Search

In this study, we combined machine learning and remote sensing techniques to estimate the value of chlorophyll-a concentration in a freshwater ecosystem in the South American continent (lake in Southern Chile). In a previous study, nine artificial intelligence (AI) algorithms were tested to predict water quality data from measurements during monitoring campaigns. In this study, in addition to field data (Case A), meteorological variables (Case B) and satellite data (Case C) were used to predict chlorophyll-a in Lake Llanquihue. The models used were SARIMAX, LSTM, and RNN, all of which showed generally good statistics for the prediction of the chlorophyll-a variable. Model validation metrics showed that all three models effectively predicted chlorophyll as an indicator of the presence of algae in water bodies. Coefficient of determination values ranging from 0.64 to 0.93 were obtained, with the LSTM model showing the best statistics in any of the cases tested. The LSTM model generally performed well across most stations, with lower values for MSE (2), RMSE (

Phytoplankton is considered a strong predictor of the environmental quality of lakes, while Chlorophyll-a is an indicator of primary productivity. In this study, 25 LANDSAT images covering the 2014–2021 period were used to predict Chlorophyll-a in the Villarrica lacustrine system. A Chlorophyll-a recovery algorithm was calculated using two spectral indices (FAI and SABI). The indices that presented the best statistical indicators were the floating algal index (R2 = 0.87) and surface algal bloom index (R2 = 0.59). A multiparametric linear model for Chlorophyll-a estimation was constructed with the indices. Statistical indicators were used to validate the multiple linear regression model used to predict Chlorophyll-a by means of spectral indices, with the following results: a MBE of −0.136 μ, RMSE of 0.055 μ, and NRMSE of 0.019%. All results revealed the strength of the model. It is necessary to raise awareness among the population that carries out activities around the lake in order for them to take policy actions related to water resources in this Chilean lake. Furthermore, it is important to note that this study is the first to address the detection of algal blooms in this Chilean lake through remote sensing.

The diffuse attenuation coefficient of photosynthetically active radiation is an important inherent optical property of the subaquatic light field. This parameter, as a measure of the transparency of the medium, is a good indicator of water quality. Degradation of the optical properties of water due to anthropogenic disturbances is a common phenomenon in freshwater ecosystems. In this study, we used four algorithm-based Landsat 8 OLI and Sentinel-2A/B MSI images to estimate the diffuse attenuation coefficient of photosynthetically active radiation in Lake Villarrica located in south-central Chile. The algorithms’ estimated data from the ACOLITE module were validated with in situ measurements from six sampling stations. Seasonal and intralake variations of the light attenuation coefficient were studied. The relationship between the diffuse attenuation coefficient of photosynthetically active radiation, meteorological parameters, and an optical classification was also explored. The best results were obtained with QAA v6 KdPAR Nechad (R2 = 0.931, MBE = 0.023 m−1, RMSE = 0.088 m−1, and MAPE = 35.9%) for spring and QAA v5 Kd490 algorithms (R2 = 0.919, MBE = −0.064 m−1, RMSE = −0.09 m−1, and MAPE = 30.3%) for summer. High KdPAR values are associated with the strong wind and precipitation events suggest they are caused by sediment resuspension. Finally, an optical classification of freshwater ecosystems was proposed for this lake. The promising results of this study suggest that the combination of in situ data and observation satellites can be useful for assessing the bio-optical state of water and water quality dynamics in Chilean aquatic systems.

Remote sensing was used as an early alert tool for water clarity changes in five Araucanian Lakes in South-Central Chile. Turbidity records are scarce or unavailable over large and remote areas needed to fully understand the factors associated with turbidity, and their spatial-temporal representation remains a limitation. This work aimed to develop and validate empirical models to estimate values of turbidity from Landsat images and determine the spatial distribution of estimated turbidity in the selected Araucanian Lakes. Secchi disk depth measurements were linked with turbidity measurements to obtain a turbidity dataset. This in turn was used to develop and validate a set of empirical models to predict turbidity based on four single bands and 16 combination bands from 15 multispectral Landsat images. The best empirical models predicted turbidity over the range of 0.3–12.3 NTUs with RMSE values around 0.31–1.03 NTU, R2 (Index of Agreement IA) around 0.93–0.99 (0.85–0.97) and mean bias error (MBE) around (−0.36–0.44 NTU). Estimation maps to analyze the temporal-spatial turbidity variation in the lakes were constructed. Finally, it was found that the meteorological conditions may affect the variation of turbidity, mainly precipitation and wind speed. The data indicate that the turbidity has slightly increased in winter–spring. These models will be used in the future to reconstruct large datasets that allow analyzing transparency trends in those lakes.

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

In this study, we employ in situ, meteorological, and remote sensing data to estimate chlorophyll-a concentration at different depths in a South American freshwater ecosystem, focusing specifically on a lake in southern Chile known as Lake Maihue. For our analysis, we explored four different scenarios using three deep learning and traditional statistical models. These scenarios involved using field data (Scenario 1), meteorological variables (Scenario 2), and satellite data (Scenarios 3.1 and 3.2) to predict chlorophyll-a levels in Lake Maihue at three different depths (0, 15, and 30 m). Our choice of models included SARIMAX, DGLM, and LSTM, all of which showed promising statistical performance in predicting chlorophyll-a concentrations in this lake. Validation metrics for these models indicated their effectiveness in predicting chlorophyll levels, which serve as valuable indicators of the presence of algae in the water body. The coefficient of determination values ranged from 0.30 to 0.98, with the DGLM model showing the most favorable statistics in all scenarios tested. It is worth noting that the LSTM model yielded comparatively lower metrics, mainly due to the limitations of the available training data. The models employed, which use traditional statistical and machine learning models and meteorological and remote sensing data, have great potential for application in lakes in Chile and the rest of the world with similar characteristics. In addition, these results constitute a fundamental resource for decision-makers involved in the protection and conservation of water resource quality.