Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item ANFIS-based soft computing models for forecasting effective drought index over an arid region of India(IWA Publishing, 2023) Kikon, A.; Dodamani, B.M.; Deb Barma, S.D.; Naganna, S.R.Drought is a natural hazard that is characterized by a low amount of precipitation in a region. In order to evaluate the drought-related issues that cause chaos for human well-being, drought indices have become increasingly important. In this study, the monthly precipitation data from 1964 to 2013 (about 50 years) of the Jodhpur district in the drought-prone Rajasthan state of India was used to derive the effective drought index (EDI). The machine learning models hybridized with evolutionary optimizers such as the genetic algorithm adaptive neuro-fuzzy inference system (GA-ANFIS) and particle swarm optimization ANFIS (PSO-ANFIS) were used in addition to the generalized regression neural network (GRNN) to predict the EDI index. Using the partial autocorrelation function (PACF), models for forecasting the monthly EDI were constructed with 2-, 3- and 5-input combinations to evaluate their outcomes based on various performance indices. The results of the different combination models were compared. With reference to 2-input and 3-input combination models, both GA-ANFIS and PSO-ANFIS show better performance results with R2 ¼ 0.75, while among the models with 5-input combination, GA-ANFIS depicts better performance results compared to other models with R2 ¼ 0.78. The results are presented suitably with the aid of scatter plots, Taylor’s diagram and violin plots. Overall, the GA-ANFIS and PSO-ANFIS models outperformed the GRNN model. © 2023 The Authors.Item Trend Analysis of Rainfall and Meteorological Drought Indices over India During 1958–2017(Springer Nature, 2023) Kikon, A.; Dodamani, B.M.Rainfall plays a very vital role and its deficit causes a huge impact on the environment. Understanding the pattern of rainfall and drought trends has become increasingly crucial in many regions due to climate change. In this study, using the rainfall data from 1958 to 2017 for thirty-four meteorological subdivisions of India, trend analysis is performed for annual and seasonal rainfall. Along with the rainfall trend analysis, the study is also performed for meteorological drought indices, i.e., Effective Drought Index (EDI), Standardized Precipitation Index-9 (SPI-9), and Standardized Precipitation Index-12 (SPI-12). The results obtained from the Mann–Kendall test show that the rainfall patterns in the area under investigation are changing over time. As evidenced by the decrease in rainfall, the study region has been experiencing a lack of water supply in numerous subdivisions. The drought frequency for the meteorological drought indices has also been investigated, and it has been observed that the region is experiencing drought from extremely dry conditions to normal dry conditions. The findings in this study will help us to better comprehend the changes in rainfall and drought severity over the study region. This study may also benefit effective disaster management and preparedness strategies for this catastrophe, which is wreaking havoc on the environment. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item Deep Learning-Based Hydrological Drought Prediction in the Wardha River Basin, India(John Wiley and Sons Inc, 2025) Janardhana, M.; Kikon, A.Drought is an abnormal condition characterized by dry weather which can continue for days, months, and years. Drought often has major effects on the ecosystems and agriculture of vulnerable regions leading to catastrophe on the local economies. Deep learning was employed in this study to forecast hydrological drought in the Wardha River basin in Maharashtra, Vidarbha region, India. Monthly streamflow data from 1971 to 2020 for the Wardha River serve as the basis for analysis. The study calculates the standardized streamflow index (SSI) at several timescales (3, 6, 9, 12, and 24 months). Deep learning models, specifically the long short-term memory (LSTM) model and the multilayer perceptron (MLP) model, are employed for drought prediction within the study region. The models are trained with data spanning from 1971 to 2005 and tested against data from 2006 to 2020. Predictions are made for lead time scales of 6 and 12 months by considering lagged SSI values. Drought event lead time scale forecasts will serve as an early warning strategy. The 6- and 12-month lead times of the SSI forecast could be used as a warning for anticipated drought conditions. The study assesses model efficiency by comparing the root mean square error (RMSE) and mean absolute error (MAE) between the LSTM and MLP models. The results indicate that the LSTM model performs better for higher time scales in predicting hydrological drought, whereas the MLP model demonstrates superior predictive capabilities for lower time scales of drought index. © 2025 Wiley-VCH GmbH.