Extremes events

Last updated Mar 23, 2023 Edit Source

See:

• AI/Anomaly and Outlier Detection

• CASCADE - multidivisional, collaborative project at Lawrence Berkeley National Laboratory (LBNL)
• CLIMATE EXTREMES (Coumou)
• EO-ALERT (2018-2021) - Next generation satellite processing chain for rapid civil alerts
  • AI for Earth observation and numerical weather prediction
• National Meteorological Library and Archive Fact sheet 3 — Water in the atmosphere
• https://www.deeprain-project.de/en/publications-2/
• Severe weather Europe

• Hurricanes Database
• Barometric Pressure & Hurricanes

• EOS - Forest Fire Monitoring
• [2017 Conference on Fire Prediction Across Scales]( http://extremeweather.columbia.edu/events/past-events/2017-conference-on-fire-prediction-across-scales/
• Climate Change Increases the Risk of Wildfires
• Leverhulme Centre for Wildfires, Environment and Society

• See ClimateNet dataset
• https://en.wikipedia.org/wiki/Atmospheric_river
• About ARs (NOAA)

• #CODE ecPoint-Rainfall - Global probabilistic rainfall at point-scale from ECMWF ensemble
• #CODE TECA - the Toolkit for Extreme Climate Analysis
  • TECA (Toolkit for Extreme Climate Analysis) is a collection of climate analysis algorithms geared toward extreme event detection and tracking implemented in a scalable parallel framework. The core is written in modern c++ and uses MPI+thread for parallelism

See AI4ES/AI4ES data

• Copernicus Emergency Management Service (EMS)
  • EMS uses satellite imagery and other geospatial data to provide free of charge mapping service in cases of natural disasters, human-made emergency situations and humanitarian crises throughout the world
  • List of EMS Rapid Mapping Activations
  • Flood, wildfire, volcanic events, earthquakes
• European Drought Observatory
• IBTrACS
  • https://climetlab.readthedocs.io/en/latest/firststeps.html
• ESWD
  • “Extreme Weather Database” will be a nice thing to test because it contains events that are not resolved by the reanalysis. So will really help to identify local-scale (convective) high-impact events
  • Type of events: dust, sand- or steam devils, gustnadoes, large hail, heavy rain, tornadoes, severe wind gusts, heavy snowfalls/snowstorms, ice accumulations, avalanches, damaging lightning strikes
• NCEI’s Severe Weather Data Inventory (US)
• TEMPEST (UK)
  • Tracking Extremes of Meteorological Phenomena Experienced in Space and Time
  • Work in progress

• #PAPER Climate and Weather Extremes (Nature paper collection)
  • Progress in subseasonal to seasonal prediction through a joint weather and climate community effort (Mariotti 2018)
  • The sub-seasonal to seasonal prediction project (S2S) and the prediction of extreme events (Vitart 2018)
• #PAPER Simulation and Prediction of Category 4 and 5 Hurricanes in the High-Resolution GFDL HiFLOR Coupled Climate Model (Murakami 2015)
• #PAPER A toolkit for climate change analysis and pattern recognition for extreme weather conditions – Case study: California-Baja California Peninsula (Vaghefi 2017)
• #PAPER Urban heat wave hazard and risk assessment (Jedlovec 2017)
• #PAPER Defining Extreme Events: A Cross‐Disciplinary Review (McPhillips, 2018)
  • Extreme events are of interest worldwide given their potential for substantial impacts on social, ecological, and technical systems
  • Many climate‐related extreme events are increasing in frequency and/or magnitude due to anthropogenic climate change
  • A lack of coherence exists in what constitutes and defines an extreme event across these fields, which impedes our ability to holistically understand and manage these events
  • Found a wide range in definitions and thresholds, with more than half of examined papers not providing an explicit definition, and disagreement over whether impacts are included in the definition
  • Distinction should be made between extreme events and their impacts, so that we can better assess when responses to extreme events have actually enhanced resilience
• #PAPER Sense‐making in social media during extreme events (Stieglitz, 2018)
• #PAPER Complex networks reveal global pattern of extreme-rainfall teleconnections (Boers 2019)
• #PAPER A ranking of concurrent precipitation and wind events for the Iberian Peninsula (Henin 2020)
• #PAPER Atmospheric convection, dynamics and topography shape the scaling pattern of hourly rainfall extremes with temperature globally (Moustakis 2020)

