Daily Reservoir Inflow Research Articles

Data-driven forecasting framework for daily reservoir inflow time series considering the flood peaks based on multi-head attention mechanism

Accurate and reliable daily reservoir inflow forecast plays an essential role in several applications involving the management and planning of water resources, such as hydroelectric generation, flood control, water supply, and basin ecological dispatching. Runoff usually exhibits strong non-linearity, high uncertainty, and spatial and temporal variability. Existing techniques fail to capture complete dynamics change processes effectively. A data-driven forecasting framework for daily reservoir inflow time series considering the flood peaks based on a multi-head attention mechanism was developed, referred to as the GWOCS-VMD-CNN-Transformer (GCVCT). First, the model utilize Grey Wolf Optimizer coupled with Cuckoo Search (GWO-CS) algorithms to optimize parameters in variational mode decomposition model (VMD). This approach helps obtain highly correlated intrinsic mode function (IMF) components, enhancing the frequency resolution of the input dataset. The proposed method overcomes the bottleneck of other available methods by decomposing the time series to capture the main long-term and short-term properties of hydrological processes. Second, the convolution neural network and Transformer (CNN-Transformer) are based on a multi-head attention mechanism as the objective predictive method. Finally, six evaluation indicators verify the performance of the proposed approach. The approach’s reliability was evaluated using the historical daily reservoir inflow data from the Xiluodu (XLD) and Wudongde (WDD) reservoirs in the Jinsha River Basin, China. Several single and hybrid models were developed for comparative analysis. The results indicate that the proposed ensemble approach fits better than other developed model methods. The GCVCT model showed excellent performance in forecasting the inflows of XLD and WDD reservoirs, with NSE values of 0.985 and 0.984, respectively. Furthermore, the GCVCT framework forecast capacity for peak inflow was further verified through discussion and analysis of the 48 peak flows during the validation period, consistently outperforming other models in predicting peak flow for both study reservoirs. This framework provides an effective method for the scientific optimal scheduling of hydropower reservoirs, enabling more sustainable and efficient management practices. It also demonstrates the potential of powerful deep-learning models in intelligent hydrological forecasting.

Utilizing Artificial Intelligence Techniques for a Long–Term Water Resource Assessment in the ShihMen Reservoir for Water Resource Allocation

Accurate long–term water resource supply simulation and demand estimation are crucial for effective water resource allocation. This study proposes advanced artificial intelligence (AI)–based models for both long–term water resource supply simulation and demand estimation, specifically focusing on the ShihMen Reservoir in Taiwan. A Long Short–Term Memory (LSTM) network model was developed to simulate daily reservoir inflow. The climate factors from the Taiwan Central Weather Bureau’s one–tiered atmosphere–ocean coupled climate forecast system (TCWB1T1) were downscaled using the K–Nearest Neighbors (KNN) method and integrated with the reservoir inflow model to forecast inflow six months ahead. Additionally, Multilayer Perceptron (MLP) and Gated Recurrent Unit (GRU) were employed to estimate agricultural and public water demand, integrating both hydrological and socio–economic factors. The models were trained and validated using historical data, with the LSTM model demonstrating a strong ability to capture seasonal variations in inflow patterns and the MLP and GRU models effectively estimating water demand. The results highlight the models’ high accuracy and robustness, offering valuable insights into regional water resource allocation. This research provides a framework for integrating AI–driven models with Decision Support Systems (DSSs) to enhance water resource management, especially in regions vulnerable to climatic variability.

Daily reservoir inflow prediction using stacking ensemble of machine learning algorithms

ABSTRACT The present study aims to evaluate the potentiality of Bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Networks (CNNs), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and Random Forest (RF) for predicting daily inflows to the Sri Ram Sagar Project (SRSP), Telangana, India. Inputs to the model are rainfall, evaporation, time lag inflows, and climate indices. Seven combinations (S1–S7) of inputs were made. Fifteen and a half years of data were considered, out of which 11 years were used for training. Hyperparameter tuning is performed with the Tree-Structured Parzen Estimator. The performance of the algorithms is assessed using Kling–Gupta efficiency (KGE). Results indicate that Bi-LSTM with combination S7 performed better than others, as evident from KGE values of 0.92 and 0.87 during the training and testing, respectively. Furthermore, the Stacking Ensemble Mechanism (SEM) has also been employed to ascertain its efficacy over other chosen algorithms, resulting in KGE values of 0.94 and 0.89 during training and testing. It has also been able to simulate peak inflow events satisfactorily. Thus, SEM is a better alternative for reservoir inflow predictions.

