Performance of a very high-resolution global forecast system model (GFS T1534) at 12.5 km over the Indian region during the 2016–2017 monsoon seasons

Mukhopadhyay, P.; Prasad, V. S.; Krishna, R. Phani Murali; Deshpande, Medha; Ganai, Malay K.; Tirkey, Snehlata; Sarkar, Sahadat; Goswami, Tanmoy; Johny, C. J.; Roy, Kumar; Mahakur, M.; Durai, V. R.; Rajeevan, M.

doi:10.1007/s12040-019-1186-6

Cited by 43 publications

(26 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the pattern correlations again fall quickly after 1 day lead time. The forecast obtained from this deep learning model is comparable with the same is from state of the art dynamical models such as provided in [8]. The forecast skill was also analysed using the ROC curve for homogeneous regions.…”

Section: Calculation Of Receiver Operating Characteristics (Roc) Curvementioning

confidence: 65%

Deep learning–based downscaling of summer monsoon rainfall data over Indian region

Kumar

Chattopadhyay

Singh

et al. 2021

Theor Appl Climatol

View full text Add to dashboard Cite

Accurate short-range weather forecasting has significant implications for various sectors. Machine learning based approaches, e.g. deep learning, have gained popularity in this domain where the existing numerical weather prediction (NWP) models still have modest skill after a few days. Here we use a ConvLSTM network to develop a deep learning model for precipitation forecasting. The crux of the idea is to develop a forecasting model which involves convolution based feature selection and uses long term memory in the meteorological fields in conjunction with gradient based learning algorithm. Prior to using the input data, we explore various techniques to overcome dataset difficulties. We follow a strategic approach to deal with missing values and discuss the model's fidelity to capture realistic precipitation. The model resolution used is ( 25 km). A comparison between 5 years of predicted data and corresponding observational records for 2 days lead time forecast show correlation coefficients of 0.67 and 0.42 for lead day 1 and 2 respectively. The patterns indicate higher correlation over the Western Ghats and Monsoon trough region ( 0.8 and 0.6 for lead day 1 and 2 respectively). Further, the model performance is evaluated based on skill scores, Mean Square Error, correlation coefficient and ROC curves. This study demonstrates that the adopted deep learning approach based only on a single precipitation variable, has a reasonable skill in the short range. Incorporating multivariable based deep learning has the potential to match or even better the short range precipitation forecasts based on the state-of-the-art NWP models.

show abstract

Section: Calculation Of Receiver Operating Characteristics (Roc) Curvementioning

confidence: 65%

Deep learning–based downscaling of summer monsoon rainfall data over Indian region

Kumar

Chattopadhyay

Singh

et al. 2021

Theor Appl Climatol

View full text Add to dashboard Cite

show abstract

“…The 3-day model forecast skill was meaningful but lower than the 1-day forecast in terms of correlation and RMSE performance relative to the Landsat reference. This is expected since the GFS predictions have generally lower performance with longer lead time [ 63 ]; larger uncertainties likely stem from a lack of satellite surface wetness observations closer to the forecast dates. The SMAP FW and SSM records were the two most important features in the 1-day forecast, which suggests that the background surface wetness level is generally crucial in determining how the coming precipitation affects short-term (e.g., 1 day) inundation changes and potential flood risk.…”

Section: Discussionmentioning

confidence: 99%

Satellite Flood Inundation Assessment and Forecast Using SMAP and Landsat

Kimball

Sheffield

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The capability and synergistic use of multi-source satellite observations for flood monitoring and forecasts is crucial for improving disaster preparedness and mitigation. Here, surface fractional water cover (FW) retrievals derived from Soil Moisture Active Passive (SMAP) L-band (1.4 GHz) brightness temperatures were used for flood assessment over southeast Africa during the Cyclone Idai event. We then focused on five sub-catchments of the Pungwe basin and developed a machine learning-based approach with the support of Google Earth Engine (GEE) for daily (24-hour) forecasting of FW and 30-m inundation downscaling and mapping. The Classification and Regression Trees (CART) model was selected and trained using retrievals derived from SMAP and Landsat coupled with rainfall forecasts from the NOAA Global Forecast System (GFS). Independent validation showed that FW predictions over randomly selected dates are highly correlated (R=0.87) with the Landsat observations. The forecast results captured the flood temporal dynamics from the Idai event; and the associated 30-m downscaling results showed inundation spatial patterns consistent with independent satellite Synthetic Aperture Radar (SAR) observations. The data-driven approach provides new capacity for flood monitoring and forecasts leveraging synergistic satellite observations and big data analysis, which is particularly valuable for data sparse regions.

show abstract

“…ERA5 reanalysis is used to compare the meteorological variables other than precipitation. Downscaled outputs are also compared against high-resolution (12 km) deterministic forecast of Global Forecast System version 14 Mukhopadhyay et al (2019) (hereafter GFS-12km) which is used for short range prediction at IMD. The same initial conditions are used in this study for GFS-12km, raw-ERP and BC-D-ERP (Table 1).…”

Section: Observational and Verification Datamentioning

confidence: 99%

Dynamical downscaling of a multimodel ensemble prediction system: Application to tropical cyclones

Kaur

Krishna

Joseph

et al. 2020

Atmospheric Science Letters

View full text Add to dashboard Cite

This study attempts dynamical downscaling to improve north Indian ocean (NIO) tropical cyclone prediction from a global multimodel ensemble prediction system using weather research and forecasting (WRF) model. A total of 16 ensembles are used in the WRF simulations, these ensembles are biascorrected prior to downscaling for model climatological errors. The ensemble mean constructed from the output of all downscaled ensembles is analyzed for added value to global predictions. This mean is also compared against observation as well as high-resolution (12 km) deterministic forecast from global forecast system (GFS). Two devastating NIO tropical cyclone cases of year 2017 which were not reliably predicted by global systems have been selected for this study. The results show that downscaled predictions well simulate the intensity and spatial distribution of the rainfall and relative vorticity associated with these cyclonic storms. The wind and temperature vertical profiles during cyclone mature stage are also captured more accurately than raw prediction and high-resolution global deterministic forecast. The study affirms the adequacy of dynamical downscaling in predicting the cyclonic storms over global real-time weather forecasting system.

show abstract

Performance of a very high-resolution global forecast system model (GFS T1534) at 12.5 km over the Indian region during the 2016–2017 monsoon seasons

Cited by 43 publications

References 24 publications

Deep learning–based downscaling of summer monsoon rainfall data over Indian region

Deep learning–based downscaling of summer monsoon rainfall data over Indian region

Satellite Flood Inundation Assessment and Forecast Using SMAP and Landsat

Dynamical downscaling of a multimodel ensemble prediction system: Application to tropical cyclones

Contact Info

Product

Resources

About