Monthly Streamflow Prediction Research Articles

Coupling SWAT and Transformer Models for Enhanced Monthly Streamflow Prediction

The establishment of an accurate and reliable predictive model is essential for water resources planning and management. Standalone models, such as physics-based hydrological models or data-driven hydrological models, have their specific applications, strengths, and limitations. In this study, a hybrid model (namely SWAT-Transformer) was developed by coupling the physics-based Soil and Water Assessment Tool (SWAT) with the data-driven Transformer to enhance monthly streamflow prediction accuracy. SWAT is first constructed and calibrated, and then its outputs are used as part of the inputs to Transformer. By correcting the prediction errors of SWAT using Transformer, the two models are effectively coupled. Monthly runoff data at Yan’an and Ganguyi stations on Yan River, a first-order tributary of the Yellow River Basin, were used to evaluate the proposed model’s performance. The results indicated that SWAT performed well in predicting high flows but poorly in low flows. In contrast, Transformer was able to capture low-flow period information more accurately and outperformed SWAT overall. SWAT-Transformer could correct the errors of SWAT predictions and overcome the limitations of a single model. By integrating SWAT’s detailed physical process portrayal with Transformer’s powerful time-series analysis, the coupled model significantly improved streamflow prediction accuracy. The proposed models offer more accurate and reliable predictions for optimal water resource management, which is crucial for sustainable economic and societal development.

Enhancing Monthly Streamflow Prediction Using Meteorological Factors and Machine Learning Models in the Upper Colorado River Basin

Streamflow prediction is crucial for planning future developments and safety measures along river basins, especially in the face of changing climate patterns. In this study, we utilized monthly streamflow data from the United States Bureau of Reclamation and meteorological data (snow water equivalent, temperature, and precipitation) from the various weather monitoring stations of the Snow Telemetry Network within the Upper Colorado River Basin to forecast monthly streamflow at Lees Ferry, a specific location along the Colorado River in the basin. Four machine learning models—Random Forest Regression, Long short-term memory, Gated Recurrent Unit, and Seasonal AutoRegresive Integrated Moving Average—were trained using 30 years of monthly data (1991–2020), split into 80% for training (1991–2014) and 20% for testing (2015–2020). Initially, only historical streamflow data were used for predictions, followed by including meteorological factors to assess their impact on streamflow. Subsequently, sequence analysis was conducted to explore various input-output sequence window combinations. We then evaluated the influence of each factor on streamflow by testing all possible combinations to identify the optimal feature combination for prediction. Our results indicate that the Random Forest Regression model consistently outperformed others, especially after integrating all meteorological factors with historical streamflow data. The best performance was achieved with a 24-month look-back period to predict 12 months of streamflow, yielding a Root Mean Square Error of 2.25 and R-squared (R2) of 0.80. Finally, to assess model generalizability, we tested the best model at other locations—Greenwood Springs (Colorado River), Maybell (Yampa River), and Archuleta (San Juan) in the basin.

Dynamic Bayesian-Network-Based Approach to Enhance the Performance of Monthly Streamflow Prediction Considering Nonstationarity

In recognizing the pervasive nonstationarity of hydrometeorological variables, a paradigm shift towards alternative analytical methodologies is imperative for refining hydroclimatic data modeling and prediction. We introduce a novel approach leveraging nonstationary Graphical Modeling and Bayesian Networks (NGM-BNs) tailored for hydrometeorological applications. Demonstrated through monthly streamflow forecasting in the Kashgar River Basin of China, our method illuminates the temporal evolution of network relationships, underscoring the dynamism inherent in both input variables and modeling parameters. The key to our approach is identifying the most suitable time horizon (MST) for model updates, which is intricately problem-specific and crucial for peak performance. This methodology not only unveils changing predictor significance across varying flow conditions but also elucidates the fluctuating temporal links between variables, especially under the lens of climate change, for instance, the growing impact of snowmelt on the Kashgar Basin’s streamflow. Compared to stationary counterparts, our nonstationary Bayesian framework excels in capturing extreme events by adeptly accommodating temporal shifts, outperforming traditional models including both stationary and nonstationary variants of Support Vector Regression (SVR) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS).

