Uncovering the Influence of Hydrological and Climate Variables in Chlorophyll-A Concentration in Tropical Reservoirs with Machine Learning

Abstract

Climate variability and change, associated with increasing water demands, can have significant implications for water availability. In the Brazilian semi-arid, eutrophication in reservoirs raises the risk of water scarcity. The reservoirs have also a high seasonal and annual variability of water level and volume, which can have important effects on Chlorophyll-a concentration (Chla). Assessing the influence of climate and hydrological variability on phytoplankton growth can be important to find strategies to achieve water security in tropical regions with similar problems. This study explores the potential of machine learning models to predict Chla in reservoirs and to understand their relationship with hydrological and climate variables. The model is based mainly on satellite data, which makes the methodology useful for data-scarce regions. Tree-based ensemble methods had the best performances among six machine learning methods and one parametric model. This performance can be considered satisfactory as classical empirical relationships between Chla and phosphorus may not hold for tropical reservoirs. Water volume and the mix-layer depth are inversely related to Chla, while mean surface temperature, water level, and surface solar radiation have direct relationships with Chla. These findings provide insights on how seasonal climate prediction and reservoir operation might influence water quality in regions supplied by superficial reservoirs.

Analysis of total nitrogen and chlorophyll a correlations in reservoirs in Ceará/Brazil

“…The high density of reservoirs can affect water quality because the existence of several small reservoirs favors the trapping of nutrients due to sedimentation and biological capture (FREIRE; COSTA; LIMA NETO, 2022;LI et al, 2022; LIMA NETO; WIEGAND; ARAÚJO, 2011). Similarly, the lowest means of TN and Chla were identified in Serra da Ibiapaba (0.631 mg×L -1 and 3681 μg×L -1 , n = 39), which has a much lower number of water bodies than what was verified in the other hydrographic regions of the state, which is mainly due to its sedimentary hydrogeological characteristic (CEARÁ, 2021b).…”

“…Thus, discussions about nutrient management strategies to mitigate eutrophication in aquatic environments have focused on identifying the nutrient with the best predictive capacity for algal biomass production (GELETU, 2023;ZHOU et al, 2022). In the Northeast region of Brazil, significant water-level variability and generally higher trophic levels (WIEGAND et al, 2021) imply more complex mechanisms behind eutrophication, making it challenging to predict Chla (CARVALHO; LIMA NETO; SOUZA FILHO, 2022). Thus, understanding the patterns of Chla and nutrient dynamics in these reservoirs is often a prerequisite for reversing current water quality problems and managing reservoir ecosystems (PHAM et al, 2020;LI et al, 2022).…”

“…Thus, understanding the patterns of Chla and nutrient dynamics in these reservoirs is often a prerequisite for reversing current water quality problems and managing reservoir ecosystems (LI et al, 2022). Despite the abundance of studies that provide a better understanding of limnology, sources of polluting loads, the eutrophication process, and its relationship with hydroclimatic variables in some reservoirs in the Brazilian semi-arid region (MOURA et al, 2020;RAULINO;SILVEIRA;LIMA NETO, 2021;LIMA NETO, 2021;LIMA NETO et al, 2022), studies that investigate the correlations between Chla and TN are still scarce and local. Therefore, this study aimed to analyze data from 155 reservoirs located in the state of Ceará, Brazil, verify the predictive capability of TN for Chla, and identify the factors that influence the dynamics of these correlations in the studied reservoirs.…”

Eutrophication risk assessment of a large reservoir in the Brazilian semiarid region under climate change scenarios

“…Extreme meteorological and hydrological events can be expected in future, resulting in more frequent droughts and floods posing more uncertainty and risk in water resources management (Shrestha et al 2017, Raulino et al 2021. There is evidence that the water quality of the reservoirs is influenced by various climatic mechanisms (Hamilton et al 2016, Carvalho et al 2022. Therefore, climate change can impact not only the quantitative aspects, but also the qualitative aspects of reservoirs, affecting the input nutrient loads and the internal concentration of pollutants (Bucak et al 2018, Me et al 2018.…”