A stacking ensemble model for hydrological post-processing to improve streamflow forecasts at medium-range timescales over South Korea

2021 ◽  
pp. 126681
Author(s):  
Dong-Gi Lee ◽  
Kuk-Hyun Ahn
Keyword(s):  
South Korea ◽  
Ensemble Model ◽  
Post Processing ◽  
Medium Range ◽  
Streamflow Forecasts

scholarly journals Evaluating the impact of post-processing medium-range ensemble streamflow forecasts from the European Flood Awareness System

2021 ◽  
Author(s):  
Gwyneth Matthews ◽  
Christopher Barnard ◽  
Hannah Cloke ◽  
Sarah L. Dance ◽  
Toni Jurlina ◽  
...  
Keyword(s):  
Response Times ◽  
Weather Prediction ◽  
High Elevation ◽  
Processing Method ◽  
Lead Times ◽  
Post Processing ◽  
Medium Range ◽  
Streamflow Forecasts ◽  
The Impact ◽  
Awareness System

Abstract. Streamflow forecasts provide vital information to aid emergency response preparedness and disaster risk reduction. Medium-range forecasts are created by forcing a hydrological model with output from numerical weather prediction systems. Uncertainties are unavoidably introduced throughout the system and can reduce the skill of the streamflow forecasts. Post-processing is a method used to quantify and reduce the overall uncertainties in order to improve the usefulness of the forecasts. The post-processing method that is used within the operational European Flood Awareness System is based on the Model Conditional Processor and the Ensemble Model Output Statistics method. Using 2-years of reforecasts with daily timesteps this method is evaluated for 522 stations across Europe. Post-processing was found to increase the skill of the forecasts at the majority of stations both in terms of the accuracy of the forecast median and the reliability of the forecast probability distribution. This improvement is seen at all lead-times (up to 15 days) but is largest at short lead-times. The greatest improvement was seen in low-lying, large catchments with long response times, whereas for catchments at high elevation and with very short response times the forecasts often failed to capture the magnitude of peak flows. Additionally, the quality and length of the observational time-series used in the offline calibration of the method were found to be important. This evaluation of the post-processing method, and specifically the new information provided on characteristics that affect the performance of the method, will aid end-users to make more informed decisions. It also highlights the potential issues that may be encountered when developing new post-processing methods.

scholarly journals Assessing the Skill of Medium-Range Ensemble Precipitation and Streamflow Forecasts from the Hydrologic Ensemble Forecast Service (HEFS) for the Upper Trinity River Basin in North Texas

2018 ◽  
Vol 19 (9) ◽  
pp. 1467-1483 ◽  
Author(s):  
Sunghee Kim ◽  
Hossein Sadeghi ◽  
Reza Ahmad Limon ◽  
Manabendra Saharia ◽  
Dong-Jun Seo ◽  
...  
Keyword(s):  
River Basin ◽  
Time Horizon ◽  
Weather Prediction ◽  
Ensemble Forecast ◽  
Trinity River ◽  
Daily Streamflow ◽  
Emergency Managers ◽  
Medium Range ◽  
Streamflow Forecasts ◽  
The Impact

Abstract To issue early warnings for the public to act, for emergency managers to take preventive actions, and for water managers to operate their systems cost-effectively, it is necessary to maximize the time horizon over which streamflow forecasts are skillful. In this work, we assess the value of medium-range ensemble precipitation forecasts generated with the Hydrologic Ensemble Forecast Service (HEFS) of the U.S. National Weather Service (NWS) in increasing the lead time and skill of streamflow forecasts for five headwater basins in the upper Trinity River basin in north-central Texas. The HEFS uses ensemble mean precipitation forecasts from the Global Ensemble Forecast System (GEFS) of the National Centers for Environment Prediction (NCEP). For comparative evaluation, we verify ensemble streamflow forecasts generated with the HEFS forced by the GEFS forecast with those forced by the short-range quantitative precipitation forecasts (QPFs) from the NWS West Gulf River Forecast Center (WGRFC) based on guidance from the NCEP’s Weather Prediction Center. We also assess the benefits of postprocessing the raw ensemble streamflow forecasts and evaluate the impact of selected parameters within the HEFS on forecast quality. The results show that the use of medium-range precipitation forecasts from the GEFS with the HEFS extends the time horizon for skillful forecasting of mean daily streamflow by 1–3 days for significant events when compared with using only the 72-h River Forecast Center (RFC) QPF with the HEFS. The HEFS forced by the GEFS also improves the skill of two-week-ahead biweekly streamflow forecast by about 20% over climatological forecast for the largest 1% of the observed biweekly flow.

scholarly journals Developing a New Hourly Forest Fire Risk Index Based on Catboost in South Korea

2020 ◽  
Vol 10 (22) ◽  
pp. 8213
Author(s):  
Yoojin Kang ◽  
Eunna Jang ◽  
Jungho Im ◽  
Chungeun Kwon ◽  
Sungyong Kim
Keyword(s):  
South Korea ◽  
Forest Fire ◽  
Forest Fires ◽  
Risk Index ◽  
Fire Risk ◽  
Ensemble Model ◽  
Weather Factors ◽  
Meteorological Model ◽  
Forest Fire Risk ◽  
Fire Risk Index

