首页|New Machine Learning Findings from Anhui Agricultural of University Described (H yperspectral Estimation for Nitrogen and Phosphorus Content In camellia Oleifera Leaves Based On Machine Learning Algorithms)
New Machine Learning Findings from Anhui Agricultural of University Described (H yperspectral Estimation for Nitrogen and Phosphorus Content In camellia Oleifera Leaves Based On Machine Learning Algorithms)
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
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews-A new study on Machine Learning is now available. According to news reporting originating fromHefei, People's Republic of China, by NewsRx correspondents, research stated, "Nitrogen and phosphorusare essenti al elements of plants, which play important roles in representing plant growth, physiologicalfunction regulation, fruit harvest, etc. Hyperspectral technology provides a nondestructive, rapid, highlyaccurate, and cost-efficient method for plant leaf nutrient content estimation."Financial support for this research came from National Natural Science Foundatio n of China (NSFC).Our news editors obtained a quote from the research from the Anhui Agricultural of University, "Thereare very limited studies on nutrient diagnosis of Camellia oleifera leaves using hyperspectral technology. Inthis work, 160 Camellia olei fera samples were used. Hyperspectral data were obtained using a full-bandspect rometer. On the basis of preprocessing, the spectral response characteristics of leaf nitrogen content(LNC) and leaf phosphorus content (LPC) were revealed by comparing different combinations of spectralindices, and the spectral variables were further selected. The optimal LNC and LPC estimation modelsbased on three machine learning algorithms [i.e., support vector machine (S VM), random forest (RF),and back propagation neural network (BPNN)] were constructed. The results showed that the spectralsensitive regions of leaf nitrogen and phosphorus content were mainly reflected in green band, followedb y red band and the long-wave direction of short-wave infrared band. Savitzky-Gol ay first derivative(SGFD) pretreatment method was generally better than multipl icative scatter correction. The maximumcorrelation coefficients of the absolute values of LNC, LPC, and spectral transformation features were 0.56and 0.49. Th e optimal LNC and LPC models were both SGFD-TBNDSI-BPNN, with R-2 of 0.81 and 0.79, and RMSEP of 0.55 and 0.06 g/kg, respectively."
HefeiPeople's Republic of ChinaAsiaAlgorithmsCyborgsEmerging TechnologiesMachine LearningNitrogenPhospho rusTechnologyAnhui Agricultural of University
NETL
NSTL
