Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning

The barriers for the development of continuous monitoring of Suspended Sediment Concentration (SSC) in channels/rivers include costs and technological gaps but this paper shows that a solution is feasible by: (i) using readily available high-resolution images; (ii) transforming the images into image...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Scientific reports Ročník 10; číslo 1; s. 8589
Hlavní autoři: Ghorbani, Mohammad Ali, Khatibi, Rahman, Singh, Vijay P., Kahya, Ercan, Ruskeepää, Heikki, Saggi, Mandeep Kaur, Sivakumar, Bellie, Kim, Sungwon, Salmasi, Farzin, Hasanpour Kashani, Mahsa, Samadianfard, Saeed, Shahabi, Mahmood, Jani, Rasoul
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Nature Publishing Group UK 22.05.2020
Nature Publishing Group
Témata:
639/166/986
704/242
Environmental monitoring
Humanities and Social Sciences
Learning algorithms
Machine learning
multidisciplinary
Observational learning
Prediction models
Rivers
Science
Science (multidisciplinary)
Sediment concentration
Suspended sediments
ISSN:2045-2322, 2045-2322
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The barriers for the development of continuous monitoring of Suspended Sediment Concentration (SSC) in channels/rivers include costs and technological gaps but this paper shows that a solution is feasible by: (i) using readily available high-resolution images; (ii) transforming the images into image analytics to form a modelling dataset; and (iii) constructing predictive models by learning inherent correlation between observed SSC values and their image analytics. High-resolution images were taken of water containing a series of SSC values using an exploratory flume. Machine learning is processed by dividing the dataset into training and testing sets and the paper uses the following models: Generalized Linear Machine (GLM) and Distributed Random Forest (DRF). Results show that each model is capable of reliable predictions but the errors at higher SSC are not fully explained by modelling alone. Here we offer sufficient evidence for the feasibility of a continuous SSC monitoring capability in channels before the next phase of the study with the goal of producing practice guidelines.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-64707-9