale, vapor pressure deficit (or air temperature) is replaced by soil temperature; mixing station datasets elevates soil water content as important but its impact decreases when site-label inputs are added.\"}]","Explainable machine learning for modeling of net ecosystem exchange in boreal forests - Research article | PDF",1785896782,81,{"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},"explainable-machine-learning-for-modeling-of-net-ecosystem-exchange-in-boreal-forests-research-article","",{"@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/explainable-machine-learning-for-modeling-of-net-ecosystem-exchange-in-boreal-forests-research-article/125122/",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 models are used to predict NEE in boreal forests?","Question",{"text":75,"@type":76},"The study applies cubist, random forest, averaged neural networks, and linear regression to predict net ecosystem exchange from site and climatic variables.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does model performance compare across the two stations and time scales?",{"text":80,"@type":76},"For Hyytiälä, nonlinear models show similar performance with R2 around 0.88 for the peak season and 0.90 for the whole year. For Värriö, nonlinear models yield lower R2 (about 0.73–0.76) for the peak season, while random forest and cubist perform somewhat better than averaged neural networks on the full-year scale.",{"name":82,"@type":73,"acceptedAnswer":83},"Which variables are identified as most important by explainable AI, and how does that change seasonally?",{"text":84,"@type":76},"During the peak season, photosynthetically active radiation, diffuse radiation, and vapor pressure deficit (or air temperature) are most important. On the whole-year scale, vapor pressure deficit (or air temperature) is replaced by soil temperature; mixing station datasets elevates soil water content as important but its impact decreases when site-label inputs are added.","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"]