• #PAPER Development of a Combined Drought Indicator to detect agricultural drought in Europe (Sepulcre-Canto 2012)
• #PAPER Seasonal Drought Prediction: Advances, Challenges, and Future Prospects (Hao 2018)
• #PAPER Machine learning–based observation-constrained projections reveal elevated global socioeconomic risks from wildfire (Yu 2022)
• #PAPER Status and prospects for drought forecasting: opportunities in artificial intelligence and hybrid physical–statistical forecasting (AghaKouchak 2022)

• #PAPER Seasonal predictions of Fire Weather Index: Paving the way for their operational applicability in Mediterranean Europe (Bedia 2018)
  • See AI4ES/S2S
• #PAPER Skillful forecasting of global fire activity using seasonal climate predictions (Turco 2018)
  • See AI4ES/S2S
• #PAPER The Global Fire Atlas of individual fire size, duration, speed and direction (Andela 2019)
• #PAPER Global Wildfire Outlook Forecast with Neural Networks (Song 2022)

• #PAPER Daily Precipitation Extreme Events in the Iberian Peninsula and Its Association with Atmospheric Rivers (Ramos 2015)
• #PAPER On the relationship between atmospheric rivers, weather types and floods in Galicia, NW Spain (Eiras-Barca 2018)
• #PAPER Predictive skill for atmospheric rivers in the western Iberian Peninsula (Ramos 2020)
• #PAPER Atmospheric Rivers and Associated Precipitation over France and Western Europe: 1980–2020 Climatology and Case Study (Doiteau 2021)

• Extreme Climate and Weather Events in a Warmer World
• Wildfires and Climate Change
• Commentary: How summer 2021 has changed our understanding of extreme weather
• Extreme weather: How is it connected to climate change?
• Yes, climate change can affect extreme weather – but there is still a lot to learn
• Is the weather actually becoming more extreme? - R. Saravanan (TED, POPSCI)
• Attributing extreme weather toclimate change (interactive map of studies worldwide)
• ClimExtreme - A research network on climate change and extreme events
  • https://www.xces.dkrz.de/

• #PAPER Machine Learning for Projecting Extreme Precipitation Intensity for Short Durations in a Changing Climate (Hu 2019)
• #PAPER Extreme precipitation events under climate change in the Iberian Peninsula (Cardoso, 2019)
  • https://www.researchgate.net/publication/335040085_Extreme_Precipitation_Events_under_Climate_Change_in_the_Iberian_Peninsula

