The Applicability of LSTM-KNN Model for Real-Time Flood Forecasting in Different Climate Zones in China

Use of one-dimensional CNN for input data size reduction in LSTM for improved computational efficiency and accuracy in hourly rainfall-runoff modeling

A deep learning architecture, denoted as CNNsLSTM, is proposed for hourly rainfall-runoff modeling in this study. The architecture involves a serial coupling of the one-dimensional convolutional neural network (1D-CNN) and the long short-term memory (LSTM) network. In the proposed framework, multiple layers of the CNN component process long-term hourly meteorological time series data, while the LSTM component handles short-term meteorological time series data and utilizes the extracted features from the 1D-CNN. In order to demonstrate the effectiveness of the proposed approach, it was implemented for hourly rainfall-runoff modeling in the Ishikari River watershed, Japan. A meteorological dataset, including precipitation, air temperature, evapotranspiration, longwave radiation, and shortwave radiation, was utilized as input. The results of the proposed approach (CNNsLSTM) were compared with those of previously proposed deep learning approaches used in hydrologic modeling, such as 1D-CNN, LSTM with only hourly inputs (LSTMwHour), a parallel architecture of 1D-CNN and LSTM (CNNpLSTM), and the LSTM architecture, which uses both daily and hourly input data (LSTMwDpH). Meteorological and runoff datasets were separated into training, validation, and test periods to train the deep learning model without overfitting, and evaluate the model with an independent dataset. The proposed approach clearly improved estimation accuracy compared to previously utilized deep learning approaches in rainfall = runoff modeling. In comparison with the observed flows, the median values of the Nash-Sutcliffe efficiency for the test period were 0.455-0.469 for 1D-CNN, 0.639-0.656 for CNNpLSTM, 0.745 for LSTMwHour, 0.831 for LSTMwDpH, and 0.865-0.873 for the proposed CNNsLSTM. Furthermore, the proposed CNNsLSTM reduced the median root mean square error (RMSE) of 1D-CNN by 50.2%-51.4%, CNNpLSTM by 37.4%-40.8%, LSTMwHour by 27.3%-29.5%, and LSTMwDpH by 10.6%-13.4%. Particularly, the proposed CNNsLSTM improved the estimations for high flows (≧75th percentile) and peak flows (≧95th percentile). The computational speed of LSTMwDpH is the fastest among the five architectures. Although the computation speed of CNNsLSTM is slower than LSTMwDpH's, it is still 6.9-7.9 times faster than that of LSTMwHour. Therefore, the proposed CNNsLSTM would be an effective approach for flood management and hydraulic structure design, mainly under climate change conditions that require estimating hourly river flows using meteorological datasets.

The development of dissolved oxygen forecast model using hybrid machine learning algorithm with hydro-meteorological variables

Dissolved oxygen (DO) forecasting is essential for aquatic managers responsible for maintaining ecosystem health and the management of water bodies affected by water quality parameters. This paper aims to forecast dissolved oxygen (DO) concentration using a multivariate adaptive regression spline (MARS) hybrid model coupled with maximum overlap discrete wavelet transformation (MODWT) as a feature decomposition approach for Surma River water using a set of water quality hydro-meteorological variables. The proposed hybrid model is compared with numerous machine learning methods, namely Bayesian ridge regression (BNR), k-nearest neighbourhood (KNN), kernel ridge regression (KRR), random forest (RF), and support vector regression (SVR). The investigational results show that the proposed model of MODWT-MARS has a better prediction than the comparing benchmark models and individual standalone counter parts. The result shows that the hybrid algorithms (i.e. MODWT-MARS) outperformed the other models (r = 0.981, WI = 0.990, RMAE = 2.47%, and MAE = 0.089). This hybrid method may serve to forecast water quality variables with fewer predictor variables.

Improved runoff forecasting based on time-varying model averaging method and deep learning

In order to improve the accuracy and stability of runoff prediction. This study proposed a dynamic model averaging method with Time-varying weight (TV-DMA). Using this method, an integrated prediction model framework for runoff prediction was constructed. The framework determines the main variables suitable for runoff prediction through correlation analysis, and uses TV-DMA and deep learning algorithm to construct an integrated prediction model for runoff. The results demonstrate that the current monthly runoff, the runoff of the previous month, the current monthly temperature, the temperature of the previous month and the current monthly rainfall were the variables suitable for runoff prediction. The results of runoff prediction show that the TV-DMA model has the highest prediction accuracy (with 0.97 Nash-efficiency coefficient (NSE)) and low uncertainty. The interval band of uncertainty was 33.3%-65.5% lower than single model. And the prediction performance of the single model and TV-DMA model in flood season is obviously lower than that in non-flood season. In addition, this study indicate that the current monthly runoff, rainfall and temperature are the important factor affecting the runoff prediction, which should be paid special attention in the runoff prediction.

