Browsing by Author "Yashas Kumar, H.K."

Now showing 1 - 4 of 4

Assessing the changing pattern of hydro-climatic variables in the Aghanashini River watershed, India
(Springer Science and Business Media Deutschland GmbH, 2023) Yashas Kumar, H.K.; Varija, K.
Growing population and climate change have altered the hydro-climatic trend from past decades. This manuscript analyses the abrupt shift in these time series and their changing pattern using historical data sets. The Pettitt test and the Standard Normal Homogeneity Test were used to evaluate the time series' homogeneity. The Concentration Index, Precipitation Concentration Index and Seasonality Index were employed to analyse the spatial variability of daily, monthly and seasonal rainfall patterns over the Aghanashini River watershed. Furthermore, the temporal trend in the rainfall, streamflow, and temperature time series was investigated using Mann–Kendall (MK) and the graphical Innovative-Şen (IŞ) test. Clear evidence of climate change impact on the rainfall and streamflow pattern was recognized, as there is an upward shift in the maximum temperature time series and a downward shift in the rainfall and streamflow time series after 2001. The rainfall indices showed that the watershed has fewer percentage of rainy days and stronger rainfall seasonality, indicating a possible risk of flash floods in the downstream of the watershed. Additionally, the results of the MK and IŞ trend tests paralleled each other and provided support for the findings emphasized by rainfall indices. © 2023, The Author(s) under exclusive licence to Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences.
Enhancing infiltration rate predictions with hybrid machine learning and empirical models: addressing challenges in southern India
(Springer Science and Business Media Deutschland GmbH, 2025) Ramaswamy, M.V.; Yashas Kumar, H.K.; Reddy, V.J.; Nyamathi, S.J.
Despite the success of machine learning (ML) in many disciplines, its application in hydrology, especially in water-scarce regions, faces challenges due to the lack of interpretability and physical consistency. This study addresses these challenges by integrating empirical hydrological models with ML techniques to predict infiltration rates in water-scarce regions of southern India. Using data from 199 observations across 11 sites, including soil characteristics and infiltration measurements, traditional models such as Philip’s, Horton’s, and Kostiakov’s were parameterized and combined with artificial neural networks (ANNs) and the MissForest (MF) algorithm to form hybrid models. The results demonstrate that the hybrid models, particularly those integrating Philip’s model with ANN and multiple predictors, achieved substantial improvements in prediction accuracy, with R2 values ranging from 0.803 to 0.918, root mean-square error (RMSE) from 0.083 to 0.118 cm/min, and Legates’ coefficient of efficiency (LCE) from 0.575 to 0.717 across the target sites. In contrast, empirical models alone at the test sites show lower performance, with R2 ranging from 0.499 to 0.902, RMSE from 0.091 to 0.152 cm/min, and LCE from 0.46 to 0.728, underscoring the limitations of traditional empirical models and the enhancement achieved through ML integration. By leveraging the strengths of empirical models and ML, the hybrid approach improves predictive accuracy and provides a more robust understanding of infiltration dynamics. The hybrid models enable accurate predictions using minimal, readily accessible data, offering a practical solution for water resource management and soil conservation in semi-arid, data-scarce regions. This study demonstrates that blending empirical knowledge with ML algorithms not only improves accuracy but also retains physical interpretability, presenting an innovative solution to hydrological modeling challenges in water-scarce environments. © The Author(s) under exclusive licence to Institute of Geophysics, Polish Academy of Sciences 2025.
Generation of intensity duration frequency curve using daily rainfall data for aghanashini river watershed, uttara kannada
(Springer Science and Business Media Deutschland GmbH, 2021) Nyamathi, S.J.; Yashas Kumar, H.K.
Most of water resource projects are carried out after analysis of rainfall data. Intensityâ€“durationâ€“frequency (IDF) curves are used to analyze the quantity of rainfall of different duration (t) and return periods (T). The study area in Aghanashini watershed lies between 74Â°18â€²15.95â€³ and 74Â°55â€²22.84â€³ E longitude and 14Â°15â€²26.21â€³-14Â°37â€²17.65â€³ N latitude. Area is about 1400.47Â km2, and altitude ranges from zero meters to 784 meters above mean sea level. The river extends from Sirsi to Kumta of Uttara Kannada, Karnataka State where it reaches Arabian Sea. The daily rainfall data of nine stations collected from Directorate of Economics and Statistics Bengaluru for years 1998 to 2016 was gone through, and 24-h maximum annual rainfall data was extracted. Indian Meteorological Department (IMD) proposed formula is used to estimate rainfall values for various shorter duration such as 0.083, 0.167, 0.25, 0.5, 1, 2, 12, 24-h. Probability distributions is used to estimate maximum annual rainfall values for various duration (t) and return periods (T) and Chi-square test is carried out to check the best probability distribution. Chi-square test shows that normal distribution is best fit to calculate rainfall intensity (mm/h) for six stations (Balale, Nilkundi, Sirsi, Hittalahally, Tyagali, Katagal), Log-Pearson type III probability distribution is best fit for two stations (Bandal and Siddapur) and Log-Normal distribution for one station, i.e., Kumta in Uttara Kannada. Â© Springer Nature Singapore Pte Ltd 2021.
Revitalizing temperature records: A novel framework towards continuous data reconstruction using univariate and multivariate imputation techniques
(Elsevier Ltd, 2024) Yashas Kumar, H.K.; Varija, K.
Data gaps are a recurring challenge in climate research, hindering effective time series analysis and modeling. This study proposes a novel two-step data imputation framework to address temperature time series with a long continuous gap surrounded by predictor stations with sporadic missingness. The method leverages iterative gap-filling Singular Spectrum Analysis (SSA) for the small sporadic gaps, followed by multivariate techniques like Inverse Distance Weightage (IDW), Kriging, Spatial Regression Test (SRT), Point Estimation method of Biased Sentinel Hospital-based Area Disease Estimation (P-BSHADE), Random Forest (RF), Support Vector Machines (SVM), and MissForest (MF) for the longer gap. Once the sporadic gaps are effectively addressed with SSA, the method carefully applies multivariate techniques to impute the long continuous gap. Prioritizing accuracy, comprehensive cross-validation with class-based statistical indicators are employed to minimize any potential biases introduced by the imputation process. The study shows the effectiveness of SSA in filling small sporadic gaps using an optimal window length (M ? 365 days) and eigentriple grouping (ET = 30). Notably, for maximum temperature, P-BSHADE and SVM achieve an impressive accuracy (e.g., Legates's Coefficient of Efficiency (LCE), 0.75?0.44, Combined Performance Index (CPI), 6.3%?19.1%) attributed to their ability to capture spatial and/or temporal heterogeneity. While SRT and P-BSHADE offers acceptable performance for minimum temperature (e.g., LCE, 0.51?0.27, CPI, 0.7%?23.7%), the study also uncovers a complex interplay between missing data, predictor stations, and autocorrelation affecting imputation accuracy. This suggests that the reduced performance of certain techniques likely stems from the decline in spatial and spatiotemporal autocorrelation between the target station and its predictors. Overall, this study presents a promising framework for handling complex missing data scenarios often encountered in climate time series analysis, paving the way for more robust and reliable analysis and modeling. © 2024 Elsevier B.V.