Monthly Streamflow Prediction of the Source Region of the Yellow River Based on Long Short-Term Memory Considering Different Lagged Months

Accurate and reliable monthly streamflow prediction plays a crucial role in the scientific allocation and efficient utilization of water resources. In this paper, we proposed a prediction framework that integrates the input variable selection method and Long Short-Term Memory (LSTM). The input selection methods, including autocorrelation function (ACF), partial autocorrelation function (PACF), and time lag cross-correlation (TLCC), were used to analyze the lagged time between variables. Then, the performance of the LSTM model was compared with three other traditional methods. The framework was used to predict monthly streamflow at the Jimai, Maqu, and Tangnaihai stations in the source area of the Yellow River. The results indicated that grid search and cross-validation can improve the efficiency of determining model parameters. The models incorporating ACF, PACF, and TLCC with lagged time are evidently superior to the models using the current variable as the model inputs. Furthermore, the LSTM model, which considers the lagged time, demonstrated better performance in predicting monthly streamflow. The coefficient of determination (R2) improved by an average of 17.46%, 33.94%, and 15.29% for each station, respectively. The integrated framework shows promise in enhancing the accuracy of monthly streamflow prediction, thereby aiding in strategic decision-making for water resources management.

Coupling Deep Learning and Physically Based Hydrological Models for Monthly Streamflow Predictions

AbstractThis study proposes a new hybrid model for monthly streamflow predictions by coupling a physically based distributed hydrological model with a deep learning (DL) model. Specifically, a simplified hydrological model is first developed by optimally selecting grid cells from a distributed hydrological model according to their soil moisture characteristics. It is then driven by bias corrected general circulation model (GCM) predictions to generate soil moistures for the forecasting months. Finally, model‐simulated soil moisture along with other predictors from multiple sources are used as inputs of the DL model to predict future monthly streamflows. The proposed hybrid model, using the simplified Variable Infiltration Capacity (VIC) as the hydrological model and the combination of Convolutional Neural Network and Gated Recurrent Unit (CNN‐GRU) as the DL model, is applied to predict 1‐, 3‐, and 6‐month ahead reservoir inflows for the Danjiangkou Reservoir in China. The results show that the hybrid model consistently performs better than VIC and CNN‐GRU models with great improvement in Kling‐Gupta efficiency (KGE) values for lead times up to 6 months. Additional tests indicate that hybrid models based on CNN‐GRU outperform those based on LASSO, XGBoost, CNN, and GRU models. Moreover, compared with the distributed hydrological model, the hybrid model greatly reduces the computation burden of rolling prediction. It also saves decision‐makers the time and effort of trying different combinations of predictors, which is indispensable when building DL models. Overall, the new hybrid model demonstrates great potential for monthly streamflow prediction where training data are limited.

Application of hybridized ANN–GARCH, ANN–SETAR, MARS–SPSO, and CANFIS–SPSO meta-models for improving accuracy of monthly streamflow prediction

Application of hybridized ANN–GARCH, ANN–SETAR, MARS–SPSO, and CANFIS–SPSO meta-models for improving accuracy of monthly streamflow prediction

A Novel Intelligent Model for Monthly Streamflow Prediction Using Similarity-Derived Method

Accurate monthly streamflow prediction is crucial for effective flood mitigation and water resource management. The present study proposes an innovative similarity-derived model (SDM), developed based on the observation that similar monthly streamflow patterns recur across different years under comparable hydrological and climate conditions. The model is applied to the Lancang River Basin in China. The model performance is compared with the commonly used support vector machine (SVM) and Mean methods. Evaluation measures such as RMSE, MAPE, and NSE confirm that SDM6 with a reference period of six months achieves the best performance, improving the Mean model by 79.9 m3/s in RMSE, 6.07% in MAPE, and 8.62% in NSE, and the SVM by 53.65 m3/s, 0.24%, and 5.53%, respectively.

Improved prediction of monthly streamflow in a mountainous region by Metaheuristic-Enhanced deep learning and machine learning models using hydroclimatic data

Improved prediction of monthly streamflow in a mountainous region by Metaheuristic-Enhanced deep learning and machine learning models using hydroclimatic data

Novel hybrid model to improve the monthly streamflow prediction: Integrating ANN and PSO

Precise streamflow forecasting is crucial when designing water resource planning and management, predicting flooding, and reducing flood threats. This study invented a novel approach for the monthly water streamflow of the Tigris River in Amarah City, Iraq, by integrating an artificial neural network (ANN) with the particle swarm optimisation algorithm (PSO), depending on data preprocessing. Historical streamflow data were utilised from (2010 to 2020). The primary conclusions of this study are that data preprocessing enhances data quality and identifies the optimal predictor scenario. In addition, it was revealed that the PSO algorithm effectively forecasts the parameters of the suggested model. Also, the outcomes indicated that the suggested approach successfully simulated the streamflow according to multiple statistical criteria, including R2, RMSE, and MAE.

