Browse
Abstract
This study attempted to forecast the morning fog expansion (MFE), commonly referred to as the “sea of clouds,” utilizing an artificial intelligence (AI) algorithm. The radiation fog phenomenon that contributes to the sea of clouds is caused by various weather conditions. Hence, the MFE was predicted using datasets from public meteorological observations and a mesoscale numerical model (MSM). In this study, a machine learning technique, the gradient-boosting method, was adopted as the AI algorithm. The Miyoshi basin in Japan, renowned for its MFE, was selected as the experimental region. Training models were developed using datasets from October to December 2018–21. Subsequently, these models were applied to forecast MFE in 2022. The model employing the upper-atmospheric prediction data from the MSM demonstrated the highest robustness and accuracy among the proposed models. For untrained data in the fog season during 2022, the model was confirmed to be sufficiently reliable for forecasting MFE, with a high hit rate of 0.935, a low Brier score of 0.119, and a high area under the curve (AUC) of 0.944. Furthermore, the analysis of the importance of the features elucidated that the meteorological factors, such as synoptic-scale weak wind, temperatures close to the dewpoint temperature, and the absence of middle-level cloud cover at midnight, strongly contribute to the MFE. Therefore, the incorporation of upper-level meteorological elements improves the forecast accuracy for MFE.
Significance Statement
An AI-driven forecasting model for predicting morning fog expansion (MFE), sea of clouds, which often affects local livelihoods, was constructed. Fog forecasting machine learning techniques were utilized in the Japanese region famous for the morning fog. This study revealed that more accurate forecasting models incorporate numerically predicted weather elements sourced from the public routine system rather than real-time observed weather elements. Notably, the upper-level wind speed reflecting synoptic-scale dynamics, surface dewpoint depression, and middle-level cloud cover play significant roles in governing MFE. Therefore, incorporating upper-level meteorological elements into the features to machine learning is crucial for improving the forecasting accuracy of MFE.
Abstract
This study attempted to forecast the morning fog expansion (MFE), commonly referred to as the “sea of clouds,” utilizing an artificial intelligence (AI) algorithm. The radiation fog phenomenon that contributes to the sea of clouds is caused by various weather conditions. Hence, the MFE was predicted using datasets from public meteorological observations and a mesoscale numerical model (MSM). In this study, a machine learning technique, the gradient-boosting method, was adopted as the AI algorithm. The Miyoshi basin in Japan, renowned for its MFE, was selected as the experimental region. Training models were developed using datasets from October to December 2018–21. Subsequently, these models were applied to forecast MFE in 2022. The model employing the upper-atmospheric prediction data from the MSM demonstrated the highest robustness and accuracy among the proposed models. For untrained data in the fog season during 2022, the model was confirmed to be sufficiently reliable for forecasting MFE, with a high hit rate of 0.935, a low Brier score of 0.119, and a high area under the curve (AUC) of 0.944. Furthermore, the analysis of the importance of the features elucidated that the meteorological factors, such as synoptic-scale weak wind, temperatures close to the dewpoint temperature, and the absence of middle-level cloud cover at midnight, strongly contribute to the MFE. Therefore, the incorporation of upper-level meteorological elements improves the forecast accuracy for MFE.
Significance Statement
An AI-driven forecasting model for predicting morning fog expansion (MFE), sea of clouds, which often affects local livelihoods, was constructed. Fog forecasting machine learning techniques were utilized in the Japanese region famous for the morning fog. This study revealed that more accurate forecasting models incorporate numerically predicted weather elements sourced from the public routine system rather than real-time observed weather elements. Notably, the upper-level wind speed reflecting synoptic-scale dynamics, surface dewpoint depression, and middle-level cloud cover play significant roles in governing MFE. Therefore, incorporating upper-level meteorological elements into the features to machine learning is crucial for improving the forecasting accuracy of MFE.
