Towards a Paradigm Shift on Mapping Muddy Waters with Sentinel-2 Using Machine Learning

Psychalas, Christos; Vlachos, Konstantinos; Moumtzidou, Anastasia; Gialampoukidis, Ilias; Vrochidis, Stefanos; Kompatsiaris, Ioannis

doi:10.3390/su151813441

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They found that bands 5, 6, 7, and 8A contributed the most to this end. In another study by Psychalas et al [105], their results showed significant contributions from bands 4, 5, 8A, 11, and 12 for identifying highly turbid waters in reservoirs. Specifically, the contributions from bands 11 and 12 were attributed to the variety of land classes and cloud formations present in their remote sensing data.…”

Section: Bands and Indices Selectionmentioning

confidence: 91%

Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel‐2 Remote Sensing Data: A Generalizability Analysis

Costa Rocha,

Oliveira Santos,

Thé

et al. 2024

Preprint

View full text Add to dashboard Cite

Turbidity is an important indicator of water quality in hydrology. More traditional ways to monitor turbidity can provide reliable results. However, they are prone to human error, have elevated costs, and lack real-time monitoring capacity. Addressing these hindrances, in this work we combine spectral bands and indices from Sentinel-2 with several machine learning paradigms, namely XGBoost, Random Forests, GMDH, Support Vector Regression, k-Nearest Neighbors and Least Absolute Shrinkage and Selection Operator to model turbidity, using data from twelve monitoring stations encompassing the Mississippi River, USA. Results show that considering the individual monitoring stations, the ML paradigms for turbidity modeling were satisfactory at locations with a larger range and standard deviation values, achieving a mean R2 value of 59.5%. Tree-based models were the best overall approach, often ranking as the best or second-best performing model. When all the samples from the monitoring stations were used, the XGBoost provided superior output for turbidity modeling, reaching an R2 equal to 75.7%. A comprehensive comparison with the literature found values showed that the models implemented using this study’s methodology could provide competitive results, deeming it as an alternative for turbidity modeling from remote sensing data.

show abstract

Section: Bands and Indices Selectionmentioning

confidence: 91%

Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel‐2 Remote Sensing Data: A Generalizability Analysis

Costa Rocha,

Oliveira Santos,

Thé

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Lake total suspended matter retrieval by wind speed: A machine learning model trained by time-series satellite imagery

Noori,

Mohajeri,

Mehraein

et al. 2024

Ecological Informatics

View full text Add to dashboard Cite

Land Use/Cover Classification of Large Conservation Areas Using a Ground-Linked High-Resolution Unmanned Aerial Vehicle

Mangewa,

Ndakidemi,

Alward

et al. 2024

Resources

View full text Add to dashboard Cite

High-resolution remote sensing platforms are crucial to map land use/cover (LULC) types. Unmanned aerial vehicle (UAV) technology has been widely used in the northern hemisphere, addressing the challenges facing low- to medium-resolution satellite platforms. This study establishes the scalability of Sentinel-2 LULC classification with ground-linked UAV orthoimages to large African ecosystems, particularly the Burunge Wildlife Management Area in Tanzania. It involved UAV flights in 19 ground-surveyed plots followed by upscaling orthoimages to a 10 m × 10 m resolution to guide Sentinel-2 LULC classification. The results were compared with unguided Sentinel-2 using the best classifier (random forest, RFC) compared to support vector machines (SVMs) and maximum likelihood classification (MLC). The guided classification approach, with an overall accuracy (OA) of 94% and a kappa coefficient (k) of 0.92, outperformed the unguided classification approach (OA = 90%; k = 0.87). It registered grasslands (55.2%) as a major vegetated class, followed by woodlands (7.6%) and shrublands (4.7%). The unguided approach registered grasslands (43.3%), followed by shrublands (27.4%) and woodlands (1.7%). Powerful ground-linked UAV-based training samples and RFC improved the performance. The area size, heterogeneity, pre-UAV flight ground data, and UAV-based woody plant encroachment detection contribute to the study’s novelty. The findings are useful in conservation planning and rangelands management. Thus, they are recommended for similar conservation areas.

show abstract

Towards a Paradigm Shift on Mapping Muddy Waters with Sentinel-2 Using Machine Learning

Cited by 3 publications

References 37 publications

Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel‐2 Remote Sensing Data: A Generalizability Analysis

Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel‐2 Remote Sensing Data: A Generalizability Analysis

Lake total suspended matter retrieval by wind speed: A machine learning model trained by time-series satellite imagery

Land Use/Cover Classification of Large Conservation Areas Using a Ground-Linked High-Resolution Unmanned Aerial Vehicle

Contact Info

Product

Resources

About