Machine learning modeling of lake chlorophyll content in a data scarce region (Northern Patagonia, Chile): insights for environmental monitoring DOI
Luciano Caputo, Cristian Ríos Molina,

Roxanna Ayllon

et al.

Inland Waters, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 24

Published: May 28, 2024

Among South America, Chile is highly susceptible to climate change impacts on water resources and ecosystems. Chilean lakes rivers have been impacted by anthropogenic activities leading chemical pollution eutrophication. Concerns for conservation management of has led the current development secondary norms environmental quality Northern Patagonian lakes. In this context, we analyze historical limnological databases (1979-2022) these utilizing Random Forest (RF) models. After filtering, retained data 11 including key variables of: dissolved oxygen, electric conductivity, transparency, temperature, pH, total nitrogen, phosphorus chlorophyll-a. This dataset yielded robust results, accurately predicting chlorophyll-a content. Furthermore, added lake geomorphological parameters, enhancing performance model. Our study demonstrates need improve long-term monitoring programs, optimizing recording decreasing costs. We conclude that studied generally maintain their oligotrophic characteristics, however further analysis suggests are more sensitive nitrogen loading than phosphorus. results highlight implement adaptative plans at watershed level regulate contamination (from agriculture, pisciculture urbanization). The features selected RF, coupled with assessment trophic state variation, allow establishment permissible concentration thresholds major nutrients other sentinel informing regulations such as quality. Lastly, enhanced RF modeling when geographical parameters unveils standardize integrate in practices.

Language: Английский

Research on Water Resource Modeling Based on Machine Learning Technologies DOI Open Access
Liu Ze,

Jingzhao Zhou,

Xiaoyang Yang

et al.

Water, Journal Year: 2024, Volume and Issue: 16(3), P. 472 - 472

Published: Jan. 31, 2024

Water resource modeling is an important means of studying the distribution, change, utilization, and management water resources. By establishing various models, resources can be quantitatively described predicted, providing a scientific basis for management, protection, planning. Traditional hydrological observation methods, often reliant on experience statistical are time-consuming labor-intensive, frequently resulting in predictions limited accuracy. However, machine learning technologies enhance efficiency sustainability by analyzing extensive hydrogeological data, thereby improving optimizing utilization allocation. This review investigates application predicting aspects, including precipitation, flood, runoff, soil moisture, evapotranspiration, groundwater level, quality. It provides detailed summary algorithms, examines their technical strengths weaknesses, discusses potential applications modeling. Finally, this paper anticipates future development trends to

Language: Английский

Citations

21
Machine learning-based evolution of water quality prediction model: an integrated robust framework for comparative application on periodic return and jitter data DOI
Xizhi Nong, Yi He, Lihua Chen

et al.

Environmental Pollution, Journal Year: 2025, Volume and Issue: unknown, P. 125834 - 125834

Published: Feb. 1, 2025

Language: Английский

Citations

2
How does the choice of DEMs affect catchment hydrological modeling? DOI Creative Commons
Desalew Meseret Moges, Holger Virro, Alexander Kmoch

et al.

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 892, P. 164627 - 164627

Published: June 5, 2023

The digital elevation models (DEMs) are the primary and most important spatial inputs for a wide range of hydrological applications. However, their availability from multiple sources at various resolutions poses challenge in watershed modeling as they influence feature delineation model simulations. In this study, we evaluated effect DEM choice on stream catchment streamflow simulation using SWAT four distinct geographic regions with diverse terrain surfaces. Performance evaluation metrics, including Willmott's index agreement, nRMSE combined visual comparisons were employed to assess each DEM's performance. Our results revealed that has significant impact accuracy delineation, while its within same was relatively minor. Among DEMs, AW3D30 COP30 performed best, closely followed by MERIT, whereas TanDEM-X HydroSHEDS exhibited poorer All DEMs displayed better mountainous larger catchments compared smaller flatter catchments. Forest cover also played role accuracy, mainly due association steep slopes. findings provide valuable insights making informed data selection decisions modeling, considering specific characteristics desired level accuracy.

Language: Английский

Citations

28
Large-scale prediction of stream water quality using an interpretable deep learning approach DOI
Hang Zheng,

Yueyi Liu,

Wenhua Wan

et al.