See AI/Supervised Learning/Supervised learning

• #PAPER Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets (Liu 2016)
  • Detecting extreme events in large datasets is a major challenge in climate science research.
  • Current algorithms for extreme event detection are build upon human expertise in defining events based on subjective thresholds of relevant physical variables
  • Developed deep AI/Deep learning/CNNs classification system and demonstrated the usefulness of AI/Deep learning/DL technique for tackling climate pattern detection problems
  • Achieved 89%-99% of accuracy in detecting extreme events (Tropical Cyclones, Atmospheric Rivers and Weather Fronts)
• #PAPER Resolution Reconstruction of Climate Data with Pixel Recursive Model (Kim 2017)
  • https://www.researchgate.net/publication/322001089_Resolution_Reconstruction_of_Climate_Data_with_Pixel_Recursive_Model
  • CNNs to detect extreme climate events without handcrafted algorithmic definition: detect and localize tropical cyclone in GCM scaled low resolution reanalysis data, which suggests the possibility to reduce the computing load of conventional expensive downscaling process
  • Combined pixel recursive super resolution techniques with localization CNNs to achieve better SR performance and to improve localization accuracy
  • Implemented distributed training in pixel recursive module to fasten training using GPU
• #PAPER Segmenting and Tracking Extreme Climate Events using Neural Networks (Mudigonda 2017)
  • https://dl4physicalsciences.github.io/files/nips_dlps_2017_20.pdf
• #PAPER Leveraging LSTM for rapid intensifications prediction of tropical cyclones (Gong Li 2017)
  • TC intensity forecasting helps people prepare for the extreme weather and could save lives and properties. Rapid Intensifications (RI) of TCs are the major error sources of TC intensity forecasting
  • Experiments show that the long short-term memory (LSTM) network provides the ability to leverage past conditions to predict TC rapid intensifications
  • SHIPS (DeMaria and Kaplan 1994) database is chosen for this study as it contains most well-known environmental predictors relevant to TC intensity changes, such as Reynolds SST (sea surface temperature), SLP (sea level pressure).
  • These predictor values are from reanalysis fields as well as satellite derived variable values and stored as a text file in ASCII format
  • According to the definition of RI, if the maximum wind increased more than 30 knots (15.4 m/s) over the past 24 hours (Kaplan and DeMaria 2003), the record is marked as RI case, otherwise, it is labeled UNRI
• #PAPER A machine learning workflow for hurricane prediction (Kahira 2018)
  • #BSC LP Caron, Leonardo Bautista
• #PAPER Training deep neural networks with low precision input data: a hurricane prediction case study (Kahira 2018)
• #PAPER Fused DL for Hurricane Track Forecast from Reanalysis Data (Giffard-Roisin 2018)
• #PAPER Lightning Prediction for Australia Using Multivariate Analyses of Large-Scale Atmospheric Variables (Bates 2018)
• #PAPER Defining heatwave thresholds using an inductive machine learning approach (Park and Kim, 2018)
  • Establishing appropriate heatwave thresholds is important in reducing adverse human health consequences as it enables a more effective heatwave warning system and response plan
  • This paper defined such thresholds by focusing on the non-linear relationship between heatwave outcomes and meteorological variables as part of an inductive approach
  • Daily data on emergency department visitors who were diagnosed with heat illnesses and information on 19 meteorological variables were obtained for the years 2011 to 2016 from relevant government agencies
  • A Multivariate Adaptive Regression Splines (MARS) analysis was performed to explore points (referred to as “knots”) where the behaviour of the variables rapidly changed
• #PAPER Predicting Hurricane Trajectories using a Recurrent Neural Network (Alemany 2018)
• #PAPER Exascale DL for Climate Analytics (Kurth 2018)
  • #CODE https://github.com/sparticlesteve/climate-seg-benchmark
  • #TALK Exascale Deep Learning for Climate Analytics (Thorsten Kurth, Lawrence Berkeley National Laboratory, TF Dev Summit ‘19)
    • Climate change will have fundamental socio-economic impact and it is imperative for us to understand it better. This talk will show how TensorFlow was utilized on the world’s fastest supercomputer in order to extract pixel level segmentation masks of extreme weather phenomena in climate simulation data, thereby enabling climate scientists to perform high-fidelity, fine grained geo-spatial analyses of the effects of climate change
  • DeepLabv3 — Atrous Convolution (Semantic Segmentation)
    • https://towardsdatascience.com/review-deeplabv3-atrous-convolution-semantic-segmentation-6d818bfd1d74
