[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118868-en":3,"doc-seo-118868-105":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},118868,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Machine learning algorithms improve MODIS GPP estimates in United States croplands","Machine learning methods combined with satellite imagery are evaluated for improving gross primary productivity (GPP) estimates over U.S. croplands. MODIS GPP outputs were integrated for three LTAR cropland sites and initially benchmarked against in situ eddy covariance measurements, then against the combined dataset. AutoML-driven modeling uses air temperature, precipitation, crop type, agroecosystem, and MODIS GPP as inputs. Compared with raw agreement (r2 = 0.38), the best stacked ensemble model substantially improves performance with validated r2 = 0.87, RMSE = 2.62, and MAE = 1.59.","TYPE Original Research PUBLISHED 02 November 2023 DOI 10.3389/frsen.2023.1240895  \nOPEN ACCESS  \nEDITED BY  \nLiangxiu Han,  \nManchester Metropolitan University, United Kingdom  \nREVIEWED BY  \nXiaotong Zhang,  \nBeijing Normal University, China Zexia Duan,  \nNantong University, China  \n*CORRESPONDENCE  \nDorothy Menefee,  \n [dmenefee@tarleton.edu](dmenefee@tarleton.edu)  \nRECEIVED 15 June 2023  \nACCEPTED 09 October 2023  \nPUBLISHED 02 November 2023  \nCITATION  \nMenefee D, Lee TO, Flynn KC, Chen J, Abraha M, Baker J and Suyker A (2023), Machine learning algorithms improve  \nMODIS GPP estimates in United States croplands.  \nFront. Remote Sens. 4:1240895 .  \ndoi: 10.3389/frsen.2023.1240895  \nCOPYRIGHT  \n© 2023 Menefee, Lee, Flynn, Chen, Abraha, Baker and Suyker. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nMachine learning algorithms improve MODIS GPP estimates in United States croplands  \nDorothy Menefee 1*, Trey O. Lee 1, K. Colton Flynn 1, Jiquan Chen 2, Michael Abraha 2, John Baker 3 and Andy Suyker 4  \n1Grassland Soil and Water Research Laboratory, United States Department of Agriculture-Agricultural Research Service, Temple, TX, United States, 2Landscape Ecology and Ecosystem Science (LEES), Michigan State University, East Lansing, MI, United States, 3Soil and Water Management Research, United States Department of Agriculture-Agricultural Research Service, St. Paul, MN, United States, 4Institute of Agriculture and Natural Resources, University of Nebraska-Lincoln, Lincoln, NE, United States  \nIntroduction: Machine learning methods combined with satellite imagery have the potential to improve estimates of carbon uptake of terrestrial ecosystems, including croplands. Studying carbon uptake patterns across the U. S. using research networks, like the Long-Term Agroecosystem Research (LTAR) network, can allow for the study of broader trends in crop productivity and sustainability.  \nMethods: In this study, gross primary productivity (GPP) estimates from the Moderate Resolution Imaging Spectroradiometer (MODIS) for three LTAR cropland sites were integrated for use in a machine learning modeling effort. They are Kellogg Biological Station (KBS, 2 towers and 20 site-years), Upper Mississippi River Basin (UMRB - Rosemount, 1 tower and 12 site-years), and Platte River High Plains Aquifer (PRHPA, 3 towers and 52 site-years) . All sites were planted to maize (Zea mays L.) and soybean (Glycine max L.) . The MODIS GPP product was initially compared to in-situ measurements from Eddy Covariance (EC) instruments at each site and then to all sites combined. Next, machine learning algorithms were used to create refined GPP estimates using air temperature, precipitation, crop type (maize or soybean), agroecosystem, and the MODIS GPP product as inputs. The AutoML program inthe h2o package tested a variety of individual and combined algorithms, including Gradient Boosting Machines (GBM), eXtreme Gradient Boosting Models (XGBoost), and Stacked Ensemble.  \nResults and discussion: The coefficient of determination (r2) of the raw comparison (MODIS GPP to EC GPP) was 0.38, prior to machine learning model incorporation. The optimal model for simulating GPP across all sites was a Stacked Ensemble type with a validated r2 value of 0 . 87, RMSE of 2. 62 units, and MAE of 1 .59. The machine learning methodology was able to successfully simulate GPP across three agroecosystems and two crops.  \nKEYWORDS  \nmachine learning, gross primary productivity, eddy covariance, agroecosystems, remote sensing  \nFrontiers in Remote Sensing 01 [frontiersin.org](frontiersin.org","cbCainmyZUTZ2P70","https://ap.wps.com/l/cbCainmyZUTZ2P70","pdf",1965018,1,12,"English","en",105,"# Introduction\n## Satellite-derived ecosystem productivity\n## LTAR network and remote sensing\n# Methods\n## Study sites and MODIS GPP inputs\n## Model development and AutoML approach\n# Results and discussion\n## Raw comparison performance\n## Best model performance across agroecosystems","[{\"question\":\"What data sources are used to improve MODIS GPP estimates in the study?\",\"answer\":\"The study integrates MODIS GPP products across three LTAR cropland sites and uses in situ eddy covariance measurements for validation. Machine learning models also use air temperature, precipitation, crop type, and agroecosystem as predictors.\"},{\"question\":\"How were the cropland sites set up for modeling and comparison?\",\"answer\":\"Three LTAR cropland sites were included: KBS, UMRB (Rosemount), and PRHPA, all planted to maize and soybean. Each site had multiple towers and site-years, and MODIS GPP was compared to eddy covariance both per site and combined.\"},{\"question\":\"Which machine learning approach produced the best GPP estimates?\",\"answer\":\"A stacked ensemble model achieved the best validated performance across all sites, improving agreement from r2 = 0.38 (raw MODIS vs. eddy covariance) to r2 = 0.87, with RMSE = 2.62 and MAE = 1.59.\"}]","Machine learning algorithms improve MODIS GPP estimates in United States croplands | PDF",1785720701,30,{"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-algorithms-improve-modis-gpp-estimates-in-united-states-croplands","",{"@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-algorithms-improve-modis-gpp-estimates-in-united-states-croplands/118868/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data sources are used to improve MODIS GPP estimates in the study?","Question",{"text":75,"@type":76},"The study integrates MODIS GPP products across three LTAR cropland sites and uses in situ eddy covariance measurements for validation. Machine learning models also use air temperature, precipitation, crop type, and agroecosystem as predictors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the cropland sites set up for modeling and comparison?",{"text":80,"@type":76},"Three LTAR cropland sites were included: KBS, UMRB (Rosemount), and PRHPA, all planted to maize and soybean. Each site had multiple towers and site-years, and MODIS GPP was compared to eddy covariance both per site and combined.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning approach produced the best GPP estimates?",{"text":84,"@type":76},"A stacked ensemble model achieved the best validated performance across all sites, improving agreement from r2 = 0.38 (raw MODIS vs. eddy covariance) to r2 = 0.87, with RMSE = 2.62 and MAE = 1.59.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]