{"id":496,"date":"2025-09-05T18:32:19","date_gmt":"2025-09-05T18:32:19","guid":{"rendered":"https:\/\/eurageng.eu\/?p=496"},"modified":"2025-09-10T18:36:20","modified_gmt":"2025-09-10T18:36:20","slug":"ai-model-trains-real-time-weed-recognition","status":"publish","type":"post","link":"https:\/\/eurageng.eu\/?p=496","title":{"rendered":"AI Model Trains Real Time Weed Recognition"},"content":{"rendered":"

Czech startup Skymaps has launched \u201cZoneye\u201d, an AI model that detects crops and weeds from drone images, trains on local species, and helps farmers cut input costs by 50 percent while boosting yields 20 percent. Crop counting and germination detection also included \u2013 system to be presented at Agritechnica 2025.<\/em><\/p>\n

Czech startup Skymaps has launched Zoneye, an AI model that allows farmers to train the system to recognize weeds unique to their region. Trained to recognize 37 common weed species, Zoneye pinpoints their exact location in the field using drone images. Integrated into the company\u2019s CultiWise prescription-map platform, the tool enables growers to cut input costs by up to 50 percent while boosting yields by up to 20 percent.<\/p>\n

Trained on millions of drone-captured images of crops and weeds, Zoneye can identify, within minutes, all common weeds such as thistle, mayweed and ragweed among major crops including corn, winter wheat, soybean, sugar beet, sunflower, rapeseed, potatoes, and onions. Farmers upload their own drone images to the cloud-based software, which delivers results in minutes.<\/p>\n

Zoneye is available worldwide to CultiWise subscribers and costs 5-20 euros per hectare. Optional CultiWise drones start at 4,200\u202feuros.<\/p>\n

\u201cFarmers have repeatedly stressed the importance of knowing precisely where the weeds are at the plant level so they can tackle these annoying field invaders more effectively while using fewer inputs and reducing environmental impact,\u201d said Kornel Cziria, Chief Technology Officer at Skymaps.<\/p>\n

\u201cAfter more than 500,000 man-hours of development and testing, we are bringing Zoneye to their fields. It is extremely satisfying to achieve this centimeter-level accuracy,\u201d adds Cziria.<\/p>\n

How Zoneye works in practice<\/strong><\/p>\n

Farmers capture field images using drones with RGB cameras \u2014flying at heights of 40 to 120 meters, depending on weed size\u2014and upload them to the CultiWise platform. The system processes images through a proprietary AI model trained on millions of drone photos.<\/p>\n

Within minutes, CultiWise generates precise prescription maps detailing the location, density, and species of weeds, enabling the farmer to decide the exact amount of herbicide required for each area. These maps are exported directly to machinery terminals, guiding sprayers to apply herbicides only to weed-infested areas.<\/p>\n

\u201cIn regions with unusual conditions, like Australia with its red soils, farmers can upload sample drone images of problem areas in real time to CultiWise. The system quickly adapts to the local conditions, allowing what we call a \u2018field-specific adjustment,\u2019\u201d says Cziria.<\/p>\n

\u201cLocal conditions vary, every farmer\u2019s field is different. Now we have put the power in the farmers\u2019 hands so they can train the system for their specific requirements.\u201d<\/p>\n

Turning maps into actions<\/strong><\/p>\n

Known as spot-spraying and variable rate application, this precise crop protection method relies on prescription maps to accurately distribute herbicide. Equipment from companies like Agrifac, Amazone, Horsch, and John Deere uses these maps to target crops effectively.<\/p>\n

Many farmers already own sprayers capable of spot application but often lack the tools and expertise to detect weeds and generate prescription maps.<\/p>\n

The maps inform farmers of expected volume savings. \u201cZoneye offers up to 50 percent reduced herbicide input, because farmers apply only what\u2019s needed and only to the individual weed plants. This can result in increased yields of up to 20 percent due to reduced crop stress,\u201d adds Cziria.<\/p>\n

Unlike conventional \u201cgreen-on-brown\u201d systems that detect weeds only on bare soil, Zoneye distinguishes crops from weeds even in \u201cgreen-on-green\u201d situations where both appear similar to the eye and to cameras.<\/p>\n

Because Zoneye is so precise, it can see right down to the plant level and count every individual crop in a field. This is especially useful when farmers need to decide whether to continue the crop or reseed missing plants.<\/p>\n

