Search Results
and seasonal factors such as the state of El Niño, soil moisture, snow, and sea ice, along with others, is not yet well established for subseasonal forecasts. Sharma et al. (2017) and Pan et al. (2019) studied precipitation forecasts in the eastern United States and the West Coast from short to extended range and found the current state-of-the-art models provide little useful forecast skill beyond week 1–2. Numerical forecast of the atmospheric rivers, atmospheric blocking, and tropical
and seasonal factors such as the state of El Niño, soil moisture, snow, and sea ice, along with others, is not yet well established for subseasonal forecasts. Sharma et al. (2017) and Pan et al. (2019) studied precipitation forecasts in the eastern United States and the West Coast from short to extended range and found the current state-of-the-art models provide little useful forecast skill beyond week 1–2. Numerical forecast of the atmospheric rivers, atmospheric blocking, and tropical
, Le et al. (2019) applied LSTM for flood forecasting based on 24 years of daily data with 18 years of data for training, 5 years for validation, and the remaining 2 years for testing. Tian et al. (2018) trained the LSTM models with 10 years of daily data and validated streamflow simulation at two river basins using another 5 years. Kratzert et al. (2019a) considered 30 years of daily data and trained LSTM on 15 years and tested the performance on the remaining 15 years. Regardless of the
, Le et al. (2019) applied LSTM for flood forecasting based on 24 years of daily data with 18 years of data for training, 5 years for validation, and the remaining 2 years for testing. Tian et al. (2018) trained the LSTM models with 10 years of daily data and validated streamflow simulation at two river basins using another 5 years. Kratzert et al. (2019a) considered 30 years of daily data and trained LSTM on 15 years and tested the performance on the remaining 15 years. Regardless of the
. Atlantic Forest is the second-largest rain forest of the American continent and one of the world’s regions hosting the biggest biodiversity. Annual rainfall is between 1000 and 3000 mm. The Brazilian Pampa represents 2.07% of the national territory and lies within the South Temperate Zone ( Roesch et al. 2009 ). The annual precipitation in the region is around 1200–1600 mm. The Pantanal wetland is a complex of seasonally inundated floodplains along the upper Paraguay River, located mostly in Brazil
. Atlantic Forest is the second-largest rain forest of the American continent and one of the world’s regions hosting the biggest biodiversity. Annual rainfall is between 1000 and 3000 mm. The Brazilian Pampa represents 2.07% of the national territory and lies within the South Temperate Zone ( Roesch et al. 2009 ). The annual precipitation in the region is around 1200–1600 mm. The Pantanal wetland is a complex of seasonally inundated floodplains along the upper Paraguay River, located mostly in Brazil
-020-10234-7 He , J. , X. Bian , Y. Fu , and Y. Qin , 2012 : Research on water consumption and its law of main crops in west Liaohe River plain . Jieshui Guan’gai , 11 , 1 – 4 . Hirschi , M. , and Coauthors , 2011 : Observational evidence for soil-moisture impact on hot extremes in southeastern Europe . Nat. Geosci. , 4 , 17 – 21 , https://doi.org/10.1038/ngeo1032 . 10.1038/ngeo1032 Huang , P. M. , Y. Li , and M. E. Sumner , 2011 : Handbook of Soil Sciences: Properties and
-020-10234-7 He , J. , X. Bian , Y. Fu , and Y. Qin , 2012 : Research on water consumption and its law of main crops in west Liaohe River plain . Jieshui Guan’gai , 11 , 1 – 4 . Hirschi , M. , and Coauthors , 2011 : Observational evidence for soil-moisture impact on hot extremes in southeastern Europe . Nat. Geosci. , 4 , 17 – 21 , https://doi.org/10.1038/ngeo1032 . 10.1038/ngeo1032 Huang , P. M. , Y. Li , and M. E. Sumner , 2011 : Handbook of Soil Sciences: Properties and
extreme weather patterns such as tropical cyclones, atmospheric rivers, and synoptic-scale fronts ( Liu et al. 2016 ; Mahesh et al. 2018 ; Kunkel et al. 2018 ; Lagerquist et al. 2019b ). The authors have extensive experience using ML to improve forecasting and understanding of weather phenomena ( Gagne et al. 2017a , b ; Lagerquist et al. 2017 ; McGovern et al. 2017; Gagne et al. 2019 ; Lagerquist et al. 2018 ). Many of these products have been used by human meteorologists in experiments and day
extreme weather patterns such as tropical cyclones, atmospheric rivers, and synoptic-scale fronts ( Liu et al. 2016 ; Mahesh et al. 2018 ; Kunkel et al. 2018 ; Lagerquist et al. 2019b ). The authors have extensive experience using ML to improve forecasting and understanding of weather phenomena ( Gagne et al. 2017a , b ; Lagerquist et al. 2017 ; McGovern et al. 2017; Gagne et al. 2019 ; Lagerquist et al. 2018 ). Many of these products have been used by human meteorologists in experiments and day
flash flooding, geomorphological parameters were derived from the National Elevation Dataset (NED; http://ned.usgs.gov/ ) digital elevation model (DEM) across the CONUS. To ensure compatibility between DEM-based flow accumulations and the actual river network, flow accumulation and direction was extracted by delineating basins with USGS stations, and the National Hydrography Dataset (NHD; http://nhd.usgs.gov/ ) was used to resample the 30-m DEM to a 1-km grid. The geomorphologic parameters for
flash flooding, geomorphological parameters were derived from the National Elevation Dataset (NED; http://ned.usgs.gov/ ) digital elevation model (DEM) across the CONUS. To ensure compatibility between DEM-based flow accumulations and the actual river network, flow accumulation and direction was extracted by delineating basins with USGS stations, and the National Hydrography Dataset (NHD; http://nhd.usgs.gov/ ) was used to resample the 30-m DEM to a 1-km grid. The geomorphologic parameters for
. Pattern complexity is very difficult to evaluate for several reasons: 1) patterns can only be evaluated after NN training is completed; 2) techniques for discovering patterns, such as feature visualization ( Olah et al. 2017 , 2018 ), to date only provide limited answers; and 3) feature visualization is even more challenging for meteorological imagery, because it tends to have amorphous boundaries (e.g., clouds, atmospheric rivers, ocean eddies) ( Karpatne et al. 2019 ) rather than the crisp
. Pattern complexity is very difficult to evaluate for several reasons: 1) patterns can only be evaluated after NN training is completed; 2) techniques for discovering patterns, such as feature visualization ( Olah et al. 2017 , 2018 ), to date only provide limited answers; and 3) feature visualization is even more challenging for meteorological imagery, because it tends to have amorphous boundaries (e.g., clouds, atmospheric rivers, ocean eddies) ( Karpatne et al. 2019 ) rather than the crisp
