2011
DOI: 10.1002/hyp.8216
|View full text |Cite
|
Sign up to set email alerts
|

Daily river water temperature forecast model with a k‐nearest neighbour approach

Abstract: Abstract:Water temperature is a key abiotic variable that modulates both water chemistry and aquatic life in rivers and streams. For this reason, numerous water temperature models have been developed in recent years. In this paper, a k-nearest neighbour model (KNN) is proposed and validated to simulate and eventually produce a one-day forecast of mean water temperature on the Moisie River, a watercourse with an important salmon population in eastern Canada. Numerous KNN model configurations were compared by se… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
26
0
1

Year Published

2013
2013
2022
2022

Publication Types

Select...
8

Relationship

2
6

Authors

Journals

citations
Cited by 59 publications
(28 citation statements)
references
References 31 publications
1
26
0
1
Order By: Relevance
“…The k-nearest neighbour approach (kNN) has been applied to streamwater temperature prediction by St-Hilaire et al (2012). In the present study the kNN variant that requires neither calibration nor the use of validation set is applied.…”
Section: Nearest Neighbour Approachmentioning
confidence: 99%
See 2 more Smart Citations
“…The k-nearest neighbour approach (kNN) has been applied to streamwater temperature prediction by St-Hilaire et al (2012). In the present study the kNN variant that requires neither calibration nor the use of validation set is applied.…”
Section: Nearest Neighbour Approachmentioning
confidence: 99%
“…Streamwater temperature prediction approaches proposed in the past mainly included physically-based, temperature equilibrium concept-based or simple statistical models (Webb et al, 2008;Wehrly et al, 2009;Bustillo et al, 2014). In recent years various kinds of deterministic models (Caissie et al, 2007), data-driven approaches (St-Hilaire et al, 2012;Grbic et al, 2013;Cole et al, 2014) or artificial neural networks (ANNs) (Sahoo et al, 2006;Sivri et al, 2007;Chenard and Caissie, 2008;Sahoo et al, 2009;Daigle et al, 2009;Faruk, 2010;McKenna et al, 2010;Jeong et al, 2013;Napiorkowski et al, 2014;Piotrowski et al, 2014;Hadzima-Nyarko et al, 2014;Rabi et al, in press) have been applied to this task. In some studies (Sahoo et al, 2009;Bustillo et al, 2014) regression and ANN models are claimed to perform not worse than the more sophisticated empirical or heat budget-based models.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…The variation of CE Table 3 and Fig. 9 show that ANN and k-nn models should be carefully used for forecasts beyond the next day because of error accumulation for the former and error propagation resulting from nearest neighbors estimates (Aqil et al 2007;St-Hilaire et al 2012;Tongal and Berndtsson 2014). The performance of the k-nn and ANN models are similar for all lead times, however, the ANN models result in smaller RMSEs (Fig.…”
Section: Multi-step Forecasting Results Of Setar Ann and K-nnmentioning
confidence: 90%
“…Despite the fact that the kNN model was originally developed for pattern classification it can easily be applied to regression problems for time series [34], such as the forecast of solar radiation. Although there are very few articles in literature that apply kNN to the forecast of solar irradiation (see for instance [25,27]), kNN has been extensively applied as a forecasting technique to problems such as: electricity load and electricity price [18,19], daily river water temperature [31], water inflow [1] and weather forecast [2]. In the field of meteorology and weather forecasting the kNN method is also known as the analog method [30,33,35].…”
Section: Introductionmentioning
confidence: 99%