Li Q.,Hunan Agricultural University |
Zhou J.-H.,Hunan Agricultural University |
Yang R.-S.,Qujing Branch of Yunnan Province Tobacco Company |
Zhang Z.-Y.,Qujing Branch of Yunnan Province Tobacco Company |
And 5 more authors.
Chinese Journal of Applied Ecology | Year: 2011
By adopting GPS technique, 2088 sampling sites were installed in the tobacco planting area of Qujing City, Yunnan Province, with 0-20 cm soil samples collected to determine their main nutrients contents. The overall characteristics and spatial variability of the tobacco soil nutrients were analyzed by classic statistics and geo statistics, and the soil fertility suitability in planting to bacco was evaluated by the methods of fuzzy mathematics. In the study area, soil pH and soil organic matter, available S, and water soluble Cl contents were appropriate, soil total N and alkalihydrolyzable N contents were too high, soil available K, Ca, Mg, Cu, Fe, Zn, Mo, and Mn contents were abundant, soil available P content was at medium level, while soil total P and K and available B contents were insufficient. All the nutrient indices presented anisotropic distribution, among which, the spatial variability of soil available P and B was mainly caused by random factors, and that of other nutrients was caused by the coeffects of structural and random factors. The spatial distribution map of soil fertility suitability index (SFI) showed that there was no the excellent grade region for tobacco planting, good grade region accounted for 8 0%, general grade region accounted for 51 6%, moderate grade region accounted for 39 0%, and low grade region accounted for 1 4%.
Nie M.,Hunan University |
Zhou J.,Hunan University |
Yang R.,Qujing Branch of Yunnan Province Tobacco Company |
Xia K.,Qujing Branch of Yunnan Province Tobacco Company |
And 3 more authors.
Tobacco Science and Technology | Year: 2014
An optimized model of BP neural network for predicting the ratio of potassium to chlorine (K/Cl ratio) in flue-cured tobacco was established by using the measurable factors influencing K/Cl ratio as network inputs, selecting appropriate network parameters with empirical method, and optimizing initial weights and thresholds of neural network with particle swarm algorithm. The results showed that the total correlation coefficient between the prediction value of the test sample and the expected value was 0.97155, which increased by 13.77%, and the samples with the error within [-1, 1] accounted for 86.67%. This model features good fitting ability, certain predictive ability, and significantly improved generalization ability, it is helpful to the evaluation of smoking quality and combustibility of tobacco leaves.