Secchi Depth Retrieval in Oligotrophic to Eutrophic Chilean Lakes Using Open Access Satellite-Derived Products DOI Creative Commons
Daniela Rivera-Ruiz, José Luis Arumí, Mario Lillo‐Saavedra

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(22), P. 4327 - 4327

Published: Nov. 20, 2024

The application of the Multispectral Instrument (MSI) aboard Sentinel-2A/B constellation for assessing water quality in Chilean lakes represents an emerging area research, particularly environmental monitoring optically complex bodies. Similarly, atmospheric correction processors applied to aquatic environments, such as Case 2 Networks (C2RCC-Nets), are notably underrepresented. This study evaluates capability C2RCC-Nets using different neural networks—Case-2 Regional/Coast Color (C2RCC), C2X-Extreme (C2X), and C2X-Complex (C2XC)—to estimate Secchi depth Lake Lanalhue (eutrophic), Villarrica (oligo-mesotrophic), Panguipulli (oligotrophic). evaluation used statistical methods Spearman’s correlation normalized error metrics (nRMSE, nMAE, nbias) assess agreement between satellite-derived data situ measurements. C2XC demonstrated best fit Lanalhue, with nRMSE = 33.13%, nMAE 23.51%, nbias 8.57%, relation median ground truth values. In Villarrica, network displayed a moderate (rs 0.618) metrics, 24.67% 20.67%, 4.21%. oligotrophic Panguipulli, no relationship was observed estimated measured values, which could be related fact that selected networks were developed very case waters. These findings highlight need methodological advancements processing products Chile’s optical types, clear Nonetheless, this underscores model-specific calibration C2RCC-Nets, types trophic states may require tailored training ranges inherent properties.

Language: Английский

Investigation of Water Quality in Izmir Bay With Remote Sensing Techniques Using NDCI on Google Earth Engine Platform DOI Creative Commons
Osman Salih Yılmaz, Uğur Acar, Füsun Balık Şanlı

et al.

Transactions in GIS, Journal Year: 2025, Volume and Issue: 29(1)

Published: Jan. 12, 2025

ABSTRACT In this study, the effects of algal blooms occurring in Izmir Bay summer 2024 on marine ecosystems were investigated using remote sensing techniques Google Earth Engine platform. The normalized difference chlorophyll index (NDCI) was calculated from January to end September and chlorophyll‐a density analyzed. Additionally, an NDCI time series analysis conducted between 2018 at designated points. values, which fluctuated narrowly until 2022, showed a sharp increase 2024. NDCI, vary −0.4 0.2 up 0.8 toward months, indicate that are occurring, concentrated critical areas such as Karşıyaka, Bayraklı, Alsancak Port. These findings revealed connection sudden fish deaths bay during blooms, well deterioration water quality.

Language: Английский

Citations

0
The need for advancing algal bloom forecasting using remote sensing and modeling: Progress and future directions DOI Creative Commons
Cassia Brocca Caballero, Vitor S. Martins, Rejane S. Paulino

et al.

Ecological Indicators, Journal Year: 2025, Volume and Issue: 172, P. 113244 - 113244

Published: Feb. 21, 2025

Language: Английский

Citations

0
New perspectives on ice forcing in continental arc magma plumbing systems DOI Creative Commons
Brad S. Singer, Pablo Moreno-Yaeger, Meredith Townsend

et al.

Journal of Volcanology and Geothermal Research, Journal Year: 2024, Volume and Issue: unknown, P. 108187 - 108187

Published: Sept. 1, 2024

Language: Английский

Citations

3
Spatio-Temporal Dynamics Coupling between Land Use/Cover Change and Water Quality in Dongjiang Lake Watershed Using Satellite Remote Sensing DOI Creative Commons
Yang Song, Xiaoming Li,

Lanbo Feng

et al.

