Comparison of passive microwave brightness temperature prediction sensitivities over snow-covered land in North America using machine learning algorithms and the Advanced Microwave Scanning Radiometer

Xue, Yuan; Forman, B. A.

doi:10.1016/j.rse.2015.09.009

Cited by 30 publications

(28 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Updating a model state such as SWE using measured radiances in the form of Tb (or Δ T b ) requires the existence of significant cross covariances in the errors of both Tb (or Δ T b ) and modeled SWE. The underlying error correlation structure between the observation operator estimate of Tb (or Δ T b ) and model‐derived SWE was explored in a sensitivity analysis (Xue & Forman, ), which demonstrated the potential to integrate predictions from a well‐trained SVM with Catchment‐based SWE estimates.…”

Section: Models Data and Methodsmentioning

confidence: 99%

“…As an alternative to traditional snow emission models, several studies (Forman et al, ; Forman & Reichle, ; Forman & Xue, ; Xue & Forman, ) investigated the use of an artificial neural network (ANN) or a support vector machine (SVM) as the observation operator within a radiance assimilation framework. It was shown that such machine‐learning algorithms performed well throughout the entire snow season and were able to capture much of the temporal and spatial variability in the modeled Tb, and hence, such an algorithm was recommended for eventual use as an observation operator within the proposed DA framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Snow Mass in North America Through Assimilation of Advanced Microwave Scanning Radiometer Brightness Temperature Observations Using the Catchment Land Surface Model and Support Vector Machines

Xue

Forman

Reichle

2018

Water Resources Research

Self Cite

View full text Add to dashboard Cite

To estimate snow mass across North America, brightness temperature observations collected by the Advanced Microwave Scanning Radiometer (AMSR‐E) from 2002 to 2011 were assimilated into the Catchment model using a support vector machine as the observation operator and a one‐dimensional ensemble Kalman filter. The performance of the assimilation system is evaluated through comparisons against ground‐based measurements and reference snow products. In general, there are no statistically significant skill differences between the domain‐averaged, model‐only (open loop, or OL) snow estimates and assimilation estimates. The assessment of improvements (or degradations) in snow estimates is difficult because of limitations in the measurements (or products) used for evaluation. It is found that assimilation estimates agree slightly better in terms of root‐mean‐square error and Nash‐Sutcliffe model efficiency with ground‐based snow depth measurements than OL estimates in 82% (56 out of 62) of pixels that are colocated with at least two ground‐based stations. Assimilation estimates tend to agree slightly better in terms of mean difference with reference snow products over tundra snow, alpine snow, maritime snow, and sparsely vegetated, snow‐covered pixels. Changes in snow mass via assimilation translate into improvements (e.g., by 22% on average in terms of root‐mean‐square error, relative to OL) in cumulative runoff estimates when compared against discharge measurements in 11 out of 13 snow‐dominated basins in Alaska. These results suggest that a support vector machine can potentially serve as an effective observation operator for snow mass estimation within a radiance assimilation system, but a better observational baseline is required to document a statistically significant improvement.

show abstract

Section: Models Data and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimating Snow Mass in North America Through Assimilation of Advanced Microwave Scanning Radiometer Brightness Temperature Observations Using the Catchment Land Surface Model and Support Vector Machines

Xue

Forman

Reichle

2018

Water Resources Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bayesian neural network (BNN) and support vector machine (SVM) runs were executed but did not result in notable improvements over the ANN in spite of additional computational cost. While studies (e.g., Xue and Forman, 2015;Forman and Reichle, 2015) have shown machine learning methods such as SVM to be superior over ANNs for snow-related parameters, Lima et al (2015) found that in an evaluation of four different nonlin-ear methods across nine different environmental data sets, no single nonlinear method consistently outperformed the others. Though an exhaustive exploration of machine learning algorithms was not the objective of this manuscript, the machine learning runs completed indicated that, of the investigated algorithms, the ANN was at least comparable, if not superior, for this application and data sets.…”