    • https://towardsdatascience.com/review-dilated-convolution-semantic-segmentation-9d5a5bd768f5
• #PAPER DeepTC: ConvLSTM Network for Trajectory Prediction of Tropical Cyclone using Spatiotemporal Atmospheric Simulation Data (Kim 2018)
• #PAPER Deep-Hurricane-Tracker - Tracking and Forecasting Extreme Climate Events (Kim 2019)
  • http://www.joonseok.net/papers/wacv19.pdf
  • #CODE https://github.com/kim79sookyung/hurricane_detection_cnn
  • Convolutional LSTM (ConvLSTM)-based spatio-temporal models to track and predict hurricane trajectories from large-scale climate data. To address the tracking problem, we model time-sequential density maps of hurricane trajectories, enabling to capture not only the temporal dynamics but also spatial distribution of the trajectories. Furthermore, we introduce anew trajectory prediction approach as a problem of sequential forecasting from past to future hurricane density map sequences
  • CAM5 (zonal wind (U850), meridional wind(V850), and precipitation (PRECT)) and TECA labels (automated heuristics)
  • http://www.joonseok.net/papers/deep_tracker.pdf (Climate informatics 2018)
• #PAPER Improving Atmospheric River Forecasts With Machine Learning (Chapman 2019)
• #PAPER High Resolution Forecasting of Heat Waves impacts on Leaf Area Index by Multiscale Multitemporal Deep Learning (Gobbi 2019)
• #PAPER A hybrid CNN-LSTM model for typhoon formation forecasting (Cheng 2019)
  • Traditional numerical forecast models based on fluid mechanics have difficulty in predicting the intensity of typhoons. Forecasts based on statistics and machine learning fail to take into account the spatial and temporal relationships among typhoon formation variables leading to weaknesses in the predictive power of this model
  • Proposed a hybrid model, which we argue, can produce a more realist and accurate account of typhoon ‘behavior’ as it focuses on both the spatio-temporal correlations of atmospheric and oceanographic variables
  • The CNN-LSTM model introduces 3D convolutional neural networks (3DCNN) and 2D convolutional neural networks (2DCNN) as a method to better understand the spatial relationships of the features of typhoon formation. LSTM is used to examine the temporal sequence of relations in typhoon progression
• #PAPER Deep Learning for Spatially Explicit Prediction of Synoptic-Scale Fronts (Lagerquist, 2019)
  • This paper describes the use of AI/Deep learning/CNNs, a type of deep learning, to identify fronts in gridded data, followed by a novel postprocessing method that converts probability grids to objects
  • Synoptic-scale fronts are often associated with extreme weather in the mid latitudes
  • Predictors are 1000-mb (1 mb = 1 hPa) grids of wind velocity, temperature, specific humidity, wet-bulb potential temperature, and/or geopotential height from the North American Regional Reanalysis
  • Labels are human-drawn fronts from Weather Prediction Center bulletins
  • To evaluate our system, we compare the objects (predicted warm and cold fronts) with human-analyzed warm and cold fronts, matching fronts of the same type within a 100- or 250-km neighborhood distance. At 250 km our system obtains a probability of detection of 0.73, success ratio of 0.65 (or false-alarm rate of 0.35), and critical success index of 0.52. These values drastically outperform the baseline, which is a traditional method from numerical frontal analysis
• #PAPER High Resolution Forecasting of Heat Waves impacts on Leaf Area Index by Multiscale Multitemporal Deep Learning (Gobbi 2019)
• #PAPER Make Thunderbolts Less Frightening – Predicting Extreme Weather Using Deep Learning (Schon 2019)
• #TALK Probabilistic Detection of Extreme Weather Using Deep Learning Methods (Mahesh 2019)
  • Atmospheric rivers (ARs) are a particularly challenging class of extreme weather event, since there is no single community-accepted AR identification algorithm
  • To represent the uncertainty expressed by contemporary, state-of-the-science AR tracking methods, we create probabilistic AR detection fields from 14 algorithms submitted to the Atmospheric River Tracking Method Intercomparison Project (ARTMIP). Each algorithm identifies grid cells associated with ARs in over 30 years of 3-hourly data from the MERRA reanalysis
  • Estimated each grid cell’s probability of AR detection as the proportion of ARTMIP algorithms that identify an AR in that grid cell
  • AI/Deep learning/CNNs segmentation model used to generate probabilistic AR identifications that are quite close to the ARTMIP mean, with an average RMSE of 0.03
• #PAPER DeepRI: End-to-end Prediction of Tropical Cyclone Rapid Intensification from Climate Data (Jing 2019)
  • NeurIPS 2019
  • TC track forecasting has improved significantly in the past decades, intensity forecasting still shows large forecast error, largely due to the challenge in predicting TC rapid intensification
