A combined model based on secondary decomposition and the optimized support vector machine algorithm for regional rainfall forecasting

Mulla S., Pande C.B., Singh S.K.

In this study, the monthly rainfall time series forecasting was investigated based on the effectiveness of the Seasonal Auto Regressive Integrated Moving Average with EXogenous variables (SARIMAX) model in the coastal area of Phaltan, taluka. Rainfall forecasting is so much helpful to crops and disaster planning and development during monsoon season. The performance of model was assessed using various statistical metrics such as coefficient of determination (R2), and root mean squared error (RMSE). In this study, we have used multi-dimensional components as inputs in the SARIMAX model for prediction of monthly rainfall. In this work, we have tested two models such as first SARIMAX model orders are (1, 0, 1) and (0, 1, 0, 12), while the second model had orders of (1, 1, 1) and (1, 1, 1, 12). The results of two models have been compared and the performance of model show that the first model outperformed on the rainfall forecasting. The RMSE and R2 performance are 54.54 and 0.91 of first model, respectively, while the second model accuracy is RMSE of 71.12 and an R2 of 0.81. Hence best SARIMAX model has been used for forecasting of monthly time series rainfall from 2020 to 2025 for study area. The results of rainfall data analysis of climatic data are valuable for understanding the variations in global climate change.

Guangyi Z., Zeng X., Zheng G., Gao Z., Ji R., Zeng Y., Wang P., Lu C.

Abstract Tool wear during robotic polishing affects material removal rates and surface roughness, leading to erratic and inconsistent polishing quality. Therefore, a method that can predict the tool state is needed to replace the robot end tool in time. In this paper, based on the cutting-edge Neural Ordinary Differential Equations (Neural ODE) and BP Neural Network Optimization based on Genetic Algorithm (BP-GA), we propose a method to identify the tool state during robotic machining: Firstly, a new training method of Neural ODE is proposed to avoid the model from falling into poor stationary points, and then on this basis, Neural ODE is utilized to predict the changes of vibration signals during robot machining; Secondly, the predicted vibration signals of the tool are processed using Variable Modal Decomposition (VMD) method to extract the eigen kurtosis index and envelope entropy of the modal function as the vibration signal eigenvectors, and compare them with the traditional vibration signal eigenvectors. Finally, the predicted tool states were identified using BP-GA, and numerical experiments yielded an F1 score of 91.76% and an accuracy of 96.55% for model identification.

Li H., Zhang X., Sun S., Wen Y., Yin Q.

AbstractEnhancing flood forecasting accuracy, promoting rational water resource utilization and management, and mitigating river disasters all hinge on the crucial role of improving the accuracy of daily flow prediction. The coupled model of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Sample Entropy (SE), and Bidirectional Long Short-Term Memory (BiLSTM) demonstrates higher stability when faced with nonlinear and non-stationary data, stronger adaptability to various types and lengths of time series data by utilizing sample entropy, and significant advantages in processing sequential data through the BiLSTM network. In this study, in the context of predicting daily flow at the Huayuankou Hydrological Station in the lower reaches of the Yellow River, a coupled CEEMDAN–SE–BiLSTM model was developed and utilized. The results showed that the CEEMDAN–SE–BiLSTM coupled model achieved the utmost accuracy in prediction and optimal fitting performance. Compared with the CEEMDAN–SE–LSTM, CEEMDAN–BiLSTM, and BiLSTM coupled models, the root mean square error (RMSE) of this model is reduced by 42.77, 182.02, and 193.71, respectively; the mean absolute error (MAE) is reduced by 37.62, 118.60, and 126.67, respectively; and the coefficient of determination (R2) is increased by 0.0208, 0.1265, 0.1381.

Ghaderpour E., Dadkhah H., Dabiri H., Bozzano F., Scarascia Mugnozza G., Mazzanti P.

Li J., Wang J., Zhang H., Li Z.

Wind speed forecasting plays a crucial role in enhancing the operating efficiency of wind power systems for generating electric power. Currently, a substantial number of approaches have been developed to improve the precision of wind speed forecasting. However, owing to the instability and fluctuation of wind speed, many models ignore the deficiencies of the individual models and data preprocessing strategies, which leads to results with poor accuracy. In this study, a novel forecasting system that combines data denoising methods, traditional forecasting algorithms, and a combination optimization approach to predict wind speed is proposed. To analyze the training and testing dataset, this study uses the 10-min original wind speed dataset from a wind farm in Penglai, China. Based on the results of three comparative numerical simulations and the discussion of the proposed forecasting system, it is revealed that the developed model performs more effectively than other models. Therefore, in this study we conclude that the proposed combined forecasting system is an efficient and promising technique that provides precise results for predicting wind speed in the short term, and it could be employed for further applications in energy systems.

