{"id":101630,"date":"2025-02-27T19:11:28","date_gmt":"2025-02-27T19:11:28","guid":{"rendered":"https:\/\/www.greenkeeperapp.com\/marketing\/?p=101630"},"modified":"2025-02-28T01:43:59","modified_gmt":"2025-02-28T01:43:59","slug":"101630","status":"publish","type":"post","link":"https:\/\/www.greenkeeperapp.com\/marketing\/index.php\/101630\/","title":{"rendered":"Predict wilt hours before it strikes: Proof of Concept"},"content":{"rendered":"

[et_pb_section fb_built=”1″ _builder_version=”4.21.0″ _module_preset=”default” min_height=”6713.1px” global_colors_info=”{}”][et_pb_row _builder_version=”4.21.0″ _module_preset=”default” min_height=”6288.3px” custom_padding=”0px||0px||true|” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.21.0″ _module_preset=”default” min_height=”154px” global_colors_info=”{}”]<\/p>\n

The turf industry has embraced various technologies to improve irrigation efficiency. Hand-held moisture meters have replaced pocketknives. Mower-mounted sensors help turf managers detect soil moisture variability, while in-ground sensors relentlessly monitor changes over time. Now, machine-learning optimization\u2014a type of AI that powers GreenKeeper Insight\u2014can be used to accurately predict soil moisture changes days in advance.<\/p>\n

Recently, a good friend and GreenKeeper user called BS<\/em> on this claim. While it sounds outlandish, the data doesn\u2019t lie. GreenKeeper learns how your turf uses water and can accurately predict when wilt will occur.<\/p>\n

[\/et_pb_text][et_pb_divider _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_divider][et_pb_text _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

How Can AI Help Predict Soil Moisture?<\/strong><\/h5>\n

Turfgrass systems lose water through the process of evapotranspiration (ET) and gain water through natural precipitation and irrigation. These processes are governed by many factors, including weather conditions, shade, site slope\/exposure, soil texture, irrigation system design, grass species, mowing height, and more. Managing these variables is complex, yet experienced turf managers develop an intuitive understanding of their site over time.<\/p>\n

Hand-held moisture meters have accelerated this learning process. These tools precisely measure soil moisture content\u2014a key metric that can be tracked, recorded, and managed. Measuring moisture when turf begins to wilt helps determine a site\u2019s specific wilt point. Taking readings throughout the day reveals how quickly a site dries under different weather conditions. Measuring again the next morning demonstrates how irrigation affects soil moisture content.<\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/www.greenkeeperapp.com\/marketing\/wp-content\/uploads\/2024\/03\/x7fqm3.jpg” title_text=”x7fqm3″ _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Hand-held moisture meters don\u2019t just help humans learn\u2014they help machines learn, too. GreenKeeper App already has access to site-specific information, including grass species, soil texture, and hourly weather data, to estimate ET. In fact, hourly ET is estimated using an ensemble of 40 different ET models. By pairing these data with daily soil moisture measurements and irrigation runtimes, the machine-learning algorithm in GreenKeeper Insight can identify additional factors affecting soil moisture fluctuations. These insights are then combined with forecast ET\u2014GreenKeeper predicts reference ET up to 14 days into the future\u2014to model soil moisture changes with impressive accuracy.<\/p>\n

[\/et_pb_text][et_pb_divider _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_divider][et_pb_text _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Validating GreenKeeper Insight on a Golf Course Green<\/strong><\/h5>\n

The GreenKeeper Insight algorithm was firest validated on the sixth green at the Country Club of Lincoln. This bentgrass putting green, maintained to the highest standards, sits on a modified push-up root zone in the heart of Lincoln, NE.<\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/www.greenkeeperapp.com\/marketing\/wp-content\/uploads\/2025\/02\/20240729_132023.jpg” title_text=”20240729_132023″ _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Each morning, we measured the average soil moisture using 12 to 18 readings from a Spectrum TDR 350<\/strong> with 3-inch tines in Sand mode<\/strong>. We also recorded the previous night\u2019s irrigation runtime and entered both values into GreenKeeper App\u2019s Water Resource Planner<\/strong>. (Afternoon hand watering was not accounted for in our model.) The experiment was conducted from August 4 to September 6, 2024.<\/p>\n

In the initial model training phase<\/strong> (gray rows in the data table), the Water Resource Planner used standard estimates for variables like crop coefficient and irrigation output to predict soil moisture for the following day. Users can manually adjust some of these factors in the Settings<\/strong> section of the Water Resource Planner.<\/p>\n

After several days of consistent data entry, GreenKeeper Insight began optimizing its predictions using machine learning (white rows in our dataset). The model continued to improve in accuracy with regular soil moisture measurements.<\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/www.greenkeeperapp.com\/marketing\/wp-content\/uploads\/2025\/02\/Screenshot-2025-02-27-083451.png” title_text=”Screenshot 2025-02-27 083451″ _builder_version=”4.21.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.21.0″ _module_preset=”default” custom_margin=”||1px|||” global_colors_info=”{}”]<\/p>\n

How Accurate Were the Predictions?<\/strong><\/h5>\n

After just 10 days<\/strong>, GreenKeeper Insight dramatically improved the accuracy of soil moisture predictions. Between August 14 and September 6<\/strong>, the average difference between estimated and actual soil moisture was only 0.5% volumetric water content (VWC)<\/strong>. On most days, the difference was less than 0.3%<\/strong>. In comparison, before GreenKeeper Insight optimization, the average difference was 1.9% VWC<\/strong> over the same period.<\/p>\n

One standout day was August 14<\/strong>:<\/p>\n