An Artificial Neural Network Model for Estimating the Flood in Tehri Region of Uttarakhand Using Rainfall Data

Gandhi, B. G. Rajeev; Kumar, Dilip; Yadav, Hira Lal

doi:10.1007/978-981-15-4032-5_43

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rajeev Gandhi et al. (2020) developed a three‐hidden‐layer artificial neural network model for flood forecasting, and the results proved that the model was satisfactory for flood forecasting. These existing studies have demonstrated the strong capability of CNN, but there are two major gaps in the literature.…”

Section: Introductionmentioning

confidence: 99%

“…In comparative analysis to evaluate the performance of the 1D-CNN related to the extreme learning machine (ELM) model, the results showed that the ELM model can be an alternative to the 1D-CNN model for high-precision runoff prediction in the world's mountainous regions. Rajeev Gandhi et al (2020) developed a three-hidden-layer artificial neural network model for flood forecasting, and the results proved that the model was satisfactory for flood forecasting. These existing studies have demonstrated the strong capability of CNN, but there are two major gaps in the literature.…”

mentioning

confidence: 95%

“…Among the DL algorithms, convolutional neural network (CNN) is one of the best algorithms in terms of dealing with image-like data thanks to the convolutional and downsampling operations. CNNs have recently been applied to many problems in the field of hydrological and water resources engineering (Chen et al, 2020;Chong et al, 2020;Elmorsy et al, 2022;Hhlein et al, 2020;Hussain et al, 2020;Nagasato et al, 2021;Panahi et al, 2020;Park et al, 2019;Rajeev Gandhi et al, 2020;Shu et al, 2021;J. H. Wang et al, 2019).…”

mentioning

confidence: 99%

See 2 more Smart Citations

Concentration Field Estimation on Effluent Mixing and Transport With a Parameter‐Based Field Reconstruction Convolutional Neural Network and Random Forests

Yan

Cao

Yin

et al. 2023

Water Resources Research

View full text Add to dashboard Cite

Estimating contaminant transport is of great importance for water quality assessment and water resources management. Due to the complex mechanisms and three-dimensional (3D) variability, estimating the concentration field of effluent mixing and transport is a challenging task. It is not practical to establish spatiotemporally high-resolution observation networks for monitoring contaminant mixing phenomena; thus, it is meaningful to develop mathematical approaches to predict the relevant processes. However, the applications of analytical or simplified numerical models are typically restricted to comparably simple cases. Sophisticated numerical models based on the 3D computational fluid dynamics (CFD) technique can provide accurate predictions, but they are computationally expensive and require high-level 3D CFD expertise, impeding their widespread usage.The recent developments in machine learning (ML) techniques and computing resources have provided a new avenue for investigating complex physical processes. Deep learning (DL), which is a subset of ML, has recently been applied to various water-related problems, and has been demonstrated to be a powerful tool for the community of water resources research. Thus, DL is potentially a promising candidate tool for modeling effluent mixing and transport.To assess the suitability of DL in modeling effluent mixing and transport, we focus on a classic example: the mixing and transport of multiple buoyant effluents discharged vertically into stagnant ambient water. This is a very important example for effluent mixing and transport. First, investigating this phenomenon itself is crucial for environmental assessment and water resources research, especially because wastewater effluents from

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 95%