Artificial intelligence for geoscience: Progress, challenges and perspectives
This paper explores the evolution of geoscientific inquiry, tracing the progression from
traditional physics-based models to modern data-driven approaches facilitated by significant …
traditional physics-based models to modern data-driven approaches facilitated by significant …
Pushing the frontiers in climate modelling and analysis with machine learning
Climate modelling and analysis are facing new demands to enhance projections and
climate information. Here we argue that now is the time to push the frontiers of machine …
climate information. Here we argue that now is the time to push the frontiers of machine …
How interpretable machine learning can benefit process understanding in the geosciences
Abstract Interpretable Machine Learning (IML) has rapidly advanced in recent years, offering
new opportunities to improve our understanding of the complex Earth system. IML goes …
new opportunities to improve our understanding of the complex Earth system. IML goes …
AI-empowered next-generation multiscale climate modelling for mitigation and adaptation
Earth system models have been continously improved over the past decades, but systematic
errors compared with observations and uncertainties in climate projections remain. This is …
errors compared with observations and uncertainties in climate projections remain. This is …
Improving river routing using a differentiable Muskingum‐Cunge model and physics‐informed machine learning
Recently, rainfall‐runoff simulations in small headwater basins have been improved by
methodological advances such as deep neural networks (NNs) and hybrid physics‐NN …
methodological advances such as deep neural networks (NNs) and hybrid physics‐NN …
Explaining the mechanism of multiscale groundwater drought events: A new perspective from interpretable deep learning model
This study presents a new approach to understand the causes of groundwater drought
events with interpretable deep learning (DL) models. As prerequisites, accurate long short …
events with interpretable deep learning (DL) models. As prerequisites, accurate long short …
River water quality shaped by land–river connectivity in a changing climate
River water quality is crucial to ecosystem health and water security, yet its deterioration
under climate change is often overlooked in climate risk assessments. Here we review how …
under climate change is often overlooked in climate risk assessments. Here we review how …
Streamflow prediction in ungauged catchments through use of catchment classification and deep learning
M He, S Jiang, L Ren, H Cui, T Qin, S Du, Y Zhu… - Journal of …, 2024 - Elsevier
Streamflow prediction in ungauged catchments is a challenging task in hydrological studies.
Recently, data-driven models have demonstrated their superiority over traditional …
Recently, data-driven models have demonstrated their superiority over traditional …
Advancing parsimonious deep learning weather prediction using the HEALPix mesh
M Karlbauer, N Cresswell‐Clay… - Journal of Advances …, 2024 - Wiley Online Library
We present a parsimonious deep learning weather prediction model to forecast seven
atmospheric variables with 3‐hr time resolution for up to 1‐year lead times on a 110‐km …
atmospheric variables with 3‐hr time resolution for up to 1‐year lead times on a 110‐km …
Hybrid forecasting: using statistics and machine learning to integrate predictions from dynamical models
Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine
learning) methods to harness and integrate a broad variety of predictions from dynamical …
learning) methods to harness and integrate a broad variety of predictions from dynamical …