STL-decomposition ensemble deep learning models for daily reservoir inflow forecast for hydroelectricity production

Accurate reservoir inflow forecasting is crucial for efficient water management. In this study, different deep learning models, including Dense, Long short-term memory (LSTM), and one-dimensional convolutional neural networks (Conv1D), were used to build ensembles. Seasonal-trend decomposition using loess (STL) was applied to decompose reservoir inflows and precipitations into random, seasonal, and trend components. Seven ensemble models, namely STL-Dense, STL-Conv1D, STL-LSTM, STL-Dense-LSTM-Conv1D, STL-Dense multivariate, STL-LSTM multivariate, and STL-Conv1D multivariate, were proposed and evaluated using daily inflows and precipitation decomposed data from the Lom Pangar reservoir from 2015 to 2020. Evaluation metrics, such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Nash Sutcliff Efficiency (NSE), were applied to assess model performance. Results showed that the STL-Dense multivariate model was the best ensemble among the thirteen models with MAE of 14.636 m3/s, RMSE of 20.841 m3/s, MAPE of 6.622%, and NSE of 0.988. These findings stress the importance of considering multiple inputs and models for accurate reservoir inflow forecasting and optimal water management. Not all ensemble models were good for Lom pangar inflow forecast as the Dense, Conv1D, and LSTM models performed better than their proposed STL monovariate ensemble models.

Two-step daily reservoir inflow prediction using ARIMA-machine learning and ensemble models

The reservoirs play a crucial role in the development of civilisation as they facilitate the storage of water for multiple purposes like hydroelectric power generation, flood control, irrigation, and drinking water etc. In order to effectively meet these multiple purposes, the knowledge of the inflow in the reservoir is essential. Apart from the historical data, future prediction of the inflows is also necessary specially in context of climate change. A two-step algorithm for the prediction of reservoir inflow to enable meticulous planning and execution of daily reservoir operation keeping the historical variation of inflow in account has been proposed. The developed algorithm takes into account the patterns in the historic inflow data using the time series analysis along with the variability in the climatic patterns using the different predictors in the machine learning model. The first step uses time series model, ARIMA method to forecast the monthly inflows, which are then used as the targets in the second step for the month-wise daily forecasting of the inflows using the two types of ensemble models, namely, averaging and boosting models in machine learning. The test results show that for both the monthly models and daily models the NRMSE and NMAE values were low for the monsoon periods compared to the non-monsoon periods. The averaging ensemble models were found to perform better than the boosting ensemble models for maximum number of months. The yearly results show an error of less than 5% between actual and predicted values for all the test cases, showing the precision in the developed algorithm. Further, the uncertainty analysis shows that the prediction done using the weighted average of the different inflow scenarios performs better than the prediction against the single inflow scenario.

Daily reservoir inflow forecasting using weather forecast downscaling and rainfall-runoff modeling: Application to Urmia Lake basin, Iran

Study regionThis study develops the first daily runoff forecast system for Bukan reservoir in Urmia Lake basin (ULB), Iran, a region suffering from water shortages and competing water demands. Study focusA weather forecast downscaling model is developed for downscaling large-scale raw weather forecasts of ECMWF and NCEP to small-scale spatial resolutions. Various downscaling methods are compared, including deterministic Artificial Intelligence (AI) techniques and a Bayesian Belief Network (BBN). Downscaled precipitation and temperature forecasts are then fed into a rainfall-runoff model that accounts for daily snow and soil moisture dynamics in the sub-basins upstream of Bukan reservoir. The multi-objective Particle Swarm Optimization (MOPSO) method is used to estimate hydrological model parameters by maximizing the simulation accuracy of observed river flow (NSEQ) and the logarithm of river flow (NSELogQ) in each sub-basin. New hydrological insights for the regionResults of the weather forecast downscaling model show that the accuracy of the BBN is greater than the various deterministic AI methods tested. Calibration results of the rainfall-runoff model indicate no significant trade-off between fitting daily high and low flows, with an average NSEQ and NSELogQ of 0.43 and 0.63 for the calibration period, and 0.54 and 0.57 for the validation period. The entire forecasting system was evaluated using inflow observations for years 2020 and 2021, resulting in an NSE of 0.66 for forecasting daily inflow into Bukan reservoir. The inflow forecasts can be used by policymakers and operators of the reservoir to optimize water allocation between agricultural and environmental demands in the ULB.

