Description: Freshwater quality and quantity are some of the fundamental requirements for sustaining human life and civilization. The Water Quality Index is the most extensively used parameter for determining water quality worldwide. However, the traditional approach for the calculation of the WQI is often complex and time consuming since it requires handling large data sets and involves the calculation of several subindices. We investigated the performance of artificial intelligence techniques, including particle swarm optimization (PSO), a naive Bayes classifier (NBC), and a support vector machine (SVM), for predicting the water quality index. We used an SVM and NBC for prediction, in conjunction with PSO for optimization. To validate the obtained results, groundwater water quality parameters and their corresponding water quality indices were found for water collected from the Pindrawan tank area in Chhattisgarh, India. Our results show that PSO–NBC provided a 92.8% prediction accuracy of the WQI indices, whereas the PSO–SVM accuracy was 77.60%. The study’s outcomes further suggest that ensemble machine learning (ML) algorithms can be used to estimate and predict the Water Quality Index with significant accuracy. Thus, the proposed framework can be directly used for the prediction of the WQI using the measured field parameters while saving significant time and effort.

Description: Wetlands in urban ecosystems provide significant environmental benefits. In the present study, the concept of urban constructed wetland development is studied from the viewpoint of urban planning with dynamic water level orifice setting controller. A two-step modelling procedure is carried out: (1) development of a hybrid model, by coupling a well-established two-dimensional hydrodynamic model (International River Interface Cooperative, iRIC) with a one-dimensional physically-based, distributed-parameter model (Storm Water Management Model, SWMM), to compute and map flood scenarios and to identify the flood-prone areas; and (2) use of SWMM to simulate the water inflow to the proposed constructed wetland, which acts as a cushion for storing excess flood water. The proposed methodology is implemented on the Jahangirpuri drain catchment located in Delhi, India. Results show that the hybrid model is effective, and the simulations are observed to be in good agreement with the recorded data, which assist in detecting the flood-prone areas. Further, an estimation of the impact of the proposed constructed wetland on catchment hydrology indicates an overall reduction of 23% in flooding adjacent to the channel with a significant reduction in backflow as well as water depth in the drain. The flapgate at the outlet of the wetland helps in maintaining the desired water depth in the wetland. The outcomes of this study will assist the hydrologists and administrators in urban stormwater management and planning to mitigate the impact of floods in urban watersheds.

Description: Climate change and urbanization are significantly magnifying flood hazard, leading to a greater vulnerability of urban concentrations. This paper investigates the impact of climate change on urban flooding using future projected rainfall data and a calibrated hydraulic model. Two urban watersheds in Delhi, India (the Qudesia Nallah catchment and the Jahangirpuri drain catchment) are considered to evaluate the climate change impact on urban flooding. Regional climate models (RCMs) are used to project future precipitation, which is then utilized by the hydraulic model to evaluate the impact on flooding. Climate data from three RCMs extracted from the Coordinated Regional Climate Downscaling Experiment (CORDEX) are used to study the impact of climate change for historical (1990–2016) and future scenario (Representative Concentration Pathway (RCP) 4.5, 2021–2100). The rainfall projections are fed as 2-, 5-, 10-, and 20-year return periods to a calibrated hydrodynamic Storm Water Management Model (SWMM). The results show that the flooded nodes vary between 2–6 and 12–43, respectively, in the Qudesia Nallah catchment and the Jahangirpuri drain catchment under present conditions but increase from 11 to 51 and 42 to 91, respectively, for future climate conditions. The results suggest that the risk of occurrence of flooding, duration, and frequency in the two study areas will increase in the future when compared to those under the present conditions. The results also indicate that the damage induced by the 20-year return period rainfall at the present time will likely be caused just by the 2-year return period in the future. This is due to the greater likelihood of rainfall extremes in the region. The potential flooding sites identified in this study will provide the urban municipalities with substantive information to perform ameliorative strategies.