Neural Structures to Predict River Stages in Heavily Urbanized Catchments

Accurate flow forecasting may support responsible institutions in managing river systems and limiting damages due to high water levels. Machine-learning models are known to describe many nonlinear hydrological phenomena, but up to now, they have mainly provided a single future value with a fixed information structure. This study trains and tests multi-step deep neural networks with different inputs to forecast the water stage of two sub-alpine urbanized catchments. They prove effective for one hour ahead flood stage values and occurrences. Convolutional neural networks (CNNs) perform better when only past information on the water stage is used. Long short-term memory nets (LSTMs) are more suited to exploit the data coming from the rain gauges. Predicting a set of water stages over the following hour rather than just a single future value may help concerned agencies take the most urgent actions. The paper also shows that the architecture developed for one catchment can be adapted to similar ones maintaining high accuracy.

Prediction of Wave Energy Flux in the Bohai Sea through Automated Machine Learning

The rational assessment of regional energy distribution provides a scientific basis for the selection and siting of power generation units. This study, which focused on the Bohai Sea, set 31 research coordinate points in the Bohai sea for assessing the potential/trends of wave energy flux (WEF). We applied a point-to-point time series prediction method which modelled the different geographical coordinate points separately. Subsequently, we evaluated the performance of three traditional machine learning methods and three automated machine learning methods. To estimate WEF, the best model was applied to each research coordinate points, respectively. Then, the WEF was calculated and predicted based on the data of MWP, SWH, and water depth. The results indicate that, for all coordinates in the Bohai Sea, the H2O-AutoML algorithm is superior to the other five algorithms. Gradient boosting machine (GBM), extreme gradient boosting (XGBoost), and stacked ensemble models yielded the best performance out of the H2O algorithms. The significant wave height (SWH), the mean wave period (MWP), and the WEF in the Bohai Sea tended to be concentrated in the center of the sea and dispersed in the nearshore areas. In the year 2000, 2010, 2020, and 2030, the maximum annual average WEF at each research coordinate in the Bohai Sea is around 1.5 kW/m, with a higher flux in autumn and winter. In summary, the results provide ocean parameter characterization for the design and deployment of wave energy harvesting devices. Moreover, the automated machine learning introduced herein has potential for use in more applications in ocean engineering.

Water Level Prediction Model Applying a Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) Method for Flood Prediction

The damage caused by floods is increasing worldwide, and if floods can be predicted, the economic and human losses from floods can be reduced. A key parameter of flooding is water level data, and this paper proposes a water level prediction model using long short-term memory (LSTM) and a gated recurrent unit (GRU). As variables used as input data, meteorological data, including upstream and downstream water level, temperature, humidity, and precipitation, were used. The best results were obtained when the LSTM–GRU-based model and the Automated Synoptic Observing System (ASOS) meteorological data were included in the input data when experiments were performed with various model structures and different input data formats. As a result of the experiment, the mean squared error (MSE) value was 3.92, the Nash–Sutcliffe coefficient of efficiency (NSE) value was 0.942, and the mean absolute error (MAE) value was 2.22, the highest result in all cases. In addition, the test data included the historical maximum water level of 3552.38 cm in the study area, and the maximum water level error was also recorded as 55.49, the lowest result. Through this paper, it was possible to confirm the performance difference according to the composition of the input data and the time series prediction model. In a future study, we plan to implement a flood risk management system that can use the predicted water level to determine the risk of flooding, and evacuate in advance.

