Differentiable modelling to unify machine learning and physical models for geosciences

C Shen, AP Appling, P Gentine, T Bandai… - Nature Reviews Earth & …, 2023‏ - nature.com
Process-based modelling offers interpretability and physical consistency in many domains of
geosciences but struggles to leverage large datasets efficiently. Machine-learning methods …

The state of the art in deep learning applications, challenges, and future prospects: A comprehensive review of flood forecasting and management

V Kumar, HM Azamathulla, KV Sharma, DJ Mehta… - Sustainability, 2023‏ - mdpi.com
Floods are a devastating natural calamity that may seriously harm both infrastructure and
people. Accurate flood forecasts and control are essential to lessen these effects and …

Global prediction of extreme floods in ungauged watersheds

G Nearing, D Cohen, V Dube, M Gauch, O Gilon… - Nature, 2024‏ - nature.com
Floods are one of the most common natural disasters, with a disproportionate impact in
develo** countries that often lack dense streamflow gauge networks. Accurate and timely …

Deep learning for water quality

W Zhi, AP Appling, HE Golden, J Podgorski, L Li - Nature water, 2024‏ - nature.com
Understanding and predicting the quality of inland waters are challenging, particularly in the
context of intensifying climate extremes expected in the future. These challenges arise partly …

An ensemble CNN-LSTM and GRU adaptive weighting model based improved sparrow search algorithm for predicting runoff using historical meteorological and …

Z Yao, Z Wang, D Wang, J Wu, L Chen - Journal of Hydrology, 2023‏ - Elsevier
Accurate prediction of river runoff is of great significance for water resources management,
flood prevention and mitigation. The causes of runoff are complex and the mechanisms …

Hybridized artificial intelligence models with nature-inspired algorithms for river flow modeling: A comprehensive review, assessment, and possible future research …

H Tao, SI Abba, AM Al-Areeq, F Tangang… - … applications of artificial …, 2024‏ - Elsevier
River flow (Q flow) is a hydrological process that considerably impacts the management and
sustainability of water resources. The literature has shown great potential for nature-inspired …

[HTML][HTML] Continuous streamflow prediction in ungauged basins: long short-term memory neural networks clearly outperform traditional hydrological models

R Arsenault, JL Martel, F Brunet… - Hydrology and Earth …, 2023‏ - hess.copernicus.org
This study investigates the ability of long short-term memory (LSTM) neural networks to
perform streamflow prediction at ungauged basins. A set of state-of-the-art, hydrological …

A comprehensive review of deep learning applications in hydrology and water resources

M Sit, BZ Demiray, Z **ang, GJ Ewing… - Water Science and …, 2020‏ - iwaponline.com
The global volume of digital data is expected to reach 175 zettabytes by 2025. The volume,
variety and velocity of water-related data are increasing due to large-scale sensor networks …

[HTML][HTML] Hybrid forecasting: blending climate predictions with AI models

LJ Slater, L Arnal, MA Boucher… - Hydrology and earth …, 2023‏ - hess.copernicus.org
Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine
learning) methods to harness and integrate a broad variety of predictions from dynamical …

What role does hydrological science play in the age of machine learning?

GS Nearing, F Kratzert, AK Sampson… - Water Resources …, 2021‏ - Wiley Online Library
This paper is derived from a keynote talk given at the Google's 2020 Flood Forecasting
Meets Machine Learning Workshop. Recent experiments applying deep learning to rainfall …