A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years

Journal of Marine Science and Engineering, Год журнала: 2024, Номер 12(1), С. 159 - 159

Опубликована: Янв. 13, 2024

Water quality prediction, a well-established field with broad implications across various sectors, is thoroughly examined in this comprehensive review. Through an exhaustive analysis of over 170 studies conducted the last five years, we focus on application machine learning for predicting water quality. The review begins by presenting latest methodologies acquiring data. Categorizing learning-based predictions into two primary segments—indicator prediction and index prediction—further distinguishes between single-indicator multi-indicator predictions. A meticulous examination each method’s technical details follows. This article explores current cutting-edge research trends algorithms, providing perspective their prediction. It investigates utilization algorithms concludes highlighting significant challenges future directions. Emphasis placed key areas such as hydrodynamic coupling, effective data processing acquisition, mitigating model uncertainty. paper provides detailed present state principal characteristics emerging technologies

Язык: Английский

---

Design and application of depth control methods for autonomous underwater profilers in challenging marine environments

Results in Engineering, Год журнала: 2025, Номер unknown, С. 104031 - 104031

Опубликована: Янв. 1, 2025

Язык: Английский

---

Water quality forecasting based on data decomposition, fuzzy clustering and deep learning neural network

Environmental Pollution, Год журнала: 2022, Номер 303, С. 119136 - 119136

Опубликована: Март 10, 2022

Язык: Английский

---

Comparison and integration of physical and interpretable AI-driven models for rainfall-runoff simulation

Results in Engineering, Год журнала: 2024, Номер 24, С. 103048 - 103048

Опубликована: Окт. 5, 2024

Язык: Английский

---

On the implementation of a novel data-intelligence model based on extreme learning machine optimized by bat algorithm for estimating daily chlorophyll-a concentration: Case studies of river and lake in USA

Journal of Cleaner Production, Год журнала: 2020, Номер 285, С. 124868 - 124868

Опубликована: Окт. 30, 2020

Язык: Английский

---

Recurrent neural networks for water quality assessment in complex coastal lagoon environments: A case study on the Venice Lagoon

Environmental Modelling & Software, Год журнала: 2022, Номер 154, С. 105403 - 105403

Опубликована: Май 12, 2022

Язык: Английский

---

Prediction of algal blooms via data-driven machine learning models: an evaluation using data from a well-monitored mesotrophic lake

Geoscientific model development, Год журнала: 2023, Номер 16(1), С. 35 - 46

Опубликована: Янв. 3, 2023

Abstract. With increasing lake monitoring data, data-driven machine learning (ML) models might be able to capture the complex algal bloom dynamics that cannot completely described in process-based (PB) models. We applied two ML models, gradient boost regressor (GBR) and long short-term memory (LSTM) network, predict blooms seasonal changes chlorophyll concentrations (Chl) a mesotrophic lake. Three predictive workflows were tested, one based solely on available measurements others applying two-step approach, first estimating nutrients have limited observations then predicting Chl using observed pre-generated environmental factors. The third workflow was developed hydrodynamic data derived from PB model as additional training features approach. performance of superior Chl. hybrid further improved prediction timing magnitude blooms. A sparsity test shuffling order testing years showed accuracy decreased with sample interval, varied training–testing year combinations.

Язык: Английский

---

Eutrophication risk assessment considering joint effects of water quality and water quantity for a receiving reservoir in the South-to-North Water Transfer Project, China

Journal of Cleaner Production, Год журнала: 2021, Номер 331, С. 129966 - 129966

Опубликована: Дек. 2, 2021

Язык: Английский

---

A holistic approach for determining the hydrology of the mar menor coastal lagoon by combining hydrological & hydrodynamic models

Journal of Hydrology, Год журнала: 2021, Номер 603, С. 127150 - 127150

Опубликована: Ноя. 6, 2021

A combination of hydrological and hydrodynamic modelling can be applied to understand the hydrology key water balance components lakes lagoons. In this research, Soil Water Assessment Tool (SWAT) model QGIS Ecosystems (QWET) were for Mar Menor coastal lagoon its watershed known as Campo de Cartagena. First, SWAT was calibrated validated based on remote sensing evapotranspiration data. Results showed an acceptable performance in both calibration (R2 = 0.63, NSE 0.62, PBIAS 2.91%) validation 0.68, 2.47%) periods a monthly basis. The simulated streamflow fed into QWET simulate lagoon. evaluated comparison between observed temperatures also estimated evaporation. Simulated daily good agreement with data by capturing timing inter-annual variations, 0.98, BIAS 2.7%. Our estimation, using reference period 2003–2019, yields mean annual rainfall over lake 301 mm evaporation 1325 mm. average surface runoff groundwater discharge are 49 hm3/year 11 hm3/year, respectively. Extreme storm events cause vary 8 202 hm3/year. closed exchange Mediterranean Sea, resulting overall positive flow from Sea 82 study that during summer months, particular, there is considerable inflow lagoon, whereas some autumn winter months (November, December January) net outflow Mediterranean. This novel approach combining complex provides useful tool understanding may play role decision makers when developing strategies mitigating eutrophication.

Язык: Английский

---

Applying Deep Learning in the Prediction of Chlorophyll-a in the East China Sea

Remote Sensing, Год журнала: 2022, Номер 14(21), С. 5461 - 5461

Опубликована: Окт. 30, 2022

The ocean chlorophyll-a (Chl-a) concentration is an important variable in the marine environment, abnormal distribution of which closely related to hazards red tides. Thus, accurate prediction its East China Sea (ECS) greatly for preventing water eutrophication and protecting coastal ecological environment. Processed by two different pre-processing methods, 10-year (2011–2020) satellite-observed data logarithmic were used as long short-term memory (LSTM) neural network training datasets this study. 2021 comparison results. past 15 days’ predict five following days. Results showed that predictions obtained both methods could simulate seasonal Chl-a ECS effectively. Moreover, performance model driven original values was better medium- low-concentration regions. However, high-concentration region, extreme concentrations data-driven LSTM models underestimation, considering better. sensitivity experiments accuracy decreased considerably when backward time step increased. In study, only chlorophyll-a, whose forecasted, effect other relevant elements on not considered, current weakness

Язык: Английский

---