The Discharge Forecasting of Multiple Monitoring Station for Humber River by Hybrid LSTM Models

An early warning flood forecasting system that uses machine-learning models can be utilized for saving lives from floods, which are now exacerbated due to climate change. Flood forecasting is carried out by determining the river discharge and water level using hydrologic models at the target sites. If the water level and discharge are forecasted to reach dangerous levels, the flood forecasting system sends warning messages to residents in flood-prone areas. In the past, hybrid Long Short-Term Memory (LSTM) models have been successfully used for the time series forecasting. However, the prediction errors grow exponentially with the forecasting period, making the forecast unreliable as an early warning tool with enough lead time. Therefore, this research aimed to improve the accuracy of flood forecasting models by employing real-time monitoring network datasets and establishing temporal and spatial links between adjacent monitoring stations. We evaluated the performance of the LSTM, the Convolutional Neural Networks LSTM (CNN-LSTM), the Convolutional LSTM (ConvLSTM), and the Spatio-Temporal Attention LSTM (STA-LSTM) models for flood forecasting. The dataset, employed for validation, includes hourly discharge records, from 2012 to 2017, on six stations of the Humber River in the City of Toronto, Canada. Experiments included forecasting for both 6 and 12 h ahead, using discharge data as input for the past 24 h. The STA-LSTM model’s performance was superior to the CNN-LSTM, the ConvLSTM, and the basic LSTM models when the forecast time was longer than 6 h.

LSTM-Based Model for Predicting Inland River Runoff in Arid Region: A Case Study on Yarkant River, Northwest China

Inland river runoff variations in arid regions play a decisive role in maintaining regional ecological stability. Observation data of inland river runoff in arid regions have short time series and imperfect attributes due to limitations in the terrain environment and other factors. These shortages not only restrict the accurate simulation of inland river runoff in arid regions significantly, but also influence scientific evaluation and management of the water resources of a basin in arid regions. In recent years, research and applications of machine learning and in-depth learning technologies in the hydrological field have been developing gradually around the world. However, the simulation accuracy is low, and it often has over-fitting phenomenon in previous studies due to influences of complicated characteristics such as “unsteady runoff”. Fortunately, the circulation layer of Long-Short Term Memory (LSTM) can explore time series information of runoffs deeply to avoid long-term dependence problems. In this study, the LSTM algorithm was introduced and improved based on the in-depth learning theory of artificial intelligence and relevant meteorological factors that were monitored by coupling runoffs. The runoff data of the Yarkant River was chosen for training and test of the LSTM model. The results demonstrated that Mean Absolute Error (MAE) and Root Mean Square error (RMSE) of the LSTM model were 3.633 and 7.337, respectively. This indicates that the prediction effect and accuracy of the LSTM model were significantly better than those of the convolution neural network (CNN), Decision Tree Regressor (DTR) and Random Forest (RF). Comparison of accuracy of different models made the research reliable. Hence, time series data was converted into a problem of supervised learning through LSTM in the present study. The improved LSTM model solved prediction difficulties in runoff data to some extent and it applied to hydrological simulation in arid regions under several climate scenarios. It not only decreased runoff prediction uncertainty brought by heterogeneity of climate models and increased inland river runoff prediction accuracy in arid regions, but also provided references to basin water resource management in arid regions. In particular, the LSTM model provides an effective solution to runoff simulation in regions with limited data.

Plausible Precipitation Trends over the Large River Basins of Pakistan in Twenty First Century

Inter alia, inter-annual and spatial variability of climate, particularly rainfall, shall trigger frequent floods and droughts in Pakistan. Subsequently, a higher proportion of the country’s population will be exposed to water-related challenges. This study analyzes and projects the long-term spatio-temporal changes in precipitation using the data from 2005 to 2099 across two large river basins of Pakistan. The plausible precipitation data to detect the projected trends seems inevitable to study the future water resources in the region. For, policy decisions taken in the wake of such studies can be instrumental in mitigating climate change impacts and shape water management strategies. Outputs of the Coupled Model Intercomparison Project 5 (CMIP5) climate models for the two forcing scenarios of RCP 4.5 and RCP 8.5 have been used for the synthesis of projected precipitation data. The projected precipitation data have been synthesized in three steps (1) dividing the area in different climate zones based on the similar precipitation statistics (2) selection of climate models in each climate zone in a way to shrink the ensemble to a few representative members, conserving the model spread and accounting for model similarity in a baseline period of 1971–2004 and the projected period of 2005–2099 and (3) combining the selected model’s data in mean and median combinations. The future precipitation trends were detected and quantified, for the set of four scenarios. The spatial distribution of the precipitation trends was mapped for better understanding. All the scenarios produced consistent increasing or decreasing trends. Significant declining trends were projected in the warm wet season at 0.05% significance level and the increasing trends were projected in cold dry, cold wet and warm dry seasons. Framework developed to project climate change trends during the study can be replicated for any other area. The study therefore can be of interest for researchers working on climate impact modeling.

