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

Abstract

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

Comparison between Different Mustard Yield Prediction Models Developed using Various Techniques for Udaipur Region of Rajasthan

“…As shown in Table 6, D index value of SPSS is close to 1 (0.99) whereas that of ANN (0.1 to 0.4) and ARIMA (0.3) which is nowhere close to 1, this clearly indicated that the performance of SPSS model was far better than ANN and ARIMA model to predict mustard yield for Udaipur region. [13] also conducted study on the performance evaluation for wheat yield prediction using PCA-stepwise multiple linear regression (SMLR), ANN and other techniques. The results showed that out of five regions of study area, in three regions (Ludhiana, Amritsar and IARI-New Delhi) the prediction of wheat using ANN during validation showed comparatively more error due to over fitting than validation results using SPSS.…”

Multistage wheat yield prediction using hybrid machine learning techniques

“…Weights are taken as correlation coefficients between yield and weather variables in respective periods. In the same way, indices were also produced for interaction of weather variables by using weekly products of weather variables taking two at a time (Aravind et al, 2022).…”

“…Tibshirani (1996) proposed LASSO, which can be utilized in the crop yield forecasting technique. Aravind et al (2022) reported that elastic Net and LASSO were found to be the best model followed by PCA-SMLR, SMLR, PCA-ANN and ANN respectively for wheat yield prediction of different locations of north-west India. Support vector machine is a classification and regression prediction tool that uses machine learning theory to maximize predictive accuracy while automatically avoiding over-fitting to the data.…”

Comparison of weather-based wheat yield forecasting models for different districts of Uttarakhand using statistical and machine learning Techniques

“…But it consumes a lot of time and needs more human effort. The other alternate of this traditional method is the crop yield estimation by models developed using various statistical techniques.In the current scenario, forecasting of crop yield using Artificial Neural Network (ANN), Least Absolute Shrinkage and Selection Operator (LASSO) and Elastic Net (ELNET) getting a great deal of attention (Das et al, 2020, Aravind et al, 2022. Various efforts have been made by the researchers to develop preharvest yield forecast models based on yield and weather-datasets.…”

“…In the current scenario, forecasting of crop yield using Artificial Neural Network (ANN), Least Absolute Shrinkage and Selection Operator (LASSO) and Elastic Net (ELNET) getting a great deal of attention (Das et al, 2020, Aravind et al, 2022. Various efforts have been made by the researchers to develop preharvest yield forecast models based on yield and weather-datasets.…”