Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

14284256 · Jun 202019922001200920172026
48 results for climate extremes

Combines GANs and EVT for better modeling of spatial climate extremes.

problem Modeling dependencies between climate extremes, especially in high-dimensional spaces.
method Generative Adversarial Networks (GANs) combined with Extreme Value Theory (EVT).
result evtGAN outperforms classical GANs and statistical approaches in modeling spatial extremes.

The paper analyzes extreme temperature forecasting using machine learning models.

problem Forecasting extreme temperatures in U.S. cities.
method Auto-Regressive Integrated Moving Average, Exponential Smoothing, Multilayer Perceptrons, Gaussian Processes.
result Multilayer Perceptrons were found to be the most effective approach for forecasting extreme temperatures.

Paper models spatio-temporal extremes using conditional variational autoencoders.

problem Modeling co-occurrence of extreme weather events under changing climate conditions.
method Conditional Variational Autoencoder (cXVAE) with CNN integration.
result Accurately emulates spatial fields and recovers extremal dependence with low computational cost.

The study uses machine learning to predict CAT bond coupons based on climate data.

problem Predicting CAT bond coupons using climate data.
method Combining climate indicators with machine learning models (random forest, gradient boosting, etc.).
result Extremely randomized trees achieved the lowest RMSE in predicting CAT bond coupons.

Geospatial framework assesses climate risks for California's banking and exposed sectors.

problem Evaluating climate risks on banking and exposed sectors in California.
method Integrates hazard mapping, exposure analysis, and scenario-based financial risk assessment.
result Framework supports portfolio monitoring and institutional readiness under new standards.

Flexible XVAE model for efficient spatial extremes simulation.

problem Complex tail dependence structures in spatial extremes processes.
method Variational autoencoder (XVAE) for modeling flexible and non-stationary dependence.
result XVAE provides fast inference and outperforms traditional models in high dimensions.

Study identifies key drivers and spatio-temporal trends of extreme Mediterranean wildfires.

problem Understanding and predicting the impacts of climate change on wildfire activity.
method Statistical deep-learning model combining meteorological, land cover, and orographic data.
result Vapour-pressure deficit significantly affects wildfire occurrence, while air temperature and drought affect spread.

Deep learning framework predicts streamflow and flood probabilities in Australian catchments.

problem Large-scale flooding prediction challenges due to model calibration and missing data.
method Ensemble quantile-based deep learning framework using quantile regression and CAMELS dataset.
result Notable efficacy and uncertainties in streamflow forecasts with varied catchment properties.

New method uses neural networks to predict extreme wildfires, improving accuracy over traditional models.

problem Predicting extreme wildfires using complex, non-linear relationships.
method Partially-interpretable neural networks for extreme quantile regression.
result Significant improvement in predictive performance over traditional methods.

New method preserves GCM spatial dependencies for better climate projections.

problem Systemic biases in GCM output and loss of spatial/temporal dependencies.
method SPECD approach using Vecchia approximation and semi-parametric quantile regression.
result SPECD preserves key marginal and joint distribution properties of precipitation and temperature.

Machine learning improves sub-seasonal climate forecasting, especially gradient boosting and deep learning.

problem Predicting climate variables like temperature and precipitation in 2-week to 2-month time scales.
method Carefully constructed feature representations and ML approaches including gradient boosting and deep learning.
result ML methods can outperform climatological baselines and improve prediction accuracy.

Unified framework detects shifts in climate boundaries using GP regression and MAD test.

problem Challenges in quantifying and testing for temporal shifts in spatial boundaries from noisy data.
method Combines heteroskedastic GP regression with scaled MAD GET.
result No significant decade-scale changes in arid and semi-arid interfaces, but localized shifts during extreme droughts identified.

Study assesses drought and late-frost risks in Bavaria using vine copulas.

problem Assessing risks of late-frost and drought in Bavaria due to climate change.
method Used vine copula models for non-Gaussian and asymmetric dependencies, with univariate and bivariate regression analyses.
result Identified 'at-risk' regions for forest adaptation.

Unified model estimates landslide hazard combining susceptibility, intensity, and frequency.

problem Lack of unified statistical models for landslide hazard estimation.
method Deep learning combined with extreme-value theory.
result Model performs excellently and can estimate hazard for multiple return periods.