Capabilities of deep learning models on learning physical relationships: Case of rainfall-runoff modeling with LSTM

This study investigates the relationships which deep learning methods can identify between the input and output data. As a case study, rainfall-runoff modeling in a snow-dominated watershed by means of a long short-term memory (LSTM) network is selected. Daily precipitation and mean air temperature were used as model input to estimate daily flow discharge. After model training and verification, two experimental simulations were conducted with hypothetical inputs instead of observed meteorological data to clarify the response of the trained model to the inputs. The first numerical experiment showed that even without input precipitation, the trained model generated flow discharge, particularly winter low flow and high flow during the snow melting period. The effects of warmer and colder conditions on the flow discharge were also replicated by the trained model without precipitation. Additionally, the model reflected only 17-39% of the total precipitation mass during the snow accumulation period in the total annual flow discharge, revealing a strong lack of water mass conservation. The results of this study indicated that a deep learning method may not properly learn the explicit physical relationships between input and target variables, although they are still capable of maintaining strong goodness-of-fit results.

Development and Assessment of Water-Level Prediction Models for Small Reservoirs Using a Deep Learning Algorithm

In this study, we aimed to develop and assess a hydrological model using a deep learning algorithm for improved water management. Single-output long short-term memory (LSTM SO) and encoder-decoder long short-term memory (LSTM ED) models were developed, and their performances were compared using different input variables. We used water-level and rainfall data from 2018 to 2020 in the Takayama Reservoir (Nara Prefecture, Japan) to train, test, and assess both models. The root-mean-squared error and Nash–Sutcliffe efficiency were estimated to compare the model performances. The results showed that the LSTM ED model had better accuracy. Analysis of water levels and water-level changes presented better results than the analysis of water levels. However, the accuracy of the model was significantly lower when predicting water levels outside the range of the training datasets. Within this range, the developed model could be used for water management to reduce the risk of downstream flooding, while ensuring sufficient water storage for irrigation, because of its ability to determine an appropriate amount of water for release from the reservoir before rainfall events.

Bagging Machine Learning Algorithms: A Generic Computing Framework Based on Machine-Learning Methods for Regional Rainfall Forecasting in Upstate New York

Regional rainfall forecasting is an important issue in hydrology and meteorology. Machine learning algorithms especially deep learning methods have emerged as a part of prediction tools for regional rainfall forecasting. This paper aims to design and implement a generic computing framework that can assemble a variety of machine learning algorithms as computational engines for regional rainfall forecasting in Upstate New York. The algorithms that have been bagged in the computing framework include the classical algorithms and the state-of-the-art deep learning algorithms, such as K-Nearest Neighbors, Support Vector Machine, Deep Neural Network, Wide Neural Network, Deep and Wide Neural Network, Reservoir Computing, and Long Short Term Memory methods. Through the experimental results and the performance comparisons of these various engines, we have observed that the SVM- and KNN-based method are outstanding models over other models in classification while DWNN- and KNN-based methods outstrip other models in regression, particularly those prevailing deep-learning-based methods, for handling uncertain and complex climatic data for precipitation forecasting. Meanwhile, the normalization methods such as Z-score and Minmax are also integrated into the generic computing framework for the investigation and evaluation of their impacts on machine learning models.

Rainfall and runoff time-series trend analysis using LSTM recurrent neural network and wavelet neural network with satellite-based meteorological data: case study of Nzoia hydrologic basin

This study compares LSTM neural network and wavelet neural network (WNN) for spatio-temporal prediction of rainfall and runoff time-series trends in scarcely gauged hydrologic basins. Using long-term in situ observed data for 30 years (1980–2009) from ten rain gauge stations and three discharge measurement stations, the rainfall and runoff trends in the Nzoia River basin are predicted through satellite-based meteorological data comprising of: precipitation, mean temperature, relative humidity, wind speed and solar radiation. The prediction modelling was carried out in three sub-basins corresponding to the three discharge stations. LSTM and WNN were implemented with the same deep learning topological structure consisting of 4 hidden layers, each with 30 neurons. In the prediction of the basin runoff with the five meteorological parameters using LSTM and WNN, both models performed well with respective R2 values of 0.8967 and 0.8820. The MAE and RMSE measures for LSTM and WNN predictions ranged between 11–13 m3/s for the mean monthly runoff prediction. With the satellite-based meteorological data, LSTM predicted the mean monthly rainfall within the basin with R2 = 0.8610 as compared to R2 = 0.7825 using WNN. The MAE for mean monthly rainfall trend prediction was between 9 and 11 mm, while the RMSE varied between 15 and 21 mm. The performance of the models improved with increase in the number of input parameters, which corresponded to the size of the sub-basin. In terms of the computational time, both models converged at the lowest RMSE at nearly the same number of epochs, with WNN taking slightly longer to attain the minimum RMSE. The study shows that in hydrologic basins with scarce meteorological and hydrological monitoring networks, the use satellite-based meteorological data in deep learning neural network models are suitable for spatial and temporal analysis of rainfall and runoff trends.

