{"id":7097,"date":"2026-10-14T13:58:00","date_gmt":"2026-10-14T11:58:00","guid":{"rendered":"https:\/\/ist.blogs.inrae.fr\/afs\/?p=7097"},"modified":"2026-10-14T09:47:06","modified_gmt":"2026-10-14T07:47:06","slug":"knowledge-guided-machine-learning-for-predicting-the-carbon-sequestration-potential-of-natural-forests-in-heilongjiang-province","status":"publish","type":"post","link":"https:\/\/ist.blogs.inrae.fr\/afs\/2026\/10\/14\/knowledge-guided-machine-learning-for-predicting-the-carbon-sequestration-potential-of-natural-forests-in-heilongjiang-province\/","title":{"rendered":"Knowledge-guided machine learning for predicting the carbon sequestration potential of natural forests in Heilongjiang Province"},"content":{"rendered":"<script type='text\/javascript' src='https:\/\/d1bxh8uas1mnw7.cloudfront.net\/assets\/embed.js'><\/script><p><span style=\"color: #0d5c06\"><span style=\"font-size: 13.3333px\"><b><a href=\"https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1.png\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-7098 alignright\" src=\"https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1-300x196.png\" alt=\"\" width=\"300\" height=\"196\" srcset=\"https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1-300x196.png 300w, https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1-1024x669.png 1024w, https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1-768x502.png 768w, https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1-640x418.png 640w, https:\/\/ist.blogs.inrae.fr\/afs\/wp-content\/uploads\/sites\/5\/2026\/10\/13595_2026_1359_Fig1.png 1102w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a>Research paper<\/b><\/span><\/span><\/p>\n<p><strong>Key message<\/strong><\/p>\n<p align=\"justify\">Integrating ecological process knowledge into machine learning substantially improves the robustness and extrapolation of forest carbon stock predictions. The knowledge-guided model maintained strong predictive performance over 10\u201315-year horizons, when conventional machine-learning performance declined markedly, providing a promising framework for long-term forest carbon assessment under climate change.<\/p>\n<section class=\"c-article-recommendations\" aria-labelledby=\"inline-recommendations\" data-title=\"Inline Recommendations\" data-track-component=\"inline-recommendations\"><\/section>\n<section class=\"c-article-recommendations\" aria-labelledby=\"inline-recommendations\" data-title=\"Inline Recommendations\" data-track-component=\"inline-recommendations\"><\/section>\n<p><strong>Keywords<br \/>\n<\/strong>Forest carbon stock; Long-term extrapolation; XGBoost; CO<sub>2<\/sub> fertilization effect; Process-based modeling; Climate change scenarios; Forest biomass density; Ecological process knowledge<\/p>\n<div class='altmetric-embed' data-badge-type='donut' data-doi='10.1186\/s13595-026-01359-1'  style='float: right; ' ><\/div>\n<p><strong>Publication<br \/>\n<\/strong>Geng, L., Bian, S., Ma, X.\u00a0<i>et al.<\/i> Knowledge-guided machine learning for predicting\u00a0the carbon sequestration potential of natural forests in Heilongjiang Province.\u00a0<i>Annals of Forest Science<\/i>\u00a0<b>83<\/b>, 42 (2026). <a href=\"https:\/\/doi.org\/10.1186\/s13595-026-01359-1\">https:\/\/doi.org\/10.1186\/s13595-026-01359-1<\/a><\/p>\n<p><strong>Handling editor<br \/>\n<\/strong>Fr\u00e9d\u00e9ric Frappart<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Research paper Key message Integrating ecological process knowledge into machine learning substantially improves the robustness and extrapolation of forest carbon stock predictions. The knowledge-guided model maintained strong predictive performance over 10\u201315-year horizons, when conventional machine-learning performance declined markedly, providing a promising framework for long-term forest carbon assessment under climate change. Keywords Forest carbon stock; Long-term [&hellip;]<\/p>\n","protected":false},"author":240,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14,1,109,15],"tags":[],"class_list":["post-7097","post","type-post","status-publish","format-standard","hentry","category-article-type","category-non-classe","category-open-access","category-research-paper","cat-14-id","cat-1-id","cat-109-id","cat-15-id"],"_links":{"self":[{"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/posts\/7097","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/users\/240"}],"replies":[{"embeddable":true,"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/comments?post=7097"}],"version-history":[{"count":1,"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/posts\/7097\/revisions"}],"predecessor-version":[{"id":7099,"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/posts\/7097\/revisions\/7099"}],"wp:attachment":[{"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/media?parent=7097"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/categories?post=7097"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ist.blogs.inrae.fr\/afs\/wp-json\/wp\/v2\/tags?post=7097"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}