\u201cOne farm expected 100,000 sugar beet seeds per hectare to germinate, but many died over winter,\u201d explains Cziria. Zoneye showed the zones where over 65,000 plants per hectare had survived\u2014above the economic threshold\u2014so the farmer was able to reseed only the zones below the threshold.<\/p>\n

Using the same prescription-map technology, Zoneye can also guide seeding. By analyzing plant density and gaps in the field, the system can recommend adjusting seeding rates for areas where germination is low. This ensures uniform crop establishment, optimizes input use, and helps farmers maximize productivity across the field.<\/p>\n

Additionally, Zoneye provides early harvest estimates, giving farmers an advantage when planning resources, managing grain storage, and scheduling sales.<\/p>\n

\u201cWe are pleased with Zoneye\u2019s performance. It was a huge technical challenge for the software to decipher from the drone images what was crop and what was weed and that is because we are dealing with multitude shades of green and in that jungle, the software will have to identify the shape of a particular weed.\u201d<\/p>\n

Zoneye will be presented at Agritechnica 2025, Nov. 9-15 in Germany at the CultiWise stand H35 in hall 9.<\/p>\n

Related news:<\/p>\n

\n
\n
\n
\n\t\t\t\t\t\t\t\t82nd International Conference on Agricultural Engineering, LAND.TECHNIK \u2013 AgEng 2025<\/a>
\n\t\t\t\t\t\t\t<\/h5>\n

\n\t\t\t\t\t\t\t\tWill be held in Hannover (Germany) on November 07-08, as one of the prelude events to AGRITECHNICA, the most important agricultural engineering fair worldwide.\u2026\t\t\t\t\t\t\t<\/p>\n

\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tThe European Society of Agricultural Engineers\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t<\/div>\n<\/p><\/div>\n<\/p><\/div>\n
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\"\"
\n\t\t\t\t\t\t<\/a>\n\t\t\t\t\t<\/div>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

