Novel Ensemble Forecasting of Streamflow Using Locally Weighted Learning Algorithm

Abstract

The development of advanced computational models for improving the accuracy of streamflow forecasting could save time and cost for sustainable water resource management. In this study, a locally weighted learning (LWL) algorithm is combined with the Additive Regression (AR), Bagging (BG), Dagging (DG), Random Subspace (RS), and Rotation Forest (RF) ensemble techniques for the streamflow forecasting in the Jhelum Catchment, Pakistan. To build the models, we grouped the initial parameters into four different scenarios (M1–M4) of input data with a five-fold cross-validation (I–V) approach. To evaluate the accuracy of the developed ensemble models, previous lagged values of streamflow were used as inputs whereas the cross-validation technique and periodicity input were used to examine prediction accuracy on the basis of root correlation coefficient (R), root mean squared error (RMSE), mean absolute error (MAE), relative absolute error (RAE), and root relative squared error (RRSE). The results showed that the incorporation of periodicity (i.e., MN) as an additional input variable considerably improved both the training performance and predictive performance of the models. A comparison between the results obtained from the input combinations III and IV revealed a significant performance improvement. The cross-validation revealed that the dataset M3 provided more accurate results compared to the other datasets. While all the ensemble models successfully outperformed the standalone LWL model, the ensemble LWL-AR model was identified as the best model. Our study demonstrated that the ensemble modeling approach is a robust and promising alternative to the single forecasting of streamflow that should be further investigated with different datasets from other regions around the world.

Cracking spoilage in jar cream cheese: Introducing, modeling and preventing

“…We were expecting this pattern given the previous works reported for various machine-learning modeling projects [ 45 , 46 ]. Since the models are fed by a greater number of samples during the training phase of the modeling, they can better explore the pattern hidden in data and achieve higher values of R 2 with lower error rates [ [47] , [48] , [49] ]. The advanced REPTree model is resistant to overfitting and insensitive to noise and unbiased error compared to conventional methods, such as MLP and LR [ 26 ].…”

Novel Ensemble Models Based on the Split‐Point Sampling and Node Attribute Subsampling Classifier for Groundwater Potential Mapping

“…RSS is a widely used ensemble learning technique that aims to enhance the accuracy and performance of weak classifiers by using random subsets of features to train them (Adnan et al., 2021; Pham et al., 2020; Zhou et al., 2022). RSS randomly samples the features from the original data set with replacement, and then trains a separate classifier on each sample.…”

Ensemble hybrid machine learning to simulate dye/divalent salt fractionation using a loose nanofiltration membrane

“…Each model's output is connected to a neuron in the input layer of the neural ensemble model. 55,56 When training a nonlinear ensemble model, such as a single NF or ANN using the activation function of the output and hidden layers, any algorithm can be trained by the network, and the epoch number and best structure of the ensemble network can be established via the trial and error technique. 57 In this study we used hybrid NF as the ensemble algorithm, although other non-linear kernels such as BPNN might also be utilized as such, a nonlinear ensemble, NF, was used in this research because it is the combination of the neural network and fuzzy logic.…”