Forest fires can cause enormous damage, such as deforestation and environmental pollution, even with a single occurrence. It takes a lot of effort and long time to restore areas damaged by wildfires. Therefore, it is crucial to know the forest fire risk of a region to appropriately prepare and respond to such disastrous events. The purpose of this study is to develop an hourly forest fire risk index (HFRI) with 1 km spatial resolution using accessibility, fuel, time, and weather factors based on Catboost machine learning over South Korea. HFRI was calculated through an ensemble model that combined an integrated model using all factors and a meteorological model using weather factors only. To confirm the generalized performance of the proposed model, all forest fires that occurred from 2014 to 2019 were validated using the receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) values through one-year-out cross-validation. The AUC value of HFRI ensemble model was 0.8434, higher than the meteorological model. HFRI was compared with the modified version of Fine Fuel Moisture Code (FFMC) used in the Canadian Forest Fire Danger Rating Systems and Daily Weather Index (DWI), South Korea’s current forest fire risk index. When compared to DWI and the revised FFMC, HFRI enabled a more spatially detailed and seasonally stable forest fire risk simulation. In addition, the feature contribution to the forest fire risk prediction was analyzed through the Shapley Additive exPlanations (SHAP) value of Catboost. The contributing variables were in the order of relative humidity, elevation, road density, and population density. It was confirmed that the accessibility factors played very important roles in forest fire risk modeling where most forest fires were caused by anthropogenic factors. The interaction between the variables was also examined.

Incorporating Medium-Range Numerical Weather Model Output into the Ensemble Streamflow Prediction System of the National Weather Service

2005 ◽  
Vol 6 (2) ◽  
pp. 101-114 ◽  
Author(s):  
Kevin Werner ◽  
David Brandon ◽  
Martyn Clark ◽  
Subhrendu Gangopadhyay
Keyword(s):  
Streamflow Prediction ◽  
National Weather Service ◽  
Temperature And Precipitation ◽  
Medium Range Forecast ◽  
Weather Model ◽  
Medium Range ◽  
Streamflow Forecasts ◽  
Ensemble Streamflow Prediction ◽  
Statistical Relationships ◽  
Weather Service

Abstract This study introduces medium-range meteorological ensemble inputs of temperature and precipitation into the Ensemble Streamflow Prediction component of the National Weather Service River Forecast System (NWSRFS). The Climate Diagnostics Center (CDC) produced a reforecast archive of model forecast runs from a dynamically frozen version of the Medium-Range Forecast (MRF) model. This archive was used to derive statistical relationships between MRF variables and historical basin-average precipitation and temperatures. The latter are used to feed the Ensemble Streamflow Prediction (ESP) component of the NWSRFS. Two sets of ESP reforecasts were produced: A control run based on historically observed temperature and precipitation and an experimental run based on MRF-derived temperature and precipitation. This study found the MRF reforecasts to be generally superior to the control reforecasts, although there were situations when the downscaled MRF output actually degraded the forecast. Forecast improvements were most pronounced during the rising limb of the hydrograph—at this time accurate temperature forecasts improve predictions of the rate of snowmelt. Further improvements in streamflow forecasts at short forecast lead times may be possible by incorporating output from high-resolution regional atmospheric models into the NWSRFS.

scholarly journals Improving Operational Short- to Medium-Range (SR2MR) Streamflow Forecasts in the Upper Zambezi Basin and Its Sub-Basins Using Variational Ensemble Forecasting

Hydrology ◽  
2021 ◽  
Vol 8 (4) ◽  
pp. 188
Author(s):  
Rodrigo Valdés-Pineda ◽  
Juan B. Valdés ◽  
Sungwook Wi ◽  
Aleix Serrat-Capdevila ◽  
Tirthankar Roy
Keyword(s):  
Real Time ◽  
Optimal Parameter ◽  
Ensemble Forecasting ◽  
Hydrological Models ◽  
Streamflow Forecasting ◽  
Satellite Precipitation ◽  
Daily Streamflow ◽  
Medium Range ◽  
Streamflow Forecasts ◽  
Forecasting System