Czech startup Skymaps has launched \u201cZoneye\u201d, an AI model that detects crops and weeds from drone images, trains on local species, and helps farmers cut input costs by 50 percent while boosting yields 20 percent. Crop counting and germination detection also included \u2013 system to be presented at Agritechnica 2025. Czech startup Skymaps has launched […]<\/p>\n","protected":false},"author":1,"featured_media":494,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"vkexunit_cta_each_option":"","footnotes":""},"categories":[8],"tags":[67],"class_list":["post-496","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-zoneye"],"yoast_head":"\nAI Model Trains Real Time Weed Recognition - The European Society of Agricultural Engineers<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/eurageng.eu\/?p=496\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI Model Trains Real Time Weed Recognition - The European Society of Agricultural Engineers\" \/>\n<meta property=\"og:description\" content=\"Czech startup Skymaps has launched \u201cZoneye\u201d, an AI model that detects crops and weeds from drone images, trains on local species, and helps farmers cut input costs by 50 percent while boosting yields 20 percent. Crop counting and germination detection also included \u2013 system to be presented at Agritechnica 2025. Czech startup Skymaps has launched […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/eurageng.eu\/?p=496\" \/>\n<meta property=\"og:site_name\" content=\"The European Society of Agricultural Engineers\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-05T18:32:19+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-10T18:36:20+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1280\" \/>\n\t<meta property=\"og:image:height\" content=\"714\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/eurageng.eu\/?p=496\",\"url\":\"https:\/\/eurageng.eu\/?p=496\",\"name\":\"AI Model Trains Real Time Weed Recognition - The European Society of Agricultural Engineers\",\"isPartOf\":{\"@id\":\"https:\/\/eurageng.eu\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/eurageng.eu\/?p=496#primaryimage\"},\"image\":{\"@id\":\"https:\/\/eurageng.eu\/?p=496#primaryimage\"},\"thumbnailUrl\":\"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg\",\"datePublished\":\"2025-09-05T18:32:19+00:00\",\"dateModified\":\"2025-09-10T18:36:20+00:00\",\"author\":{\"@id\":\"https:\/\/eurageng.eu\/#\/schema\/person\/d2b38f3d02e84eb5f1d362b95d2b7792\"},\"breadcrumb\":{\"@id\":\"https:\/\/eurageng.eu\/?p=496#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/eurageng.eu\/?p=496\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/eurageng.eu\/?p=496#primaryimage\",\"url\":\"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg\",\"contentUrl\":\"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg\",\"width\":1280,\"height\":714},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/eurageng.eu\/?p=496#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/eurageng.eu\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI Model Trains Real Time Weed Recognition\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/eurageng.eu\/#website\",\"url\":\"https:\/\/eurageng.eu\/\",\"name\":\"The European Society of Agricultural Engineers\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/eurageng.eu\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/eurageng.eu\/#\/schema\/person\/d2b38f3d02e84eb5f1d362b95d2b7792\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/eurageng.eu\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/235d6a4135a5e8a44ae89c5261905df9140d9a71bf948a184da4c00f66d23c2a?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/235d6a4135a5e8a44ae89c5261905df9140d9a71bf948a184da4c00f66d23c2a?s=96&d=mm&r=g\",\"caption\":\"admin\"},\"sameAs\":[\"https:\/\/eurageng.eu\"],\"url\":\"https:\/\/eurageng.eu\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI Model Trains Real Time Weed Recognition - The European Society of Agricultural Engineers","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/eurageng.eu\/?p=496","og_locale":"en_GB","og_type":"article","og_title":"AI Model Trains Real Time Weed Recognition - The European Society of Agricultural Engineers","og_description":"Czech startup Skymaps has launched \u201cZoneye\u201d, an AI model that detects crops and weeds from drone images, trains on local species, and helps farmers cut input costs by 50 percent while boosting yields 20 percent. Crop counting and germination detection also included \u2013 system to be presented at Agritechnica 2025. Czech startup Skymaps has launched […]","og_url":"https:\/\/eurageng.eu\/?p=496","og_site_name":"The European Society of Agricultural Engineers","article_published_time":"2025-09-05T18:32:19+00:00","article_modified_time":"2025-09-10T18:36:20+00:00","og_image":[{"width":1280,"height":714,"url":"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg","type":"image\/jpeg"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Estimated reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/eurageng.eu\/?p=496","url":"https:\/\/eurageng.eu\/?p=496","name":"AI Model Trains Real Time Weed Recognition - The European Society of Agricultural Engineers","isPartOf":{"@id":"https:\/\/eurageng.eu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/eurageng.eu\/?p=496#primaryimage"},"image":{"@id":"https:\/\/eurageng.eu\/?p=496#primaryimage"},"thumbnailUrl":"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg","datePublished":"2025-09-05T18:32:19+00:00","dateModified":"2025-09-10T18:36:20+00:00","author":{"@id":"https:\/\/eurageng.eu\/#\/schema\/person\/d2b38f3d02e84eb5f1d362b95d2b7792"},"breadcrumb":{"@id":"https:\/\/eurageng.eu\/?p=496#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/eurageng.eu\/?p=496"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/eurageng.eu\/?p=496#primaryimage","url":"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg","contentUrl":"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg","width":1280,"height":714},{"@type":"BreadcrumbList","@id":"https:\/\/eurageng.eu\/?p=496#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/eurageng.eu\/"},{"@type":"ListItem","position":2,"name":"AI Model Trains Real Time Weed Recognition"}]},{"@type":"WebSite","@id":"https:\/\/eurageng.eu\/#website","url":"https:\/\/eurageng.eu\/","name":"The European Society of Agricultural Engineers","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/eurageng.eu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Person","@id":"https:\/\/eurageng.eu\/#\/schema\/person\/d2b38f3d02e84eb5f1d362b95d2b7792","name":"admin","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/eurageng.eu\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/235d6a4135a5e8a44ae89c5261905df9140d9a71bf948a184da4c00f66d23c2a?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/235d6a4135a5e8a44ae89c5261905df9140d9a71bf948a184da4c00f66d23c2a?s=96&d=mm&r=g","caption":"admin"},"sameAs":["https:\/\/eurageng.eu"],"url":"https:\/\/eurageng.eu\/?author=1"}]}},"jetpack_featured_media_url":"https:\/\/eurageng.eu\/wp-content\/uploads\/2025\/09\/Cultiwise.jpg","_links":{"self":[{"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/posts\/496","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/eurageng.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=496"}],"version-history":[{"count":1,"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/posts\/496\/revisions"}],"predecessor-version":[{"id":497,"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/posts\/496\/revisions\/497"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/eurageng.eu\/index.php?rest_route=\/wp\/v2\/media\/494"}],"wp:attachment":[{"href":"https:\/\/eurageng.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=496"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/eurageng.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=496"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/eurageng.eu\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=496"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}