Wheat yield prediction based on weather parameters using multiple linear, neural network and penalised regression models

Wheat yield production is largely attributed by weather parameters. Model developed multiple linear, neural network and penalised regression techniques using data have the potential to provide reliable, timely cost-effective prediction of wheat yield. parameter during crop growing period (46th 15th SMW) for more than 30 years were collected study area model was stepwise linear (SMLR), principal component analysis (PCA) in combination with SMLR, artificial (ANN) alone PCA, least absolute shrinkage selection operator (LASSO) elastic net (ENET) techniques. Analysis carried out fixing 70% calibration remaining dataset validation. On examining these models, LASSO are performing excellent having nRMSE value less 10 % four five location good one location, because prevention over fitting reducing coefficient penalization.