Reservoir Inflow Prediction by Employing Response Surface-Based Models Conjunction with Wavelet and Bootstrap Techniques

Reservoir inflow prediction is a vital subject in the field of hydrology because it determines the flood event. The negative impact of the floods could be minimized greatly if the flood frequency is predicted accurately in advance. In the present study, a novel hybrid model, bootstrap quadratic response surface is developed to test daily streamflow prediction. The developed bootstrap quadratic response surface model is compared with multiple linear regression model, first-order response surface model, quadratic response surface model, wavelet first-order response surface model, wavelet quadratic response surface model, and bootstrap first-order response surface model. Time series data of monsoon season (1 July to 30 September) for the year 2010 of the Chenab river basin are analyzed. The studied models are tested by using performance indices: Nash–Sutcliffe coefficient of efficiency, mean absolute error, persistence index, and root mean square error. Results reveal that the proposed model, i.e., bootstrap quadratic response surface shows good performance and produces optimum results for daily reservoir inflow prediction than other models used in the study.

IGDT-Based Medium-Term Optimal Cascade Hydropower Operation in Multimarket with Hydrologic and Economic Uncertainties

Hydrologic uncertainty and economic uncertainty both affect market-oriented hydropower operation. For medium-term cascade hydropower operation, the uncertainties of daily reservoir inflow and market clearing power price can pose risks to operation, especially when power stations participate in multiple power markets. It is difficult to obtain the fluctuation range of uncertain variables for different expected power sale profits, and to plan the operation range of cascade hydropower stations. For a cascade hydropower system dispatching power to two markets, this work developed a risk assessment method for medium-term optimal cascade hydropower operation based on information gap decision-making theory (IGDT). We established a bilevel stochastic IGDT model for the main hydrologic and economic uncertainties in hydropower market participation. The lower-level model solves the minimum robustness profit or maximum opportunity profit from power sale, and the upper-level model solves the maximum robustness fluctuation range or minimum opportunity fluctuation range of the uncertain variables for different expected profits. Then we converted the bilevel model to two equivalent single-level models, and provided solutions. The proposed method does not require the probability distribution of uncertain variables, which is often unavailable; moreover, it reduces computational complexity while ensuring accuracy of results. The proposed method can provide decision makers with reasonable power dispatch options. This work used a cascade hydropower system in Southwest China as a case study. The proposed method provided acceptable fluctuation range of uncertain reservoir inflow and power price under different expected profits, and provided the operation range to guarantee the expected profit. Decision makers with different risk preferences can evaluate various strategies to optimize medium-term cascade hydropower operation to ensure the expected profit.

An Ensemble Modeling Approach to Forecast Daily Reservoir Inflow Using Bidirectional Long- and Short-Term Memory (Bi-LSTM), Variational Mode Decomposition (VMD), and Energy Entropy Method

An Ensemble Modeling Approach to Forecast Daily Reservoir Inflow Using Bidirectional Long- and Short-Term Memory (Bi-LSTM), Variational Mode Decomposition (VMD), and Energy Entropy Method

Improving Daily Peak Flow Forecasts Using Hybrid Fourier-Series Autoregressive Integrated Moving Average and Recurrent Artificial Neural Network Models

In multi-purpose reservoirs, to achieve optimal operation, sophisticated models are required to forecast reservoir inflow in both short- and long-horizon times with an acceptable accuracy, particularly for peak flows. In this study, an auto-regressive hybrid model is proposed for long-horizon forecasting of daily reservoir inflow. The model is examined for a one-year horizon forecasting of high-oscillated daily flow time series. First, a Fourier-Series Filtered Autoregressive Integrated Moving Average (FSF-ARIMA) model is applied to forecast linear behavior of daily flow time series. Second, a Recurrent Artificial Neural Network (RANN) model is utilized to forecast FSF-ARIMA model’s residuals. The hybrid model follows the detail of observed flow time variation and forecasted peak flow more accurately than previous models. The proposed model enhances the ability to forecast reservoir inflow, especially in peak flows, compared to previous linear and nonlinear auto-regressive models. The hybrid model has a potential to decrease maximum and average forecasting error by 81% and 80%, respectively. The results of this investigation are useful for stakeholders and water resources managers to schedule optimum operation of multi-purpose reservoirs in controlling floods and generating hydropower.