Abstract
Synoptic-scale vortices known as monsoon low pressure systems (LPSs) frequently produce intense precipitation and hydrological disasters in South Asia, so accurately forecasting LPS genesis is crucial for improving disaster preparedness and response. However, the accuracy of LPS genesis forecasts by numerical weather prediction models has remained unknown. Here, we evaluate the performance of two global ensemble models—the U.S. Global Ensemble Forecast System (GEFS) and the Ensemble Prediction System of the European Centre for Medium-Range Weather Forecasts (ECMWF)—in predicting LPS genesis during the years 2021–22. The GEFS successfully predicted about half the observed LPS genesis events 1–2 days in advance; the ECMWF model captured an additional 10% of observed genesis events. Both models had a false alarm ratio (FAR) of around 50% for 1–2-day lead times. In both ensembles, the control run typically exhibited a higher probability of detection (POD) of observed events and a lower FAR compared to the perturbed ensemble members. However, a consensus forecast, in which genesis is predicted when at least 20% of ensemble members forecast LPS formation, had POD values surpassing those of the control run for all lead times. Moreover, probabilistic predictions of genesis over the Bay of Bengal, where most LPSs form, were skillful, with the fraction of ensemble members predicting LPS formation over a 5-day lead time approximating the observed frequency of genesis, without any adjustment or bias correction.
Abstract
Synoptic-scale vortices known as monsoon low pressure systems (LPSs) frequently produce intense precipitation and hydrological disasters in South Asia, so accurately forecasting LPS genesis is crucial for improving disaster preparedness and response. However, the accuracy of LPS genesis forecasts by numerical weather prediction models has remained unknown. Here, we evaluate the performance of two global ensemble models—the U.S. Global Ensemble Forecast System (GEFS) and the Ensemble Prediction System of the European Centre for Medium-Range Weather Forecasts (ECMWF)—in predicting LPS genesis during the years 2021–22. The GEFS successfully predicted about half the observed LPS genesis events 1–2 days in advance; the ECMWF model captured an additional 10% of observed genesis events. Both models had a false alarm ratio (FAR) of around 50% for 1–2-day lead times. In both ensembles, the control run typically exhibited a higher probability of detection (POD) of observed events and a lower FAR compared to the perturbed ensemble members. However, a consensus forecast, in which genesis is predicted when at least 20% of ensemble members forecast LPS formation, had POD values surpassing those of the control run for all lead times. Moreover, probabilistic predictions of genesis over the Bay of Bengal, where most LPSs form, were skillful, with the fraction of ensemble members predicting LPS formation over a 5-day lead time approximating the observed frequency of genesis, without any adjustment or bias correction.
Abstract
The St. Lawrence River Valley experiences a variety of precipitation types (p-types) during the cold season, such as rain, freezing rain, ice pellets, and snow. These varied precipitation types exert considerable impacts on aviation, road transportation, power generation and distribution, and winter recreation and are shaped by diverse multiscale processes that interact with the region’s complex topography. This study utilizes ERA5 reanalysis data, surface cyclone climatology, and hourly station observations from Montréal, Québec, and Burlington, Vermont, during October–April 2000–18 to investigate the spectrum of synoptic-scale weather regimes that induce cold-season precipitation across the St. Lawrence River Valley. In particular, k-means clustering and self-organizing maps (SOMs) are used to classify cyclone tracks passing near the St. Lawrence River Valley, and their accompanying thermodynamic profiles, into a set of event types that include a U.S. East Coast track, a central U.S. track, and two Canadian clipper tracks. Composite analyses are subsequently performed to reveal the synoptic-scale environments and the characteristic p-types that most frequently accompany each event type. Global Ensemble Forecast System version 12 (GEFSv12) reforecasts are then used to examine the relative predictability of cyclone characteristics and the local thermodynamic profile associated with each event type at 0–5-day forecast lead times. The analysis suggests that forecasted cyclones near the St. Lawrence River Valley develop too quickly and are located left-of-track relative to the reanalysis on average, which has implications for forecasts of the local thermodynamic profile and p-type across the region when the temperature is near 0°C.
Significance Statement
Diverse precipitation types are observed when near-surface temperatures approach 0°C during the cold season, especially across the St. Lawrence River Valley in southern Québec. This study classifies cold-season precipitation events impacting the St. Lawrence River Valley based on the track of storm systems across the region and quantifies the average meteorological characteristics and predictability of each track. Our analysis reveals that forecasted low pressure systems develop too quickly and are left of their observed track 0–5 days prior to an event on average, which has implications for forecasted temperatures and the type of precipitation observed across the region. Our results can inform future operational forecasts of cold-season precipitation events by providing a storm-focused perspective on forecast errors during these impactful events.
