Application of soft computing techniques in coastal study – A review

Dwarakish, G. S.; Nithyapriya, B.

doi:10.1016/j.joes.2016.06.004

Cited by 28 publications

(5 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TNDVI (Transformed Normalized Difference Vegetation Index) is the transformation of NDVI so as not to work with negative values. TNDVI indicates a slightly better correlation than the original one between the amount of green biomass found in a considered pixel [32]. Its formula is: ) + 0.5…”

Section: Methodsmentioning

confidence: 99%

Monitoring of Forty Years of Agricultural Expansion in the Oum Er Rbia Valley (Morocco). The Use of Google Earth Engine Compared to Sentinel Application Platform

Adell¹,

Ja²,

Soria³

2021

Preprint

View full text Add to dashboard Cite

Agriculture in Morocco has been extensive until the middle of the 20th century due to the distribution of rainfall and the availability of water. In the middle of the last century hydraulic works were built that allowed the transition to intensive agriculture by the increase of irrigated areas, allowing that in the territories where there is water for irrigation and the climate allows it, the crops adapt to the demands of the market. The objective of the study is to assess by satellite images the land cover between 1985 and 2020, analyzing the changes in cultivation areas, as well as the changes in desert, sub-desert and forest areas of the Oum Er Rbia hydrological basin in Morocco. Landsat satellite images have been used since 1984 by the US government (Aerospace and Geological Agencies). A series of vegetation indices (NDVI, RVI, TNDVI and EVI) have been used; among which TNDVI (Transformed Normalized Vegetation Index) stands out for its better accuracy, which has allowed us to distinguish vegetation in cultivated and forest areas, as well as arid zones. In addition, the study has compared the use of two methodologies to calculate changes in the coverage of the Earth’s surface, has used local image processing from the Sentinel Application Platform tool and has also used the Google Earth Engine tool. The latter being the most optimal, although at the moment it has great limitations. In both methodologies and in the different indices it has been possible to observe during these 35 years as the cultivated area has increased (related to the availability of water by the construction of reservoirs and canals), how plant cover has improved in forest areas, and a range of variations in arid areas.

show abstract

Section: Methodsmentioning

confidence: 99%

Monitoring of Forty Years of Agricultural Expansion in the Oum Er Rbia Valley (Morocco). The Use of Google Earth Engine Compared to Sentinel Application Platform

Adell¹,

Ja²,

Soria³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Physical shoreline changes can be measured using different remote sensing data and geophysical location systems [42,51,[71][72][73]. Moreover, soft computing techniques can be used on remote sensing data in shoreline mapping to estimate land use (LU) and land cover (LC), which are terms used to describe the use of land for human activities and the physical characteristics of the land surface.…”

Section: Physical Impactsmentioning

confidence: 99%

“…Moreover, soft computing techniques can be used on remote sensing data in shoreline mapping to estimate land use (LU) and land cover (LC), which are terms used to describe the use of land for human activities and the physical characteristics of the land surface. Dwarakish and Nithyapriya [73] conducted a comparison study between conventional and soft computing methods of inundation mapping using remote sensing data, and concluded that support vector machine (SVM) [74] algorithms show promising applications due to their adaptability and learning capacity with limited data. Data that were used to analyze shoreline changes were geomorphology, LU/LC, elevation data, and tide gauges.…”

Section: Physical Impactsmentioning

confidence: 99%

Exploring Key Aspects of Sea Level Rise and Their Implications: An Overview

Elneel,

Zitouni,

Mukhtar

et al. 2024

Water

View full text Add to dashboard Cite

Sea level rise (SLR) is one of the most pressing challenges of climate change and has drawn noticeable research interest over the past few decades. Factors induced by global climate change, such as temperature increase, have resulted in both direct and indirect changes in sea levels at different spatial scales. Various climatic and non-climatic events contribute to sea level changes, posing risks to coastal and low-lying areas. Nevertheless, changes in sea level are not uniformly distributed globally due to several regional factors such as wave actions, storm surge frequencies, and tectonic land movement. The high exposure to those factors increases the vulnerability of subjected areas to SLR impacts. The impacts of events induced by climate change and SLR are reflected in biophysical, socioeconomic, and environmental aspects. Different indicator-based and model-based approaches are used to assess coastal areas’ vulnerabilities, response to impacts, and implementation of adaptation and mitigation measures. Various studies have been conducted to project future SLR impacts and evaluate implemented protection and adaptation approaches, aiding policymakers in planning effective adaptation and mitigation measures to reduce damage. This paper provides an overview of SLR and its key elements, encompassing contributing factors, impacts, and mitigation and adaptation measures, featuring a dedicated section on the Arabian Gulf, a semi-enclosed sea.

show abstract

“…Neural networks have to be trained to establish a relation between the input and output given during training. A good data set is required to draw better classification accuracy [37].…”

Section: Softcomputing Techniques For Hyperspectral Image Classificationmentioning

confidence: 99%

Hyperspectral Image Classification using Softcomputing Techniques: A Review

Rajitha¹,

Bhargavi²,

Jyothi³

2018

IJCA

View full text Add to dashboard Cite

Hyperspectral image classification plays a major role in remote image analysis. Hyperspectral images provide both spatial details of airborne imagery and spectral resolution for spectroscopic analysis and narrow band analysis techniques. Available satellite sensors like Hyperion, HyMap and AVIRIS are good sources of hyperspectral data. Applications of hyperspectral images are remote sensing, seed viability study, biotechnology, environmental monitoring, medical diagnose, food, pharmaceuticals and so on. Traditional techniques are difficult to deal with hyperspectral images directly, because hyperspectral images have continuous narrow spectral bands. To overcome this, hyperspectral image classification can be done using different softcomputing techniques. Softcomputing is an emerging field consisting of Fuzzy Logic, Neural Network and Genetic Algorithms. This paper reviews how hyperspectral image classification can be done using different softcomputing techniques.

show abstract

Application of soft computing techniques in coastal study – A review

Cited by 28 publications

References 56 publications

Monitoring of Forty Years of Agricultural Expansion in the Oum Er Rbia Valley (Morocco). The Use of Google Earth Engine Compared to Sentinel Application Platform

Monitoring of Forty Years of Agricultural Expansion in the Oum Er Rbia Valley (Morocco). The Use of Google Earth Engine Compared to Sentinel Application Platform

Exploring Key Aspects of Sea Level Rise and Their Implications: An Overview

Hyperspectral Image Classification using Softcomputing Techniques: A Review

Contact Info

Product

Resources

About