【不同品种水稻氮素吸收率】Richard Norman ^*a Trenton Roberts^a Nathan Slaton^a and Anthony Fulford^a. Nitrogen Uptake Efficiency of a Hybrid Compared with a Conventional Pure-Line Rice Cultivar. SSSAJ Vol. 77 No. 4 p. 1235-1240

Abstract

Hybrid rice (Oryza sativa L.) hectarage has increased substantially in the southern United States and necessitated research into the N nutrition of this new type of rice and how it compares to the traditional pure-line rice. Consequently a study was conducted utilizing ¹⁵N-labeled urea applied at a range of N rates on two silt loam soils differing in native soil N to evaluate and compare the N fertilizer uptake efficiency the native soil N uptake and total N uptake of a RiceTec hybrid and a pure-line rice cultivar. The hybrid (60.5 kg N ha⁻¹) had greater soil N uptake compared with the pure-line cultivar (51.7 kg N ha⁻¹). The hybrid had a higher fertilizer N uptake efficiency (FNUE) compared with the pure-line at the location with the lesser native soil N (62.2 vs. 56.2% respectively) but had a similar FNUE at the location with the greater soil N (63.8 vs. 60.0% respectively). Also the pure-line had a higher FNUE and greater N fertilizer response at the location with the greater soil N while the hybrid had a similar FNUE at both locations. The greater total N uptake by the hybrid compared with the pure-line was due to greater soil N uptake at both locations and fertilizer N uptake at the location with the lower native soil N. The results suggest that if the native soil N is below a critical level a pure-line rice cultivar might benefit from a higher rate of N fertilization to maximize FNUE.

【土系地图】Sakthi K. Subburayalu ^*a and Brian K. Slater^a. Soil Series Mapping By Knowledge Discovery from an Ohio County Soil Map. SSSAJ Vol. 77 No. 4 p. 1254-1268

Abstract

Machine learning can be used to derive predictive spatial models from existing soil maps for updating soil surveys improving efficiency of new surveys in similar landscapes and to disaggregate map units containing multiple soil series such as in the Soil Survey Geographic Database (SSURGO). One challenge with using aggregated soil map units as a source for training machine learning systems to map series is ambiguity in labeling the training set. Ambiguity emerges while assigning soil series to instances that would be used as training instances in modeling the data as a map unit in SSURGO can contain more than one component soil series. Disambiguation of training instances is proposed as a technique to handle ambiguity. The k-nearest neighbor (kNN) algorithm which classifies the training examples based on closest training examples in attribute space using the list of component soil series information available in the tabular data of SSURGO is proposed as a viable method to assign most likely soil series t