Reservoir Inflow Prediction by Ensembling Wavelet and Bootstrap Techniques to Multiple Linear Regression Model

In this study, a new hybrid model, bootstrap multiple linear regression (BMLR) is suggested to investigate the potential of bootstrap resampling technique for daily reservoir inflow prediction. The proposed model compares with three other models: Multiple linear regression (MLR), wavelet multiple linear regression (WMLR) and wavelet bootstrap multiple linear regression (WBMLR). River stage data of monsoon season (1st July 2010 to 30 September 2010) from three gauging stations of Chenab river basin are used. In wavelet transformation, input vectors are decomposed using discrete wavelet transformation (DWT) into discrete wavelet components (DWCs). Then suitable DWCs are used to provide input to MLR model to develop WMLR model. Bootstrap technique coupled with MLR model to build up BMLR model. While WBMLR model is the conjunction of suitable DWCs and bootstrap technique to MLR model. Performance indices namely root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe coefficient of efficiency (NSC), and persistence index (CP) are used in study to evaluate the performance of model. Results showed that hybrid model BMLR produce significantly better results on performance indices than other models MLR, WMLR and WBMLR.

A Decomposition-Ensemble Learning Model Based on LSTM Neural Network for Daily Reservoir Inflow Forecasting

Reservoir inflow forecasting is one of the most important issues in delicacy water resource management at reservoirs. Considering the non-linearity and of daily reservoir inflow data, a decomposition-ensemble learning model based on the long short-term memory neural network (DEL-LSTM) is developed in this paper for daily reservoir inflow forecasting. DEL-LSTM employs the logarithmic transformation based preprocessing method to cope with the non-stationary of the inflow data. Then, the ensemble empirical mode decomposition and Fourier spectrum methods are used to decompose the inflow data into the trend term, period term, and random term. For each decomposed term, a regression model based on the LSTM neural network is built to obtain the corresponding prediction result. Finally, the prediction results of the three items are integrated to get the final prediction result. Case studies on the Ankang reservoir in China have been conducted by using data from 1/1/1943 to 12/31/1971. Experimental results illustrated the superiority of the decomposition-ensemble framework and the LSTM neural network in forecasting daily reservoir inflow with big fluctuations. Comparing with some representative models, the proposed DEL-LSTM performs better in prediction accuracy, the average absolute percentage error is reduced to 13.11%, and the normalized mean square error is reduced by 4%, the coefficient of determination was increased by 5%.

Prediction of daily reservoir inflow using atmospheric predictors

Reservoir systems need the forecast of rainfall and inflow on daily time scale for planning of water allocation to different users. Prediction of daily rainfall or daily reservoir inflow is a challenging task in water resource management. This study aims at forecasting the daily reservoir inflow using the projections of atmospheric variables extracted from the global climatic models as input. Daily rainfall series for the future period is simulated using a calibrated weather generator based on generalized linear models. The simulated daily rainfall series are compared with the monthly predictions obtained from local polynomial regression model, and the best correlated daily rainfall simulation is transformed into stream flow using a calibrated and validated soil and water assessment tool to generate the daily inflow series. The modelling procedure was applied to a typical reservoir catchment in India. Diagnostic checks carried out to assess the performance of the rainfall simulations revealed that the simulated series are having the same statistical characteristics as that of the observed series. The simulated inflow was found to be acceptable with respect to the performance indicators evaluated in the study. The methodology adopted is data driven, flexible and easy to implement.

