首页|New Machine Learning Data Have Been Reported by Investigators at Kansas State Un iversity (Machine Learning and Fluorosensing for Estimation of Maize Nitrogen St atus At Early Growth-stages)
New Machine Learning Data Have Been Reported by Investigators at Kansas State Un iversity (Machine Learning and Fluorosensing for Estimation of Maize Nitrogen St atus At Early Growth-stages)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Current study results on Machine Learn ing have been published. According to news reporting out of Manhattan, Kansas, b y NewsRx editors, research stated, "Potential of mobile fluorescence sensor meas urements have been in focus for quantifying plant nitrogen (N) variability early in the crop growing season. Real time estimation of such N status indicators at field scale would enable precision management of N fertilizers." Our news journalists obtained a quote from the research from Kansas State Univer sity, "In standard practice, linear regression analysis involves the use of seve ral fluorescence channels and indices as predictive variables for estimating pla nt nitrogen content. Considering the multi-collinearity between these predictor variables, the conventional regression analysis (multiple linear regression) oft en fails to deliver a good range of prediction accuracies. Hence, machine learni ng regression techniques are utilized in this study to estimate N status indicat ors i.e., %N, above ground biomass, and N uptake at V6 and V9 growt h stages of maize across three site-years in 2012 and 2013 crop growing seasons. The Multiplex ®3 (FORCE-A) portable active fluorescence system was used to cap ture fluorescence information. Derived indices including four N balance indices (NBI_R, NBI_B, NBI_B, and NBI1), two chlo rophyll indices (CHL and CHL1), and one flavonoid index (FLAV) were used as pred ictors. The independent site data were first utilized in a Support Vector Regres sion (SVR) model to assess the training and test accuracies in estimation of N s tatus indicators considering a comparative analysis between V6 and V9 growth sta ges. The current research also involved assessing how well the machine learning-trained model could be applied to a different dataset and validated its performa nce in a cross-site experimental setting. Subsequently, cross-site comparisons o f nitrogen status estimates were conducted to recommend the selection of machine learning strategies. These strategies include (1) Partial Least Square Regressi on, (2) Support Vector Regression, (3) Gaussian Process Regression, (4) Random F orest Regression, and (5) Artificial Neural Network. The comparative investigati on demonstrated promising accuracy in estimating plant nitrogen content, above-g round biomass, and nitrogen uptake at the V6 stages of maize, with correlation c oefficients in the moderate range (r = 0.72 +/-0.03) and Root Mean Square Error . Superior prediction accuracies were obtained at V9 growth stages than at V6."
ManhattanKansasUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningNitrogenSupport Vector RegressionKansas State University
NETL
NSTL
