Evaluating Decision Support Tools for Precision Nitrogen Management on Creeping Bentgrass Putting Greens

Abstract

Nitrogen (N) is the most limiting nutrient for turfgrass growth. Few tools or soil tests exist to help managers guide N fertilizer decisions. Turf growth prediction models have the potential to be useful, but the lone turfgrass growth prediction model only takes into account temperature, limiting its accuracy. This study investigated the ability of a machine learning (ML)-based turf growth model using the random forest (RF) algorithm (ML-RF model) to improve creeping bentgrass (Agrostis stolonifera) putting green management by estimating short-term clipping yield. This method was compared against three alternative N application strategies including (1) PACE Turf growth potential (GP) model, (2) an experience-based method for applying N fertilizer (experience-based method), and (3) the experience-based method guided by a vegetative index, normalized difference red edge (NDRE)-based method. The ML-RF model was built based on a set of variables including 7-day weather, evapotranspiration (ET), traffic intensity, soil moisture content, N fertilization rate, NDRE, and root zone type. The field experiment was conducted on two sand-based research greens in 2020 and 2021. The cumulative applied N fertilizer was 281 kg ha−1 for the PACE Turf GP model, 190 kg ha−1 for the experience-based method, 140 kg ha−1 for the ML-RF model, and around 75 kg ha−1 NDRE-based method. ML-RF model and NDRE-based method were able to provide customized N fertilization recommendations on different root zones. The methods resulted in different mean turfgrass qualities and NDRE. From highest to lowest, they were PACE Turf GP model, experience-based, ML-RF model, and NDRE-based method, and the first three methods produced turfgrass quality over 7 (on a scale from 1 to 9) and NDRE value over 0.30. N fertilization guided by the ML-RF model resulted in a moderate amount of fertilizer applied and acceptable turfgrass performance characteristics. This application strategy is based on the N cycle and has the potential to assist turfgrass managers in making N fertilization decisions for creeping bentgrass putting greens.

Quantifying golf course nitrogen use efficiency

“…Thus N max , as estimated by Woods (2013) and Zhou and Soldat (2022), is an overestimate of the N required on golf courses from this study. This study finds that N max values needed to predict golf course N use rates are lower than currently published N max values.…”

“…The implicit assumption in this method of estimating N max is that all N leaving the system is leaving through clippings, and that replacing this N will lead to a balanced N budget. Zhou and Soldat (2022) found that the amount of N leaving a research green through clippings loss in the 2019 growing season was 230 kg N ha −1 , on a plot of creeping bentgrass that was fertilized with 120 kg N ha −1 which was the highest N rate in the study. This resulted in an N max value of 39 kg ha −1 month −1 , within the range of the values used by Woods (2013).…”

“…Another strategy for choosing N max is to base the parameter on the N harvest rate of research plot turfgrass (Zhou & Soldat, 2022). Zhou and Soldat (2022) chose an N max value that matched the N being removed from the system via clippings. On research plots of bentgrass ( Agrostis stolonifera ) mowed at the height of a golf green and fertilized with 120 kg N ha −1 year −1 , turfgrass N loss via clippings was 39 kg N ha −1 month −1 .…”

“…Using the default N max values as suggested by Woods (2013), 35 kg N ha −1 month −1 for C 3 grasses and 40 kg N ha −1 month −1 for C 4 grasses, the GP Woods (2013) does not specify where their N max values are derived from. Zhou and Soldat (2022) used the GP N Requirement model and derived the N max parameter for greens by estimating the amount of N leaving the system in the form of clippings and then used this amount of N as the N max value. The implicit assumption in this method of estimating N max is that all N leaving the system is leaving through clippings, and that replacing this N will lead to a balanced N budget.…”

“…Another strategy for choosing N max is to base the parameter on the N harvest rate of research plot turfgrass (Zhou & Soldat, 2022). Zhou and Soldat (2022) chose an N max value that matched the N being removed from the system via clippings.…”