Zaghloul M.S., Ghaderpour E., Dastour H., Farjad B., Gupta A., Eum H., Achari G., Hassan Q.K.

Changes in water resources within basins can significantly impact ecosystems, agriculture, and biodiversity, among others. Basins in northern Canada have a cold climate, and the recent changes in climate can have a profound impact on water resources in these basins. Therefore, it is crucial to study long term trends in water flow as well as their influential factors, such as temperature and precipitation. This study focused on analyzing long term trends in water flow across the Athabasca River Basin (ARB) and Peace River Basin (PRB). Long term trends in temperature and precipitation within these basins were also studied. Water flow data from 18 hydrometric stations provided by Water Survey of Canada were analyzed using the Mann-Kendall test and Sen’s slope. In addition, hybrid climate data provided by Alberta Environment and Parks at approximately 10 km spatial resolution were analyzed for the ARB and its surrounding regions during 1950–2019. Trend analysis was performed on the water flow data on monthly, seasonal, and annual scales, and the results were cross-checked with trends in temperature and precipitation and land use and land cover data. The overall temperature across the basins has been increasing since 1950, while precipitation showed an insignificant decrease during this period. Winter water flow in the upper ARB has been slowly and steadily increasing since 1956 because of the rising temperatures and the subsequent slow melting of snowpacks/glaciers. The warm season flows in the middle and lower subregions declined up to 1981, then started to show an increasing trend. The middle and lower ARB exhibited a rapid increase in warm-season water flow since 2015. A similar trend change was also observed in the PRB. The gradual increase in water flow observed in the recent decades may continue by the mid-century, which is beneficial for agriculture, forestry, fishery, and industry. However, climate and land cover changes may alter the trend of water flow in the future; therefore, it is important to have a proper management plan for water usage in the next decades.

Zhang P., Sun W., Xiao P., Yao W., Liu G.

In the context of climate change, extreme rainfall events have greatly increased the frequency and risk of flash floods in the Yellow River Basin. In this study, the heavy rainfall and flash flood processes were studied as a system. Taking the driving factors of the heavy rainfall causing the flash floods as the main focus, the key factors of the heavy rainfall causing typical flash flood processes were identified, and the driving mechanism by which the heavy rainfall caused flash floods was revealed. Through comparative analysis of the rainfall related to 13 floods with peak discharges of greater than 2000 m3/s since measurements began at Baijiachuan hydrological station, it was found that different rainfall factors played a major driving role in the different flood factors. The factor that had the largest impact on the peak discharge was the average rainfall intensity; the factor that had the largest impact on the flood volume was the rainfall duration; and the factor that had the largest impact on the sediment volume was the maximum 1 h rainfall. The ecological construction of soil and water conservation projects on the Loess Plateau has had obvious peak-cutting and sediment-reducing effects on the flood processes driven by medium- and low-intensity rainfall events, but for high-intensity flash floods, the flood-reducing and sediment-reducing effects of these projects have been smaller. Therefore, despite the background of continuous ecological improvement on the Loess Plateau, the possibility of floods with large sediment loads occurring in the middle reaches of the Yellow River still exists.

Lian L.

Abstract Accurate forecasting of runoff is necessary for water resources management. However, the runoff time series consists of complex nonlinear and non-stationary characteristics, which makes forecasting difficult. To contribute towards improved forecasting accuracy, a novel combination model based on complementary ensemble empirical mode decomposition (CEEMD) for runoff forecasting is proposed and applied in this paper. Firstly, the original runoff series is decomposed into a limited number of intrinsic mode functions (IMFs) and one residual based on CEEMD, which makes the runoff time series stationary. Then, approximate entropy is introduced to judge the complexity of each IMF and residual. According to the calculation results of approximate entropy, the high complexity components are predicted by Gaussian process regression (GPR), the medium complexity components are predicted by support vector machine (SVM), and the low complexity components are predicted by autoregressive integrated moving average model (ARIMA). The advantages of each forecasting model are used to forecast the appropriate components. In order to solve the problem that the forecasting performance of GPR and SVM is affected by their parameters, an improved fireworks algorithm (IFWA) is proposed to optimize the parameters of two models. Finally, the final forecasting result is obtained by adding the forecasted values of each component. The runoff data collected from the Manasi River, China is chosen as the research object. Compared with some state-of-the-art forecasting models, the comparison result curve between the forecasted value and actual value of runoff, the forecasting error, the histogram of the forecasting error distribution, the performance indicators and related statistical indicators show that the developed forecasting model has higher prediction accuracy and is able to reflect the change laws of runoff correctly.

