River water temperature forecasting using a deep learning method

Qiu, Rujian; Wang, Yuankun; Rhoads, Bruce L.; Wei, Dong; Qiu, Wenjie; Tao, Yong; Wu, Jichun

doi:10.1016/j.jhydrol.2021.126016

Cited by 72 publications

(43 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The superiority of LSTM in RWT prediction, as demonstrated in this work, was found to agree with Feigl et al, Qiu et al, and Stajkowski et al 73 , 74 , 76 . However, it can be noted that the study was conducted by Feigl et al 76 used AT, runoff, precipitation, and global radiation values as input in the RWT prediction for daily data, the study by Qiu et al 74 used daily AT, and discharge as input in RWT prediction, and the study by Stajkowski et al 73 used AT values as input in RWT prediction for hourly data.…”

Section: Discussionsupporting

confidence: 92%

“…3 ) for the kNN-LSTM model for monthly data, which is reasonable compared with earlier standalone LSTM models by Stajkowski et al 73 (NSE: 0.913) and Qiu et al 74 (NSE: 0.74–0.99 °C). However, Stajkowski et al 73 used AT values as input for hourly data in their analysis, Qiu et al 74 used AT and discharge as input for daily data in RWT predictions, and the current study is dedicated to monthly timescales. Based on RSR, KGE, R 2 , and NSE performance values (Fig.…”

Section: Resultssupporting

confidence: 86%

“…The KGE values for Narmada (0.715), Tunga-Bhadra (0.790), Musi (0.701), and Ganga (0.868) catchments pertaining to the kNN-LSTM model for monthly data, which are reasonable compared to the earlier model of LSTM by Stajkowski et al 73 (0.923). The NSE values for Narmada (0.728), Musi (0.735), and Ganga (0.920) catchments pertaining to the kNN-LSTM model for monthly data, which are sensible compared to the earlier model of LSTM by Qiu et al 74 (0.74–0.99). The superiority of LSTM in RWT prediction, as demonstrated in this work, was found to agree with Feigl et al, Qiu et al, and Stajkowski et al 73 , 74 , 76 .…”

Section: Discussionmentioning

confidence: 72%

“…The RMSE scores for all the catchments ranged between 1.266 and 2.361 °C pertaining to the kNN-LSTM model for monthly data, which are reasonable in comparison to earlier models of the Spatio-temporal approach by Jackson et al 75 (1.570 °C); Bayesian regression approach by Sohrabi et al 68 (1.250 °C); random forest (RF), ANN, recurrent neural networks (RNNs) by Feigl et al 76 (0.422–0.815 °C); extreme gradient boosted tree algorithm and support vector regression by Weierbach et al 36 (0.92–1.02 °C); Wavelets-ANN by Graf et al 77 (0.981–1.434 °C); LSTM by Stajkowski et al 73 (0.755 °C); LSTM by Qiu et al 74 (0.500–2.700 °C); and ANN by Temizyurek et al 78 (2.100–2.640 °C). The MAE values for all the catchments range from 0.802 to 1.872 °C pertaining to the kNN-LSTM model for monthly data, which are reasonable in comparison to earlier models of RF, ANN, RNN by Feigl et al 76 (0.329–0.675 °C); Wavelets-ANN by Graf et al 77 (0.781–1.286 °C); and LSTM by Qiu et al 74 (0.39–2.15 °C). The KGE values for Narmada (0.715), Tunga-Bhadra (0.790), Musi (0.701), and Ganga (0.868) catchments pertaining to the kNN-LSTM model for monthly data, which are reasonable compared to the earlier model of LSTM by Stajkowski et al 73 (0.923).…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Impact of climate change on river water temperature and dissolved oxygen: Indian riverine thermal regimes

Rajesh

Rehana

2022

Sci Rep

View full text Add to dashboard Cite

The impact of climate change on the oxygen saturation content of the world’s surface waters is a significant topic for future water quality in a warming environment. While increasing river water temperatures (RWTs) with climate change signals have been the subject of several recent research, how climate change affects Dissolved Oxygen (DO) saturation levels have not been intensively studied. This study examined the direct effect of rising RWTs on saturated DO concentrations. For this, a hybrid deep learning model using Long Short-Term Memory integrated with k-nearest neighbor bootstrap resampling algorithm is developed for RWT prediction addressing sparse spatiotemporal RWT data for seven major polluted river catchments of India at a monthly scale. The summer RWT increase for Tunga-Bhadra, Sabarmati, Musi, Ganga, and Narmada basins are predicted as 3.1, 3.8, 5.8, 7.3, 7.8 °C, respectively, for 2071–2100 with ensemble of NASA Earth Exchange Global Daily Downscaled Projections of air temperature with Representative Concentration Pathway 8.5 scenario. The RWT increases up to7 °C for summer, reaching close to 35 °C, and decreases DO saturation capacity by 2–12% for 2071–2100. Overall, for every 1 °C RWT increase, there will be about 2.3% decrease in DO saturation level concentrations over Indian catchments under climate signals.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Resultssupporting

confidence: 86%

Section: Discussionmentioning

confidence: 72%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Impact of climate change on river water temperature and dissolved oxygen: Indian riverine thermal regimes

