Related papers: Machine learning of committor functions for predic…
The El Ni\~no Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interannual variability in regional hydrology across the world…
The committor functions are central to investigating rare but important events in molecular simulations. It is known that computing the committor function suffers from the curse of dimensionality. Recently, using neural networks to estimate…
Decision-makers often act in response to data-driven predictions, with the goal of achieving favorable outcomes. In such settings, predictions don't passively forecast the future; instead, predictions actively shape the distribution of…
Latent state space models are a fundamental and widely used tool for modeling dynamical systems. However, they are difficult to learn from data and learned models often lack performance guarantees on inference tasks such as filtering and…
It is well-established that human activity is driving extreme weather patterns, and that these extreme events influence human behaviour. However, few models allow for human behaviours and the climate to dynamically interact. The models…
El Ni\~no episodes are part of the El Ni\~no-Southern Oscillation (ENSO), which is the strongest driver of interannual climate variability, and can trigger extreme weather events and disasters in various parts of the globe. Previously we…
When performing predictions that use Machine Learning (ML), we are mainly interested in performance and interpretability. This generates a natural trade-off, where complex models generally have higher skills but are harder to explain and…
The committor function is a central object for quantifying the transitions between metastable states of dynamical systems. Recently, a number of computational methods based on deep neural networks have been developed for computing the…
Complex Earth System Models are widely utilised to make conditional statements about the future climate under some assumptions about changes in future atmospheric greenhouse gas concentrations; these statements are often referred to as…
The El Nino-Southern Oscillation (ENSO) is one of the most important phenomena in climate. By studying the fluctuations of surface air temperature within one year between 1979-01-01 and 2016-12-31 of the region (30S-30N, 0E-360E) with…
Global Climate Models are key tools for predicting the future response of the climate system to a variety of natural and anthropogenic forcings. Here we show how to use statistical mechanics to construct operators able to flexibly predict…
Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction. However, these complex models often lack inherent transparency and interpretability, acting as "black boxes" that impede…
The prediction of the Madden-Julian Oscillation (MJO), a massive tropical weather event with vast global socio-economic impacts, has been infamously difficult with physics-based weather prediction models. Here we construct a machine…
Though the Boltzmann-Gibbs framework of equilibrium statistical mechanics has been successful in many arenas, it is clearly inadequate for describing many interesting natural phenomena driven far from equilibrium. The simplest step towards…
El Ni\~no Southern Oscillation (ENSO) is the Earth's strongest source of interannual climate variability. Although its center of action is in the tropical Pacific, it has significant influences on the climate at the planetary scale. ENSO is…
Equilibrium climate sensitivity (ECS) is a key predictor of climate change. However, it is not very well constrained, either by climate models or by observational data. The reasons for this include strong internal variability and forcing on…
We show that the monthly recorded history (1878-2013) of the Southern Oscillation Index (SOI), a descriptor of the El Ni\~no Southern Oscillation (ENSO) phenomenon, can be well described as a dynamic system that supports an average…
The North Atlantic Oscillation (NAO) is the dominant mode of atmospheric variability over the North Atlantic sector, influencing temperature and precipitation across Europe. While the NAO's impact on North Atlantic sea surface temperatures…
Deep learning has achieved remarkable success across many domains, but it has also created a growing demand for interpretability in model predictions. Although many explainable machine learning methods have been proposed, post-hoc…
Accurate precipitation forecasting is becoming increasingly important in the context of climate change. In response, machine learning-based approaches have recently gained attention as an emerging alternative to traditional methods such as…