Participants were tasked with training\u00a0machine learning\u00a0models to estimate pasture biomass directly from images,\u00a0using data collected across different\u00a0Australian\u00a0regions,\u00a0seasons\u00a0and pasture types.\u00a0<\/p>\n
The winning teams\u00a0demonstrated\u00a0that advanced models\u00a0can\u00a0learn to extract meaningful information from images \u2013 such as the amount of plant material,\u00a0including grass and other vegetation available for livestock to graze \u2013 and do so reliably across changing conditions.\u00a0<\/p>\n
This approach supports a shift\u00a0from broad monitoring to targeted, site-specific management that pinpoints exactly where fertiliser or other interventions are needed.\u00a0<\/p>\n
With a US$75,000 prize pool, the competition attracted\u00a0nearly 100,000\u00a0model submissions from approximately 14,000 registrations across 109 countries, highlighting strong global interest in applying specialised data science to\u00a0real-world\u00a0agricultural challenges.\u00a0<\/p>\n
CSIRO Senior Principal Research Scientist,\u00a0Dr\u00a0Dadong\u00a0Wang,\u00a0said the results were\u00a0an important step\u00a0forward for\u00a0agricultural research, environmental monitoring and sustainable land management.\u00a0<\/p>\n
“Within a short period,\u00a0competitors tested a wide range of approaches and refined their models in different ways,\u00a0leading to major improvements in how accurately feed levels could be predicted\u00a0across different regions,\u00a0seasons and pasture conditions,”\u00a0said Dr Wang.\u00a0\u00a0<\/p>\n
“The winning solutions showed that reliable results can be achieved using relatively small amounts of data,\u00a0making these tools practical for real-world farming environments where conditions are constantly changing.”\u00a0<\/p>\n
Rather than building\u00a0solutions\u00a0tailored to individual sites or seasons,\u00a0top\u2011performing teams focused on enabling systems to perform reliably across different environments by\u00a0recognising\u00a0patterns in pasture\u00a0and capturing\u00a0fine botanical details in the images,\u00a0such as dying grass or small clover leaves.\u00a0This approach helped ensure predictions remained reliable even as landscapes,\u00a0weather conditions and pasture composition changed.\u00a0<\/p>\n
MLA Group Manager \u2013 Science and Innovation,\u00a0Michael Lee,\u00a0said the outcomes highlighted growing opportunities to support producers with better information.\u00a0<\/p>\n
“Accurately understanding how much feed is available and what the feed is comprised of is fundamental to grazing management,” Mr Lee said.\u00a0<\/p>\n
\u201cThe approaches demonstrated through this competition point to future tools that could reduce reliance on manual measurement and provide producers with faster, richer insights to support\u00a0day\u2011to\u2011day\u00a0decisions.\u201d\u00a0<\/p>\n
Google Australia’s Partnerships Principal,\u00a0Mr Scott Riddle,\u00a0said the competition showed the value of connecting research,\u00a0industry\u00a0and the global technology community.\u00a0<\/p>\n
“By bringing together CSIRO’s scientific expertise,\u00a0MLA’s industry knowledge and the global Kaggle community,\u00a0this challenge demonstrates how partnerships can help bridge the gap between research and practical solutions,”\u00a0Mr Riddle said.\u00a0
\n
\n
\n
\n ![\"FrontierSI](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2026\/05\/FrontierSI.png\")
\n
\n
\n
\n
\n <\/p>\n
CSIRO will now analyse the winning approaches in detail to inform future research and\u00a0development,\u00a0and\u00a0will continue working with industry partners to explore how the most promising methods could be translated into practical,\u00a0scalable pasture measurement tools.\u00a0<\/p>\n
This work has been supported by FrontierSI (previously known as the Cooperative Research Centre for Spatial Information).\u00a0<\/p>\n
\u00a0
\nThe winning teams of the Image2Biomass Prediction Competition include:\u00a0\u00a0<\/p>\n
Team \u5377\u4e0d\u52a8\u4e86 from China took a novel approach by treating available feed as a counting problem rather than a simple estimate, enabling models to adapt to new conditions and improve accuracy on unseen data.\u00a0
\n Team dino series from Vietnam focused on understanding where feed appears within an image, estimating spatial distribution and using simulated environmental variation to strengthen performance.\u00a0
\n Team embee from the United States prioritised robustness by combining multiple models into a single system, reducing overfitting and delivering more consistent results across a highly variable dataset.\u00a0
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
27 April 2026
News Release
…\n","protected":false},"author":2,"featured_media":643555,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":["post-643554","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-au","tag-australia","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/643554","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/comments?post=643554"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/643554\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/643555"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=643554"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=643554"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=643554"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}