The drug yielding potential of turmeric (Curcuma longa L.) is largely due to the presence of phyto-constituent ‘curcumin’. Curcumin has been found to possess a myriad of therapeutic activities ranging from anti-inflammatory to neuroprotective. Lack of requisite high curcumin containing genotypes and variation in the curcumin content of turmeric at different agro climatic regions are the major stumbling blocks in commercial production of turmeric. Curcumin content of turmeric is greatly influenced by environmental factors. Hence, a prediction model based on artificial neural network (ANN) was developed to map genome environment interaction basing on curcumin content, soli and climatic factors from different agroclimatic regions for prediction of maximum curcumin content at various sites to facilitate the selection of suitable region for commercial cultivation of turmeric. The ANN model was developed and tested using a data set of 119 generated by collecting samples from 8 different agroclimatic regions of Odisha. The curcumin content from these samples was measured that varied from 7.2% to 0.4%. The ANN model was trained with 11 parameters of soil and climatic factors as input and curcumin content as output. The results showed that feed-forward ANN model with 8 nodes (MLFN-8) was the most suitable one with R2 value of 0.91. Sensitivity analysis revealed that minimum relative humidity, altitude, soil nitrogen content and soil pH had greater effect on curcumin content. This ANN model has shown proven efficiency for predicting and optimizing the curcumin content at a specific site.
Ocimum basilicum var. thyrsiflora is valuable for its medicinal properties. The barriers to the commercialization of essential oil are the lack of requisite high oil-containing genotypes and variations in the quantity and quality of essential oils in different geographic areas. Thai basil’s essential oil content is significantly influenced by soil and environmental factors. To optimize and predict the essential oil yield of Thai basil in various agroclimatic regions, the current study was conducted. The 93 datasets used to construct the model were collected from samples taken across 10 different agroclimatic regions of Odisha. Climate variables, soil parameters, and oil content were used to train the Artificial Neural Network (ANN) model. The outcome showed that a multilayer feed-forward neural network with an R squared value of 0.95 was the most suitable model. To understand how the variables interact and to determine the optimum value of each variable for the greatest response, the response surface curves were plotted. Garson’s algorithm was used to discover the influential predictors. Soil potassium content was found to have a very strong influence on responses, followed by maximum relative humidity and average rainfall, respectively. The study reveals that by adjusting the changeable parameters for high commercial significance, the ANN-based prediction model with the response surface methodology technique is a new and promising way to estimate the oil yield at a new site and maximize the essential oil yield at a particular region. To our knowledge, this is the first report on an ANN-based prediction model for Ocimum basilicum var. thyrsiflora.