Impact of Simulated Acid Rain on Seed Germination: A Predictive Study of Solanum Melongena Linn and Vigna Unguiculata Ssp Cylendrica (L.) Walpers by Using ML-based CART Algorithm

Abstract The present study was design to assess the effect of simulated acid rain (SAR) on seed germination of crop plants Brinjal (Solanum melongena Linn.) and Cowpea (Vigna unguiculata ssp. cylindrica (L.) Walpers. The experiments were conducted using 8 plastic trays of approximately 25 cm. x 30 cm, dimensions. Four trays were used for experiments with Brinjal seeds (Set I) while the other four were used for Cowpea seeds (Set II). One tray of each set used as control and treated with distilled water while the rest four trays of each set were provided treatments as: one each for pH 5.6, 4.5, 3.5 and 2.5 SAR solutions. The germination percentage and seed vigour of Brinjal seeds were quite poorer as compared to Cowpea seeds. The treatment of seeds treated with SAR (pH 4.5, 3.5 and 2.5) inhibited seed germination; the inhibitory effect increased with decrease in pH. Mean germination percentage of seeds was highest in normal SAR (pH 5.6) in case of Brinjal seeds but was lowest in the case of Cowpea seeds. It can be concluded that all the plants do not respond to SAR uniformly. This study strategically regressed the simulated acid rain data for necessary behavioral investigation and utilized corresponding Machine Learning based Decision Tree Algorithm to identify and optimize the conditions for the proper germination of these plants. Findings can further help in developing predictive models to predict germination under different environmental conditions to improving crop yield and productivity.