Abstract The predictability of sea ice during extreme sea ice loss events on subseasonal (daily to weekly) time scales is explored in dynamical forecast models. These extreme sea ice loss events (defined as the 5th percentile of the 5-day change in sea ice extent) exhibit substantial regional and seasonal variability; in the central Arctic Ocean basin, most subseasonal rapid ice loss occurs in the summer, but in the marginal seas rapid sea ice loss occurs year-round. Dynamical forecast models are largely able to capture the seasonality of these extreme sea ice loss events. In most regions in the summertime, sea ice forecast skill is lower on extreme sea ice loss days than on nonextreme days, despite evidence that links these extreme events to large-scale atmospheric patterns; in the wintertime, the difference between extreme and nonextreme days is less pronounced. In a damped anomaly forecast benchmark estimate, the forecast error remains high following extreme sea ice loss events and does not return to typical error levels for many weeks; this signal is less robust in the dynamical forecast models but still present. Overall, these results suggest that sea ice forecast skill is generally lower during and after extreme sea ice loss events and also that, while dynamical forecast models are capable of simulating extreme sea ice loss events with similar characteristics to what we observe, forecast skill from dynamical models is limited by biases in mean state and variability and errors in the initialization. Significance Statement We studied weather model forecasts of changes in Arctic sea ice extent on day-to-day time scales in different regions and seasons. We were especially interested in extreme sea ice loss days, or days in which sea ice melts very quickly or is reduced due to diverging forces such as winds, ocean currents, and waves. We find that forecast models generally capture the observed timing of extreme sea ice loss days. We also find that forecasts of sea ice extent are worse on extreme sea ice loss days compared to typical days, and that forecast errors remain elevated following extreme sea ice loss events.
more »
« less
Global Extreme Heat Forecasting Using Neural Weather Models
Heatwaves are projected to increase in frequency and severity with global warming. Improved warning systems would help reduce the associated loss of lives, wildfires, power disruptions, and reduction in crop yields. In this work, we explore the potential for deep learning systems trained on historical data to forecast extreme heat on short, medium and subseasonal time scales. To this purpose, we train a set of neural weather models (NWMs) with convolutional architectures to forecast surface temperature anomalies globally, 1 to 28 days ahead, at ∼200-km resolution and on the cubed sphere. The NWMs are trained using the ERA5 reanalysis product and a set of candidate loss functions, including the mean-square error and exponential losses targeting extremes. We find that training models to minimize custom losses tailored to emphasize extremes leads to significant skill improvements in the heatwave prediction task, relative to NWMs trained on the mean-square-error loss. This improvement is accomplished with almost no skill reduction in the general temperature prediction task, and it can be efficiently realized through transfer learning, by retraining NWMs with the custom losses for a few epochs. In addition, we find that the use of a symmetric exponential loss reduces the smoothing of NWM forecasts with lead time. Our best NWM is able to outperform persistence in a regressive sense for all lead times and temperature anomaly thresholds considered, and shows positive regressive skill relative to the ECMWF subseasonal-to-seasonal control forecast after 2 weeks.
Heatwaves are projected to become stronger and more frequent as a result of global warming. Accurate forecasting of these events would enable the implementation of effective mitigation strategies. Here we analyze the forecast accuracy of artificial intelligence systems trained on historical surface temperature data to predict extreme heat events globally, 1 to 28 days ahead. We find that artificial intelligence systems trained to focus on extreme temperatures are significantly more accurate at predicting heatwaves than systems trained to minimize errors in surface temperatures and remain equally skillful at predicting moderate temperatures. Furthermore, the extreme-focused systems compete with state-of-the-art physics-based forecast systems in the subseasonal range, while incurring a much lower computational cost.
- Award ID(s):
- 2019758
- PAR ID:
- 10512820
- Publisher / Repository:
- AMS Journals
- Date Published:
- Journal Name:
- Artificial Intelligence for the Earth Systems
- Volume:
- 2
- Issue:
- 1
- ISSN:
- 2769-7525
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Extreme precipitation over a two-week period can cause significant impacts to life and property. Trustworthy and easy-to-understand forecasts of these extreme periods on the subseasonal-to-seasonal timeframe may provide additional time for planning. The Prediction of Rainfall Extremes at Subseasonal to Seasonal Periods (PRES2iP) project team conducted three workshops over six years to engage with stakeholders to learn what is needed for decision-making for subseasonal precipitation. In this study experimental subseasonal to seasonal (S2S) forecast products were designed, using knowledge gained from previous stakeholder workshops, and shown to decision-makers to evaluate the products for two 14-day extreme precipitation period scenarios. Our stakeholders preferred a combination of products that covered the spatial extent, regional daily values, with associated uncertainty, and text narratives with anticipated impacts for planning within the S2S timeframe. When targeting longer extremes, having information regarding timing of expected impacts was seen as crucial for planning. We found that there is increased uncertainty tolerance with stakeholders when using products at longer lead times that typical skill metrics, such as critical success index or anomaly correlation coefficient, do not capture. Therefore, the use of object-oriented verification, that allows for more flexibility in spatial uncertainty, might be beneficial for evaluating S2S forecasts. These results help to create a foundation for design, verification, and implementation of future operational forecast products with longer lead times, while also providing an example for future workshops that engage both researchers and decision-makers.