Abstract
The St. Lawrence River Valley experiences a variety of precipitation types (p-types) during the cold season, such as rain, freezing rain, ice pellets, and snow. These varied precipitation types exert considerable impacts on aviation, road transportation, power generation and distribution, and winter recreation and are shaped by diverse multiscale processes that interact with the region’s complex topography. This study utilizes ERA5 reanalysis data, surface cyclone climatology, and hourly station observations from Montréal, Québec, and Burlington, Vermont, during October–April 2000–18 to investigate the spectrum of synoptic-scale weather regimes that induce cold-season precipitation across the St. Lawrence River Valley. In particular, k-means clustering and self-organizing maps (SOMs) are used to classify cyclone tracks passing near the St. Lawrence River Valley, and their accompanying thermodynamic profiles, into a set of event types that include a U.S. East Coast track, a central U.S. track, and two Canadian clipper tracks. Composite analyses are subsequently performed to reveal the synoptic-scale environments and the characteristic p-types that most frequently accompany each event type. Global Ensemble Forecast System version 12 (GEFSv12) reforecasts are then used to examine the relative predictability of cyclone characteristics and the local thermodynamic profile associated with each event type at 0–5-day forecast lead times. The analysis suggests that forecasted cyclones near the St. Lawrence River Valley develop too quickly and are located left-of-track relative to the reanalysis on average, which has implications for forecasts of the local thermodynamic profile and p-type across the region when the temperature is near 0°C.
Significance Statement
Diverse precipitation types are observed when near-surface temperatures approach 0°C during the cold season, especially across the St. Lawrence River Valley in southern Québec. This study classifies cold-season precipitation events impacting the St. Lawrence River Valley based on the track of storm systems across the region and quantifies the average meteorological characteristics and predictability of each track. Our analysis reveals that forecasted low pressure systems develop too quickly and are left of their observed track 0–5 days prior to an event on average, which has implications for forecasted temperatures and the type of precipitation observed across the region. Our results can inform future operational forecasts of cold-season precipitation events by providing a storm-focused perspective on forecast errors during these impactful events.
Abstract
Data assimilation is an important approach to improve the prediction performance of near-surface wind and wind power. Based on the four-dimensional variational technique, this study proposes an approach to improve near-surface wind and wind power prediction by extracting and assimilating the principal components of cabin radar radial wind observations installed at wind turbines within a wind farm. The verification for a series of cases under strong and weak vertical wind shear conditions indicates that compared to the simulations without assimilation, the predicted ultra-short-term (0–4 h) mean absolute error of near-surface wind and single turbine wind power could be reduced by 0.09–1.17 m s−1 and 53–209 kW after the assimilation of radial wind directly and by 0.33–1.38 m s−1 and 62–239 kW after the assimilation of principal components. These illustrate that assimilating the principal components of radial wind is superior to assimilating radial wind directly and could obviously reduce prediction error. Further investigation suggests that extracting the principal components of radial wind has marginal influences on the density and distribution of observations, but could obviously reduce the fluctuation of the observations and the correlation among the observations. The prediction improvement by assimilating the principal components of radial wind is essentially due to the assimilation of low-frequency and low-correlation information involved in the observations.
Abstract
Data assimilation is an important approach to improve the prediction performance of near-surface wind and wind power. Based on the four-dimensional variational technique, this study proposes an approach to improve near-surface wind and wind power prediction by extracting and assimilating the principal components of cabin radar radial wind observations installed at wind turbines within a wind farm. The verification for a series of cases under strong and weak vertical wind shear conditions indicates that compared to the simulations without assimilation, the predicted ultra-short-term (0–4 h) mean absolute error of near-surface wind and single turbine wind power could be reduced by 0.09–1.17 m s−1 and 53–209 kW after the assimilation of radial wind directly and by 0.33–1.38 m s−1 and 62–239 kW after the assimilation of principal components. These illustrate that assimilating the principal components of radial wind is superior to assimilating radial wind directly and could obviously reduce prediction error. Further investigation suggests that extracting the principal components of radial wind has marginal influences on the density and distribution of observations, but could obviously reduce the fluctuation of the observations and the correlation among the observations. The prediction improvement by assimilating the principal components of radial wind is essentially due to the assimilation of low-frequency and low-correlation information involved in the observations.
