Abstract:Daily hydrological modelling is among the most challenging tasks in water resource management, particularly in terms of streamflow prediction in semi-arid areas. Various methods were applied in order to deal with this complex phenomenon, but recently data-driven models have taken a better space, given their ability to solve prediction problems in time series. In this study, we have employed the Long Short-Term Memory (LSTM) network to simulate the daily streamflow over the Ait Ouchene watershed (AIO) in the Ou… Show more
“…The results obtained from these metrics collectively indicate that the LSTM model did not meet the desired level of accuracy and reliability in predicting the flow data. Additionally LSTM for Daily Streamflow Prediction in a Semi-Arid Area reported similar findings, indicating that the application of the LSTM model was unable to predict streamflow using default data, indicating the need for more data to feed the model and capture streamflow accurately (Nifa et al, 2023).…”
Section: Evaluation Of Lstm Model Performancementioning
Accurate streamflow estimation is vital for effective water resources management, including flood mitigation, drought warning, and reservoir operation. This research assesses the predictive performance of popular machine learning algorithms (LSTM, Regression Tree, AdaBoost, and Gradient Boosting) for daily streamflow forecasting in the Swat River basin. Three key predictor variables (maximum temperature, minimum temperature, and precipitation) are utilized. The study evaluates and compares the effectiveness of ML models (Gradient Boosting, Regression Tree, AdaBoost, and LSTM) during two timeframes (2021–2050 and 2051–2100). Bias-corrected data from ten general circulation models, considering greenhouse gas trajectories (SSP245 and SSP585), are used. Statistical metrics like Coefficient of determination (R2), Mean square Error (MSE), Mean Absolute error (MAE), and Root Mean Square Error (RMSE) are employed for evaluation. Regression Tree exhibits exceptional performance (R2: 0.88 during training, 0.78 during testing). Ensembling Regression Tree, AdaBoost, and Gradient Boosting, future daily streamflow projections are made for SSP245 and SSP585 scenarios. Bias correction enhances reliability, with the ensemble mean indicating an increase in mean annual streamflow between the 2050s and 2080s (3.26–7.52% for SSP245, 3.77–13.55% for SSP585).
“…The results obtained from these metrics collectively indicate that the LSTM model did not meet the desired level of accuracy and reliability in predicting the flow data. Additionally LSTM for Daily Streamflow Prediction in a Semi-Arid Area reported similar findings, indicating that the application of the LSTM model was unable to predict streamflow using default data, indicating the need for more data to feed the model and capture streamflow accurately (Nifa et al, 2023).…”
Section: Evaluation Of Lstm Model Performancementioning
Accurate streamflow estimation is vital for effective water resources management, including flood mitigation, drought warning, and reservoir operation. This research assesses the predictive performance of popular machine learning algorithms (LSTM, Regression Tree, AdaBoost, and Gradient Boosting) for daily streamflow forecasting in the Swat River basin. Three key predictor variables (maximum temperature, minimum temperature, and precipitation) are utilized. The study evaluates and compares the effectiveness of ML models (Gradient Boosting, Regression Tree, AdaBoost, and LSTM) during two timeframes (2021–2050 and 2051–2100). Bias-corrected data from ten general circulation models, considering greenhouse gas trajectories (SSP245 and SSP585), are used. Statistical metrics like Coefficient of determination (R2), Mean square Error (MSE), Mean Absolute error (MAE), and Root Mean Square Error (RMSE) are employed for evaluation. Regression Tree exhibits exceptional performance (R2: 0.88 during training, 0.78 during testing). Ensembling Regression Tree, AdaBoost, and Gradient Boosting, future daily streamflow projections are made for SSP245 and SSP585 scenarios. Bias correction enhances reliability, with the ensemble mean indicating an increase in mean annual streamflow between the 2050s and 2080s (3.26–7.52% for SSP245, 3.77–13.55% for SSP585).