The combination of Hydrological Models and high-resolution Satellite Precipitation Products (SPPs) or regional Climatological Models (RCMs), has provided the means to establish baselines for the quantification, propagation, and reduction in hydrological uncertainty when generating streamflow forecasts. This study aimed to improve operational real-time streamflow forecasts for the Upper Zambezi River Basin (UZRB), in Africa, utilizing the novel Variational Ensemble Forecasting (VEF) approach. In this regard, we describe and discuss the main steps required to implement, calibrate, and validate an operational hydrologic forecasting system (HFS) using VEF and Hydrologic Processing Strategies (HPS). The operational HFS was constructed to monitor daily streamflow and forecast them up to eight days in the future. The forecasting process called short- to medium-range (SR2MR) streamflow forecasting was implemented using real-time rainfall data from three Satellite Precipitation Products or SPPs (The real-time TRMM Multisatellite Precipitation Analysis TMPA-RT, the NOAA CPC Morphing Technique CMORPH, and the Precipitation Estimation from Remotely Sensed data using Artificial Neural Networks, PERSIANN) and rainfall forecasts from the Global Forecasting System (GFS). The hydrologic preprocessing (HPR) strategy considered using all raw and bias corrected rainfall estimates to calibrate three distributed hydrological models (HYMOD_DS, HBV_DS, and VIC 4.2.b). The hydrologic processing (HP) strategy considered using all optimal parameter sets estimated during the calibration process to increase the number of ensembles available for operational forecasting. Finally, inference-based approaches were evaluated during the application of a hydrological postprocessing (HPP) strategy. The final evaluation and reduction in uncertainty from multiple sources, i.e., multiple precipitation products, hydrologic models, and optimal parameter sets, was significantly achieved through a fully operational implementation of VEF combined with several HPS. Finally, the main challenges and opportunities associated with operational SR2MR streamflow forecasting using VEF are evaluated and discussed.

scholarly journals Evaluation of the ECMWF System 4 climate forecasts for streamflow forecasting in the Upper Hanjiang River Basin

2018 ◽  
Vol 49 (6) ◽  
pp. 1864-1879 ◽  
Author(s):  
Fuqiang Tian ◽  
Yilu Li ◽  
Tongtiegang Zhao ◽  
Hongchang Hu ◽  
Florian Pappenberger ◽  
...  
Keyword(s):  
River Basin ◽  
Processing Method ◽  
Water Diversion ◽  
Ensemble Prediction ◽  
Distributed Hydrological Model ◽  
Streamflow Forecasting ◽  
Post Processing ◽  
Ensemble Prediction System ◽  
Streamflow Forecasts ◽  
Hanjiang River

Abstract This paper assesses the potential of the European Centre for Medium-Range Weather Forecasts (ECMWF) System 4 forecasts and investigates the post-processing precipitation to enhance the skill of streamflow forecasts. The investigation is based on hydrological modelling and is conducted through the case study of the Upper Hanjiang River Basin (UHRB). A semi-distributed hydrological model, TsingHua Representative Elementary Watershed (THREW), is implemented to simulate the rainfall–runoff processes, with the help of hydrological ensemble prediction system (HEPS) approach. A post-processing method, quantile mapping method, is applied to bias correct the raw precipitation forecasts. Then we evaluate the performance of raw and post-processed streamflow forecasts for the four hydrological stations along the mainstream of Hanjiang River from 2001 to 2008. The results show that the performance of the streamflow forecasts is greatly enhanced with post-processing precipitation forecasts, especially in pre-dry season (November and December), thus providing useful information for water supply management of the central route of South to North Water Diversion Project (SNWDP). The raw streamflow forecasts tend to overpredict and present similarly to forecast accuracy with the extended streamflow prediction (ESP) approach. Streamflow forecast skill is considerably improved when applying post-processing method to bias correct the ECMWF System 4 precipitation forecasts.

scholarly journals Calibrated ensemble forecasts of the height of new snow using quantile regression forests and ensemble model output statistics

2021 ◽  
Vol 28 (3) ◽  
pp. 467-480
Author(s):  
Guillaume Evin ◽  
Matthieu Lafaysse ◽  
Maxime Taillardat ◽  
Michaël Zamo
Keyword(s):  
Quantile Regression ◽  
Specific Humidity ◽  
Ensemble Model ◽  
Model Output ◽  
Post Processing ◽  
Ensemble Forecasts ◽  
Mountain Areas ◽  
Processing Methods ◽  
Ensemble Model Output Statistics ◽  
Model Output Statistics

Abstract. Height of new snow (HN) forecasts help to prevent critical failures of infrastructures in mountain areas, e.g. transport networks and ski resorts. The French national meteorological service, Météo-France, operates a probabilistic forecasting system based on ensemble meteorological forecasts and a detailed snowpack model to provide ensembles of HN forecasts. These forecasts are, however, biased and underdispersed. As for many weather variables, post-processing methods can be used to alleviate these drawbacks and obtain meaningful 1 to 4 d HN forecasts. In this paper, we compare the skill of two post-processing methods. The first approach is an ensemble model output statistics (EMOS) method, which can be described as a nonhomogeneous regression with a censored shifted Gamma distribution. The second approach is based on quantile regression forests, using different meteorological and snow predictors. Both approaches are evaluated using a 22 year reforecast. Thanks to a larger number of predictors, the quantile regression forest is shown to be a powerful alternative to EMOS for the post-processing of HN ensemble forecasts. The gain of performance is large in all situations but is particularly marked when raw forecasts completely miss the snow event. This type of situation happens when the rain–snow transition elevation is overestimated by the raw forecasts (rain instead of snow in the raw forecasts) or when there is no precipitation in the forecast. In that case, quantile regression forests improve the predictions using the other weather predictors (wind, temperature, and specific humidity).

Sign in / Sign up

Export Citation Format

Share Document