Pei Y., Liu C., Lou R.

Using observational data to determine the edges of the sources is an important task in the interpretation of potential field data. Extracting the edges of deep and shallow bodies effectively is the key to correctly understanding the underground structure. Based on the good multi-scale decomposition ability of two-dimensional variational mode decomposition (2D-VMD) and the outstanding shape analysis capability of mathematical morphology (MM), a new multi-scale edge detection method for potential field data is proposed. We propose using the variance of this morphological filter as a basis for selecting the optimal structural element (SE) scale. By establishing theoretical models and comparing the results of our method with those of traditional edge detection methods, the proposed method is shown to be effective at detecting edges within potential field data. Taking the Hanmiao area of Chifeng city, Inner Mongolia, China, as an example, 1:50000 aeromagnetic data are processed and analysed by this method. The physical properties of the rocks in the study area are also discussed. The results of theoretical calculations and real data processing show that this method can accurately extract the edges of the sources at different scales. And the real data processing results show that this method is suitable for the identification of structural faults.

Nabipour N., Dehghani M., Mosavi A., Shamshirband S.

Hydrological drought forecasting plays a substantial role in water resources management. Hydrological drought highly affects the water allocation and hydropower generation. In this research, short term hydrological drought forecasted based on the hybridized of novel nature-inspired optimization algorithms and Artificial Neural Networks (ANN). For this purpose, the Standardized Hydrological Drought Index (SHDI) and the Standardized Precipitation Index (SPI) were calculated in one, three, and six aggregated months. Then, three states where proposed for SHDI forecasting, and 36 input-output combinations were extracted based on the cross-correlation analysis. In the next step, newly proposed optimization algorithms, including Grasshopper Optimization Algorithm (GOA), Salp Swarm algorithm (SSA), Biogeography-based optimization (BBO), and Particle Swarm Optimization (PSO) hybridized with the ANN were utilized for SHDI forecasting and the results compared to the conventional ANN. Results indicated that the hybridized model outperformed compared to the conventional ANN. PSO performed better than the other optimization algorithms. The best models forecasted SHDI1 with R2 = 0.68 and RMSE = 0.58, SHDI3 with R 2 = 0.81 and RMSE = 0.45 and SHDI6 with R 2 = 0.82 and RMSE = 0.40.

Shaker Reddy P.C., Sureshbabu A.

Aims & Background: India is a country which has exemplary climate circumstances comprising of different seasons and topographical conditions like high temperatures, cold atmosphere, and drought, heavy rainfall seasonal wise. These utmost varieties in climate make us exact weather prediction is a challenging task. Majority people of the country depend on agriculture. Farmers require climate information to decide the planting. Weather prediction turns into an orientation in farming sector to deciding the start of the planting season and furthermore quality and amount of their harvesting. One of the variables are influencing agriculture is rainfall. Objectives & Methods: The main goal of this project is early and proper rainfall forecasting, that helpful to people who live in regions which are inclined natural calamities such as floods and it helps agriculturists for decision making in their crop and water management using big data analytics which produces high in terms of profit and production for farmers. In this project, we proposed an advanced automated framework called Enhanced Multiple Linear Regression Model (EMLRM) with MapReduce algorithm and Hadoop file system. We used climate data from IMD (Indian Metrological Department, Hyderabad) in 1901 to 2002 period. Results: Our experimental outcomes demonstrate that the proposed model forecasting the rainfall with better accuracy compared with other existing models. Conclusion: The results of the analysis will help the farmers to adopt effective modeling approach by anticipating long-term seasonal rainfall.

He X., Luo J., Zuo G., Xie J.