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 331, P. 117309 - 117309

Published: Jan. 17, 2023

Language: Английский

Citations

27
Exploring Random Forest Machine Learning and Remote Sensing Data for Streamflow Prediction: An Alternative Approach to a Process-Based Hydrologic Modeling in a Snowmelt-Driven Watershed DOI Creative Commons
Khandaker Iftekharul Islam, Emile Elias, Kenneth C. Carroll

et al.

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(16), P. 3999 - 3999

Published: Aug. 11, 2023

Physically based hydrologic models require significant effort and extensive information for development, calibration, validation. The study explored the use of random forest regression (RFR), a supervised machine learning (ML) model, as an alternative to physically Soil Water Assessment Tool (SWAT) predicting streamflow in Rio Grande Headwaters near Del Norte, snowmelt-dominated mountainous watershed Upper Basin. Remotely sensed data were used analysis (RFML) RStudio processing synthesizing. RFML model outperformed SWAT accuracy demonstrated its capability this region. We implemented customized approach RFR assess model’s performance three training periods, across 1991–2010, 1996–2010, 2001–2010; results indicated that improved with longer implying trained on more extended period is better able capture parameters’ variability reproduce accurately. variable importance (i.e., IncNodePurity) measure revealed snow depth minimum temperature consistently top two predictors all periods. paper also evaluated how well performs reproducing conventional approach. needed time set up calibrate, delivering acceptable annual mean simulation, satisfactory index agreement (d), coefficient determination (R2), percent bias (PBIAS) values, but monthly simulation warrants further exploration adjustments. recommends exploring snowmelt runoff processes, dust-driven sublimation effects, detailed topographic input parameters update routine flow estimation. provide critical enhancing prediction, which valuable research water resource management, including snowmelt-driven semi-arid regions.

Language: Английский

Citations

25
Forecasting water quality variable using deep learning and weighted averaging ensemble models DOI
Mohammad Zamani, Mohammad Reza Nikoo, Sina Jahanshahi

et al.

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(59), P. 124316 - 124340

Published: Nov. 24, 2023

Language: Английский

Citations

23
Precipitation recycling impacts on runoff in arid regions of China and Mongolia: a machine learning approach DOI
Ruolin Li,

Qi Feng,

Yang Cui

et al.

Hydrological Sciences Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 20, 2025

Language: Английский

Citations

1
Global patterns and key drivers of stream nitrogen concentration: A machine learning approach DOI Creative Commons
Razi Sheikholeslami, Jim W. Hall

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 868, P. 161623 - 161623

Published: Jan. 16, 2023

Anthropogenic loading of nitrogen to river systems can pose serious health hazards and create critical environmental threats. Quantification the magnitude impact freshwater requires identifying key controls dynamics analyzing both past present patterns flows. To tackle this challenge, we adopted a machine learning (ML) approach built an ML-driven representation that captures spatiotemporal variability in concentrations at global scale. Our model uses random forests regress large sample monthly measured stream onto set 17 predictors with spatial resolution 0.5-degree over 1990-2013, including observations within pixel upstream drivers. The was validated data from rivers outside training dataset used predict 520 major basins world, many scarce or no observations. We predicted regions highest median their (in 2013) were: United States (Mississippi), Pakistan, Bangladesh, India (Indus, Ganges), China (Yellow, Yangtze, Yongding, Huai), most Europe (Rhine, Danube, Vistula, Thames, Trent, Severn). Other hotspots were Sebou (Morroco), Nakdong (South Korea), Kitakami (Japan), Egypt's Nile Delta. analysis showed rate increase concentration between 1990s 2000s greatest located eastern China, central parts Canada, Baltic states, mainland southeast Asia, south-eastern Australia. Using new grouped variable importance measure, also found temporality (month year cumulative month count) is influential predictor, followed by factors representing hydroclimatic conditions, diffuse nutrient emissions agriculture, topographic features. be further applied assess strategies designed reduce pollution bodies scales.

Language: Английский

Citations

20
An integrated approach based on the correction of imbalanced small datasets and the application of machine learning algorithms to predict total phosphorus concentration in rivers DOI
Manuel Almeida, Pedro Coelho

Ecological Informatics, Journal Year: 2023, Volume and Issue: 76, P. 102138 - 102138

Published: May 24, 2023

Language: Английский

Citations

17
A random forest approach to improve estimates of tributary nutrient loading DOI
Peter D. F. Isles

Water Research, Journal Year: 2023, Volume and Issue: 248, P. 120876 - 120876

Published: Nov. 15, 2023

Language: Английский

Citations

17