Related papers: A Deep Learning Synthetic Likelihood Approximation…

In light of growing threats posed by climate change in general and sea level rise (SLR) in particular, the necessity for computationally efficient means to estimate and analyze potential coastal flood hazards has become increasingly…

Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate…

We predict the emergence of extreme events in a parametrically driven nonlinear dynamical system using three Deep Learning models, namely Multi-Layer Perceptron, Convolutional Neural Network and Long Short-Term Memory. The Deep Learning…

The Standardized Precipitation Index (SPI) is a critical tool for monitoring drought conditions, typically relying on normalized accumulated precipitation. While longer historical records of precipitation yield more accurate parameter…

Machine learning for weather prediction increasingly relies on ensemble methods to provide probabilistic forecasts. Diffusion-based models have shown strong performance in Limited-Area Modeling (LAM) but remain computationally expensive at…

Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at both forecasting tasks, and at quantifying the uncertainty associated with those forecasts (prediction intervals). One example is Multivariate…

We present a deep neural network for a model-free prediction of a chaotic dynamical system from noisy observations. The proposed deep learning model aims to predict the conditional probability distribution of a state variable. The Long…

Modeling nonstationarity that often prevails in extremal dependence of spatial data can be challenging, and typically requires bespoke or complex spatial models that are difficult to estimate. Inference for stationary and isotropic models…

The evaluation of possible climate change consequence on extreme rainfall has significant implications for the design of engineering structure and socioeconomic resources development. While many studies have assessed the impact of climate…

The sparse and spatio-temporally discontinuous nature of precipitation data presents significant challenges for simulation and statistical processing for bias correction and downscaling. These include incorrect representation of…

This study introduces a deep learning-based framework for forecasting weather-related traffic crash risk using heterogeneous spatiotemporal data. Given the complex, non-linear relationship between crash occurrence and factors such as road…

Urban downscaling is a link to transfer the knowledge from coarser climate information to city scale assessments. These high-resolution assessments need multiyear climatology of past data and future projections, which are complex and…

Flood prediction is critical for emergency planning and response to mitigate human and economic losses. Traditional physics-based hydrodynamic models generate high-resolution flood maps using numerical methods requiring fine-grid…

Models for extreme values accommodating non-stationarity have been amply studied and evaluated from a parametric perspective. Whilst these models are flexible, in the sense that many parametrizations can be explored, they assume an…

The astounding success of these methods has made it imperative to obtain more explainable and trustworthy estimates from these models. In hydrology, basin characteristics can be noisy or missing, impacting streamflow prediction. For solving…

Spatial nonstationarity, the location variance of features' statistical distributions, is ubiquitous in many natural settings. For example, in geological reservoirs rock matrix porosity varies vertically due to geomechanical compaction…

Robust hydrological simulation is key for sustainable development, water management strategies, and climate change adaptation. In recent years, deep learning methods have been demonstrated to outperform mechanistic models at the task of…

A configuration of the NCAR WRF-Hydro model was sought using well established data models to guide the initial hydrologic model setup, as well as a seasonal streamflow post-processing by neural networks. Discharge was simulated using an…

To mitigate the risk posed by extreme rainfall events, we require statistical models that reliably capture extremes in continuous space with dependence. However, assuming a stationary dependence structure in such models is often erroneous,…

This study aims to improve the spatial representation of uncertainties when regressing surface wind speeds from large-scale atmospheric predictors for sub-seasonal forecasting. Sub-seasonal forecasting often relies on large-scale…