Machine Learning Approach to Predict Quality Parameters for Bacterial Consortium-Treated Hospital Wastewater and Phytotoxicity Assessment on Radish, Cauliflower, Hot Pepper, Rice and Wheat Crops

Raw hospital wastewater is a source of excessive heavy metals and pharmaceutical pollutants. In water-stressed countries such as Pakistan, the practice unsafe reuse by local farmers for crop irrigation major concern. our previous work, we developed low-cost bacterial consortium treatment method. Here, in two-part study, first aimed to find what physico-chemical parameters were most important differentiating consortium-treated untreated its safe reuse. This was achieved using Kruskal–Wallis test on suite measurements those which differentially abundant between wastewater. The then input Random Forest classifier. classifier showed that ‘turbidity’ influential parameter predicting biotreatment. second part wanted know if irrigation. We therefore carried out plant growth experiment range popular plants Pakistan (Radish, Cauliflower, Hot pepper, Rice Wheat), grown from at dilutions (turbidity levels) performed phytotoxicity assessment. Our results an increasing trend germination indices decreasing one after with (at each dilution/turbidity measure). comparative study following trend: Cauliflower > Radish Wheat pepper. adaptive (PI: −0.28, −0.13, −0.16, −0.06) treated wastewater, while hot pepper susceptible reuse; hence, conclude cauliflower, radish, wheat rice. further turbidity bio-treatment efficiency prior water method, therefore, could represent low-cost, low-tech means grow crops stressed areas.