Rajesh

Rehana

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…All machine learning algorithms, such as supervised, unsupervised, and clustering approaches, are analyzed. Qiu et al [27] predicted the river temperature by using a long short-term neural network. The temporal effects of the temperature in the river area are analyzed on the basis of the forecasted values by LSTM.…”

Section: Literature Surveymentioning

confidence: 99%

Big Data Analytics Using Swarm-Based Long Short-Term Memory for Temperature Forecasting

Patil¹,

Rekha²,

Solanki³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In the past few decades, climatic changes led by environmental pollution, the emittance of greenhouse gases, and the emergence of brown energy utilization have led to global warming. Global warming increases the Earth's temperature, thereby causing severe effects on human and environmental conditions and threatening the livelihoods of millions of people. Global warming issues are the increase in global temperatures that lead to heat strokes and high-temperature-related diseases during the summer, causing the untimely death of thousands of people. To forecast weather conditions, researchers have utilized machine learning algorithms, such as autoregressive integrated moving average, ensemble learning, and long short-term memory network. These techniques have been widely used for the prediction of temperature. In this paper, we present a swarm-based approach called Cauchy particle swarm optimization (CPSO) to find the hyperparameters of the long shortterm memory (LSTM) network. The hyperparameters were determined by minimizing the LSTM validation mean square error rate. The optimized hyperparameters of the LSTM were used to forecast the temperature of Chennai City. The proposed CPSO-LSTM model was tested on the openly available 25-year Chennai temperature dataset. The experimental evaluation on MAT-LABR2020a analyzed the root mean square error rate and mean absolute error to evaluate the forecasted output. The proposed CPSO-LSTM outperforms the traditional LSTM algorithm by reducing its computational time to 25 min under 200 epochs and 150 hidden neurons during training. The proposed hyperparameter-based LSTM can predict the temperature accurately by having a root mean square error (RMSE) value of 0.250 compared with the traditional LSTM of 0.35 RMSE.

show abstract

Ecological responses of spawning habitat suitability to changes in flow and thermal regimes influenced by hydropower operation

et al. 2022

Self Cite

View full text Add to dashboard Cite

Large reservoirs and dams can fundamentally alter downstream flow and thermal regimes by resetting the flow and water temperature release boundary conditions, resulting in significant impacts on fish habitat suitability. Therefore, it is critically important to understand how the volume and temperature of dam releases to influence downstream hydraulic and temperature dynamics and predict the ecological responses of fish habitat suitability to these changes. In this study, a physically based coupled model framework was developed to identify the temporal and spatial variations of hydraulic and water temperature regimes and the spawning habitat suitability of four major Chinese carps (FMCC) in the middle reach of the Yangtze River below Three Gorges Reservoir (TGR) responded to different upstream boundary conditions established by dam operation. The results showed that the dam discharge volume from TGR mainly affected the downstream hydraulic regime, while dam discharge temperature would have most impact on downstream water temperature. The spawning habitat suitability of FMCC obviously decreased due to TGR operation, and the declined water temperature suitability and the delayed and narrowed window of suitable water temperature were the main influencing factors. For the purpose of maximizing the spawning habitat suitability of FMCC in the downstream reaches below TGR, dam discharge volume ranged from 10,000 to 22,500 m 3 /s, and dam discharge temperature varied from 22 to 23.5 C would be recommended as the outflow conditions in the ecological operation of TGR.

show abstract

River water temperature forecasting using a deep learning method

Cited by 72 publications

References 62 publications

Impact of climate change on river water temperature and dissolved oxygen: Indian riverine thermal regimes

Impact of climate change on river water temperature and dissolved oxygen: Indian riverine thermal regimes

Big Data Analytics Using Swarm-Based Long Short-Term Memory for Temperature Forecasting

Ecological responses of spawning habitat suitability to changes in flow and thermal regimes influenced by hydropower operation

Contact Info

Product

Resources

About