AI-integrated model shows improved accuracy in streamflow prediction: IIT-D Study

Researchers from the Indian Institute of Technology IIT Delhi have combined traditional models used to predict streamflow in Indias rivers with artificial intelligence finding that the new approach significantly improved prediction accuracy in 208 of the 220 rivers testedAccurate information of river flow is critical for water resources management including irrigation scheduling reducing flood risk and reservoir operationsThe team Bhanu Magotra and Manabendra Saharia said that largescale hydrological models often produce significant uncertainties in streamflow estimates at local scales unless extensive basinspecific calibration is performedSuch calibration is computationally expensive and challenging to implement across a country as hydrologically diverse as India they saidCalibration refers to the technique of adjusting a models output to better align with observed realworld dataThe AIintegrated approach described in a paper in the journal Water Resources Research shows how integrating artificial intelligence with traditional hydrological models can help overcome longstanding challenges in water cycle prediction the researchers said in a statement to PTIThey employed long shortterm memory LSTM neural networks a type of AI particularly effective at recognising patterns over time to systematically correct river streamflow from the Indian Land Data Assimilation System ILDASThe ILDAS is aimed at producing highquality longterm estimates over India for land surface conditions such as evapotranspiration soil moisture runoff and streamflowThe AIintegrated model was trained on at least two decades of streamflow data from 220 river gauge stations across India maintained by the Central Water Commission CWC under the Ministry of Jal Shakti the researchers saidThe framework is showcased on a national scale using a multimodel hydrologic ensemble from the Indian Land Data Assimilation System ILDAS the authors wroteTrained on multidecadal data from 220 catchments across India the framework improves KlingGupta Efficiency in 208 catchments raising the national median typical from 018 uncalibrated to 060 they saidThe KlingGupta Efficiency is a widely used measure of a hydrological models performanceIt the AIintegrated model also reduced peak flow timing error and peak mean absolute percentage error by 25 per cent in 135 catchments the team saidOur research combines LSMs land surface models with deep learning to improve daily streamflow predictions without needing complex adjustments for each area We tested this method across 220 rivers in India and found it improved streamflow accuracy in 208 of them the authors wroteThe study presents a significant step forward in integrating traditional hydrological science with modern artificial intelligence the researchers saidThey added that the technology can be used to develop river basin digital twins supporting informed decision making in IndiaThis story has been sourced from a third party syndicated feed agencies Midday accepts no responsibility or liability for its dependability trustworthiness reliability and data of the text Midday managementmiddaycom reserves the sole right to alter delete or remove without notice the content in its absolute discretion for any reason whatsoever