Subseasonal forecasting—predicting temperature and precipitation 2 to 6 weeks ahead—is critical for effective water allocation, wildfire management, and drought and flood mitigation. Recent international research efforts have advanced the subseasonal capabilities of operational dynamical models, yet temperature and precipitation prediction skills remain poor, partly due to stubborn errors in representing atmospheric dynamics and physics inside dynamical models. Here, to counter these errors, we introduce an
Producing high-quality forecasts of key climate variables, such as temperature and precipitation, on subseasonal time scales has long been a gap in operational forecasting. This study explores an application of machine learning (ML) models as postprocessing tools for subseasonal forecasting. Lagged numerical ensemble forecasts (i.e., an ensemble where the members have different initialization dates) and observational data, including relative humidity, pressure at sea level, and geopotential height, are incorporated into various ML methods to predict monthly average precipitation and 2-m temperature 2 weeks in advance for the continental United States. For regression, quantile regression, and tercile classification tasks, we consider using linear models, random forests, convolutional neural networks, and stacked models (a multimodel approach based on the prediction of the individual ML models). Unlike previous ML approaches that often use ensemble mean alone, we leverage information embedded in the ensemble forecasts to enhance prediction accuracy. Additionally, we investigate extreme event predictions that are crucial for planning and mitigation efforts. Considering ensemble members as a collection of spatial forecasts, we explore different approaches to using spatial information. Trade-offs between different approaches may be mitigated with model stacking. Our proposed models outperform standard baselines such as climatological forecasts and ensemble means. In addition, we investigate feature importance, trade-offs between using the full ensemble or only the ensemble mean, and different modes of accounting for spatial variability.
Accurately forecasting temperature and precipitation on subseasonal time scales—2 weeks–2 months in advance—is extremely challenging. These forecasts would have immense value in agriculture, insurance, and economics. Our paper describes an application of machine learning techniques to improve forecasts of monthly average precipitation and 2-m temperature using lagged physics-based predictions and observational data 2 weeks in advance for the entire continental United States. For lagged ensembles, the proposed models outperform standard benchmarks such as historical averages and averages of physics-based predictions. Our findings suggest that utilizing the full set of physics-based predictions instead of the average enhances the accuracy of the final forecast.
- PAR ID:
- 10543904
- Publisher / Repository:
- American Meteorological Society
- Date Published:
- Journal Name:
- Artificial Intelligence for the Earth Systems
- Volume:
- 3
- Issue:
- 4
- ISSN:
- 2769-7525
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract adaptive bias correction (ABC) method that combines state-of-the-art dynamical forecasts with observations using machine learning. We show that, when applied to the leading subseasonal model from the European Centre for Medium-Range Weather Forecasts (ECMWF), ABC improves temperature forecasting skill by 60–90% (over baseline skills of 0.18–0.25) and precipitation forecasting skill by 40–69% (over baseline skills of 0.11–0.15) in the contiguous U.S. We couple these performance improvements with a practical workflow to explain ABC skill gains and identify higher-skill windows of opportunity based on specific climate conditions. -
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.
-
more » « less
Abstract We describe a new effort to enhance climate forecast relevance and usability through the development of a system for evaluating and displaying real‐time subseasonal to seasonal (S2S) climate forecasts on a watershed scale. Water managers may not use climate forecasts to their full potential due to perceived low skill, mismatched spatial and temporal resolutions, or lack of knowledge or tools to ingest data. Most forecasts are disseminated as large‐domain maps or gridded datasets and may be systematically biased relative to watershed climatologies. Forecasts presented on a watershed scale allow water managers to view forecasts for their specific basins, thereby increasing the usability and relevance of climate forecasts. This paper describes the formulation of S2S climate forecast products based on the Climate Forecast System version 2 (CFSv2) and the North American Multi‐Model Ensemble (NMME). Forecast products include bi‐weekly CFSv2 forecasts, and monthly and seasonal NMME forecasts. Precipitation and temperature forecasts are aggregated spatially to a United States Geological Survey (USGS) hydrologic unit code 4 (HUC‐4) watershed scale. Forecast verification reveals appreciable skill in the first two bi‐weekly periods (Weeks 1–2 and 2–3) from CFSv2, and usable skill in NMME Month 1 forecast with varying skills at longer lead times dependent on the season. Application of a bias‐correction technique (quantile mapping) eliminates forecast bias in the CFSv2 reforecasts, without adding significantly to correlation skill.
-
Abstract Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that IceNet advances the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model in seasonal forecasts of summer sea ice, particularly for extreme sea ice events. This step-change in sea ice forecasting ability brings us closer to conservation tools that mitigate risks associated with rapid sea ice loss.more » « less
-
more » « less
Abstract Studies have indicated exaggerated Maritime Continent (MC) barrier effect in simulations of the Madden–Julian oscillation (MJO), a dominant source of subseasonal predictability in the tropics. This issue has plagued the modeling and operational forecasting communities for decades, while the sensitivity of MC barrier on MJO predictability has not been addressed quantitatively. In this study, perfect-model ensemble forecasts are conducted with an aquaplanet configuration of the Community Earth System Model version 2 (CESM2) in which both basic state and tropical modes of variability are reasonably simulated with a warm pool–like SST distribution. When water-covered terrain mimicking MC landmasses is added to the warm pool–like SST framework, the eastward propagation of the MJO is disturbed by the prescribed MC aqua-mountain. The MJO predictability estimate with the perfect-model experiment is about 6 weeks but reduces to about 4 weeks when the MJO is impeded by the MC aqua-mountain. Given that the recent operational forecasts show an average of 3–4 weeks of MJO prediction skill, we can conclude that improving the MJO propagation crossing the MC could improve the MJO skill to 5–6 weeks, close to the potential predictability found in this study (6 weeks). Therefore, more effort toward understanding and improving the MJO propagation is needed to enhance the MJO and MJO-related forecasts to improve the subseasonal-to-seasonal prediction.
