Spatial variation of N2-fixation in field pea (Pisum sativum L.) at the field scale determined by the 15N natural abundance method

Grain legumes such as field pea are known to have high variability of yield and dinitrogen (N2) fixation between seasons, but less is known about the yearly spatial variability within a field. The objective of this study was to improve the understanding of spatial field scale variability of field pea dry matter (DM) yield and nitrogen (N) acquisition from fixation and soil within a 10 ha farmer’s field. A 42 m systematic random grid providing 56 plant sampling locations across 10 ha supplemented by soil data provided from an existing database were used to determine whether the observed spatial variability could be explained by the variability in selected abiotic soil properties. All measured soil variables showed substantial variability across the field and the pea dry matter production ranged between 4.9 and 13.8 Mg ha−1 at maturity. The percent of total N derived from the atmosphere (%Ndfa) at flowering, estimated using the 15N natural abundance method, ranged from 65% to 92% with quantitative N2-fixation estimates from 93 kg to 202 kg N ha−1. At maturity %Ndfa ranged from 26% to 81% with quantitative N2-fixation estimates from 48 kg to 167 kg N ha−1. Significant correlations were found between pea dry matter production and humus content, potassium content (collinear with humus) and total N in the 0–25 cm topsoil. No correlation was found between any individual soil property and %Ndfa or kg N fixed ha−1. It was not possible to create a satisfactory global multi-regression model for the field dry matter production and N2-fixation. A number of other models were tested, but the best was only able to explain less than 40% of the variance in %Ndfa using seven soil properties. Together with the use of interpolated soil data, high spatial variation of soil 15N natural abundance, a mean increase in pea 15N natural abundance of 1 δ unit between flowering and maturity and a reference crop decline of 1.3 δ15N unit over the same period increased noise of derived variables, making modeling of N2-fixation difficult. Furthermore, complex interactions with other soil variables and biotic stresses not measured in this study may have contributed significantly to the variability of fixation and yield of pea within the field. Pea N2-fixation obtained from two additional 10 ha farmer fields was in agreement with the other findings highlighting that N2-fixation takes place under a range of physical and chemical soil properties and is controlled by local site specific conditions. In future studies addressing field scale variability we recommend that soil variables wherever possible should be measured in the same plots as the sampled crop. Sampling designs that optimize the use of a priori information about the field soil and landscape properties for positioning plots and that facilitate estimates of local variances should be considered.