Characterizing Antecedent Conditions Prior to Annual Maximum Flood Events in a High-Elevation Watershed Using Self-Organizing Maps

Abstract Flood frequency estimates are required for many water management and design engineering projects, including dam safety risk management activities. Most studies assume that annual or peak-over-threshold flood events are sampled from a single homogeneous population, an assumption that is sometimes invalid. In this study, we characterize conditions prior to annual maximum flood events in the Taylor Park watershed between water years 1981 and 2016 using historical observations and the self-organizing maps (SOM) algorithm. Inputs to the SOM algorithm include annual maximum daily reservoir inflow, annual maximum snow water equivalent (SWE), SWE melt length, and 4-day antecedent precipitation. Four-day antecedent precipitation is defined as the precipitation accumulated over the 3 days prior to and on the day of the annual maximum event. Results based on a 2 × 2 SOM output map, which represents four flood categories, suggest that 58% of events are the result of snowmelt with a near-negligible contribution from antecedent precipitation, 17% of events are the result of snowmelt combined with large antecedent precipitation, and the remaining 25% of events are the result of snowmelt with no contribution from antecedent precipitation. These results, which highlight the existence of more than one flood mechanism, may have implications for future flood frequency analyses in this watershed and other watersheds within the region.

Auto-Regressive Neural-Network Models for Long Lead-Time Forecasting of Daily Flow

Accurate reservoir-inflow forecasting is especially important for optimizing operation of multi-propose reservoirs that provide hydropower generation, flood control, and water for domestic use and irrigation. There are no previous reports of successful daily flow prediction using a 1-year lead-time. This paper reports successful daily stream flow predictions for that extended lead-time. It presents the first NARX (Nonlinear Auto Regressive model with eXogenous inputs)-type recurrent neural network (NARX-RNN) model used to forecast daily reservoir inflow for a long lead-time. It is the first use of dynamic memory to extend the forecast lead-time beyond the previously reported 1-week lead-times. For new nonlinear NARX-RNN models, we present and test 1600 alternative structures, differing in transfer functions (2), and numbers of inputs (2 to 5), neurons per hidden layer (1 to 20), input delays and output delays. For predicting inflow to the reservoir of the multi-purpose Dez Dam, we contrast accuracies of forecasts from the new models, and from a conventional auto-regressive linear ARIMA model. Based upon normalized root-mean-square error $$ \mathrm{RMSE}/{\overline{Q}}_{obs} $$ the best NARX-RNN has log-sigmoid transfer functions, three inputs, one hidden layers, four neurons in the hidden layer, two input delays, and 10 output delays. That NARX-RNN structure yields $$ \mathrm{RMSE}/{\overline{Q}}_{obs} $$ values of 0.616 in training and 0.678 in forecasting. The proposed model’s forecasting $$ \mathrm{RMSE}/{\overline{Q}}_{obs} $$ is 20% lower than that of the ARIMA model.

Reservoir Inflow Forecast Using a Clustered Random Deep Fusion Approach in the Three Gorges Reservoir, China

Reservoir inflow forecast plays a crucial part in programming, development, operation, and management of water resource systems. To better reveal the complex properties of daily reservoir inflow, a clustered deep fusion (CDF) approach is proposed in this paper. First, variational mode decomposition (VMD) is used to decompose the daily reservoir inflow series into multiple modes, which are clustered into different sets by fuzzy c-means according to the Xie-Beni index in view of attribute domain. In each cluster, a deep autoencoder model (DAE) is developed for deep representations of the attributes in the deep domain. DAE outputs are finally fused at the synthesis domain into the forecasting results using random forest (RF). In this way, the inflow time series may be successively observed in the attribute domain, deep domain, and synthesis domain, which results in a clearer understanding of reservoir inflow trend. The present approach is modeled and evaluated using historical data collected from the Three Gorges Reservoir, China. For comparison, two kinds of learning patterns—deep learning (VMD-DAE-RF and DAE) and shallow learning (feed-forward neural network, least-squares support regression, and RF)—are applied to the same case. The results indicate that the proposed CDF model outperforms all comparison models in terms of mean absolute percentage error (6.174%), root mean-square error (1,077.428 m3/s), and correlation coefficient criteria (0.987). Thus, it is concluded that deep learning in the cluster fusion architecture is more promising.