Land, Journal Year: 2024, Volume and Issue: 13(6), P. 861 - 861

Published: June 15, 2024

With rapid social and economic development, land use/land cover change (LUCC) has intensified with serious impacts on water quality in the watershed. In this study, we took Dongjiang Lake watershed as study area obtained measured data parameters from watershed’s monitoring stations. Based Landsat-5, Landsat-8, or Sentinel-2 remote sensing for multiple periods per year between 1992 2022, sensitive satellite bands band combinations of each parameter were determined. The Random Forest method was used to classify use types into six categories, proportion type calculated. We established machine learning regression models polynomial WQI dependent variable independent variable. Accuracy test results showed that, among them, quadratic cubic model grassland, forest land, construction unused its variables best coupling LUCC. This study’s provide a scientific basis spatial temporal changes caused by LUCC

Language: Английский

Citations

2
Leveraging Machine Learning and Remote Sensing for Water Quality Analysis in Lake Ranco, Southern Chile DOI Creative Commons
Lien Rodríguez‐López, Lisandra Bravo Alvarez, Iongel Duran-Llacer

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(18), P. 3401 - 3401

Published: Sept. 13, 2024

This study examines the dynamics of limnological parameters a South American lake located in southern Chile with objective predicting chlorophyll-a levels, which are key indicator algal biomass and water quality, by integrating combined remote sensing machine learning techniques. Employing four advanced models (recurrent neural network (RNNs), long short-term memory (LSTM), recurrent gate unit (GRU), temporal convolutional (TCNs)), research focuses on estimation concentrations at three sampling stations within Lake Ranco. The data span from 1987 to 2020 used different cases: using only situ (Case 1), meteorological 2), situ, satellite Landsat Sentinel missions 3). In all cases, each model shows robust performance, promising results concentrations. Among these models, LSTM stands out as most effective, best metrics estimation, performance was Case 1, R2 = 0.89, an RSME 0.32 µg/L, MAE 1.25 µg/L MSE 0.25 (µg/L)2, consistently outperforming others according static for validation. finding underscores effectiveness capturing complex relationships inherent dataset. However, increasing dataset 3 better TCNs (R2 0.96; 0.33 (µg/L)2; RMSE 0.13 µg/L; 0.06 µg/L). successful application algorithms emphasizes their potential elucidate Ranco, region Chile. These not contribute deeper understanding ecosystem but also highlight utility computational techniques environmental management.

Language: Английский

Citations

1
Secchi Depth Retrieval in Oligotrophic to Eutrophic Chilean Lakes Using Open Access Satellite-Derived Products DOI Creative Commons
Daniela Rivera-Ruiz, José Luis Arumí, Mario Lillo‐Saavedra

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(22), P. 4327 - 4327

Published: Nov. 20, 2024

The application of the Multispectral Instrument (MSI) aboard Sentinel-2A/B constellation for assessing water quality in Chilean lakes represents an emerging area research, particularly environmental monitoring optically complex bodies. Similarly, atmospheric correction processors applied to aquatic environments, such as Case 2 Networks (C2RCC-Nets), are notably underrepresented. This study evaluates capability C2RCC-Nets using different neural networks—Case-2 Regional/Coast Color (C2RCC), C2X-Extreme (C2X), and C2X-Complex (C2XC)—to estimate Secchi depth Lake Lanalhue (eutrophic), Villarrica (oligo-mesotrophic), Panguipulli (oligotrophic). evaluation used statistical methods Spearman’s correlation normalized error metrics (nRMSE, nMAE, nbias) assess agreement between satellite-derived data situ measurements. C2XC demonstrated best fit Lanalhue, with nRMSE = 33.13%, nMAE 23.51%, nbias 8.57%, relation median ground truth values. In Villarrica, network displayed a moderate (rs 0.618) metrics, 24.67% 20.67%, 4.21%. oligotrophic Panguipulli, no relationship was observed estimated measured values, which could be related fact that selected networks were developed very case waters. These findings highlight need methodological advancements processing products Chile’s optical types, clear Nonetheless, this underscores model-specific calibration C2RCC-Nets, types trophic states may require tailored training ranges inherent properties.

Language: Английский

Citations

0