Analysis of Lakes Over the Period of Time Through Image Processing

Ghosal, Sattam; Karmakar, Abhishek; Sahay, Pushkar; Das, Uma

doi:10.1007/978-981-15-8610-1_18

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two reservoirs near this site-the Manton Dam with a volume of 13.3 gigalitres (GL) is less than 1 km from the site, and the Darwin River Dam which can hold up to 259.0 GL of water is in the 10 km range from the site. The CEDA site located in Utah state of the USA is about 20 km from the Great Salt Lake, one of the largest saltwater lakes in the world (Ghosal et al 2021). The P053 site is located in Whitewater, Montana, USA.…”

Section: Feature Importance Analysismentioning

confidence: 99%

Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches

Gao

Chen

et al. 2022

J Geod

View full text Add to dashboard Cite

Global navigation satellite system (GNSS) site coordinate time series provides essential data for geodynamic and geophysical studies, realisation of a regional or global geodetic reference frames, and crustal deformation research. The coordinate time series has been conventionally modelled by least squares (LS) fitting with harmonic functions, alongside many other analysis methods. As a key limitation, the traditional modelling approaches simply use the functions of time variable, despite good knowledge of various underlying physical mechanisms responsible for the site displacements. This paper examines the use of machine learning (ML) models to reflect the effects or residential effects of physical variables related to Sun and the Moon ephemerides, polar motion, temperature, atmospheric pressure, and hydrology on the site displacements. To form the ML problem, these variables are constructed as the input vector of each ML training sample, while the vertical displacement of a GNSS site is regarded as the output value. In the evaluation experiments, three ML approaches, namely the gradient boosting decision tree (GBDT) approach, long short-term memory (LSTM) approach, and support vector machine (SVM) approach, are introduced and evaluated with the time series datasets collected from 9 GNSS sites over the period of 13 years. The results indicate that all three approaches achieve similar fitting precision in the range of 3–5 mm in the vertical displacement component, which is an improvement in over 30% with respect to the traditional LS fitting precision in the range of 4–7 mm. The prediction of the vertical time series with the three ML approaches shows the precision in the range of 4–7 mm over the future 24- month period. The results also indicate the relative importance of different physical features causing the displacements of each site. Overall, ML approaches demonstrate better performance and effectiveness in modelling and prediction of GNSS time series, thus impacting maintenance of geodetic reference frames, geodynamics, geophysics, and crustal deformation analysis.

show abstract

Section: Feature Importance Analysismentioning

confidence: 99%

Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches

Gao

Chen

et al. 2022

J Geod

View full text Add to dashboard Cite

show abstract

“…The perception about the reduction and colour of the water during the dry season shows that citizens, even in remote areas, feel the climate change and are among the most affected. The report of plants on the lamina water signals a probable change in and the colouration is influenced by the vegetables, animals, minerals, tannins and algae in these surface water bodies such as lakes (Ghosal et al 2020;Abel et al 2021).…”

Section: Analysis Of the Interviews With Community Citizensmentioning

confidence: 99%

Sustainability Perception of Lotic and Lentic Ecosystems in the Amazon Basin Through the Lens of a Local Community

Veras

Vidal

Barros

et al. 2021

Sustainable Policies and Practices in Energy, Environment and Health Research

View full text Add to dashboard Cite

In the context of hydric resources distribution, Brazil holds the highest hydric availability on the planet, being responsible for almost all the total average change of water bed stream in South America. Brazil has an unequal distribution of its resources, specifically considering the Amazon basin, located in a region with low population density. Therefore, to study the lotic ecosystem is relevant, particularly in the Amazon region, to provide knowledge on lakes comprehension, i.e., naturally formed depression that stores freshwater, and hydrological conditions that play a key role in interactions with terrestrial processes, essential to sustain life through the quality of water in many igarapés (streams), i.e., small rivers. This ecosystem is part of the Earth's bloodstream, vital to individuals survival, as well as for nature balance, food and raw material provision, playing a crucial role in remote communities, namely those located in the Amazon Basin.Water is the second most important component of the Earth, in addition to air, used as irrigation for crops, cooling equipment, industrial chemical processes, city growth, hygiene, as geopolitical divider and means of connectivity, navigation, leisure and recreation (

show abstract

Analysis of Lakes Over the Period of Time Through Image Processing

Cited by 2 publications

References 2 publications

Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches

Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches

Sustainability Perception of Lotic and Lentic Ecosystems in the Amazon Basin Through the Lens of a Local Community

Contact Info

Product

Resources

About