Accurate and reliable runoff forecasting plays an increasingly important role in the optimal management of water resources. To improve the prediction accuracy, a hybrid model based on variational mode decomposition (VMD) and deep neural networks (DNN), referred to as VMD-DNN, is proposed to perform daily runoff forecasting. First, VMD is applied to decompose the original runoff series into multiple intrinsic mode functions (IMFs), each with a relatively local frequency range. Second, predicted models of decomposed IMFs are established by learning the deep feature values of the DNN. Finally, the ensemble forecasting result is formulated by summing the prediction sub-results of the modelled IMFs. The proposed model is demonstrated using daily runoff series data from the Zhangjiashan Hydrological Station in Jing River, China. To fully illustrate the feasibility and superiority of this approach, the VMD-DNN hybrid model was compared with EMD-DNN, EEMD-DNN, and multi-scale feature extraction -based VMD-DNN, EMD-DNN and EEMD-DNN. The results reveal that the proposed hybrid VMD-DNN model produces the best performance based on the Nash-Sutcliffe efficiency (NSE = 0.95), root mean square error (RMSE = 9.92) and mean absolute error (MAE = 3.82) values. Thus the proposed hybrid VMD-DNN model is a promising new method for daily runoff forecasting.

Seo Y., Kim S., Singh V.

Accurate modeling for nonlinear and nonstationary rainfall-runoff processes is essential for performing hydrologic practices effectively. This paper proposes two hybrid machine learning models (MLMs) coupled with variational mode decomposition (VMD) to enhance the accuracy for daily rainfall-runoff modeling. These hybrid MLMs consist of VMD-based extreme learning machine (VMD-ELM) and VMD-based least squares support vector regression (VMD-LSSVR). The VMD is employed to decompose original input and target time series into sub-time series called intrinsic mode functions (IMFs). The ELM and LSSVR models are selected for developing daily rainfall-runoff models utilizing the IMFs as inputs. The performances of VMD-ELM and VMD-LSSVR models are evaluated utilizing efficiency and effectiveness indices. Their performances are also compared with those of VMD-based artificial neural network (VMD-ANN), discrete wavelet transform (DWT)-based MLMs (DWT-ELM, DWT-LSSVR, and DWT-ANN) and single MLMs (ELM, LSSVR, and ANN). As a result, the VMD-based MLMs provide better accuracy compared with the single MLMs and yield slightly better performance than the DWT-based MLMs. Among all models, the VMD-ELM and VMD-LSSVR models achieve the best performance in daily rainfall-runoff modeling with respect to efficiency and effectiveness. Therefore, the VMD-ELM and VMD-LSSVR models can be an alternative tool for reliable and accurate daily rainfall-runoff modeling.

Bagirov A.M., Mahmood A.

Accurate rainfall prediction is a challenging task. It is especially challenging in Australia where the climate is highly variable. Australia’s climatic zones range from high rainfall tropical regions in the north to the driest desert region in the interior. The performance of prediction models may vary depending on climatic conditions. It is, therefore, important to assess and compare the performance of these models in different climatic zones. This paper examines the performance of data driven models such as the support vector machines for regression, the multiple linear regression, the k-nearest neighbors and the artificial neural networks for monthly rainfall prediction in Australia depending on climatic conditions. Rainfall data with five meteorological variables over the period of 1970–2014 from 24 geographically diverse weather stations are used for this purpose. The prediction performance of each model was evaluated by comparing observed and predicted rainfall using various measures for prediction accuracy.

Alizadeh F., Farajzadeh J.

Abstract The present study aimed to develop a hybrid model to predict the rainfall time series of Urmia Lake watershed. For this purpose, a model based on discrete wavelet transform, ARIMAX and least squares support vector machine (LSSVM) (W-S-LSSVM) was developed. The proposed model was designed to handle linear, nonlinear and seasonality of rainfall time series. In the proposed model, time series were decomposed into sub-series (approximation (a) and details (d)). Next, the sub-series were predicted separately. In the proposed model, sub-series were fed into SARIMAX to be predicted. The residual of predicted sub-series (error) of the rainfall time series was then fed into LSSVM to predict the residual components. Then, all predicted values were aggregated to rebuild the predicted time series. In order to compare results, first a classic modeling was performed by LSSVM. Later, wavelet-based LSSVM was used to capture the peak values of rainfall. Results revealed that Daubechies 4 and decomposition level 4 (db(4,4)) led to the best outcome. Due to the performance of db(4,4), it was selected to be applied in the proposed model. Based on results, it was observed that the W-S-LSSVM's performance was improved in comparison with other models.