Browse
Abstract
In this study, we analyze drivers of non–El Niño–Southern Oscillation (ENSO) precipitation variability in the Southwest United States (SWUS) and the influence of the atmospheric basic state, using atmosphere-only and ocean–atmosphere coupled simulations from the Community Earth System Model version 2 (CESM2) large ensemble. A cluster analysis identifies three main wave trains associated with non-ENSO SWUS precipitation in the experiments: a meridional ENSO-type wave train, an arching Pacific–North American-type (PNA) wave train, and a circumglobal zonal wave train. The zonal wave train cluster frequency differs between models and ENSO phase, with decreased frequency during El Niño and the coupled runs, and increased frequency during La Niña and the atmosphere-only runs. This is consistent with an El Niño–like bias of the atmospheric circulation in the coupled model, with strengthened subtropical westerlies in the central and eastern North Pacific that cause a retraction of the waveguide in the midlatitude eastern North Pacific. As such, zonal wave trains from the East Asian jet stream (EAJS) are more likely to be diverted southward in the east Pacific in the coupled large ensemble, with a consequently smaller role in driving SWUS precipitation variability. This study illustrates the need to reduce model biases in the background flow, particularly relating to the jet stream, in order to accurately capture the role of large-scale teleconnections in driving SWUS precipitation variability and improve future forecasting capabilities.
Abstract
In this study, we analyze drivers of non–El Niño–Southern Oscillation (ENSO) precipitation variability in the Southwest United States (SWUS) and the influence of the atmospheric basic state, using atmosphere-only and ocean–atmosphere coupled simulations from the Community Earth System Model version 2 (CESM2) large ensemble. A cluster analysis identifies three main wave trains associated with non-ENSO SWUS precipitation in the experiments: a meridional ENSO-type wave train, an arching Pacific–North American-type (PNA) wave train, and a circumglobal zonal wave train. The zonal wave train cluster frequency differs between models and ENSO phase, with decreased frequency during El Niño and the coupled runs, and increased frequency during La Niña and the atmosphere-only runs. This is consistent with an El Niño–like bias of the atmospheric circulation in the coupled model, with strengthened subtropical westerlies in the central and eastern North Pacific that cause a retraction of the waveguide in the midlatitude eastern North Pacific. As such, zonal wave trains from the East Asian jet stream (EAJS) are more likely to be diverted southward in the east Pacific in the coupled large ensemble, with a consequently smaller role in driving SWUS precipitation variability. This study illustrates the need to reduce model biases in the background flow, particularly relating to the jet stream, in order to accurately capture the role of large-scale teleconnections in driving SWUS precipitation variability and improve future forecasting capabilities.
Abstract
Machine learning algorithms are able to capture complex, nonlinear, interacting relationships and are increasingly used to predict agricultural yield variability at regional and national scales. Using explainable artificial intelligence (XAI) methods applied to such algorithms may enable better scientific understanding of drivers of yield variability. However, XAI methods may provide misleading results when applied to spatiotemporal correlated datasets. In this study, machine learning models are trained to predict simulated crop yield from climate indices, and the impact of cross-validation strategy on the interpretation and performance of the resulting models is assessed. Using data from a process-based crop model allows us to then comment on the plausibility of the “explanations” provided by XAI methods. Our results show that the choice of evaluation strategy has an impact on (i) interpretations of the model and (ii) model skill on held-out years and regions, after the evaluation strategy is used for hyperparameter tuning and feature selection. We find that use of a cross-validation strategy based on clustering in feature space achieves the most plausible interpretations as well as the best model performance on held-out years and regions. Our results provide the first steps toward identifying domain-specific “best practices” for the use of XAI tools on spatiotemporal agricultural or climatic data.
Significance Statement
“Explainable” or “interpretable” machine learning (XAI) methods have been increasingly used in scientific research to study complex relationships between climatic and biogeoscientific variables (such as crop yield). However, these methods can return contradictory, implausible, or ambiguous results. In this study, we train machine learning models to predict maize yield anomalies and vary the model evaluation method used. We find that the evaluation (cross validation) method used has an effect on model interpretation results and on the skill of resulting models in held-out years and regions. These results have implications for the methodological design of studies that aim to use XAI tools to identify drivers of, for example, crop yield variability.
Abstract
Machine learning algorithms are able to capture complex, nonlinear, interacting relationships and are increasingly used to predict agricultural yield variability at regional and national scales. Using explainable artificial intelligence (XAI) methods applied to such algorithms may enable better scientific understanding of drivers of yield variability. However, XAI methods may provide misleading results when applied to spatiotemporal correlated datasets. In this study, machine learning models are trained to predict simulated crop yield from climate indices, and the impact of cross-validation strategy on the interpretation and performance of the resulting models is assessed. Using data from a process-based crop model allows us to then comment on the plausibility of the “explanations” provided by XAI methods. Our results show that the choice of evaluation strategy has an impact on (i) interpretations of the model and (ii) model skill on held-out years and regions, after the evaluation strategy is used for hyperparameter tuning and feature selection. We find that use of a cross-validation strategy based on clustering in feature space achieves the most plausible interpretations as well as the best model performance on held-out years and regions. Our results provide the first steps toward identifying domain-specific “best practices” for the use of XAI tools on spatiotemporal agricultural or climatic data.
