Bayesian spatio-temporal models for stream networks

Santos-Fernandez, Edgar; Hoef, Jay M. Ver; Peterson, Erin E.; McGree, James; Isaak, Daniel; Mengersen, Kerrie

doi:10.48550/arxiv.2103.03538

Cited by 2 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future implementations will incorporate other modelling variations. Two of them are: (I) expressing φ s as a linear combination of covariates such as elevation and watershed, and (II) using a 2-Nearest Neigbours (2-NN) method, where the off-diagonal elements of Φ are different from zero in the two closest, allowing temporal dependence to be established between neighbouring spatial locations connected by flow (Santos-Fernandez et al, 2021). However, there are numerous other spacetime covariance structures that could be implemented for stream network data, which allow more modelling flexibility.…”

Section: Discussionmentioning

confidence: 99%

“…Other VAR structures consider φ as a linear combination of spatial covariates and cross-correlation between time series (Santos-Fernandez et al, 2021). This variation is not currently implemented in SSNbayes but is under development.…”

Section: Case 2 (Var)mentioning

confidence: 99%

“…The core function of SSNbayes is ssnbayes. It provides the functionality to fit linear spatio-temporal regression models (Santos-Fernandez et al, 2021). q q q q q q q q q q q q q q q q q q 1 2 3 We specify the following linear regression model using the covariates in the observed dataset:…”

Section: Fitting Spatio-temporal Linear Modelsmentioning

confidence: 99%

“…The dist_wei_mat_preds() function produces the same information for observed and prediction locations, with n o n p × n o n p dimensions. Details and detailed descriptions of the computation of these matrices can be found in Peterson and Ver Hoef (2010), and Santos-Fernandez et al (2021.…”

Section: Longitudementioning

confidence: 99%

See 3 more Smart Citations

SSNbayes: An R package for Bayesian spatio-temporal modelling on stream networks

Santos–Fernández¹,

Hoef²,

Burrell³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Spatio-temporal models are widely used in many research areas from ecology to epidemiology. However, most covariance functions describe spatial relationships based on Euclidean distance only. In this paper, we introduce the R package SSNbayes for fitting Bayesian spatio-temporal models and making predictions on branching stream networks. SSNbayes provides a linear regression framework with multiple options for incorporating spatial and temporal autocorrelation. Spatial dependence is captured using stream distance and flow connectivity while temporal autocorrelation is modelled using vector autoregression approaches. SSNbayes provides the functionality to make predictions across the whole network, compute exceedance probabilities and other probabilistic estimates such as the proportion of suitable habitat. We illustrate the functionality of the package using a stream temperature dataset collected in Idaho, USA.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Case 2 (Var)mentioning

confidence: 99%

Section: Fitting Spatio-temporal Linear Modelsmentioning

confidence: 99%

Section: Longitudementioning

confidence: 99%

See 2 more Smart Citations

SSNbayes: An R package for Bayesian spatio-temporal modelling on stream networks

Santos–Fernández¹,

Hoef²,

Burrell³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the predictive TRW models developed for the Warta River, we included daily temperature delays as an input variable. According to Santos-Fernandez et al [87], when the purpose of the application of the stochastic method is time interpolation and forecasting of future TRW values at the locations of measuring points (water gauges), and there is no need to describe unique spatial relationships on streams, thermal conditions reflect the standard models of time series.…”

Section: Discussionmentioning

confidence: 99%

Daily River Water Temperature Prediction: A Comparison between Neural Network and Stochastic Techniques

Graf

Aghelpour

2021

Atmosphere

View full text Add to dashboard Cite

The temperature of river water (TRW) is an important factor in river ecosystem predictions. This study aims to compare two different types of numerical model for predicting daily TRW in the Warta River basin in Poland. The implemented models were of the stochastic type—Autoregressive (AR), Moving Average (MA), Autoregressive Moving Average (ARMA) and Autoregressive Integrated Moving Average (ARIMA)—and the artificial intelligence (AI) type—Adaptive Neuro Fuzzy Inference System (ANFIS), Radial Basis Function (RBF) and Group Method of Data Handling (GMDH). The ANFIS and RBF models had the most fitted outputs and the AR, ARMA and ARIMA patterns were the most accurate ones. The results showed that both of the model types can significantly present suitable predictions. The stochastic models have somewhat less error with respect to both the highest and lowest TRW deciles than the AIs and were found to be better for prediction studies, with the GMDH complex model in some cases reaching Root Mean Square Error (RMSE) = 0.619 °C and Nash-Sutcliff coefficient (NS) = 0.992, while the AR(2) simple linear model with just two inputs was partially able to achieve better results (RMSE = 0.606 °C and NS = 0.994). Due to these promising outcomes, it is suggested that this work be extended to other catchment areas to extend and generalize the results.

show abstract

Bayesian spatio-temporal models for stream networks

Cited by 2 publications

References 47 publications

SSNbayes: An R package for Bayesian spatio-temporal modelling on stream networks

SSNbayes: An R package for Bayesian spatio-temporal modelling on stream networks

Daily River Water Temperature Prediction: A Comparison between Neural Network and Stochastic Techniques

Contact Info

Product

Resources

About