Monthly Streamflow Prediction Using ANN, KNN and ANFIS models: Example of Gediz River Basin

Stream flow forecasting is very important in many aspects such as water supply, irrigation, building water infrastructures, and taking precautions against floods. The ability to forecast future streamflow helps us anticipate and plan for upcoming flooding, decreasing property destruction, preventing deaths and managing water in the best way possible. Different hydrological models have been developed for predicting streamflow and they have different characteristics, driven by the research area and available data. İn this study, three types of Artificial Intelligence models; K-Nearest Neighbor (KNN), Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) have been used to study the Gediz River Basin which is located in the Aegean region of western Turkey. The results varied due to the complication of the data and different parts of the study area as well as the structure of the models, over all, looking at Regression coefficient (R2), Root Mean Square Error (RMSE) and Wilcoxon (WT) values, ANFIS is more accurate compared to ANN and KNN models. Conversely, according to Taylor diagram, KNN is more accurate compared to ANN and ANFIS.

Application of novel binary optimized machine learning models for monthly streamflow prediction

Accurate measurements of available water resources play a key role in achieving a sustainable environment of a society. Precise river flow estimation is an essential task for optimal use of hydropower generation, flood forecasting, and best utilization of water resources in river engineering. The current paper presents the development and verification of the prediction abilities of new hybrid extreme learning machine (ELM)-based models coupling with metaheuristic methods, e.g., Particle swarm optimization (PSO), Mayfly optimization algorithm (MOA), Grey wolf optimization (GWO), and simulated annealing (SA) for monthly streamflow prediction. Prediction precision of standalone ELM model was compared with two-phase optimized state-of-the-arts models, e.g., ELM–PSO, ELM–MOA, ELM–PSOGWO, and ELM–SAMOA, respectively. Hydro-meteorological data acquired from Gorai and Padma Hardinge Bridge stations at Padma River Basin, northwestern Bangladesh, were utilized as inputs in this study to employ models in the form of seven different input combinations. The model’s performances are appraised using Nash–Sutcliffe efficiency, root-mean-square-error (RMSE), mean absolute error, mean absolute percentage error and determination coefficient. The tested results of both stations reported that the ELM–SAMOA and ELM–PSOGWO models offered the best accuracy in the prediction of monthly streamflows compared to ELM–PSO, ELM–MOA, and ELM models. Based on the local data, the ELM–SAMOA reduced the RMSE of ELM, ELM–PSO, ELM–MOA, and ELM–PSOGWO by 31%, 27%, 19%, and 14% for the Gorai station and by 29%, 27%, 19%, and 14% for Padma Hardinge bridge station, in the testing stage, respectively. In contrast, based on external data, ELM–PSOGWO improves in RMSE of ELM, ELM–PSO, ELM–MOA, and ELM–SAMOA by 20%, 5.1%, 6.2%, and 4.6% in the testing stage, respectively. The results confirmed the superiority of two-phase optimized ELM–SAMOA and ELM–PSOGWO models over a single ELM model. The overall results suggest that ELM–SAMOA and ELM–PSOGWO models can be successfully applied in modeling monthly streamflow prediction with either local or external hydro-meteorological datasets.

Monthly Streamflow Prediction by Metaheuristic Regression Approaches Considering Satellite Precipitation Data