Abstract
Blowing snow is a hazard for motorists because it may rapidly reduce visibility. Numerical weather prediction models in the United States do not capture the movement of snow once it reaches the ground, but visibility reductions due to blowing snow can be diagnosed based on model-predicted land surface and environmental conditions that correlate with blowing snow occurrence. A recently developed diagnostic framework for forecasting blowing snow concentration and the associated visibility reduction is applied to High-Resolution Rapid Refresh (HRRR) and Rapid Refresh Forecast System (RRFS) model output including surface snow conditions to predict surface visibility reduction due to blowing snow. Twelve blowing snow events around Wyoming from 2018 to 2023 are examined. The analysis shows that visibility reductions due to blowing snow tend to be overpredicted, caused by the initial assumption of full driftability of the snowpack. This study refines the aging of the blowing snow reservoir with two methods. The first method estimates driftability based on time-varying snow density from the Rapid Update Cycle land surface model (RUC LSM) used in the HRRR and experimental RRFS models and is evaluated in a real-time context with the RRFS model. The second, complementary method diagnoses snowpack driftability using a process-based approach that requires data for recent snowfall, wind speed, and skin temperature. Compared to the full driftability assumption, this method shows limited improvements in forecasting skill. To improve model-based diagnosis of visibility reduction due to blowing snow, empirical work is needed to determine the relation between snowpack driftability and the recent history of snowfall and other weather conditions.
Significance Statement
Blowing snow presents a significant hazard to motorists and airport operations through sometimes very rapid and intense reductions in visibility, yet little predictive guidance exists for blowing snow. This study aims to improve the prediction of blowing snow occurrence and associated surface visibility reduction using diagnostics from an operational high-resolution weather model. One key challenge regards the question of driftability of the snowpack. This study evaluates two approaches to quantify driftability in terms of visibility reduction due to blowing snow and acknowledges that more measurements are needed to improve the representation of blowing snow physics in NWP models.
Abstract
Blowing snow is a hazard for motorists because it may rapidly reduce visibility. Numerical weather prediction models in the United States do not capture the movement of snow once it reaches the ground, but visibility reductions due to blowing snow can be diagnosed based on model-predicted land surface and environmental conditions that correlate with blowing snow occurrence. A recently developed diagnostic framework for forecasting blowing snow concentration and the associated visibility reduction is applied to High-Resolution Rapid Refresh (HRRR) and Rapid Refresh Forecast System (RRFS) model output including surface snow conditions to predict surface visibility reduction due to blowing snow. Twelve blowing snow events around Wyoming from 2018 to 2023 are examined. The analysis shows that visibility reductions due to blowing snow tend to be overpredicted, caused by the initial assumption of full driftability of the snowpack. This study refines the aging of the blowing snow reservoir with two methods. The first method estimates driftability based on time-varying snow density from the Rapid Update Cycle land surface model (RUC LSM) used in the HRRR and experimental RRFS models and is evaluated in a real-time context with the RRFS model. The second, complementary method diagnoses snowpack driftability using a process-based approach that requires data for recent snowfall, wind speed, and skin temperature. Compared to the full driftability assumption, this method shows limited improvements in forecasting skill. To improve model-based diagnosis of visibility reduction due to blowing snow, empirical work is needed to determine the relation between snowpack driftability and the recent history of snowfall and other weather conditions.
Significance Statement
Blowing snow presents a significant hazard to motorists and airport operations through sometimes very rapid and intense reductions in visibility, yet little predictive guidance exists for blowing snow. This study aims to improve the prediction of blowing snow occurrence and associated surface visibility reduction using diagnostics from an operational high-resolution weather model. One key challenge regards the question of driftability of the snowpack. This study evaluates two approaches to quantify driftability in terms of visibility reduction due to blowing snow and acknowledges that more measurements are needed to improve the representation of blowing snow physics in NWP models.
