Search

Accurate flood forecasting is a crucial process for predicting the timing, occurrence, duration, and magnitude of floods in specific zones. This prediction often involves analyzing various hydrological, meteorological, and environmental parameters. In recent years, several soft computing techniques have been widely used for flood forecasting. In this study, flood forecasting for the Narmada River at the Hoshangabad gauging site in Madhya Pradesh, India, was conducted using an Artificial Neural Network (ANN) model, a Fuzzy Logic (FL) model, and an Adaptive Neuro-Fuzzy Inference System (ANFIS) model. To assess their capacity to handle different levels of information, three separate input data sets were used. Our objective was to compare the performance and evaluate the suitability of soft computing data-driven models for flood forecasting. For the development of these models, monthly discharge data spanning 33 years from six gauging sites were selected. Various performance measures, such as regression, root mean square error (RMSE), and percentage deviation, were used to compare and evaluate the performances of the different models. The results indicated that the ANN and ANFIS models performed similarly in some cases. However, the ANFIS model generally predicted much better than the ANN model in most cases. The ANFIS model, developed using the hybrid method, delivered the best performance with an RMSE of 211.97 and a coefficient of regression of 0.96, demonstrating the potential of using these models for flood forecasting. This research highlighted the effectiveness of soft computing techniques in flood forecasting and established useful suitability criteria that can be employed by flood control departments in various countries, regions, and states for accurate flood prognosis.

Land use/land cover (LU/LC) change has a considerable effect on the runoff characteristics of any watershed. LU/LC change studies are necessary for policymakers to identify the challenges and adopt the course of action such as soil and water conservation measures for improvement. The current research is undertaken for the upper Shetrunji River basin using a hydrological model linked with GIS. Input data like LU/LC, meteorological, and soil elements are necessary to execute watershed modeling. The model was calibrated and validated in SWAT-CUP using the SUFI-2 algorithm. The data from 2000 to 2010 were utilized for calibration, whereas the data from 2011 to 2020 were used for validation with a three-year warm-up period from 1997 to 1999. LU/LC change detection has been accomplished using ERDAS IMAGINE 2015 via a supervised classification approach. Close agreement was obtained between simulated and observed streamflow data during model calibration (NSE = 0.74 and R2 = 0.78) and validation (NSE = 0.70 and R2 = 0.73). LU/LC change detection shows that agricultural, urban, and water body areas increased between 2000–2010 and 2010–2020, and forest areas increased in 2010 and decreased in 2020. Thus, it is concluded that the change in LU/LC significantly influenced the runoff of the upper Shetrunji River basin. HIGHLIGHTS The study has been made for a water-scarce area of India.; Modern technique of data collection in fastest manner (remote sensing) is used for analysis to get quick and reliable results.; The study relates to the problems of man-made changes to the Earth's surface, thereby tilting the balance of water.;

Hydrological climate variables such as precipitation, temperature, humidity, evapotranspiration, infiltration, and streamflow provide useful information for the effective planning, design, and management of water resources. In the present study, monthly precipitation and streamflow data were analyzed to assess the variability in trends of precipitation over the Upper Narmada Basin (UNB), Middle Narmada Basin (MNB), and Lower Narmada Basin (LNB) for 41 years (1981–2021) using the widely accepted Mann–Kendall Test (MKT), Innovative Trend Analysis (ITA), and magnitude by Sen's Slope estimator, thereby extending further by a decade, the last study by Thomas and others in 2015. The inclusion of more factors affecting the streamflow in response to the rainfall often makes the model very complex and unreliable. In the present study, to overcome this limitation, a simple yet most definite correlation was established between rainfall and streamflow, which can serve as a meaningful indicator of basin behavior. Poor correlation was observed for the UNB and the MNB compared to the LNB, which may be attributed to the presence of tributaries. The result of this study will be helpful to policymakers and water resource managers to plan and adopt suitable schemes of water conservation and management in the Narmada basin. HIGHLIGHTS The study area is falling in the western Indian region having low water conditions.; The rainfall trend has been changing due to climate change and the present study highlights this trend in the recent 20 years.; A rainfall response in the form of streamflow is a much-needed information for watershed management.; Correlation between precipitation and streamflow provides insights about this fundamental relation in the study area.;