Section: Gridded Productsmentioning

confidence: 99%

Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models

et al. 2018

View full text Add to dashboard Cite

Abstract. Estimates of surface snow water equivalent (SWE) in mixed alpine environments with seasonal melts are particularly difficult in areas of high vegetation density, topographic relief, and snow accumulations. These three confounding factors dominate much of the province of British Columbia (BC), Canada. An artificial neural network (ANN) was created using as predictors six gridded SWE products previously evaluated for BC. Relevant spatiotemporal covariates were also included as predictors, and observations from manual snow surveys at stations located throughout BC were used as target data. Mean absolute errors (MAEs) and interannual correlations for April surveys were found using cross-validation. The ANN using the three best-performing SWE products (ANN3) had the lowest mean station MAE across the province. ANN3 outperformed each product as well as product means and multiple linear regression (MLR) models in all of BC's five physiographic regions except for the BC Plains. Subsequent comparisons with predictions generated by the Variable Infiltration Capacity (VIC) hydrologic model found ANN3 to better estimate SWE over the VIC domain and within most regions. The superior performance of ANN3 over the individual products, product means, MLR, and VIC was found to be statistically significant across the province.

show abstract

“…The key to these studies lies in the analysis and prediction of the temperature time series. The common methods for this research point include extreme learning machine (Xue & Forman, 2015), vector machine regression (Erdemir & Ayata, 2016), data assimilation (Xu et al, 2017), neural network (Korteby et al, 2016;Shirvani et al, 2015), and autoregressive integrated moving average (ARIMA) model (Das M., Ghosh, 2017;Wang et al, 2016). For time sequence analysis in the general sense, the existing strategies range from Bayesian network (Rheinwalt et al, 2016), echo state network (Tu and Yi, 2017), nonlinear time series (Grigorievskiy et al, 2013), vector autoregression, multi-core extreme learning machines.…”

Section: Introductionmentioning

confidence: 99%

Temperature time series prediction based on autoregressive integrated moving average model

Zheng¹,

Bai²,

Zhang³

2018

isi

View full text Add to dashboard Cite

This paper establishes a prediction model for land and ocean temperature time series based on the improved autoregressive integrated moving average (ARIMA) model. First, the temperature time series was normalized and differenced before passing the stationarity test by augmented Dickey-Fuller (ADF) method, while the model parameters were determined by the autocorrelation coefficient and the partial autocorrelation coefficient. After that, the model was trained by the historical temperature data series, and applied to predict the temperatures in future. To validate the model, several experiments were conducted using the average land and ocean temperature data of Lawrence Berkeley National Laboratory. The results of the ARIMAbased model were contrasted against those of the support vector regression (SVR) and the random forest (RF). The comparison shows that the ARIMA-based model was 10%~30% smaller than the SVR and the RF in the values of RMSE and MAE, and 1%~10% higher in the value of R 2 . This means our model outperformed the two benchmark algorithms. KEYWORDS: autoregressive integrated moving average (ARIMA) model, temperature prediction, time series analysis, difference, stationarity test. MOTS-CLÉS: modè le à moyenne mobile inté gré et autoré gressif (ARIMA), pré vision de la tempé rature, analyse des sé ries temporelles, diffé rence, test de stationnarité .

show abstract

Comparison of passive microwave brightness temperature prediction sensitivities over snow-covered land in North America using machine learning algorithms and the Advanced Microwave Scanning Radiometer

Cited by 30 publications

References 67 publications

Estimating Snow Mass in North America Through Assimilation of Advanced Microwave Scanning Radiometer Brightness Temperature Observations Using the Catchment Land Surface Model and Support Vector Machines

Estimating Snow Mass in North America Through Assimilation of Advanced Microwave Scanning Radiometer Brightness Temperature Observations Using the Catchment Land Surface Model and Support Vector Machines

Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models

Temperature time series prediction based on autoregressive integrated moving average model

Contact Info

Product

Resources

About