A Multivariate and Multistage Medium- and Long-Term Streamflow Prediction Based on an Ensemble of Signal Decomposition Techniques with a Deep Learning Network

Sibtain, Muhammad; Li, Xianshan; Saleem, Snoober

doi:10.1155/2020/8828664

Cited by 20 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, LSTM was proposed as an innovative form of RNN to solve the issues faced by the RNN. By utilizing a framework of gates and cell states, long-term dependencies, can be preserved in LSTM (Sibtain et al, 2020).…”

Section: Extreme Gradient Boostingmentioning

confidence: 99%

Improving Multivariate Runoff Prediction Through Multistage Novel Hybrid Models

Sibtain,

Li,

et al. 2024

Water Resour Manage

View full text Add to dashboard Cite

The exploitation of hydropower provides cleaner, sustainable and cheaper energy contrary to fossil fuels.Therefore, hydropower offers prospects to meet the sustainable development goals of the United Nations.These bene ts motivate this study to develop different models for e cient runoff prediction utilizing multivariate hydro-meteorological data. The techniques employed for this purpose include correlation analysis, time series decomposition, sample entropy (SE), and sequence2sequence (S2S) algorithm with spatio-temporal attention (STAtt). The decomposition techniques include improved complete ensemble empirical mode decomposition with additive noise (ICEEMDAN) and the maxim overlap discrete wavelet transform (MODWT). The ICEEMDAN-STAtt-S2S model reveals the best prediction results over the counterpart hybrid and standalone models in terms of statistical metrics and comparison plots. The surpassed prediction outcomes substantiate the merger of ICEEMDAN and S2S utilizing STAtt for runoff prediction. Moreover, ICEEMDAN-STAtt-S2S offers the potential for reliable prediction of similar applications, including renewable energy, environment monitoring, and energy resources management.

show abstract

Section: Extreme Gradient Boostingmentioning

confidence: 99%

Improving Multivariate Runoff Prediction Through Multistage Novel Hybrid Models

Sibtain,

Li,

et al. 2024

Water Resour Manage

View full text Add to dashboard Cite

show abstract

“…The Sentinel-1 datasets provided information on the flood extent, forest cover, agricultural areas, and land deformation, and these datasets were obtained from the Copernicus Open Access Hub (https://scihub.copernicus.eu/, accessed on 20 August 2022). The atmospheric correction is necessary to generalize the SAR images, which helps reduce SAR data filtering [39,40]. The SAR data underwent preprocessing steps, including the application of orbit files, thermal noise removal, radiometric calibration, removing GRD image noise, atmospheric correction, and terrain Doppler correction [8,41].…”

Section: Sar Data Pre-processing and The Gee Platformmentioning

confidence: 99%

Large-Scale Flood Hazard Monitoring and Impact Assessment on Landscape: Representative Case Study in India

et al. 2023

View full text Add to dashboard Cite

Currently, natural hazards are a significant concern as they contribute to increased vulnerability, environmental degradation, and loss of life, among other consequences. Climate change and human activities are key factors that contribute to various natural hazards such as floods, landslides, droughts, and deforestation. Assam state in India experiences annual floods that significantly impact the local environment. In 2022, the flooding affected approximately 1.9 million people and 2930 villages, resulting in the loss of 54 lives. This study utilized the Google Earth Engine (GEE) cloud-computing platform to investigate the extent of flood inundation and deforestation, analyzing pre-flood and post-flood C band Sentinel-1 GRD datasets. Identifying pre- and post-flood areas was conducted using Landsat 8–9 OLI/TIRS datasets and the modified and normalized difference water index (MNDWI). The districts of Cachar, Kokrajhar, Jorhat, Kamrup, and Dhubri were the most affected by floods and deforestation. The 2022 Assam flood encompassed approximately 24,507.27 km2 of vegetation loss and 33,902.49 km2 of flood inundation out of a total area of 78,438 km2. The most affected areas were the riverine regions, the capital city Dispur, Guwahati, southern parts of Assam, and certain eastern regions. Flood hazards exacerbate environmental degradation and deforestation, making satellite-based information crucial for hazard and disaster management solutions. The findings of this research can contribute to raising awareness, planning, and implementing future disaster management strategies to protect both the environment and human life.

show abstract

“…Furthermore, in recent years, in order to improve the prediction accuracy of ML algorithms, research has been directed toward the development of deep learning models (e.g., one-dimensional Convolutional Neural Networks and Long Short-Term Memory networks [11,12]) and ensemble or hybrid models [13,14]. Fu et al [15] proposed a LSTM-based deep learning model to simulate streamflow in the Kelantan River, Malaysia.…”

Section: Introductionmentioning

confidence: 99%

Runoff Prediction of Irrigated Paddy Areas in Southern China Based on EEMD-LSTM Model

Huang

Yu²,

Luo³

et al. 2023

Water

View full text Add to dashboard Cite

To overcome the difficulty that existing hydrological models cannot accurately simulate hydrological processes with limited information in irrigated paddy areas in southern China, this paper presents a prediction model combining the Ensemble Empirical Mode Decomposition (EEMD) method and the Long Short-Term Memory (LSTM) network. Meteorological factors were set as the multivariate input to the model. Rainfall, regarded as the main variable affecting runoff, was decomposed and reconstructed into a combination of new series with stronger regularity by using the EEMD and K-means algorithm. The LSTM was used to explore the data laws and then to simulate and predict the runoff of the irrigated paddy areas. The Yangshudang (YSD) watershed of the Zhanghe Irrigation System (ZIS) in Hubei Province, China was taken as the study area. Compared with the other models, the results show that the EEMD-LSTM multivariate model had better simulation performance, with an NSE above 0.85. Among them, the R2, NSE, RMSE and RAE of the EEMD-LSTM(3) model were the best, and they were 0.85, 0.86, 1.106 and 0.35, respectively. The prediction accuracy of peak flows was better than other models, as well as the performance of runoff prediction in rainfall and nonrainfall events, while improving the NSE by 0.05, 0.24 and 0.24, respectively, compared with the EEMD-LSTM(1) model. Overall, the EEMD-LSTM multivariations model is suited for simulating and predicting the daily-scale rainfall–runoff process of irrigated paddy areas in southern China. It can provide technical support and help decision making for efficient utilization and management of water resources.

show abstract

A Multivariate and Multistage Medium- and Long-Term Streamflow Prediction Based on an Ensemble of Signal Decomposition Techniques with a Deep Learning Network

Cited by 20 publications

References 43 publications

Improving Multivariate Runoff Prediction Through Multistage Novel Hybrid Models

Improving Multivariate Runoff Prediction Through Multistage Novel Hybrid Models

Large-Scale Flood Hazard Monitoring and Impact Assessment on Landscape: Representative Case Study in India

Runoff Prediction of Irrigated Paddy Areas in Southern China Based on EEMD-LSTM Model

Contact Info

Product

Resources

About