Researchers develop deep-learning model for streamflow, flood forecasting

Full Article

Chinese researchers have introduced a new hybrid deep-learning model aimed at improving streamflow forecasting for water catchment areas globally. The model is designed to enhance flood prediction by addressing the challenges in hydrology related to streamflow and flood forecasting. Traditional physically based models face limitations due to sparse parameters and complex calibration procedures, especially in ungauged catchments.

More than 95 percent of small and medium-sized water catchments worldwide lack monitoring data, as highlighted by the Chinese Academy of Sciences. Researchers from the Institute of Mountain Hazards and Environment of the CAS utilized datasets from over 2,000 catchments globally for model training to enhance streamflow forecasting on a global scale. The study demonstrated that the deep-learning model outperformed traditional hydrological models and other AI models in terms of forecasting accuracy.

Related News

Researchers develop deep-learning model for streamflow, flood forecasting

Новости Украины 16month

Chinese scientists propose AI-based model to address streamflow, flood forecasting

manilatimes 17month

Deep Learning Boosts Lake Water Level Prediction

AZoAI on MSN.com 14month

IIT Bhubaneswar researchers use deep learning tech for enhanced accuracy in rainfall forecast

Indiatimes 12month

Combining machine learning with a climate system model enhances flood season rainfall predictions

MSN 8month

Deep learning technique enhances lightning risk prediction for power grids

Phys.org 7month

Predicting Rainfall Using Machine Learning, Deep Learning, and Time Series Models Across an Altitudinal Gradient in the North-Western Himalayas

LJMU 10month

AI-trained CCTV in rivers can spot blockages and reduce floods

Science Daily 12month