  • Rapid intensification (RI) is the significant strengthening in storm wind speed within a short time(e.g. >30 kt over 24 hours), and almost all historical category 4 and 5 hurricanes are RI storms
  • Data from multiple resources including visible and infrared satellite imagery provided by operational geostationary satellites and passive microwave imagery from polar-orbiting satellites. Augmented with synthetic data from climate model projections, such as HiFLOR, which is able to simulate Category 4 and 5 TCs
  • Trained separate models for RI prediction for different lead-time, i.e. 6h, 12h, 18h, 24h, and create corresponding training data sets respectively. For each lead-time, we split independent TCs into training and test split to prevent potential correlations. Overall, this gives us by estimation roughly4000 TCs in training set, and each TC provides a series of pairs of feature map and ground truth binary label indicating whether RI happens.
• #PAPER Machine Learning for Generalizable Prediction of Flood Susceptibility (Sidrane 2019)
• #PAPER Forecasting El Niño with Convolutional and Recurrent Neural Networks (Mahesh 2019)
• #PAPER A mixed model approach to drought prediction using artificial neural networks: Case of an operational drought monitoring environment (Adede 2019)
  • The study uses 10 precipitation and vegetation variables that are lagged over 1, 2 and 3-month time-steps to predict drought situations
  • In the model space search for the most predictive artificial neural network (ANN) model, as opposed to the traditional greedy search for the most predictive variables, we use the General Additive Model (GAM) approach
• #PAPER Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data (Giffard-Roisin 2020)
  • Proposed a neural network model fusing past trajectory data and reanalysis atmospheric images (wind and pressure 3D fields)
  • Used a moving frame of reference that follows the storm center for the 24h tracking forecast
  • Model trained to estimate the longitude and latitude displacement of tropical cyclones and depressions from a large database from both hemispheres (more than 3000 storms since 1979, sampled at a 6 hour frequency)
• #PAPER Tropical and Extratropical Cyclone Detection Using Deep Learning (Kumler-Bonfanti 2020)
  • U-Net trained with IBTrACS labels on GOES water vapor
  • #TALK ML for Segmentation of Atmospheric Phenomena (Jebb Stewart, NOAA ESRL)
    • https://www.youtube.com/watch?v=mQ3jAxMmeRU&list=PLbelYhZAAHEIr4iC1FNcPXUUYXI0zg_96&index=14&t=0s
    • https://www2.cisl.ucar.edu/sites/default/files/1010%20June%2024%20Stewart%20%281%29.pdf
• #PAPER Tropical and Extratropical Cyclone Detection Using Deep Learning (Kumler-Bonfanti 2020)
  • This paper discusses four different state-of-the-art U-Net models designed for detection of tropical and extratropical cyclone Regions Of Interest (ROI) from two separate input sources: total precipitable water output from the Global Forecasting System (GFS) model and water vapor radiance images from the Geostationary Operational Environmental Satellite (GOES)
  • These models are referred to as IBTrACS-GFS, Heuristic-GFS, IBTrACS-GOES, and Heuristic-GOES. All four U-Nets are fast information extraction tools and perform with a ROI detection accuracy ranging from 80% to 99%
  • These are additionally evaluated with the Dice and Tversky Intersection over Union (IoU) metrics, having Dice coefficient scores ranging from 0.51 to 0.76 and Tversky coefficients ranging from 0.56 to 0.74
• #PAPER Improving Emergency Response during Hurricane Season using Computer Vision (Bosch 2020)
• #PAPER Precipitation Nowcasting with Orographic Enhanced Stacked Generalization: Improving Deep Learning Predictions on Extreme Events (Franch 202)
• #PAPER Spatio-temporal segmentation and tracking of weather patterns with light-weight Neural Networks (Kapp-Schwoerer 2020)
  • Uses the ClimateNet AI4ES/AI4ES data and the CGNet architecture AI/Computer Vision/Semantic segmentation
  • Weather pattern recognition by deep neural networks can work remarkably better than feature engineering, such as hand-crafted heuristics, used traditionally in climate science
  • Deep Learning - based semantic segmentation of atmospheric rivers and tropical cyclones on the expert-annotated ClimateNet data set, and track individual events using a spatio-temporal overlapping approach
• #PAPER HydroDeep – A Knowledge Guided Deep Neural Network for Geo-Spatiotemporal Data Analysis (Sarkar 2020)
  • Application to floods
  • This paper demonstrates a neural network architecture (HydroDeep) that couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network to build a hybrid baseline model
• #PAPER Graph Neural Networks for Improved El Niño Forecasting (Ruhling Cachay 2020)

