Papers

IDENTIFICATION OF YIELD PREDICTORS OF WHEAT (Triticum aestivum L.) UNDER SALT STRESS USING RANDOM FOREST, MULTIPLE AND STEPWISE REGRESSION (Pages : 20 - 25)

M. HASANUZZAMAN, S.H.M.G. SARWAR AND M.S. ISLAM

Salinity is one of the important limiting factors for the production of wheat in the southern coastal region of Bangladesh. The effectiveness of the selection of wheat genotypes depends on the perfectly-identified yield predictors' variables. The present study was conducted to assess the yield components under the salinity stress environment using the multiple regression, stepwise regression and random forest model. This research was conducted with ten wheat genotypes, grown in earthen pots with 10 dSm-1 salinity and control in consecutive two seasons of 2013-2014 to 2014-2015. All treatments were arranged in a complete randomized design (CRD) with three replications. Data were recorded on the shoot and root traits. The results showed that salinity treatment represses the development of roots causing grain yield loss of all wheat genotypes. Considering the predictors' variables, such as phenology: days to heading, days to maturity; yield attributes: effective tillers plant-1, plant height, spike length, spikelets spike-1, grains spike-1; root traits: length, volume, fresh weight, dry weight, random forest, multiple linear regression and stepwise regression, all three methods have identified dry root weight and number of grains bearing tillers contributes to grain yield per plant under salt stress. Selection through these traits may be effective in a saline environment. The performance of random forest is superior to multiple linear regression and stepwise regression models showing the lowest MSE. Download


Latest News

Upcoming Issue: International Journal of Sustainable Crop Production, Volume 18 Issue 2, November 2023
Upcoming Issue: Journal of Soil and Nature, Volume 10 Issue 1, November 2023
Upcoming Issue: Journal of Innovation and Development Strategy, Volume 14 Issue 1, December 2023
Upcoming Issue: International Journal of Experimental Agriculture, Volume 14 Issue 1, January 2024

Contact Us

Green Global

+880 1712 068306


Green Global

editor@ggfjournals.com rajuakhtar8@gmail.com