In this study, the viability of three metaheuristic regression techniques, CatBoost (CB), random forest (RF) and extreme gradient tree boosting (XGBoost, XGB), is investigated for the prediction of monthly streamflow considering satellite precipitation data. Monthly streamflow data from three measuring stations in Turkey and satellite rainfall data derived from Tropical Rainfall Measuring Mission (TRMM) were used as inputs to the models to predict 1 month ahead streamflow. Such predictions are crucial for decision-making in water resource planning and management associated with water allocations, water market planning, restricting water supply and managing drought. The outcomes of the metaheuristic regression methods were compared with those of artificial neural networks (ANN) and nonlinear regression (NLR). The effect of the periodicity component was also investigated by importing the month number of the streamflow data as input. In the first part of the study, the streamflow at each station was predicted using CB, RF, XGB, ANN and NLR methods and considering TRMM data. In the second part, streamflow at the downstream station was predicted using data from upstream stations. In both parts, the CB and XGB methods generally provided similar accuracy and performed superior to the RF, ANN and NLR methods. It was observed that the use of TRMM rainfall data and the periodicity component considerably improved the efficiency of the metaheuristic regression methods in modeling (prediction) streamflow. The use of TRMM data as inputs improved the root mean square error (RMSE) of CB, RF and XGB by 36%, 31% and 24%, respectively, on average, while the corresponding values were 37%, 18% and 43% after introducing periodicity information into the model’s inputs.

A framework of integrating heterogeneous data sources for monthly streamflow prediction using a state-of-the-art deep learning model

Deep learning has been widely used in hydrological prediction such as monthly streamflow and its performance is usually dependent on the abundance of training data. Even though the interest in using predictors from multiple data sources (e.g., streamflow observations, local meteorological data, and large-scale climate indexes) to train deep learning models for monthly streamflow prediction is growing, these predictors are usually selected from historical periods. Such approaches have limitations that the non-stationary future climate information is not included in the deep learning models. Climate models can provide non-stationary climate information for the future period, which may be useful for monthly streamflow prediction. Therefore, the objectives of this study are to (1) investigate the added value of using predictors derived from global climate models (GCMs) for monthly streamflow prediction based on a state-of-the-art deep learning model, and (2) propose a framework for integrating heterogeneous data sources for monthly streamflow prediction. The framework consists of five integral components: data collection, predictor combination, predictor selection, model construction, and results evaluation. In this study, a hybrid deep learning model combining Convolutional Neural Network and Gated Recurrent Unit was applied for six hydrological stations from mainstream and six stations from tributaries of the Yangtze River. Historical hydroclimate data and GCM hindcasts from 1982 to 2010 are used in monthly streamflow forecasts. Hindcasts are retrospective forecasts for many variables in the past, ideally conducted using the same model used for real-time forecasts. The results show that GCM hindcasts are useful predictors to improve the prediction accuracy for monthly streamflow predictions, especially for the 1- and 3-month lead times. Combining GCM hindcasts with either historical meteorological data or historical streamflow observations and meteorological data as predictors generally provides the best predictive performance. In addition, using large-scale climate indexes as ancillary information is able to improve the predictive performance at a lead time of 6 months. For lead times of 1, 3, and 6 months, the Kling‐Gupta efficiency (KGE) and the mean relative error (MRE)) metrics calculated based on the best-performing predictor combinations are satisfactory for hydrological stations in both mainstream and tributaries, with the median KGE being higher than 0.85 and 0.62, and the median MRE being approximately 20 % and 40 %, respectively, suggesting the monthly streamflow predictions are better for mainstream than for tributaries. Overall results show that (1) the inclusion of predicted information from GCMs can improve the performance for monthly streamflow prediction, and (2) the way of combining various heterogeneous data sources is crucial.

Scale Effects of the Monthly Streamflow Prediction Using a State-of-the-art Deep Learning Model

Scale Effects of the Monthly Streamflow Prediction Using a State-of-the-art Deep Learning Model

A Comparative Study on Prediction of Monthly Streamflow Using Hybrid ANFIS-PSO Approaches

Monthly prediction of streamflow is a fundamental and complex hydrological phenomenon. Accurate streamflow prediction helps in water resources planning, design, and management, particularly for hydropower production, irrigation, protection of dams and flood risk management. Hence, in this paper, a hybrid robust model integrating adaptive neuro-fuzzy inference system (ANFIS) with particle swarm optimization (PSO) algorithm was developed for monthly streamflow prediction of Barak River basin, India. Multiple factors like Precipitation (Pt), temperature (Tt), humidity (Ht), Infiltration loss (It), are considered as the inputs for determining the streamflow. For validating the model performance, 70% of data (1980–2007) were used for training them and 30% of data (2008–2019) were used for testing them. A comparison is made between results of developed hybrid model with simple artificial neural network (ANN) and ANFIS models for assessing accuracy and efficiency of model performances. Obtained results of proposed models were evaluated based on four assessment indices including by Root Mean Square Error (RMSE), Mean Absolute Error (MAE), determination coefficient (R2) and Nash-Sutcliffe Coefficient (ENS). Based on comparison of results, it was concluded that robust ANFIS-PSO model with RMSE = 5.887, MAE = 4.978, R2 = 0.9668, and ENS = 0.961 demonstrated best performance with more reliability and accuracy in comparison to ANFIS and ANN models. Findings of this research proved that hybrid ANFIS with an evolutionary optimization algorithm is a reliable modelling approach for monthly streamflow prediction.

