{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T06:07:50Z","timestamp":1788847670340,"version":"build-2803163510"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Reliable rice yield prediction requires machine-learning models with inputs that match the intended decision point and evaluation schemes that reflect the target deployment setting. Random record-level cross-validation remains common in crop-yield machine learning, but it can overestimate performance when models are transferred to future seasons, new sites or new site-year environments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a scenario-aware machine-learning framework using 3,204 yield records from 168 cultivars evaluated across 10 sites, 7 years and 67 site-year environments in southern China. Five modeling feature sets were compared across random five-fold cross-validation, leave-one-year-out validation, forward-year prediction, leave-one-site-out validation and leave-one-site-year-out validation. The feature sets represented whole-season weather, stage-specific climate information, leakage-controlled cultivar yield BLUP, field-survey traits and heading-stage updates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Random five-fold cross-validation produced the highest apparent accuracy, with the best field-survey-enhanced model reaching R\n                      <jats:sup>2<\/jats:sup>\n                      \u00a0=\u00a00.844 and RMSE\u00a0=\u00a0340.59 kg ha\n                      <jats:sup>\u22121<\/jats:sup>\n                      . Deployment-oriented performance was lower. The same information scenario achieved a macro mean R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.359 in forward-year prediction, 0.290 in leave-one-site-out validation and 0.131 in leave-one-site-year-out validation. Stage-specific climate information and leakage-controlled cultivar potential improved prediction before field-survey traits were available, whereas field-survey traits provided the strongest later-stage accuracy. Reduced training size lowered accuracy and increased unseen-cultivar burden. Climate-risk environments showed risk-specific error shifts rather than a uniform model failure.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study supports a deployment-oriented framework for rice yield prediction, rather than a general claim of universal out-of-sample improvement. Its main value is to show how prediction skill, feature utility and model interpretation change when validation is aligned with realistic temporal, spatial and site-year deployment settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1915306","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:35:47Z","timestamp":1788845747000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deployment-oriented evaluation of stage-specific information for rice yield prediction across years, sites and site-year environments in southern China"],"prefix":"10.3389","volume":"17","author":[{"given":"Jinshuai","family":"Zhang","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]},{"name":"School of Accounting, Anyang Institute of Technology","place":["Anyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongquan","family":"Xiong","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyao","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Ouyang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence and Low Altitude Technology, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Huang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Guo","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongzhu","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Plant Space Breeding, College of Agriculture, South China Agricultural University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.14719\/pst.5976","article-title":"Rice yield predictions using remote sensing and machine learning algorithms: A review","volume":"12","author":"Ajay","year":"2025","journal-title":"Plant Sci. Today"},{"key":"B2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2020.108275","article-title":"Integrating multi-source data for rice yield prediction across China using machine learning and deep learning approaches","volume":"297","author":"Cao","year":"2021","journal-title":"Agric. For. Meteorol."},{"key":"B4","doi-asserted-by":"crossref","first-page":"785\u201394","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B5","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1016\/j.tplants.2017.08.011","article-title":"Genomic selection in plant breeding: Methods, models, and perspectives","volume":"22","author":"Crossa","year":"2017","journal-title":"Trends Plant Sci."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109852","article-title":"Modern computational approaches for rice yield prediction: A systematic review of statistical and machine learning-based methods","volume":"231","author":"De Clercq","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolind.2020.106935","article-title":"Integrated phenology and climate in rice yields prediction using machine learning methods","volume":"120","author":"Guo","year":"2021","journal-title":"Ecol. Indic."},{"key":"B8","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: Biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1093\/jxb\/erm003","article-title":"High temperature stress and spikelet fertility in rice (Oryza sativa L.)","volume":"58","author":"Jagadish","year":"2007","journal-title":"J. Exp. Bot."},{"key":"B10","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s00122-013-2243-1","article-title":"A reaction norm model for genomic selection using high-dimensional genomic and environmental data","volume":"127","author":"Jarqu\u00edn","year":"2014","journal-title":"Theor. Appl. Genet."