Abstract
Stochastic representations of model uncertainties are of great importance for the performance of ensemble prediction systems (EPSs). The stochastically perturbed parameterization tendencies (SPPT) scheme with a single-scale random pattern has been used in the operational global EPS of China Meteorological Administration (CMA-GEPS) since 2018. To deal with deficiencies in this operational single-scale SPPT scheme, a combined scheme based on the multiscale SPPT (mSPPT) scheme and the stochastically perturbed parameterization for the planetary boundary layer (SPP-PBL) scheme is developed. In the combined scheme, the mSPPT component aims to expand model uncertainties characterized by SPPT at mesoscale, synoptic scale, and planetary scale. The SPP-PBL component with six vital parameters is used to capture uncertainties in PBL processes, which is underrepresented by SPPT for the tapering treatment within PBL. Comparisons between the operational SPPT scheme and the mSPPT scheme reveal that the mSPPT scheme can generate more improvements in both ensemble reliability and forecast skills mainly in tropics. Besides, additional benefits from SPP-PBL on top of mSPPT are shown to be primarily distributed in tropics at the lower layers below 850 hPa and surface. Furthermore, the combined scheme of mSPPT and SPP-PBL is suggested to yield better spread–error relationships and forecast skills than the operational SPPT scheme in terms of objective verification scores for standard upper-air variables and surface parameters. A case study for the extreme precipitation event on 20 July 2021 in Henan Province of China also demonstrates the better ability of the combined scheme in forecasting the precipitation intensity and location.
Significance Statement
A comprehensive and reasonable representation of model uncertainties helps to improve the performance of ensemble prediction systems (EPSs). Despite the popular usage in simulating model uncertainties, the stochastically perturbed parameterization tendencies (SPPT) scheme possesses several shortcomings. To overcome this, a combined scheme based on the multiscale SPPT (mSPPT) scheme and the stochastically perturbed parameterization for the planetary boundary layer (SPP-PBL) scheme is proposed. Based on the global EPS of China Meteorological Administration (CMA-GEPS), additional benefits from the independent usage of mSPPT and SPP-PBL are disclosed. And the combined scheme can inherit the merits of mSPPT and SPP-PBL and generate more improvements on ensemble performance than the original single-scale SPPT scheme. This research provides a guideline for future upgradation of CMA-GEPS.
Abstract
Stochastic representations of model uncertainties are of great importance for the performance of ensemble prediction systems (EPSs). The stochastically perturbed parameterization tendencies (SPPT) scheme with a single-scale random pattern has been used in the operational global EPS of China Meteorological Administration (CMA-GEPS) since 2018. To deal with deficiencies in this operational single-scale SPPT scheme, a combined scheme based on the multiscale SPPT (mSPPT) scheme and the stochastically perturbed parameterization for the planetary boundary layer (SPP-PBL) scheme is developed. In the combined scheme, the mSPPT component aims to expand model uncertainties characterized by SPPT at mesoscale, synoptic scale, and planetary scale. The SPP-PBL component with six vital parameters is used to capture uncertainties in PBL processes, which is underrepresented by SPPT for the tapering treatment within PBL. Comparisons between the operational SPPT scheme and the mSPPT scheme reveal that the mSPPT scheme can generate more improvements in both ensemble reliability and forecast skills mainly in tropics. Besides, additional benefits from SPP-PBL on top of mSPPT are shown to be primarily distributed in tropics at the lower layers below 850 hPa and surface. Furthermore, the combined scheme of mSPPT and SPP-PBL is suggested to yield better spread–error relationships and forecast skills than the operational SPPT scheme in terms of objective verification scores for standard upper-air variables and surface parameters. A case study for the extreme precipitation event on 20 July 2021 in Henan Province of China also demonstrates the better ability of the combined scheme in forecasting the precipitation intensity and location.
Significance Statement
A comprehensive and reasonable representation of model uncertainties helps to improve the performance of ensemble prediction systems (EPSs). Despite the popular usage in simulating model uncertainties, the stochastically perturbed parameterization tendencies (SPPT) scheme possesses several shortcomings. To overcome this, a combined scheme based on the multiscale SPPT (mSPPT) scheme and the stochastically perturbed parameterization for the planetary boundary layer (SPP-PBL) scheme is proposed. Based on the global EPS of China Meteorological Administration (CMA-GEPS), additional benefits from the independent usage of mSPPT and SPP-PBL are disclosed. And the combined scheme can inherit the merits of mSPPT and SPP-PBL and generate more improvements on ensemble performance than the original single-scale SPPT scheme. This research provides a guideline for future upgradation of CMA-GEPS.