The representation of nonlinear sub-grid processes, especially clouds, has been a major source of uncertainty in climate models for decades. Cloud-resolving models better represent many of these processes and can now be run globally but only for short-term simulations of at most a few years because of computational lim…

2018-06-12abs ↗pdf ↗

Models assess how USDA orange production forecasts impact FCOJ market decisions.

problem High volatility in FCOJ futures due to limited U.S. orange production.
method Developed models to assess the impact of USDA October orange production forecasts on FCOJ market participants.
result Probabilistic forecasts of USDA production forecast error can reduce FCOJ price volatility.

Estimates treatment effects in rare extreme events using EVT.

problem Estimating treatment effects in rare, impactful events like extreme climate events.
method Introduces a novel framework using EVT and multivariate regular variation for consistent treatment effect estimation.
result Developed a consistent estimator for extreme treatment effects with rigorous non-asymptotic analysis.

New method improves local precipitation predictions using video diffusion.

problem Limited high-resolution local precipitation predictions due to computational costs.
method Extends video diffusion models to capture conditional distribution of high-resolution patterns.
result Method outperforms state-of-the-art baselines in CRPS, MSE, and precipitation distribution.

Deep generative models improve global precipitation forecasts.

problem Accurately forecasting extreme rainfall is challenging and costly.
method Trained a Conditional Generative Adversarial Network (CorrectorGAN) to correct and super-resolve global precipitation forecasts.
result CorrectorGAN produces high-resolution, bias-corrected forecasts in seconds.

In this article we show the relationship between the Pareto distribution and the gamma distribution. This shows that the second one, appropriately extended, explains some anomalies that arise in the practical use of extreme value theory. The results are useful to certain phenomena that are fitted by the Pareto distribu…

2012-11-01abs ↗pdf ↗

This paper uses ML and EVT to analyze tree ring data, improving accuracy of predictions.

problem Analyzing tree ring data for climate modeling and historical studies.
method Combines machine learning algorithms with extreme value theory for data analysis.
result Random Forest method yields the most accurate results for tree ring data analysis.

First-best climate policy is a uniform carbon tax which gradually rises over time. Civil servants have complicated climate policy to expand bureaucracies, politicians to create rents. Environmentalists have exaggerated climate change to gain influence, other activists have joined the climate bandwagon. Opponents to cli…

2016-08-19abs ↗pdf ↗

Efficiently estimates GEV distribution parameters using neural networks.

problem Computational intensity of maximum likelihood estimation for GEV distribution.
method Neural network-based likelihood-free estimation method.
result Comparable accuracy to maximum likelihood method with significant speedup.

Machine learning predicts Atlantic blocking using limited data.

problem Underestimation of blocking event duration in climate models.
method Transfer Learning and Explainable AI (SHAP analysis)
result High-pressure anomalies in specific regions contribute to blocking events.

Study uses CNNs to upscale wind speed data from 100 km to 3 km, improving subgrid-scale variability.

problem Recovering fine-scale wind speed information from coarse data.
method Convolutional neural networks (CNNs) with different input configurations (coarse wind speed, fine-scale topography, diurnal cycle) were tested.
result CNN models with coarse wind and fine topography inputs perform best in generalizing to unseen regions.

Proposes a new stochastic method to calibrate climate risks in financial models.

problem Estimating climate-related financial risks in bank loan portfolios.
method Stochastic forward-looking methodology to calibrate climate macro-correlation evolution from scientific data.
result A new framework to evaluate climate risks without specific scenario assumptions.

EnScale learns to downscale climate models efficiently, capturing both spatial and temporal consistency.

problem Downscaling climate models from coarse to high-resolution data is computationally expensive and challenging.
method EnScale uses generative models and proper scoring rules to map GCM data to RCM data, reducing computational cost.
result EnScale achieves competitive performance and computational efficiency in downscaling multiple climate variables.

Stochastic model prices weather derivatives for Indian states, highlighting temperature volatility impacts.

problem Quantifying financial risk in Indian markets due to seasonal weather variations.
method Modified Ornstein-Uhlenbeck process with jumps for temperature dynamics, calibrated with historical data, Monte Carlo simulations for pricing.
result Volatility significantly impacts weather derivative pricing, with higher prices in colder states and lower in hotter states.

CE improves climate uncertainty quantification using GCM ensembles and observational data.

problem Uncertainty in climate projections due to model inadequacies and variability.
method Conformal ensembles integrating GCM ensembles and observational data.
result CE generates statistically rigorous, easy-to-interpret uncertainty estimates.