Evaluation of multiple linear, neural network and penalised regression models for prediction of rice yield based on weather parameters for west coast of India

Abstract

Rice is generally grown under completely flooded condition and providing food for more than half of the world's population. Any changes in weather parameters might affect the rice productivity thereby impacting the food security of burgeoning population. So, the crop yield forecasting based on weather parameters will help farmers, policy makers and administrators to manage adversities. The present investigation examines the application of stepwise multiple linear regression (SMLR), artificial neural network (ANN) solely and in combination with principal components analysis (PCA) and penalised regression models (e.g. least absolute shrinkage and selection operator (LASSO) or elastic net (ENET)) for rice yield prediction using long-term weather data. The R and root mean square error (RMSE) of the models varied between 0.22-0.98 and 24.02-607.29 kg ha, respectively during calibration. During validation with independent dataset, the RMSE and normalised root mean square error (nRMSE) ranged between 21.35-981.89 kg ha and 0.98-36.7%, respectively. For evaluation of multiple models for multiple locations statistically, overall average ranks on the basis of R and RMSE of calibration; RMSE and nRMSE of validation were calculated and non-parametric Friedman test was applied to check the significant difference among the models. The ranking of the models revealed that LASSO (2.63) was the best performing model followed by ENET (3.07) while PCA-ANN (4.19) was the worst model which was found significant at p < 0.001. The reason behind good performance of LASSO and ENET is that these models prevent overfitting and reduce model complexity by penalising the magnitude of coefficients. Then, pairwise multiple comparison test was performed which indicated LASSO as the best model which was found similar to SMLR and ENET. So, for prediction of rice yield, these models can very well be utilised for west coast of India.

A Comparison of Hybrid Machine Learning Algorithms for the Retrieval of Wheat Biophysical Variables from Sentinel-2

“…To assess the presence of statistically significant differences among the performances of the models, we applied a Friedman test to the computed metrics [63]. Whenever the Friedman test revealed significant differences (p < 0.001) among the metric means, which indicated the presence of significant differences among the models, a Friedman's aligned ranks post-hoc test, followed by Benjamini/Hochberg (non-negative) adjusted for p-values, was performed for multiple pairwise comparisons.…”

Artificial Neural Network to Estimate the Paddy Yield Prediction Using Climatic Data

“…ey have considered many variables including maximum and minimum temperature, average rainfall, humidity, climate, weather, types of land, types of chemical fertilizer, types of soil, soil structure, soil composition, soil moisture, soil consistency, soil reaction, and soil texture; however, instead of particularly on paddy, they have analyzed total crop yield, but including paddy too. However, Das et al [42] have used several models, including liner, neural network, and penalized regression models to predict the rice yield in west coast of India. One important common conclusion was found from all above cited references; there is always an error threshold in the prediction as the prediction is based on the climate data.…”

Rice Irrigation Schedule Optimization Based on the AquaCrop Model: Study of the Longtouqiao Irrigation District

“…However, the simulated production values for controlled, wet and basin irrigation were all less than the measured values, which were 13.70%, 7% and 7.79%, respectively. In this paper, the normalized root mean square error (NRMSE), Nash efficiency coefficient (NSE) and determination coefficient R 2 [36] are selected to evaluate the degree of coincidence between the simulated and measured values of the model [37]. The model validation results are shown in Table 3.…”

“…The model validation results are shown in Table 3. If NRMSE < 10%, the simulation value is considered excellent; if NRMSE is greater than 10% but In this paper, the normalized root mean square error (NRMSE), Nash efficiency coefficient (NSE) and determination coefficient R 2 [36] are selected to evaluate the degree of coincidence between the simulated and measured values of the model [37]. The model validation results are shown in Table 3.…”