See AI/Semi-supervised learning

• #PAPER Analog forecasting of extreme-causing weather patterns using deep learning (Chattopadhyay, 2020) ^d42267
  • LENS data (CESM1 model), AI/Deep learning/CapsNets and AI/Deep learning/CNNs, extreme temperature events
  • CapsNets are trained on midtropospheric large‐scale circulation patterns (Z500) labeled 0–4 depending on the existence and geographical region of surface temperature extremes over North America several days ahead
  • Impact‐based autolabeling strategy: Knowing the surface temperature over North America on a given day, the Z500 pattern of several days earlier is labeled as 0 (no extreme onset) or 1, 2, 3, or 4 (the cluster indices of T2m extremes)
  • The trained networks predict the occurrence/region of cold or heat waves, only using Z500, with accuracies (recalls) of 69–45% (77–48%) or 62–41% (73–47%) 1–5 days ahead

See AI/Unsupervised learning/Unsupervised learning

• #PAPER Spatial clustering of summer temperature maxima from the CNRM-CM5 climate model ensembles & E-OBS over Europe (Bador 2015)
• #PAPER Multiscale Variability in North American Summer Maximum Temperatures and Modulations from the North Atlantic Simulated by an AGCM (Vigaud 2018) ^25cb40
• #PAPER DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatio-temporal Systems (Rupe, 2019)
  • #CODE https://github.com/adamrupe/DisCo
• #PAPER Towards Unsupervised Segmentation of Extreme Weather Events (Rupe, 2019)
  • Tests on CAM5.1 water vapor data -> extreme weather identification from unlabeled climate model simulation data
  • While the results in using TECA show that DL can improve upon it, the accuracy rates reach 97% and thus essentially just reproduce the output of TECA
  • Though an improvement over automated heuristics, expert-labeled data is still not an objective ground truth
  • To circumvent these challenges of DL-based approaches, here we take an alternative physics-based unsupervised approach, complementary to DL

• #PAPER Bayesian Anomaly Detection and Classification (Roberts, 2019)
• #PAPER A probabilistic gridded product for daily precipitation extremes over the United States (Risser 2019)
• #PAPER Detection Uncertainty Matters for Understanding Atmospheric Rivers (Obrien 2020)
• #PAPER Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of data (Miloshevich 2022)
  • Demonstrate that DNNs have the ability to predict the probability of occurrence of long lasting 14-day heatwaves over France, up to 15 days ahead of time for fast dynamical drivers (500 hPa geopotential height fields), and also at much longer lead times for slow physical drivers (soil moisture)
  • Used a 8,000-year dataset obtained from the Planet Simulator (PlaSim) climate model. The PlaSim model has physical parameterizations that are of a lesser quality compared to up-to-date climate models which are used for CMIP experiment
  • Softmax parametrization is a way to output probabilities associated with a discrete variable
  • Used a definition of heatwaves that actually involves a measure related to both the persistence and the amplitude of air temperature close to the ground. We thus define heatwave as time and area average of daily 2-meter temperature
  • 3-layer CNN with ReLU activations and maxpool in between -> dense layer -> 2 outputs. Softmax function (not sigmoid? what about calibration of “probabilities”)

