Monthly Runoff Forecasting Based on Interval Sliding Window and Ensemble Learning

In recent years, machine learning, a popular artificial intelligence technique, has been successfully applied to monthly runoff forecasting. Monthly runoff autoregressive forecasting using machine learning models generally uses a sliding window algorithm to construct the dataset, which requires the selection of the optimal time step to make the machine learning tool function as intended. Based on this, this study improved the sliding window algorithm and proposes an interval sliding window (ISW) algorithm based on correlation coefficients, while the least absolute shrinkage and selection operator (LASSO) method was used to combine three machine learning models, Random Forest (RF), LightGBM, and CatBoost, into an ensemble to overcome the preference problem of individual models. Example analyses were conducted using 46 years of monthly runoff data from Jiutiaoling and Zamusi stations in the Shiyang River Basin, China. The results show that the ISW algorithm can effectively handle monthly runoff data and that the ISW algorithm produced a better dataset than the sliding window algorithm in the machine learning models. The forecast performance of the ensemble model combined the advantages of the single models and achieved the best forecast accuracy.

[1]  Q. Pham,et al.  Using machine learning methods for supporting GR2M model in runoff estimation in an ungauged basin , 2021, Scientific Reports.

[2]  Karim I. Abdrabo,et al.  Examining LightGBM and CatBoost models for wadi flash flood susceptibility prediction , 2021, Geocarto International.

[3]  Jiahua Wei,et al.  Middle- and Long-Term Streamflow Forecasting and Uncertainty Analysis Using Lasso-DBN-Bootstrap Model , 2021, Water Resources Management.

[4]  E. Baltas,et al.  Increasing the Efficiency of the Sacramento Model on Event Basis in a Mountainous River Basin , 2021, Environmental Processes.

[5]  Bahram Gharabaghi,et al.  Short to Long-Term Forecasting of River Flows by Heuristic Optimization Algorithms Hybridized with ANFIS , 2021, Water Resources Management.

[6]  Min Liu,et al.  The importance of short lag-time in the runoff forecasting model based on long short-term memory , 2020 .

[7]  Jianfeng Wu,et al.  Streamflow and rainfall forecasting by two long short-term memory-based models , 2020 .

[8]  Zbigniew Leonowicz,et al.  Forecasting Solar PV Output Using Convolutional Neural Networks with a Sliding Window Algorithm , 2020, Energies.

[9]  Zhongmin Liang,et al.  Combination of Multiple Data-Driven Models for Long-Term Monthly Runoff Predictions Based on Bayesian Model Averaging , 2019, Water Resources Management.

[10]  Sara M. Abuzied,et al.  Geospatial hazard modeling for the delineation of flash flood-prone zones in Wadi Dahab basin, Egypt , 2018, Journal of Hydroinformatics.

[11]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[12]  Long Chen,et al.  Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation , 2017 .

[13]  R. Deo,et al.  Stream-flow forecasting using extreme learning machines: a case study in a semi-arid region in Iraq , 2016 .

[14]  May Yuan,et al.  Geospatial risk assessment of flash floods in Nuweiba area, Egypt , 2016 .

[15]  James C. Bennett,et al.  Reliable long‐range ensemble streamflow forecasts: Combining calibrated climate forecasts with a conceptual runoff model and a staged error model , 2016 .

[16]  Dimitri Solomatine,et al.  A Stratified Sampling Approach for Improved Sampling from a Calibrated Ensemble Forecast Distribution , 2016 .

[17]  Gang Li,et al.  Real-time correction of antecedent precipitation for the Xinanjiang model using the genetic algorithm. , 2016 .

[18]  Kwok-wing Chau,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition , 2015, Water Resources Management.

[19]  Shengzhi Huang,et al.  Monthly streamflow prediction using modified EMD-based support vector machine , 2014 .

[20]  Jian-Jun Ni,et al.  Forecast Modeling of Monthly Runoff with Adaptive Neural Fuzzy Inference System and Wavelet Analysis , 2013 .

[21]  K. N. Tiwari,et al.  Bootstrap based artificial neural network (BANN) analysis for hierarchical prediction of monthly runoff in Upper Damodar Valley Catchment , 2009 .

[22]  Ronny Berndtsson,et al.  Monthly runoff simulation: Comparing and combining conceptual and neural network models , 2006 .

[23]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[24]  Magnus Persson,et al.  Monthly runoff prediction using phase space reconstruction , 2001 .

[25]  Zhao Ren-jun,et al.  The Xinanjiang model applied in China , 1992 .

[26]  L. Jiao,et al.  Hyperspectral Imagery Classification Based on Contrastive Learning , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Sunil L. Kukreja,et al.  A LEAST ABSOLUTE SHRINKAGE AND SELECTION OPERATOR (LASSO) FOR NONLINEAR SYSTEM IDENTIFICATION , 2006 .

[28]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.