Artificial intelligence modelling integrated with Singular Spectral analysis and Seasonal-Trend decomposition using Loess approaches for streamflow predictions

The nature of streamflow in the basins is stochastic and complex making it difficult to make an accurate prediction about the future river flows. Recently, artificial neural-based deep learning models with a nonlinear structure have become predominant in water engineering forecasting problems such as river flow predictions. In this study, we investigate the potential of Singular Spectral Analysis (SSA), Seasonal-Trend decomposition using Loess (STL) and attribute selection pre-processing approaches with the neural network methods in predicting monthly river streamflows in the Nallihan stream, Turkey. Antecedent measured streamflow, precipitation, relative humidity and temperature data between the years 1996 and 2016 from the observing stations in the basin boundaries were used as model inputs under different scenarios using the correlations between the past measured variables, to predict one-step-ahead flow data. To compare the newer hybrid model performances; evaluation metrics including coefficient of determination (R2), Nash-Sutcliffe efficiency (NE), Willmott’s Index of Agreement (WI), root mean square error, mean absolute error together with judicious plots; scatter plot, time series and the Taylor diagrams were utilized. The developed hybrid SSA-based models registered higher accuracy than other standalone Neural Networks models without pre-processing approaches. The R2 for SSA-based models were higher ranging from 0.8300 to 0.9105, and the largest R2 = 0.9105 was registered by the proposed SSA-ANN model. SSA-ANN models have also the highest NE and WI index values: 0.9045 and 0.9764, respectively. The outcomes revealed that based on NE, the SSA decomposition increased the monthly streamflow prediction accuracy by 24.11%, 18.40% and 5.11% of respective ANN, CNN and LSTM methods. The SSA pre-processing approach is able to unveil the embedded streamflow characteristics and could be further applied in basins with similar characteristics to attain more accurate predictions of river flows.

Enhanced streamflow prediction with SWAT using support vector regression for spatial calibration: A case study in the Illinois River watershed, U.S.

Accurate streamflow prediction plays a pivotal role in hydraulic project design, nonpoint source pollution estimation, and water resources planning and management. However, the highly non-linear relationship between rainfall and runoff makes prediction difficult with desirable accuracy. To improve the accuracy of monthly streamflow prediction, a seasonal Support Vector Regression (SVR) model coupled to the Soil and Water Assessment Tool (SWAT) model was developed for 13 subwatersheds in the Illinois River watershed (IRW), U.S. Terrain, precipitation, soil, land use and land cover, and monthly streamflow data were used to build the SWAT model. SWAT Streamflow output and the upstream drainage area were used as two input variables into SVR to build the hybrid SWAT-SVR model. The Calibration Uncertainty Procedure (SWAT-CUP) and Sequential Uncertainty Fitting-2 (SUFI-2) algorithms were applied to compare the model performance against SWAT-SVR. The spatial calibration and leave-one-out sampling methods were used to calibrate and validate the hybrid SWAT-SVR model. The results showed that the SWAT-SVR model had less deviation and better performance than SWAT-CUP simulations. SWAT-SVR predicted streamflow more accurately during the wet season than the dry season. The model worked well when it was applied to simulate medium flows with discharge between 5 m3 s-1 and 30 m3 s-1, and its applicable spatial scale fell between 500 to 3000 km2. The overall performance of the model on yearly time series is "Satisfactory". This new SWAT-SVR model has not only the ability to capture intrinsic non-linear behaviors between rainfall and runoff while considering the mechanism of runoff generation but also can serve as a reliable regional tool for an ungauged or limited data watershed that has similar hydrologic characteristics with the IRW.

