Comparison of artificial neural network and linear regression model for the leaf morphology of fenugreek (Trigonella foenum graecum) grown under different nitrogen fertilizer doses

•Leaf morphological parameters are indicative of plant growth and health.•Fenugreek leaf morphology is affected by fertilizer dosage.•Laminar area and roundness are the most affected leaf characteristics.•Linear regression and ANN can be used for estimation of leaf morphology parameters.•ANN exhibited a better predictive competence as compared to linear regression. Health of a plant and its growth can be assessed by the area of its leaf. The present study envisaged to develop an artificial neural network (ANN) and linear regression-based leaf area estimation model, and to compare the models in statistical terms; thereby obtaining a statistically accurate model suitable for predicting leaf area of fenugreek. Fenugreek (Trigonella foenum graecum) was grown at open field conditions at different doses (0, 50, 100, 150, 200, 250, 300, 350 and 400 kgN/ha) of nitrogenous fertilizer using a randomised block design. The morphological parameters in term of leaf area (AP, mm2), leaf width (LW, mm), leaf length (LL, mm), roundness (R), leaf perimeter (LP,mm) and eccentricity (e) using a MATLAB based graphical user interface (GUI) software. Among all the linear regression models, AP =19.66 + 00.62 (LL × LW) (R2 = 0.94, RMSE = 14.09) was found to be the best fitting for fenugreek leaf area estimation. In case of ANN model, the best results obtained when three hidden neurons were considered. The R2, RMSE and MAD values of ANN model during training (0.97, 12.55 and 8.55, respectively) as well as validation (0.97, 10.48 and 7.92, respectively) were found more accurate than the linear regression model. Thus, the proposed ANN model can be used for the estimation of leaf area of fenugreek leaves.