Adaptation Strategy to Mitigate the Impact of Climate Change on Water Resources in Arid and Semi-Arid Regions: a Case Study

Climate change and drought phenomena impacts have become a growing concern for water resources engineers and policy makers, mainly in arid and semi-arid areas. This study aims to contribute to the development of a decision support tool to prepare water resources managers and planners for climate change adaptation. The Hydrologiska Byråns Vattenbalansavdelning (The Water Balance Department of the Hydrological Bureau) hydrologic model was used to define the boundary conditions for the reservoir capacity yield model comprising daily reservoir inflow from a representative example watershed with the size of 14,924 km2 into a reservoir with the capacity of 6.80 Gm3. The reservoir capacity yield model was used to simulate variability in climate change-induced differences in reservoir capacity needs and performance (operational probability of failure, resilience, and vulnerability). Owing to the future precipitation reduction and potential evapotranspiration increase during the worst case scenario (−40% precipitation and +30% potential evapotranspiration), substantial reductions in streamflow of between −56% and −58% are anticipated for the dry and wet seasons, respectively. Furthermore, model simulations recommend that as a result of future climatic conditions, the reservoir operational probability of failure would generally increase due to declined reservoir inflow. The study developed preparedness plans to combat the consequences of climate change and drought.

Deep Feature Learning Architectures for Daily Reservoir Inflow Forecasting

Inflow forecasting applies data supports for the operations and managements of reservoirs. To better accommodate the sophisticated characteristics of the daily reservoir inflow, two deep feature learning architectures, i.e., deep restricted Boltzmann machine (DRBM) and stack Autoencoder (SAE), respectively, are introduced in this paper. This study sheds light on the application of deep learning architectures for daily reservoir inflow forecasting, which has been attracting much attention in various areas for its ability to extract and learn useful features from a large number of data. Evaluations are made comparing the basic feed forward neural network (FFNN), the autoregressive integrated moving average (ARIMA), and two categories deep neural networks (DNNs) constructed by the integrations the FFNN with two deep feature learning architectures, named DRBM-based NN and stack SAE-based NN, respectively. Two daily inflow series of the Three Gorges reservoir (1/1/2000–31/12/2014) and the Gezhouba reservoir (1/1/1992–31/12/2014), China, are applied for four modeling exercises, respectively. The results show that, the two DNN models overwhelm the FFNN and the ARIMA models in terms of mean absolute percentage error, normalized root-mean-square error, and threshold statistic criteria.

Development of an optimal reservoir pumping operation for adaptation to climate change

Optimization of operation rule curve of Layang reservoir located in southern part of peninsular Malaysia under climate change uncertainties has been presented in this study. Downscaled climate data were incorporated in a lumped rainfall-runoff model to project daily reservoir inflow, which was then used to determine the reservoir operation rule curves to minimize the operation cost. The results reveal that climatic change will cause a rise of temperature in the range of 1.5-2.9°C, but decrease in rainfall in most of the months in the end of this century which will casue a change in the seasonal pattern of inflow to reservoir. Comparison of historical and model generated operation costs indicates that annual savings of 23% and 33% is possible with optimized reservoir operation rule curves. Assessment of the performance of the optimized operation curve under climate change scenarios shows that it will be able to cope with the changing pattern of reservoir inflow with proper adjustment. It is expected that the method presented in this paper to derive pumping operation curves to optimize the total volume of water to be pumped from various sources to reservoir can be useful for reservoir operators in the context of climate change.

Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models

Summary Inflow forecasting applies data supports for the operations and managements of reservoirs. A multiscale deep feature learning (MDFL) method with hybrid models is proposed in this paper to deal with the daily reservoir inflow forecasting. Ensemble empirical mode decomposition and Fourier spectrum are first employed to extract multiscale (trend, period and random) features, which are then represented by three deep belief networks (DBNs), respectively. The weights of each DBN are subsequently applied to initialize a neural network (D-NN). The outputs of the three-scale D-NNs are finally reconstructed using a sum-up strategy toward the forecasting results. A historical daily inflow series (from 1/1/2000 to 31/12/2012) of the Three Gorges reservoir, China, is investigated by the proposed MDFL with hybrid models. For comparison, four peer models are adopted for the same task. The results show that, the present model overwhelms all the peer models in terms of mean absolute percentage error (MAPE = 11.2896%), normalized root-mean-square error (NRMSE = 0.2292), determination coefficient criteria (R2 = 0.8905), and peak percent threshold statistics (PPTS(5) = 10.0229%). The addressed method integrates the deep framework with multiscale and hybrid observations, and therefore being good at exploring sophisticated natures in the reservoir inflow forecasting.