"Identification of promising genotypes in varietal trials of sugarcane using deep learning "

Abstract

Genotypes of varietal trials for identification of promising genotypes of sugarcane undergoes location-based and multiphase testing for both plant and ratoon crop. Identification depends upon analytical studies of data collected from the trials. Data on more than twenty characters such as germination%, tillers, shoots, NMC, fibre, brix, sucrose, CCS, cane yield, etc are collected frequently, starting from germination stage till harvesting at different stages of crop. It is a quite complex and time-consuming task and information about some important parameters may remain unnoticed by experts despite best efforts. Deep learning algorithms can be developed for such complex task to extract high level features from trial data and make intelligent decisions based on it for identifying promising genotypes. Deep learning works on the principle of artificial neural networks in which multiple layers of processing are used to extract progressively higher-level features from data. In this paper, we have demonstrated use of deep learning for identification of promising genotypes. We have developed sequential model using tensorflow libraries in Python programming platform. To construct, train and test deep learning model, datasets of 181 genotypes accepted in coordinated trials of crop improvement programme for the duration 2016-21 have been used. Model uses crop characters viz. cane yield, sucrose%, CCS%, and CCS yield along with score of monitoring and red rot screening. Data management practices allowed to pre-process data for learning and testing model from it. Deep learning in this study consists of input layer, two hidden layers and output layer. Output classes are ’Promising” and “Non-promising” in binary form corresponding to promising genotype or otherwise. Model performed well with accuracy of prediction worked out to be 91.67% with loss value as 0.2832, while F-measure for both promising and non-promising genotypes got a high equivalent score of 0.91 and 0.92 respectively.