A recurrent neural network classifier for improved retrievals of areal extent of snow cover

Simpson, Joseph; McIntire, T.J.

doi:10.1109/36.957276

Cited by 38 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there have been relatively few studies involving the application of these methods in modeling of snow parameters [34,36,38]. Tedesco et al [39] employed artificial neural network (ANN) for retrieval of snow depth and SWE from special sensor microwave imager (SSMI) data and compared results of ANN with those obtained using the spectral polarization deference (SPD) algorithm, the Helsinki University of Technology (HUT) model-based iterative inversion and the Chang algorithm.…”

Section: Introductionmentioning

confidence: 99%

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

Tabari

Marofi

Abyaneh

et al. 2009

Neural Comput & Applic

View full text Add to dashboard Cite

Snow water equivalent (SWE) is a key parameter in hydrological cycle, and information on regional SWE is required for various hydrological and meteorological applications, as well as for hydropower production and flood forecasting. This study compares the snow depth and SWE estimated by multivariate linear regression (MLR), discriminant function analysis, ordinary kriging, ordinary kriging-multivariate linear regression, ordinary krigingdiscriminant function analysis, artificial neural network (ANN) and neural network-genetic algorithm (NNGA) models. The analysis was performed in the 5.2 km 2 area of Samsami basin, located in the southwest of Iran. Statistical criteria were used to measure the models' performances. The results indicated that NNGA, ANN and MLR methods were able to predict SWE at the desirable level of accuracy. However, the NNGA model with the highest coefficient of determination (R 2 = 0.70, P value \ 0.05) and minimum root mean square error (RMSE = 0.202 cm) provided the best results among the other models. The lower SWE values were registered in the east of study area and higher SWE values appeared in the west of study area where altitude was higher.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

Tabari

Marofi

Abyaneh

et al. 2009

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Partly because of differences among the methods by which f snow was approximated, large variations in the estimates have been reported. For example, most research has reported that snow contribution ratio was 75% [27][28][29][30][31], whereas other studies have produced values in the ranges of 40%-60%, 50%-80%, or 60%-90% [17,[32][33][34]. Compared with such ratio metrics, the following methods are considered more reasonable.…”

Section: Introductionmentioning

confidence: 99%

Predictive Contributions of Snowmelt and Rainfall to Streamflow Variations in the Western United States

Zheng

Wang

Li-hua

et al. 2018

Advances in Meteorology

View full text Add to dashboard Cite

is study used long-term in situ rainfall, snow, and streamflow data to explore the predictive contributions of snowmelt and rainfall to streamflow in six watersheds over the Western United States. Analysis showed that peak snow accumulation, snow-free day, and snowmelt slope all had strong correlation with peak streamflow, particularly in inland basins. Further analysis revealed that the variation of snow accumulation anomaly had strong lead correlation with the variation of streamflow anomaly. Over the entire Western United States, inner mountain areas had lead times of 4-10 pentads. However, in coastal areas, nearly all sites had lead times of less than one pentad. e relative contributions of rainfall and snowmelt to streamflow in different watersheds were calculated based on the snow lead time. e geographic distribution of annual relative contributions revealed that interior areas were dominated by snowmelt contribution, whereas the rainfall contribution dominated coastal areas. In the wet season, the snowmelt contribution increased in the western Pacific Northwest, whereas the rainfall contribution increased in the southeastern Pacific Northwest, southern Upper Colorado, and northern Rio Grande regions. e derived results demonstrated the predictive contributions of snowmelt and rainfall to streamflow. ese findings could be considered a reference both for seasonal predictions of streamflow and for prevention of hydrological disasters. Furthermore, they will be helpful in the evaluation and improvement of hydrological and climate models.

show abstract

“…They have been successfully applied to hydrological modeling and have coincidentally shown a great potential in the prediction of a wide range of hydrological parameters (Gautam et al 2003;Ahmad and Simonovic 2005;Chen and Adams 2006;Srinivasulu and Jain 2006;Dawson et al 2006;Chauhan and Shrivastava 2009;Tabari et al 2010;Shirsath and Singh 2010). However, there have been relatively few studies involving the application of these methods in modeling of snow parameters (Simpson and McIntire 2001;Tappeiner et al 2001;Roebber et al 2002). For example, Tedesco et al (2004) employed ANN for retrieval of SD and SWE from special sensor microwave imager (SSMI) data and compared results of ANN with those obtained using the spectral polarization deference (SPD) algorithm, the Helsinki University of Technology (HUT) model-based iterative inversion and the Chang algorithm.…”

Section: Introductionmentioning

confidence: 98%

Predicting Spatial Distribution of Snow Water Equivalent Using Multivariate Non-linear Regression and Computational Intelligence Methods

Marofi

Tabari

Abyaneh

2011

Water Resour Manage

View full text Add to dashboard Cite

The evaluation of water resources given by snowfall is very important in the mountainous basins. In this study, the snow depth (SD) and snow water equivalent (SWE) were investigated to quantify the water resources stored in the snow. Multivariate non-linear regression (MNLR) method, four types of artificial neural network (ANN) and neural network-genetic algorithm (NNGA) model were initially evaluated to predict SWE in the Samsami basin of Iran. Afterwards, ordinary kriging (OK) technique was applied to interpolate the SWE values estimated by the best-performed model. For this regard, seven different MNLR, ANN and NNGA models comprising various combinations of climatic and topographic parameters including elevation (El.), slope (S), north-south (N-S) and east-west (E-W) aspects, maximum upwind slope (Sx), longitude (X) and latitude (Y) were developed to evaluate degree of effect of each of these parameters on SWE. The different experiment results showed that the NNGA5 model characterized by Delta-Bar-Delta learning algorithm and Sigmoid activation function with inputs of El., Sx, N-S aspects, S and X performed best in estimating SWE. In general, the results indicated that the NNGA technique was the most suitable method for estimation of SWE in the study area. The ANN and MNLR models were identified as the next categories, respectively. The sensitivity analysis revealed that El. and Sx were more important parameters influencing SWE than the other input parameters.

show abstract

A recurrent neural network classifier for improved retrievals of areal extent of snow cover

Cited by 38 publications

References 34 publications

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

Predictive Contributions of Snowmelt and Rainfall to Streamflow Variations in the Western United States

Predicting Spatial Distribution of Snow Water Equivalent Using Multivariate Non-linear Regression and Computational Intelligence Methods

Contact Info

Product

Resources

About