An Ensemble Mode Decomposition Combined with SVR-RF Model for Prediction of Groundwater Level: The Case of Eastern Rwandan Aquifers

Kombo, Omar Haji; Kumaran, Santhi; Ndashimye, Emmanuel; Bovim, Alastair

doi:10.1007/978-3-031-09073-8_27

Cited by 1 publication

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study is one of the first applications to enhance the frequency mode separation and improve GWL prediction accuracy by decomposing the highest frequency IMF1 component obtained through EEMD into sub‐bands using VMD algorithm. Several studies have demonstrated the utility of VMD and EMD in improving the performance of ML models for hydrological processes (Ahmadi et al, 2023; Feng et al, 2020; Kombo et al, 2022; Seo et al, 2018; Wen et al, 2019). For example, Seo et al (2018) showed the enhanced accuracy of the ELM algorithm with VMD in daily rainfall‐runoff modelling, while Kombo et al (2022) integrated EEMD with the SVR‐RF model to forecast groundwater table variations, achieving notable advancements in accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…Several studies have demonstrated the utility of VMD and EMD in improving the performance of ML models for hydrological processes (Ahmadi et al, 2023; Feng et al, 2020; Kombo et al, 2022; Seo et al, 2018; Wen et al, 2019). For example, Seo et al (2018) showed the enhanced accuracy of the ELM algorithm with VMD in daily rainfall‐runoff modelling, while Kombo et al (2022) integrated EEMD with the SVR‐RF model to forecast groundwater table variations, achieving notable advancements in accuracy. These studies highlight the significant role of preprocessing techniques in advancing hydrological modelling capabilities, contributing to a deeper understanding and more accurate evaluation of hydrological processes.…”

Section: Discussionmentioning

confidence: 99%

Section: Performance Of Hybrid Models In Gwl Forecastingmentioning

confidence: 99%

“…Kombo et al (2022) integrated EEMD with the SVR-RF model to forecast groundwater table variations, achieving notable advancements in accuracy. These studies highlight the significant role of preprocessing techniques in advancing hydrological modelling capabilities, contributing to a deeper understanding and more accurate evaluation of hydrological processes.The modelling of hydrological processes that govern basin systems poses a challenge and demands substantial time due to the intricate nature of interconnected factors.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Hybrid machine learning models for groundwater level prediction in a snow‐dominated region: An evaluation of EEMD, VMD and EWT decomposition techniques

Gezici,

Katipoğlu,

Şengül

2024

Hydrological Processes

View full text Add to dashboard Cite

Water scarcity is a pressing issue, intensified by factors such as population growth and industrialization. Hence, it is crucial to monitor, conserve and analyse groundwater resources, which are essential sources of clean and usable water. This study examines changes in groundwater levels (GWLs) in northeastern Turkey's mountainous and snow‐covered area. The primary objective is to assess the effectiveness of integrated machine learning models, specifically, the extreme learning machine (ELM) technique combined with signal decomposition techniques such as ensemble empirical mode decomposition (EEMD), variational mode decomposition (VMD) and empirical wavelet transform (EWT) for monthly GWL prediction models. Seventy percent of the accessible data is allocated for training, while 30% is designated for testing. A correlation matrix involving precipitation, temperature, relative humidity and GWL parameters is generated with inputs that possess significant correlations being selected, such as GWLt−1, GWLt−2, RHt, RHt−1 and RHt−2. To evaluate model results, various metrics, including mean squared error, mean absolute error, mean absolute percentage error, mean bias error, bias factor, determination coefficient, Nash‐Sutcliffe efficiency, as well as tools such as box plots, Taylor diagrams and radar charts, are utilized to compare outcomes during the interpretation phase. The results of the analyses show that applying data decomposition methods such as EEMD, VMD and EWT significantly improves the performance of the ELM algorithm in predicting GWLs. VMD‐ELM is the most accurate for GWL forecasting among the approaches examined. The R2 values of the most successful models established in the two wells are 0.993 and 0.905. The outcomes of this research hold significance for decision‐makers and policymakers as it offers informative insights into aquifer surveillance, irrigation strategizing and efficient administration of water resources.

show abstract