Prediction of River Stage Using Multistep-Ahead Machine Learning Techniques for a Tidal River of Taiwan

Time-series prediction of a river stage during typhoons or storms is essential for flood control or flood disaster prevention. Data-driven models using machine learning (ML) techniques have become an attractive and effective approach to modeling and analyzing river stage dynamics. However, relatively new ML techniques, such as the light gradient boosting machine regression (LGBMR), have rarely been applied to predict the river stage in a tidal river. In this study, data-driven ML models were developed under a multistep-ahead prediction framework and evaluated for river stage modeling. Four ML techniques, namely support vector regression (SVR), random forest regression (RFR), multilayer perceptron regression (MLPR), and LGBMR, were employed to establish data-driven ML models with Bayesian optimization. The models were applied to simulate river stage hydrographs of the tidal reach of the Lan-Yang River Basin in Northeastern Taiwan. Historical measurements of rainfall, river stages, and tidal levels were collected from 2004 to 2017 and used for training and validation of the four models. Four scenarios were used to investigate the effect of the combinations of input variables on river stage predictions. The results indicated that (1) the tidal level at a previous stage significantly affected the prediction results; (2) the LGBMR model achieves more favorable prediction performance than the SVR, RFR, and MLPR models; and (3) the LGBMR model could efficiently and accurately predict the 1–6-h river stage in the tidal river. This study provides an extensive and insightful comparison of four data-driven ML models for river stage forecasting that can be helpful for model selection and flood mitigation.

Research on Runoff Simulations Using Deep-Learning Methods

Runoff simulations are of great significance to the planning management of water resources. Here, we discussed the influence of the model component, model parameters and model input on runoff modeling, taking Hanjiang River Basin as the research area. Convolution kernel and attention mechanism were introduced into an LSTM network, and a new data-driven model Conv-TALSTM was developed. The model parameters were analyzed based on the Conv-TALSTM, and the results suggested that the optimal parameters were greatly affected by the correlation between the input data and output data. We compared the performance of Conv-TALSTM and variant models (TALSTM, Conv-LSTM, LSTM), and found that Conv-TALSTM can reproduce high flow more accurately. Moreover, the results were comparable when the model was trained with meteorological or hydrological variables, whereas the peak values with hydrological data were closer to the observations. When the two datasets were combined, the performance of the model was better. Additionally, Conv-TALSTM was also compared with an ANN (artificial neural network) and Wetspa (a distributed model for Water and Energy Transfer between Soil, Plants and Atmosphere), which verified the advantages of Conv-TALSTM in peak simulations. This study provides a direction for improving the accuracy, simplifying model structure and shortening calculation time in runoff simulations.

Application of Machine Learning Techniques to Delineate Homogeneous Climate Zones in River Basins of Pakistan for Hydro-Climatic Change Impact Studies

Climatic data archives, including grid-based remote-sensing and general circulation model (GCM) data, are used to identify future climate change trends. The performances of climate models vary in regions with spatio-temporal climatic heterogeneities because of uncertainties in model equations, anthropogenic forcing or climate variability. Hence, GCMs should be selected from climatically homogeneous zones. This study presents a framework for selecting GCMs and detecting future climate change trends after regionalizing the Indus river sub-basins in three basic steps: (1) regionalization of large river basins, based on spatial climate homogeneities, for four seasons using different machine learning algorithms and daily gridded precipitation data for 1975–2004; (2) selection of GCMs in each homogeneous climate region based on performance to simulate past climate and its temporal distribution pattern; (3) detecting future precipitation change trends using projected data (2006–2099) from the selected model for two future scenarios. The comprehensive framework, subject to some limitations and assumptions, provides divisional boundaries for the climatic zones in the study area, suitable GCMs for climate change impact projections for adaptation studies and spatially mapped precipitation change trend projections for four seasons. Thus, the importance of machine learning techniques for different types of analyses and managing long-term data is highlighted.