Abstract
This paper analyzes the climatology, prediction skill, and predictability of tropical cyclones (TCs) in NASA’s Goddard Earth Observing System Subseasonal to Seasonal (GEOS-S2S) forecast system version 2. GEOS reasonably simulates the number and spatial distribution of TCs compared to observations except in the Atlantic where the model simulates too few TCs due to low genesis rates in the Caribbean Sea and Gulf of Mexico. The environmental conditions, diagnosed through a genesis potential index, do not clearly explain model biases in the genesis rates, especially in the Atlantic. At the storm scale, GEOS reforecasts replicate several key aspects of the thermodynamic and dynamic structures of observed TCs, such as a warm core and the secondary circulation. The model, however, fails to simulate an off-center eyewall when evaluating vertical velocity, precipitation, and moisture. The analysis of the prediction skill of TC genesis and occurrence shows that GEOS has comparable skill to other global models in WMO S2S archive and that its skill could be further improved by increasing the ensemble size. After calibration, GEOS forecasts are skillful in the western North Pacific and southern Indian Ocean up to 20 days in advance. A model-based predictability analysis demonstrates the importance of the Madden–Julian oscillation (MJO) as a source of predictability of TC occurrence beyond the 14-day lead time. Forecasts initialized under strong MJO conditions show evidence of predictability beyond week 3. However, due to model biases in the forecast distribution, there are notable gaps between the MJO-related prediction skill and predictability, which require further study.
Abstract
This paper analyzes the climatology, prediction skill, and predictability of tropical cyclones (TCs) in NASA’s Goddard Earth Observing System Subseasonal to Seasonal (GEOS-S2S) forecast system version 2. GEOS reasonably simulates the number and spatial distribution of TCs compared to observations except in the Atlantic where the model simulates too few TCs due to low genesis rates in the Caribbean Sea and Gulf of Mexico. The environmental conditions, diagnosed through a genesis potential index, do not clearly explain model biases in the genesis rates, especially in the Atlantic. At the storm scale, GEOS reforecasts replicate several key aspects of the thermodynamic and dynamic structures of observed TCs, such as a warm core and the secondary circulation. The model, however, fails to simulate an off-center eyewall when evaluating vertical velocity, precipitation, and moisture. The analysis of the prediction skill of TC genesis and occurrence shows that GEOS has comparable skill to other global models in WMO S2S archive and that its skill could be further improved by increasing the ensemble size. After calibration, GEOS forecasts are skillful in the western North Pacific and southern Indian Ocean up to 20 days in advance. A model-based predictability analysis demonstrates the importance of the Madden–Julian oscillation (MJO) as a source of predictability of TC occurrence beyond the 14-day lead time. Forecasts initialized under strong MJO conditions show evidence of predictability beyond week 3. However, due to model biases in the forecast distribution, there are notable gaps between the MJO-related prediction skill and predictability, which require further study.
Abstract
Producing a quantitative snowfall forecast (QSF) typically requires a model quantitative precipitation forecast (QPF) and snow-to-liquid ratio (SLR) estimate. QPF and SLR can vary significantly in space and time over complex terrain, necessitating fine-scale or point-specific forecasts of each component. Little Cottonwood Canyon (LCC) in Utah’s Wasatch Range frequently experiences high-impact winter storms and avalanche closures that result in substantial transportation and economic disruptions, making it an excellent testbed for evaluating snowfall forecasts. In this study, we validate QPFs, SLR forecasts, and QSFs produced by or derived from the Global Forecast System (GFS) and High-Resolution Rapid Refresh (HRRR) using liquid precipitation equivalent (LPE) and snowfall observations collected during the 2019/20–2022/23 cool seasons at the Alta–Collins snow-study site (2945 m MSL) in upper LCC. The 12-h QPFs produced by the GFS and HRRR underpredict the total LPE during the four cool seasons by 33% and 29%, respectively, and underpredict 50th, 75th, and 90th percentile event frequencies. Current operational SLR methods exhibit mean absolute errors of 4.5–7.7. In contrast, a locally trained random forest algorithm reduces SLR mean absolute errors to 3.7. Despite the random forest producing more accurate SLR forecasts, QSFs derived from operational SLR methods produce higher critical success indices since they exhibit positive SLR biases that offset negative QPF biases. These results indicate an overall underprediction of LPE by operational models in upper LCC and illustrate the need to identify sources of QSF bias to enhance QSF performance.