See AI/Active learning

• #PAPER Incorporating Expert Feedback into Active Anomaly Discovery (Das, 2016)
• #PAPER Incorporating Feedback into Tree-based Anomaly Detection (2017)

See AI/Deep learning/GANs

• #PAPER Learning to Focus and Track Extreme Climate Events (Kim 2019)
• #PAPER Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks (Schmidt 2019)
• #PAPER ExGAN: Adversarial Generation of Extreme Samples (Bhatia 2021)
  • #CODE https://github.com/Stream-AD/ExGAN
  • https://www.kdnuggets.com/2021/02/adversarial-generation-extreme-samples.html
• #PAPER Modeling and simulating spatial extremes by combining extreme value theory with generative adversarial networks (Boulaguiem 2022)

See AI4ES/Causal modeling in ES

• #PAPER Construction of Comprehensive Drought Monitoring Model in Jing-Jin-Ji Region Based on Multisource Remote Sensing Data (Yu 2019)
• #PAPER Meteorological drought forecasting based on a statistical model with machine learning techniques in Shaanxi province, China (Zhang 2019)
• #PAPER Using LSTMs for climate change assessment studies on droughts and floods (Krazert 2019)
• #PAPER Construction of a drought monitoring model using deep learning based on multi-source remote sensing data (Shen 2019)
• #PAPER A Global Probabilistic Dataset for Monitoring Meteorological Droughts (Turco 2020)
  • #BSC Markus Donat

• #PAPER Mapping regional forest fire probability using artificial neural network model in a Mediterranean forest ecosystem (Satir 2015)
• #PAPER Global Wildfire Outlook Forecast with Neural Networks (Song 2020)
• #PAPER Physics-Informed Machine Learning Simulator for Wildfire Propagation (Bottero 2020)
• #PAPER Convolutional LSTM Neural Networks for Modeling Wildland Fire Dynamics (Burge 2021)

• #PAPER Fingerprinting Heatwaves and Cold Spells and Assessing Their Response to Climate Change Using Large Deviation Theory (Galfi and Licarini 2021)
  • https://phys.org/news/2021-08-fingerprints-extreme-weather-revealed-statistical.html

• Attribution studies remain our best (and only) tool for understanding the impact of climate change on extreme weather and on our daily lives. They play a key role in helping decision makers plan for, or avoid, a future where extreme weather events are more likely and intense due to global warming.
• Attribution studies are also really important within climate science as they bridge the gap between observations and model projections. They test climate models in a real-world context, allowing scientists to understand better where they can have more confidence in their projections and where model improvements are needed before projections can be used for decision making.
• https://science2017.globalchange.gov/chapter/3/
• Detection and Attribution Methodologies Overview
• #PAPER Precipitation downscaling under climate change: Recent developments to bridge the gap between dynamical models and the end user (2010)
• #PAPER Detection and attribution of climate extremes in the observed record (Easterling 2016)
• #PAPER Adapting attribution science to the climate extremes of tomorrow (Harrington 2018)
• #PAPER Investigating the Role of the Relative Humidity in the Co‐Occurrence of Temperature and Heat Stress Extremes in CMIP5 Projections (2019)
• #PAPER Towards reliable extreme weather and climate event attribution (Bellprat 2019)
  • Showed how exploiting advanced correction techniques from the weather forecasting field, that correcting properly for model probabilities alters the attributable risk of extreme events to climate change.
  • This study illustrates the need to correct for this type of model error in order to provide trustworthy assessments of climate change impacts.