A Hybrid VMD-SVM Model for Practical Streamflow Prediction Using an Innovative Input Selection Framework

Some previous studies have proved that prediction models using traditional overall decomposition sampling (ODS) strategy are unreasonable because the subseries obtained by the ODS strategy contain future information to be predicted. It is, therefore, necessary to put forward a new sampling strategy to fix this defect and also to improve the accuracy and reliability of decomposition-based models. In this paper, a stepwise decomposition sampling (SDS) strategy according to the practical prediction process is introduced. Moreover, an innovative input selection framework is proposed to build a strong decomposition-based monthly streamflow prediction model, in which sunspots and atmospheric circulation anomaly factors are employed as candidate input variables to enhance the prediction accuracy of monthly streamflow in addition to regular inputs such as precipitation and evaporation. Meanwhile, the partial correlation algorithm is employed to select optimal input variables from candidate input variables including precipitation, evaporation, sunspots, and atmospheric circulation anomaly factors. Four basins of the U.S. MOPEX project with various climate characteristics were selected as a case study. Results indicate that: (1) adding teleconnection factors into candidate input variables helps enhance the prediction accuracy of the support vector machine (SVM) model in predicting streamflow; (2) the innovative input selection framework helps to improve the prediction capacity of models whose candidate input variables interact with each other compared with traditional selection strategy; (3) the SDS strategy can effectively prevent future information from being included into input variables, which is an appropriate substitute of the ODS strategy in developing prediction models; (4) as for monthly streamflow, the hybrid variable model decomposition-support vector machine (VMD-SVM) models, using an innovative input selection framework and the SDS strategy, perform better than those which have not adopted this framework in all study areas. Generally, the findings of this study showed that the hybrid VMD-SVM model combining the SDS strategy and innovative input selection framework is a useful and powerful tool for practical hydrological prediction work in the context of climate change.

A Comparative Evaluation of the Performance of CHIRPS and CFSR Data for Different Climate Zones Using the SWAT Model

The spatial and temporal scale of rainfall datasets is crucial in modeling hydrological processes. Recently, open-access satellite precipitation products with improved resolution have evolved as a potential alternative to sparsely distributed ground-based observations, which sometimes fail to capture the spatial variability of rainfall. However, the reliability and accuracy of the satellite precipitation products in simulating streamflow need to be verified. In this context, the objective of the current study is to assess the performance of three rainfall datasets in the prediction of daily and monthly streamflow using Soil and Water Assessment Tool (SWAT). We used rainfall data from three different sources: Climate Hazards Group InfraRed Rainfall with Station data (CHIRPS), Climate Forecast System Reanalysis (CFSR) and observed rain gauge data. Daily and monthly rainfall measurements from CHIRPS and CFSR were validated using widely accepted statistical measures, namely, correlation coefficient (CC), root mean squared error (RMSE), probability of detection (POD), false alarm ratio (FAR), and critical success index (CSI). The results showed that CHIRPS was in better agreement with ground-based rainfall at daily and monthly scale, with high rainfall detection ability, in comparison with the CFSR product. Streamflow prediction across multiple watersheds was also evaluated using Kling-Gupta Efficiency (KGE), Nash-Sutcliffe Efficiency (NSE) and Percent BIAS (PBIAS). Irrespective of the climatic characteristics, the hydrologic simulations of CHIRPS showed better agreement with the observed at the monthly scale with the majority of the NSE values ranging between 0.40 and 0.78, and KGE values ranging between 0.62 and 0.82. Overall, CHIRPS outperformed the CFSR rainfall product in driving SWAT for streamflow simulations across the multiple watersheds selected for the study. The results from the current study demonstrate the potential of CHIRPS as an alternate open access rainfall input to the hydrologic model.

Monthly Streamflow Prediction Based on Random Forest Algorithm and Phase Space Reconstruction Theory

In order to find an effective time series forecasting method, a random forest prediction model based on phase space reconstruction theory is proposed in this paper. The Cao method and mutual information function method are used to reconstruct the phase space, and the parameters of the random forest (RF) model are discussed. The feasibility of the model is verified by analyzing the monthly runoff data of Pingshan hydrological station in Jinsha River Basin. Compared with BP neural network (BPnet) model and traditional support vector machine (SVM) model which optimizes parameters by grid algorithm, random forest model has higher prediction accuracy and less calculation in dealing with complex nonlinear hydrological time series as shown by the result.