A comparative evaluation of state-of-the-art ensemble learning algorithms for land cover classification using WorldView-2, Sentinel-2 and ROSIS imagery

Çölkesen, İsmail; Öztürk, Muhammed Yusuf

doi:10.1007/s12517-022-10243-x

Cited by 16 publications

(1 citation statement)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extraction of algal bloom is possible with spectral indices viz., Algal Blooms Detection Index (ABDI), Floating Algae Index (FAI), Surface Algal Blooms Index (SABI), and Adjusted Floating Algae Index (AFAI). Object-based and pixel-based machine learning algorithms automate algal bloom prediction with high accuracy; pixel-based algorithms are more reliable and accurate [22].…”

Section: Introductionmentioning

confidence: 99%

Mapping Phytoplankton and Algal Blooms With a Novel Multisensor Water Index

Mishra,

Mishra

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Multispectral Satellite Imageries (MSI) are strong enough to delineate features of interest by suppressing others. The water index is a method applied to delineate the water features by combining the multispectral band images. This research proposes a novel index for extracting water features from multi-sensor MSIs named Multi Sensor Water Index (MSWI). The proposed index, along with existing indices, is applied on Landsat-8 OLI imageries, a comparative analysis is done, and it is found that the proposed index is outperforming with 99.77% accuracy. The proposed index was validated on other sensors, such as a series of Landsat (5, 7, 8, and 9), Sentinel-2, Resourcesat, and Modis satellite imagery, by mapping water features successfully. Further, the proposed index maps marine pollution by discriminating phytoplankton and algal bloom from the water feature. It is observed that the increase in phytoplankton or algal bloom is the result of eutrophication. The blooming of phytoplankton and algae is on the surface of the water. Thus, it causes shading at the bottom of the marine ecosystem and negatively impacts the growth of seagrasses, dissolved oxygen levels, fish suffocation, water properties, and other bottom habitats. The three test sites, viz., lake Villarrica, lake Okeechobee and the Atlantic Ocean, have been considered to study increasing phytoplankton and algal bloom. The proposed index successfully discriminates the phytoplankton and algal bloom from the water features.

show abstract

Section: Introductionmentioning

confidence: 99%

Mapping Phytoplankton and Algal Blooms With a Novel Multisensor Water Index

Mishra,

Mishra

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

Comparative evaluation of performances of algae indices, pixel- and object-based machine learning algorithms in mapping floating algal blooms using Sentinel-2 imagery

Colkesen,

Ozturk,

Altuntas

2024

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

One of the main threats to freshwater resources is pollution from anthropogenic activities such as rapid urbanization and excessive agricultural nutrient runoff. Remote sensing technologies have been effectively used in monitoring and mapping rapid changes in the marine environment and assessing the overall health of freshwater ecosystems. The main goal of this study is to comparatively evaluate the performance of index-based and classification-based approaches in mapping dense floating algal blooms observed in Lake Burdur using Sentinel-2 imagery. For index-based mapping, algae-specific indices, namely the Floating Algae Index (FAI), Adjusted Floating Algae Index, Surface Algal Blooms Index (SABI), and Algal Blooms Detection Index (ABDI), were used. At the same time, pixel- and object-based Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Long Short-Term Memory Network (LSTM) were utilized for classification-based algal mapping. For this purpose, seven Sentinel-2 images, selected through time series analysis performed on the Google Earth Engine platform, were used as the primary dataset in the application. The results show that high-density floating algae formations can be detected over 99% by both indices and classification-based approaches, whereas pixel-based classification is more successful in mapping low-density algal blooms. When two-class thematic maps representing water and floating algae classes were considered, the maps produced by index-based FAI using an appropriate threshold value and the classification-based RF algorithm reached an overall accuracy of over 99%. The highest algae density in the lake was observed on July 13, 2021, and was determined to be effective in ~ 45 km2 of the lake’s surface.

show abstract