Significance Statement
“Explainable” or “interpretable” machine learning (XAI) methods have been increasingly used in scientific research to study complex relationships between climatic and biogeoscientific variables (such as crop yield). However, these methods can return contradictory, implausible, or ambiguous results. In this study, we train machine learning models to predict maize yield anomalies and vary the model evaluation method used. We find that the evaluation (cross validation) method used has an effect on model interpretation results and on the skill of resulting models in held-out years and regions. These results have implications for the methodological design of studies that aim to use XAI tools to identify drivers of, for example, crop yield variability.
Abstract
This paper presents the Thunderstorm Nowcasting Tool (ThunderCast), a 24-hour, year round model for predicting the location of convection that is likely to initiate or remain a thunderstorm in the next 0-60 minutes in the continental United States, adapted from existing deep learning convection applications. ThunderCast utilizes a U-Net convolutional neural network for semantic segmentation trained on 320 km by 320 km data patches with four inputs and one target dataset. The inputs are satellite bands from the Geostationary Operational Environmental Satellite (GOES-16) Advanced Baseline Imager (ABI) in the visible, shortwave infrared, and longwave infrared spectrum, and the target is Multi-Radar Multi-Sensor (MRMS) radar reflectivity at the - 10°C isothermin the atmosphere. On a pixel-by-pixel basis, ThunderCast has high accuracy, recall, and specificity but is subject to false positive predictions resulting in low precision. However, the number of false positives decreases when buffering the target values with a 15×15 km centered window indicating ThunderCast’s predictions are useful within a buffered area. To demonstrate the initial prediction capabilities of ThunderCast, three case studies are presented: a mesoscale convective vortex, sea breeze convection, and monsoonal convection in the southwestern United States. The case studies illustrate that the ThunderCast model effectively nowcasts the location of newly initiated and ongoing active convection, within the next 60 minutes, under a variety of geographic and meteorological conditions.
Abstract
This paper presents the Thunderstorm Nowcasting Tool (ThunderCast), a 24-hour, year round model for predicting the location of convection that is likely to initiate or remain a thunderstorm in the next 0-60 minutes in the continental United States, adapted from existing deep learning convection applications. ThunderCast utilizes a U-Net convolutional neural network for semantic segmentation trained on 320 km by 320 km data patches with four inputs and one target dataset. The inputs are satellite bands from the Geostationary Operational Environmental Satellite (GOES-16) Advanced Baseline Imager (ABI) in the visible, shortwave infrared, and longwave infrared spectrum, and the target is Multi-Radar Multi-Sensor (MRMS) radar reflectivity at the - 10°C isothermin the atmosphere. On a pixel-by-pixel basis, ThunderCast has high accuracy, recall, and specificity but is subject to false positive predictions resulting in low precision. However, the number of false positives decreases when buffering the target values with a 15×15 km centered window indicating ThunderCast’s predictions are useful within a buffered area. To demonstrate the initial prediction capabilities of ThunderCast, three case studies are presented: a mesoscale convective vortex, sea breeze convection, and monsoonal convection in the southwestern United States. The case studies illustrate that the ThunderCast model effectively nowcasts the location of newly initiated and ongoing active convection, within the next 60 minutes, under a variety of geographic and meteorological conditions.
Abstract
Across the globe, there has been an increasing interest in improving the predictability of subseasonal hydrometeorological forecasts, as they play a valuable role in medium- to long-term planning in many sectors, such as agriculture, navigation, hydropower, and emergency management. However, these forecasts still have very limited skill at the monthly time scale; hence, this study explores the possibilities for improving forecasts through different pre- and postprocessing techniques at the interface with a Precipitationn–Runoff–Evapotranspiration Hydrological Response Unit Model (PREVAH). Specifically, this research aims to assess the benefit of European weather regime (WR) data within a hybrid forecasting setup, a combination of a traditional hydrological model and a machine learning (ML) algorithm, to improve the performance of subseasonal hydrometeorological forecasts in Switzerland. The WR data contain information about the large-scale atmospheric circulation in the North Atlantic–European region, and thus allow the hydrological model to exploit potential flow-dependent predictability. Four hydrological variables are investigated: total runoff, baseflow, soil moisture, and snowmelt. The improvements in the forecasts achieved with the pre- and postprocessing techniques vary with catchments, lead times, and variables. Adding WR data has clear benefits, but these benefits are not consistent across the study area or among the variables. The usefulness of WR data is generally observed for longer lead times, e.g., beyond the third week. Furthermore, a multimodel approach is applied to determine the “best practice” for each catchment and improve forecast skill over the entire study area. This study highlights the potential and limitations of using WR information to improve subseasonal hydrometeorological forecasts in a hybrid forecasting system in an operational mode.