Significance Statement
Winter storms in mountainous terrain can disrupt transportation and threaten life and property due to road snow and avalanche hazards. Snow-to-liquid ratio (SLR) is an important variable for snowfall and avalanche forecasts. Using high-quality historical snowfall observations and atmospheric analyses, we developed a machine learning technique for predicting SLR at a high mountain site in Utah’s Little Cottonwood Canyon that is prone to closure due to winter storms. This technique produces improved SLR forecasts for use by weather forecasters and snow-safety personnel. We also show that current operational models and SLR techniques underforecast liquid precipitation amounts and overforecast SLRs, respectively, which has implications for future model development.
Abstract
Producing a quantitative snowfall forecast (QSF) typically requires a model quantitative precipitation forecast (QPF) and snow-to-liquid ratio (SLR) estimate. QPF and SLR can vary significantly in space and time over complex terrain, necessitating fine-scale or point-specific forecasts of each component. Little Cottonwood Canyon (LCC) in Utah’s Wasatch Range frequently experiences high-impact winter storms and avalanche closures that result in substantial transportation and economic disruptions, making it an excellent testbed for evaluating snowfall forecasts. In this study, we validate QPFs, SLR forecasts, and QSFs produced by or derived from the Global Forecast System (GFS) and High-Resolution Rapid Refresh (HRRR) using liquid precipitation equivalent (LPE) and snowfall observations collected during the 2019/20–2022/23 cool seasons at the Alta–Collins snow-study site (2945 m MSL) in upper LCC. The 12-h QPFs produced by the GFS and HRRR underpredict the total LPE during the four cool seasons by 33% and 29%, respectively, and underpredict 50th, 75th, and 90th percentile event frequencies. Current operational SLR methods exhibit mean absolute errors of 4.5–7.7. In contrast, a locally trained random forest algorithm reduces SLR mean absolute errors to 3.7. Despite the random forest producing more accurate SLR forecasts, QSFs derived from operational SLR methods produce higher critical success indices since they exhibit positive SLR biases that offset negative QPF biases. These results indicate an overall underprediction of LPE by operational models in upper LCC and illustrate the need to identify sources of QSF bias to enhance QSF performance.
Significance Statement
Winter storms in mountainous terrain can disrupt transportation and threaten life and property due to road snow and avalanche hazards. Snow-to-liquid ratio (SLR) is an important variable for snowfall and avalanche forecasts. Using high-quality historical snowfall observations and atmospheric analyses, we developed a machine learning technique for predicting SLR at a high mountain site in Utah’s Little Cottonwood Canyon that is prone to closure due to winter storms. This technique produces improved SLR forecasts for use by weather forecasters and snow-safety personnel. We also show that current operational models and SLR techniques underforecast liquid precipitation amounts and overforecast SLRs, respectively, which has implications for future model development.
Abstract
Accurate tropical cyclogenesis (TCG) prediction is important because it allows national operational forecasting agencies to issue timely warnings and implement effective disaster prevention measures. In 2020, the Korea Meteorological Administration employed a self-developed operational model called the Korean Integrated Model (KIM). In this study, we verified KIM’s TCG forecast skill over the western North Pacific. Based on 9-day forecasts, TCG in the model was objectively detected and classified as well-predicted, early formation, late formation, miss, or false alarm by comparing their formation times and locations with those of 46 tropical cyclones (TCs) from June to November in 2020–21 documented by the Joint Typhoon Warning Center. The prediction of large-scale environmental conditions relevant to TCG was also evaluated. The results showed that the probability of KIM detection was comparable to or better than that of previously reported statistics of other numerical weather prediction models. The intrabasin comparison revealed that the probability of detection in the Philippine Sea was the highest, followed by the South China Sea and central Pacific. The best TCG prediction performance in the Philippine Sea was supported by unbiased forecasts in large-scale environments. The missed and false alarm cases in all three regions had the largest prediction biases in the large-scale lower-tropospheric relative vorticity. Excessive false alarms may be associated with prediction biases in the vertical gradient of equivalent potential temperature within the boundary layer. This study serves as a primary guide for national forecasters and is useful to model developers for further refinement of KIM.
