Evaluating the impact of flood inundation with the cloud computing platform over vegetation cover of Ganga Basin during COVID-19

Ghosh, Sukanya; Kumar, Deepak; Kumari, Rina

doi:10.1007/s41324-022-00430-z

Cited by 8 publications

(2 citation statements)

References 45 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Çelik 16 conducted a comparison between the C4.5 and C5.0 algorithms and found that the classification model built using the C5.0 algorithm exhibited lower misclassification rates and higher accuracy. The use of satellite-derived normalized difference vegetation index (NDVI) and EVI enables the assessment of the direct impact of floods on vegetation cover, offering an effective method for studying vegetation coverage 17 , 18 . Additionally, Dai et al 19 demonstrated that the evaluation of the influence of crop residues on vegetation index and vegetation cover estimation could be achieved by comparing enhancement values and vertical values using a 2-m pixel model and a three-dimensional radiative transfer model.…”

Section: Literature Reviewmentioning

confidence: 99%

Improved random forest classification model combined with C5.0 algorithm for vegetation feature analysis in non-agricultural environments

Wang

2024

Sci Rep

View full text Add to dashboard Cite

In response to the challenges posed by the high computational complexity and suboptimal classification performance of traditional random forest algorithms when dealing with high-dimensional and noisy non-agricultural vegetation satellite data, this paper proposes an enhanced random forest algorithm based on the C5.0 algorithm. The paper focuses on the Liaohe Plain, selecting two distinct non-agricultural landscape patterns in Shenbei New District and Changtu County as research objects. High-resolution satellite data from GF-2 serves as the experimental dataset. This paper introduces an ensemble feature method based on the bagging concept to improve the original random forest classification model. This method enhances the likelihood of selecting features beneficial to classifying positive class samples, avoiding excessive removal of useful features from negative samples. This approach ensures feature importance and model diversity. The C5.0 algorithm is then employed for feature selection, and the enhanced vegetation index (EVI) is utilized for vegetation coverage estimation. Results indicate that employing a multi-scale parameter selection tool, combined with limited field-measured data, facilitates the identification and classification of plant species in forest landscapes. The C5.0 algorithm effectively selects classification features, minimizing information redundancy. The established object-oriented random forest classification model achieves an impressive accuracy of 94.02% on the aerial imagery for forest classification dataset, with EVI-based vegetation coverage estimation demonstrating high accuracy. In experiments on the same test set, the proposed algorithm attains an average accuracy of 90.20%, outperforming common model algorithms such as bidirectional encoder representation from transformer, FastText, and convolutional neural network, which achieve average accuracies ranging from 84.41 to 88.33% in identifying non-agricultural artificial habitat vegetation features. The proposed algorithm exhibits a competitive edge compared to other algorithms. These research findings contribute scientific evidence for protecting agricultural ecosystems and restoring agricultural ecosystem biodiversity.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Improved random forest classification model combined with C5.0 algorithm for vegetation feature analysis in non-agricultural environments

Wang

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…So far, the interactions between floods and the COVID-19 pandemic have been studied in terms of flood management (Laksmi et al 2020 ; Aji et al 2021 ; Tripathy et al 2021 ; Izumi et al 2022 ; Tiwari et al 2022 ; Turay 2022 ), impact on human communities (Aura et al 2020 ; Sadique and Kamruzzaman 2021 ) or environmental impact (Ghosh et al 2022 ), flood risk perception (Mondino et al 2020 ; Zinda et al 2022 ), and disaster mitigation education (Suharini et al 2020 ). The number of studies regarding the impact of floods on COVID-19 infection rates is rather low (Quigley et al 2020 ; Han and He 2021 ; Mavroulis et al 2021a , b ).…”

Section: Introductionmentioning

confidence: 99%

Exploring the links between flood events and the COVID-19 infection cases in Romania in the new multi-hazard-prone era

Albulescu

2023

Nat Hazards

View full text Add to dashboard Cite

The occurrence of flood events amid the COVID-19 pandemic represents a prominent part of the emerging multi-hazard landscape, as floods are one of the most frequent and destructive natural hazards. This spatial and temporal overlap of hydrological and epidemiological hazards translates into compounded negative effects, causing a shift in the hazard management paradigm, in which hazard interaction takes centre stage. This paper calls into question whether the river flood events that occurred during the COVID-19 pandemic in Romania and the way that they were managed had an impact on the infection with the SARS-CoV-2 virus at county scale. To this end, hazard management data concerning the flood events that were severe enough to impose the evacuation of the population were corroborated with COVID-19 confirmed cases data. A definite link between the flood events and the dynamics of COVID-19 cases registered in the selected counties is difficult to identify, but the analysis shows that all flood events were followed by various size increases in the COVID-19 confirmed cases at the end of the incubation time range. The findings are critically interpreted by providing viral load and social-related contexts, allowing a proper understanding of the interactions between concurrent hazards.

show abstract

Impact Assessment of Flood on Agricultural Land Using Cloud-Based Computing Platform in Kosi River Basin, North Bihar, India

Kumar,

Dutta

et al. 2023

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

Evaluating the impact of flood inundation with the cloud computing platform over vegetation cover of Ganga Basin during COVID-19

Cited by 8 publications

References 45 publications

Improved random forest classification model combined with C5.0 algorithm for vegetation feature analysis in non-agricultural environments

Improved random forest classification model combined with C5.0 algorithm for vegetation feature analysis in non-agricultural environments

Exploring the links between flood events and the COVID-19 infection cases in Romania in the new multi-hazard-prone era

Impact Assessment of Flood on Agricultural Land Using Cloud-Based Computing Platform in Kosi River Basin, North Bihar, India

Contact Info

Product

Resources

About