“…where represents the weight matrices of the model, is the input data, is the previous cell state, is the previous hidden state, is the new cell state, is the new hidden state, and represent the dense layer and its weight, respectively. Figure 4. Structure of LSTM unit. Source: Nifa et al (2023). …”
Section: Methodsmentioning
confidence: 99%
“…Thus, most scientists recommend a single hidden layer (Arifin et al, 2019). Since there is no standard method for estimating the optimal number of hidden layer neurons, we used trial-and-error (Hossain et al, 2020; Bai et al, 2021; Ghamariadyan and Imteaz, 2021; Tareke and Awoke, 2023; Nifa et al, 2023). This was achieved by training the model with different numbers of hidden neurons, from 10 to 20, and making a decision based on the root mean square error (MSE) and coefficient of determination of the predicted and observed values in the training and validation datasets, as well as by analyzing the loss function curve over the number of epochs.…”
Complex physical processes that are inherent to rainfall lead to the challenging task of its prediction. To contribute to the improvement of rainfall prediction, artificial neural network (ANN) models were developed using a multilayer perceptron (MLP) approach to predict monthly rainfall 2 months in advance for six geographically diverse weather stations across the Benin Republic. For this purpose, 12 lagged values of atmospheric data were used as predictors. The models were trained using data from 1959 to 2017 and tested for 4 years (2018–2021). The proposed method was compared to long short-term memory (LSTM) and climatology forecasts (CFs). The prediction performance was evaluated using five statistical measures: root mean square error, mean absolute error, mean absolute percentage error, coefficient of determination, and Nash–Sutcliffe efficiency (NSE) coefficient. Furthermore, Taylor diagrams, violin plots, box error, and Kruskal–Wallis test were used to assess the robustness of the model’s forecast. The results revealed that MLP gives better results than LSTM and CF. The NSE obtained with the MLP, LSTM, and CF models during the test period ranges from 0.373 to 0.885, 0.297 to 0.875, and 0.335 to 0.845, respectively, depending on the weather station. Rainfall predictability was more accurate, with 0.512 improvement in NSE using MLP at higher latitudes across the country, showing the effect of geographic regions on prediction model results. In summary, this research has revealed the potential of ANN techniques in predicting monthly rainfall 2 months ahead, supplying valuable insights for decision-makers in the Republic of Benin.
“…The final lap of the study explains the use of LSTM based deep learning environment for streamflow prediction. LSTM is found to be a sophisticated deep learning model that has gained favour in the prediction of streamflow [36][37][38]. LSTMs are a sort of recurrent neural network (RNN) that is used to solve the vanishing gradient problem and detect long-term relationships in sequential data.…”
Accurate prediction of future streamflow in flood-prone regions is crucial for effective flood management and disaster mitigation. This study presents an innovative approach for streamflow projections in deep learning (DL) environment by integrating the quantitative Land-Use Land-Cover (LULC) overlaid with flow accumulation values and the various Global Climate Model (GCM) simulated data. Firstly, the Long Short Term Memory (LSTM) model was developed for the streamflow prediction of Greater Pamba River Basin (GPRB) in Kerala, India for 1985 to 2015 period, considering the climatic inputs. Then, the flow accumulation-weighted LULC integration was considered in modelling, which substantially improves the accuracy of streamflow predictions including the extremes of all the three stations, as the model accounts for the geographical variety of land cover types towards the streamflow at the sub-basin outlets. Subsequently, Reliability Ensemble Averaging (REA) technique was used to create an ensemble of three candidate GCM products to illustrate the spectrum of uncertainty associated with climate projections. Future LULC changes are accounted in regional scale based on the sub-basin approach by means of Cellular-Automata Markov Model and used for integrating with the climatic indices. The basin-scale streamflow projection is done under three climate scenarios of SSP126, SSP245 and SSP585 respectively for lowest, moderate and highest emission conditions. This work is a novel approach of integrating quantified LULC with flow accumulation and other climatic inputs in a DL environment against the conventional techniques of hydrological modelling. The DL model can adapt and account for shifting hydrological responses induced by changes in climatic and LULC inputs. The integration of flow accumulation with changes in LULC was successful in capturing the flow dynamics in long-term. It also identifies regions that are more likely to experience increased flooding in the near future under changing climate scenarios and supports decision-making for sustainable water management of the Greater Pamba Basin which was the worst affected region in Kerala during the mega floods of 2018.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