Abstract
Accurate tropical cyclogenesis (TCG) prediction is important because it allows national operational forecasting agencies to issue timely warnings and implement effective disaster prevention measures. In 2020, the Korea Meteorological Administration employed a self-developed operational model called the Korean Integrated Model (KIM). In this study, we verified KIM’s TCG forecast skill over the western North Pacific. Based on 9-day forecasts, TCG in the model was objectively detected and classified as well-predicted, early formation, late formation, miss, or false alarm by comparing their formation times and locations with those of 46 tropical cyclones (TCs) from June to November in 2020–21 documented by the Joint Typhoon Warning Center. The prediction of large-scale environmental conditions relevant to TCG was also evaluated. The results showed that the probability of KIM detection was comparable to or better than that of previously reported statistics of other numerical weather prediction models. The intrabasin comparison revealed that the probability of detection in the Philippine Sea was the highest, followed by the South China Sea and central Pacific. The best TCG prediction performance in the Philippine Sea was supported by unbiased forecasts in large-scale environments. The missed and false alarm cases in all three regions had the largest prediction biases in the large-scale lower-tropospheric relative vorticity. Excessive false alarms may be associated with prediction biases in the vertical gradient of equivalent potential temperature within the boundary layer. This study serves as a primary guide for national forecasters and is useful to model developers for further refinement of KIM.
Abstract
As artificial intelligence (AI) methods are increasingly used to develop new guidance intended for operational use by forecasters, it is critical to evaluate whether forecasters deem the guidance trustworthy. Past trust-related AI research suggests that certain attributes (e.g., understanding how the AI was trained, interactivity, and performance) contribute to users perceiving the AI as trustworthy. However, little research has been done to examine the role of these and other attributes for weather forecasters. In this study, we conducted 16 online interviews with National Weather Service (NWS) forecasters to examine (i) how they make guidance use decisions and (ii) how the AI model technique used, training, input variables, performance, and developers as well as interacting with the model output influenced their assessments of trustworthiness of new guidance. The interviews pertained to either a random forest model predicting the probability of severe hail or a 2D convolutional neural network model predicting the probability of storm mode. When taken as a whole, our findings illustrate how forecasters’ assessment of AI guidance trustworthiness is a process that occurs over time rather than automatically or at first introduction. We recommend developers center end users when creating new AI guidance tools, making end users integral to their thinking and efforts. This approach is essential for the development of useful and used tools. The details of these findings can help AI developers understand how forecasters perceive AI guidance and inform AI development and refinement efforts.
Significance Statement
We used a mixed-methods quantitative and qualitative approach to understand how National Weather Service (NWS) forecasters 1) make guidance use decisions within their operational forecasting process and 2) assess the trustworthiness of prototype guidance developed using artificial intelligence (AI). When taken as a whole, our findings illustrate that forecasters’ assessment of AI guidance trustworthiness is a process that occurs over time rather than automatically and suggest that developers must center the end user when creating new AI guidance tools to ensure that the developed tools are useful and used.
Abstract
As artificial intelligence (AI) methods are increasingly used to develop new guidance intended for operational use by forecasters, it is critical to evaluate whether forecasters deem the guidance trustworthy. Past trust-related AI research suggests that certain attributes (e.g., understanding how the AI was trained, interactivity, and performance) contribute to users perceiving the AI as trustworthy. However, little research has been done to examine the role of these and other attributes for weather forecasters. In this study, we conducted 16 online interviews with National Weather Service (NWS) forecasters to examine (i) how they make guidance use decisions and (ii) how the AI model technique used, training, input variables, performance, and developers as well as interacting with the model output influenced their assessments of trustworthiness of new guidance. The interviews pertained to either a random forest model predicting the probability of severe hail or a 2D convolutional neural network model predicting the probability of storm mode. When taken as a whole, our findings illustrate how forecasters’ assessment of AI guidance trustworthiness is a process that occurs over time rather than automatically or at first introduction. We recommend developers center end users when creating new AI guidance tools, making end users integral to their thinking and efforts. This approach is essential for the development of useful and used tools. The details of these findings can help AI developers understand how forecasters perceive AI guidance and inform AI development and refinement efforts.
Significance Statement
We used a mixed-methods quantitative and qualitative approach to understand how National Weather Service (NWS) forecasters 1) make guidance use decisions within their operational forecasting process and 2) assess the trustworthiness of prototype guidance developed using artificial intelligence (AI). When taken as a whole, our findings illustrate that forecasters’ assessment of AI guidance trustworthiness is a process that occurs over time rather than automatically and suggest that developers must center the end user when creating new AI guidance tools to ensure that the developed tools are useful and used.