-
Abstract Extreme weather events have devastating impacts on human health, economic activities, ecosystems, and infrastructure. It is therefore crucial to anticipate extremes and their impacts to allow for preparedness and emergency measures. There is indeed potential for probabilistic subseasonal prediction on time scales of several weeks for many extreme events. Here we provide an overview of subseasonal predictability for case studies of some of the most prominent extreme events across the globe using the ECMWF S2S prediction system: heatwaves, cold spells, heavy precipitation events, and tropical and extratropical cyclones. The considered heatwaves exhibit predictability on time scales of 3–4 weeks, while this time scale is 2–3 weeks for cold spells. Precipitation extremes are the least predictable among the considered case studies. Tropical cyclones, on the other hand, can exhibit probabilistic predictability on time scales of up to 3 weeks, which in the presented cases was aided by remote precursors such as the Madden–Julian oscillation. For extratropical cyclones, lead times are found to be shorter. These case studies clearly illustrate the potential for event-dependent advance warnings for a wide range of extreme events. The subseasonal predictability of extreme events demonstrated here allows for an extension of warning horizons, provides advance information to impact modelers, and informs communities and stakeholders affected by the impacts of extreme weather events.more » « less
-
more » « less
Abstract Heatwaves are extreme near-surface temperature events that can have substantial impacts on ecosystems and society. Early warning systems help to reduce these impacts by helping communities prepare for hazardous climate-related events. However, state-of-the-art prediction systems can often not make accurate forecasts of heatwaves more than two weeks in advance, which are required for advance warnings. We therefore investigate the potential of statistical and machine learning methods to understand and predict central European summer heatwaves on time scales of several weeks. As a first step, we identify the most important regional atmospheric and surface predictors based on previous studies and supported by a correlation analysis: 2-m air temperature, 500-hPa geopotential, precipitation, and soil moisture in central Europe, as well as Mediterranean and North Atlantic sea surface temperatures, and the North Atlantic jet stream. Based on these predictors, we apply machine learning methods to forecast two targets: summer temperature anomalies and the probability of heatwaves for 1–6 weeks lead time at weekly resolution. For each of these two target variables, we use both a linear and a random forest model. The performance of these statistical models decays with lead time, as expected, but outperforms persistence and climatology at all lead times. For lead times longer than two weeks, our machine learning models compete with the ensemble mean of the European Centre for Medium-Range Weather Forecast’s hindcast system. We thus show that machine learning can help improve subseasonal forecasts of summer temperature anomalies and heatwaves.
Significance Statement Heatwaves (prolonged extremely warm temperatures) cause thousands of fatalities worldwide each year. These damaging events are becoming even more severe with climate change. This study aims to improve advance predictions of summer heatwaves in central Europe by using statistical and machine learning methods. Machine learning models are shown to compete with conventional physics-based models for forecasting heatwaves more than two weeks in advance. These early warnings can be used to activate effective and timely response plans targeting vulnerable communities and regions, thereby reducing the damage caused by heatwaves.
-
Coastal marine heatwaves have destructive and lasting impacts on foundational species 13 and are increasing in frequency, duration, and magnitude. High atmospheric temperatures are 14 often associated with marine heatwaves (MHW) which are defined as 5-days of water 15 temperatures above a seasonally varying 90th percentile threshold. In this study we consider the 16 prevalence of MHW propagation into surficial sediments to cause sediment heatwaves (SHW). 17 Within a shallow, subtidal seagrass meadow in Virginia, USA, sediment temperature was 18 measured at hourly intervals at a depth of 5 cm between June 2020-October 2022 at the meadow 19 edge and central meadow interior. The observed sediment temperature, along with a 29-year 20 record of water temperature and water level was used to develop a sediment temperature model 21 for each location. Modeled sediment temperatures were used to identify sediment heatwaves that 22 may thermally stress belowground seagrass. At both meadow locations, sediment heatwave 23 frequency increased at a rate twice that of MHWs in the average global open ocean, coinciding 24 with a 172% increase in the annual number of SHW days, from 11 to 30 days year-1 between 25 1994-2022. Sediment heatwaves at both meadow locations co-occurred with a MHW 79-81% of 26 the time, with nearly all SHWs having a zero day lag. The top 10% most extreme MHWs and 27 SHWs occurred between November and April when thermal stress to seagrass was unlikely. In 28 June 2015 a SHW co-occurred with an anomalously long duration MHW that was associated 29 with a 90% decline in seagrass from this system, suggesting that SHWs may have contributed to 30 the observed seagrass loss. These results document heatwave propagation across the pelagic-31 sediment interface which likely occur broadly in shallow systems with impacts to critical coastal 32 ecosystem processes and species dynamics.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1175/AIES-D-22-0035.1
