Fig 1.
Relationship between fertilizer-N application rate (kg N ha-1) and dry root weight (g plant-1) of wheat (Triticum aestivum L.) in a sandy loam soil.
Line bars indicate standard error from mean (S.E.M).
Table 1.
Effect of nitrogen (N) and potassium (K) application on yield attributes viz. number of effective tillers, number of non-effective tillers, plant height, spike lengh and root drt weight of wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Fig 2.
Relationship between fertilizer-N application rate (kg N ha-1)and grain yield (Mg ha-1) of wheat (Triticum aestivum L.) in a sandy loam soil.
Line bars indicate standard error from mean (S.E.M).
Table 2.
Effect of nitrogen (N) and potassium (K) application on wheat grain, straw yield (Mg ha-1) and harvest index in a sandy loam soil in sub-tropical India.
Table 3.
Effect of nitrogen (N) and potassium (K) application on N uptake by grain and straw of wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Fig 3.
Effect of nitrogen (N) and potassium (K) application on SPAD value of wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Bars indicate the standard error from mean (S.E.M).
Fig 4.
Quantitative relationship between SPAD value and N uptake (kg ha-1) by grain, straw and total (grain + straw) N uptake by wheat (Triticum aestivum L.) in a sandy loam soil.
Fig 5.
Effect of nitrogen (N) and potassium (K) application on green seeker value for wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Bars indicate the standard error from mean (S.E.M).
Fig 6.
Quantitative relationship between Green seeker value and N uptake by grain, straw and total (grain + straw) N uptake by wheat (Triticum aestivum L.) in a sandy loam soil.
Table 4.
Effect of nitrogen (N) and potassium (K) application on K uptake by grain and straw of wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Table 5.
Effect of nitrogen (N) and potassium (K) application on N use efficiency in wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Table 6.
Effect of nitrogen (N) and potassium (K) application on K use efficiency in wheat (Triticum aestivum L.) in a sandy loam soil in sub-tropical India.
Fig 7.
Effect of nitrogen (N) and potassium (K) application on available-N content in a sandy loam soil in sub-tropical India.
Bars indicate the standard error from mean (S.E.M).
Fig 8.
Effect of nitrogen (N) and potassium (K) application on available-K content in a sandy loam soil in sub-tropical India.
Bars indicate the standard error from mean (S.E.M).
Table 7.
Effect of nitrogen (N) and potassium (K) application on economic indices viz. mean cost of cash inputs (MCCIs), mean gross returns (MGRs), mean net returns (MNRs), benefit-cost (B-C) ratio, economic efficiency, gross returns above the fertilizer cost (GRAFC) and returns on investment on fertilizer application (ROI) for wheat (Triticum aestivum L.) cultivation in a sandy loam soil in sub-tropical India.
(Data pooled for two study years).
Fig 9.
Correlation matrix depicting relationships between different variables and wheat grain yield (r > 0.435; significant at p<0.05 and r > 0.802 significant at p<0.01, others non-significant).
Table 8.
Stepwise regression among different variables for predicting wheat (Triticum aestivum L.) grain yield.
Fig 10.
Schematic representation of propagation neural networks technique, self organizing map (SOM) neighbour weight distance and artificial neural networks (ANNs) consisted of several layers of neurons which are inter-connected and then the weights (weight-1 and weight-2) assigned to those inter-connections.
Fig 11.
Schematic representation of weights (weight-1 and weight-2) assigned to the inter-connections for inputs used for the simulation of wheat grain yield using ten different input layers viz. grain N uptake, straw N uptake, grain K uptake, straw K uptake, total N uptake, total K uptake, SPAD value, green seeker value, RIUEN and RIUEK.
Fig 12.
Cross-correlation using scatter plot (1:1 correspondence, X = Y) of predicted and actual wheat grain (Mg ha-1) using Levenberg Marquardt (LM) algorithm in artificial neural networks (ANNs).
Table 9.
Statistical criteria for evaluating the performance of artificial neural networks (ANNs) for predicting wheat grain yield under different treatments based on grain and straw N uptake, grain and straw K uptake, total N and total K uptake, SPAD value, green seeker value, and reciprocal internal use efficiency of N (RIUEN) and K (RIUEK).