Abstract
Across the globe, there has been an increasing interest in improving the predictability of subseasonal hydrometeorological forecasts, as they play a valuable role in medium- to long-term planning in many sectors, such as agriculture, navigation, hydropower, and emergency management. However, these forecasts still have very limited skill at the monthly time scale; hence, this study explores the possibilities for improving forecasts through different pre- and postprocessing techniques at the interface with a Precipitationn–Runoff–Evapotranspiration Hydrological Response Unit Model (PREVAH). Specifically, this research aims to assess the benefit of European weather regime (WR) data within a hybrid forecasting setup, a combination of a traditional hydrological model and a machine learning (ML) algorithm, to improve the performance of subseasonal hydrometeorological forecasts in Switzerland. The WR data contain information about the large-scale atmospheric circulation in the North Atlantic–European region, and thus allow the hydrological model to exploit potential flow-dependent predictability. Four hydrological variables are investigated: total runoff, baseflow, soil moisture, and snowmelt. The improvements in the forecasts achieved with the pre- and postprocessing techniques vary with catchments, lead times, and variables. Adding WR data has clear benefits, but these benefits are not consistent across the study area or among the variables. The usefulness of WR data is generally observed for longer lead times, e.g., beyond the third week. Furthermore, a multimodel approach is applied to determine the “best practice” for each catchment and improve forecast skill over the entire study area. This study highlights the potential and limitations of using WR information to improve subseasonal hydrometeorological forecasts in a hybrid forecasting system in an operational mode.
Abstract
Analyses of the Northern Hemisphere’s sea level pressure, air surface temperature, and lower-stratospheric ozone during the period 1900–2019 reveal an existing coherence in their temporal variability. The coherence is heterogeneously distributed over the globe, and the patterns of ozone impact on the pressure and temperature are different. More specifically, the strongest ozone influence on the sea level pressure is found in the main “centers of action”—that is, the Aleutian low and the region of NAO formation. The ozone influence is localized mainly in the latitudinal belt 40°–75°N, where the ozone mixing ratio at 70 hPa is reduced during most of the twentieth century (relative to the first decade of the twenty-first century). This peculiarity of ozone spatial distribution we attribute to the energetic particles trapped in Earth’s radiation belts, activating ion-molecular reactions of ozone production in the region of Regener–Pfotzer ionization maximum. Consequently, the spatial–temporal variations of the lower-atmospheric ionization could be a good explanation for irregularly distributed ozone and its regionally specified impact on the climatic variables.
Significance Statement
We tried to understand the regional character of the Northern Hemisphere’s winter weather conditions. The latter is usually attributed to the North Atlantic Oscillation (NAO), but we actually do not know the factors impacting the NAO variability itself. We found that, at multiannual time scales, the surface pressure is only weakly related to the temperature variations, whereas its correlation with the ozone at 70 hPa is unexpectedly strong—especially in the active regions of the weather phenomena formation. We attribute the ozone variability itself to the variable intensity of energetic particles precipitating in the lower atmosphere—where they activate ion-molecular reactions producing ozone. This finding opens new horizons for understanding the regionality of atmospheric variation at different time scales.
Abstract
Analyses of the Northern Hemisphere’s sea level pressure, air surface temperature, and lower-stratospheric ozone during the period 1900–2019 reveal an existing coherence in their temporal variability. The coherence is heterogeneously distributed over the globe, and the patterns of ozone impact on the pressure and temperature are different. More specifically, the strongest ozone influence on the sea level pressure is found in the main “centers of action”—that is, the Aleutian low and the region of NAO formation. The ozone influence is localized mainly in the latitudinal belt 40°–75°N, where the ozone mixing ratio at 70 hPa is reduced during most of the twentieth century (relative to the first decade of the twenty-first century). This peculiarity of ozone spatial distribution we attribute to the energetic particles trapped in Earth’s radiation belts, activating ion-molecular reactions of ozone production in the region of Regener–Pfotzer ionization maximum. Consequently, the spatial–temporal variations of the lower-atmospheric ionization could be a good explanation for irregularly distributed ozone and its regionally specified impact on the climatic variables.
Significance Statement
We tried to understand the regional character of the Northern Hemisphere’s winter weather conditions. The latter is usually attributed to the North Atlantic Oscillation (NAO), but we actually do not know the factors impacting the NAO variability itself. We found that, at multiannual time scales, the surface pressure is only weakly related to the temperature variations, whereas its correlation with the ozone at 70 hPa is unexpectedly strong—especially in the active regions of the weather phenomena formation. We attribute the ozone variability itself to the variable intensity of energetic particles precipitating in the lower atmosphere—where they activate ion-molecular reactions producing ozone. This finding opens new horizons for understanding the regionality of atmospheric variation at different time scales.