},{"key":"B11","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: A survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B12","first-page":"3146\u201354.","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Advances in Neural Information Processing Systems","author":"Ke","year":"2017"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/insilicoplants\/diad015","article-title":"Ensemble of best linear unbiased predictor, machine learning and deep learning models predict maize yield better than each model alone","volume":"5","author":"Kick","year":"2023","journal-title":"In Silico Plants"},{"key":"B14","doi-asserted-by":"publisher","first-page":"044027","DOI":"10.1088\/1748-9326\/ab7b24","article-title":"Predicting spatial and temporal variability in crop yields: An inter-comparison of machine learning, regression and process-based models","volume":"15","author":"Leng","year":"2020","journal-title":"Environ. Res. Lett."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3390\/s18082674","article-title":"Machine learning in agriculture: A review","volume":"18","author":"Liakos","year":"2018","journal-title":"Sensors"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy16101019","article-title":"Integrating envirotyping and phenomics for AI-enabled multi-environment genomic prediction in crop breeding","volume":"16","author":"Liang","year":"2026","journal-title":"Agronomy"},{"key":"B17","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1126\/science.1204531","article-title":"Climate trends and global crop production since 1980","volume":"333","author":"Lobell","year":"2011","journal-title":"Science"},{"key":"B18","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2019.108815","article-title":"Importance of spatial predictor variable selection in machine learning applications: Moving from data reproduction to spatial prediction","volume":"411","author":"Meyer","year":"2019","journal-title":"Ecol. Modell."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1128388","article-title":"Using machine learning for crop yield prediction in the past or the future","volume":"14","author":"Morales","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"9971","DOI":"10.1073\/pnas.0403720101","article-title":"Rice yields decline with higher night temperature from global warming","volume":"101","author":"Peng","year":"2004","journal-title":"Proc. Natl. Acad. Sci."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/app15137074","article-title":"Interpretable machine learning for legume yield prediction using satellite remote sensing data","volume":"15","author":"Petropoulos","year":"2025","journal-title":"Appl. Sci."},{"key":"B23","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/BF00222462","article-title":"Best linear unbiased prediction (BLUP) for regional yield trials: A comparison to additive main effects and multiplicative interaction (AMMI) analysis","volume":"89","author":"Piepho","year":"1994","journal-title":"Theor. Appl. Genet."},{"key":"B24","first-page":"6639\u201349","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Advances in Neural Information Processing Systems","author":"Prokhorenkova","year":"2018"},{"key":"B25","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1111\/ecog.02881","article-title":"Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure","volume":"40","author":"Roberts","year":"2017","journal-title":"Ecography"},{"key":"B26","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.aiia.2022.11.003","article-title":"Explainable artificial intelligence and interpretable machine learning for agricultural data analysis","volume":"6","author":"Ryo","year":"2022","journal-title":"Artif. Intell. Agric."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1537990","article-title":"Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G x E x M interactions","volume":"16","author":"Sajid","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B28","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1626\/jcs.47.6","article-title":"High temperature-induced sterility in indica rices at flowering","volume":"47","author":"Satake","year":"1978","journal-title":"Jpn. J. Crop Sci."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.1038\/s41598-020-80820-1","article-title":"Coupling machine learning and crop modeling improves crop yield prediction in the US Corn Belt","volume":"11","author":"Shahhosseini","year":"2021","journal-title":"Sci. Rep."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1175\/AIES-D-23-0026.1","article-title":"Cross-validation strategy impacts the performance and interpretation of machine learning models","volume":"2","author":"Sweet","year":"2023","journal-title":"Artif. Intell. For. Earth Syst."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105709","article-title":"Crop yield prediction using machine learning: A systematic literature review","volume":"177","author":"van Klompenburg","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1093\/g3journal\/jkac226","article-title":"learnMET: An R package to apply machine learning methods for genomic prediction using multi-environment trial data","volume":"12","author":"Westhues","year":"2022","journal-title":"G3 Genes|Genomes|Genetics"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1038\/srep34978","article-title":"Heat-induced phytohormone changes are associated with disrupted early reproductive development and reduced yield in rice","volume":"6","author":"Wu","year":"2016","journal-title":"Sci. Rep."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1002\/fes3.70249","article-title":"Linking genetic merit and multi-trait indices with meteorological controls to maize performance across multi-environment trials","volume":"15","author":"Yue","year":"2026","journal-title":"Food Energy Secur."},{"key":"B35","doi-asserted-by":"publisher","first-page":"9326","DOI":"10.1073\/pnas.1701762114","article-title":"Temperature increase reduces global yields of major crops in four independent estimates","volume":"114","author":"Zhao","year":"2017","journal-title":"Proc. Natl. Acad. Sci."},{"key":"B36","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Society: Ser. B. (Statistical Methodology)"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1915306\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:35:48Z","timestamp":1788845748000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1915306\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":36,"alternative-id":["10.3389\/fpls.2026.1915306"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1915306","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"article-number":"1915306"}}