☆ 4.8 Article

A coupled model to improve river water quality prediction towards addressing non-stationarity and data limitation

WATER RESEARCH (2024)

Related references

Note: Only part of the references are listed.

Article Engineering, Environmental

Addressing data challenges in riverine nutrient load modeling of an intensively managed agro-industrial watershed

Sundar Niroula et al.

Summary: Data limitations often challenge the reliability of water quality models in intensively managed watersheds. This study addresses the data challenges in calibrating the Soil and Water Assessment Tool (SWAT) to the Upper Sangamon River Watershed in central Illinois, highlighting errors and inconsistencies in data and insufficient precipitation and water quality observations. The study also demonstrates the benefits of additional weather and water quality observations for reducing input uncertainties and provides suggestions for selecting appropriate observations for model calibration. After addressing the data issues, the study shows that the SWAT model can be calibrated successfully for the case study watershed.

JOURNAL OF THE AMERICAN WATER RESOURCES ASSOCIATION (2023)

Add to Collection

Article Environmental Sciences

Large-scale prediction of stream water quality using an interpretable deep learning approach

Hang Zheng et al.

Summary: Deep learning methods are increasingly used in water quality prediction due to their ability to map nonlinear relationships quickly. However, the lack of physical explanation limits their practicality. In this study, an interpretable deep learning framework was established to predict water quality variations. The model achieved satisfactory prediction performance, with coefficients of determination above 0.80 for COD, TP, and TN. The SHapley Additive exPlanations method was effective in interpreting the results and identifying important variables affecting water quality variations.

JOURNAL OF ENVIRONMENTAL MANAGEMENT (2023)

Add to Collection

Article Environmental Sciences

A deep learning-based novel approach to generate continuous daily stream nitrate concentration for nitrate data-sparse watersheds

Gourab Kumer Saha et al.

Summary: High-frequency stream nitrate concentration provides critical insights into nutrient dynamics and can help to improve sustainable ecosystem management. A data-driven model based on optical sensors was developed to estimate continuous daily stream nitrate concentration in Iowa, USA, with unprecedented performance levels.

SCIENCE OF THE TOTAL ENVIRONMENT (2023)

Add to Collection

Review Engineering, Environmental

Application of machine learning in groundwater quality modeling-A comprehensive review

Ryan Haggerty et al.

Summary: This review assesses the development of machine learning techniques in predicting groundwater quality over the past two decades. It evaluates the application of various supervised, semi-supervised, unsupervised, and ensemble ML models, with neural networks being the most widely used. The usage of neural networks has decreased in recent years, leading to the emergence of more accurate or advanced techniques like deep learning or unsupervised algorithms. Iran and the United States lead in the number of modeled areas, with extensive historical data available. Future advancements include further implementation of deep learning, explainable artificial intelligence, and other cutting-edge techniques, as well as modeling of sparsely studied variables and unique study areas, and the application of ML techniques for groundwater quality management.

WATER RESEARCH (2023)

Add to Collection

Article Environmental Sciences

A Random Forest in the Great Lakes: Stream Nutrient Concentrations Across the Transboundary Great Lakes Basin

Nandita B. Basu et al.

Summary: Excess nutrient inputs from agricultural and urban sources have led to eutrophication and algal blooms in the Great Lakes Basin. Using a random forest machine learning model, we found that land use and management, including agricultural and urban land, tile drainage, and wetland density, are important predictors of nutrient concentrations in the basin. The study highlights the importance of livestock and drainage management, as well as wetland restoration, in addressing eutrophication in intensively managed landscapes.

EARTHS FUTURE (2023)

Add to Collection

Article Environmental Sciences

A comparative study of data-driven models for runoff, sediment, and nitrate forecasting

Mohammad G. Zamani et al.

Summary: Effective prediction of qualitative and quantitative indicators for runoff is crucial in water resources planning and management. This study compares data-driven techniques (ANN, LSTM, WANN, and WLSTM models) for runoff evaluation and demonstrates their superiority over model-driven approaches. The comparisons are based on statistical indices such as R-Squared, NSE, MAE, and RMSE, with wavelet function improving the accuracy of ANN and LSTM models. The proposed framework, successfully applied to ECW, Indiana, U.S., proves to be applicable and efficient.

JOURNAL OF ENVIRONMENTAL MANAGEMENT (2023)

Add to Collection

Article Environmental Sciences

Short-term changes in algal blooms and phytoplankton community after the passage of Super Typhoon Lekima in a temperate and inner sea (Bohai Sea) in China

Tao Jiang et al.

Summary: Extensive multi-species harmful algal blooms (HABs) were triggered by Super Typhoon Lekima in Laizhou Bay. After the typhoon, the abundance of phytoplankton and Chl a concentration significantly increased. The study suggests that typhoons may introduce freshwater and nutrients, leading to changes in the phytoplankton community and HABs in temperate inner bays.

ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY (2022)

Add to Collection

Article Engineering, Environmental

Siamese Network-Based Transfer Learning Model to Predict Geogenic Contaminated Groundwaters

Hailong Cao et al.

Summary: By utilizing transfer learning with Siamese networks, this study addresses the issue of insufficient groundwater quality data and class imbalance, achieving accurate and balanced predictions of geogenic contaminated groundwaters (GCGs) and non-GCGs.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2022)

Add to Collection

Article Engineering, Environmental

Predicting Dynamic Riverine Nitrogen Export in Unmonitored Watersheds: Leveraging Insights of AI from Data-Rich Regions

Rui Xiong et al.

Summary: This study uses deep learning models to accurately predict the daily dynamics of riverine nitrogen export and discovers interbasin consistency across different regions. It provides a new method for studying the global daily-resolution dynamics of riverine nitrogen export.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2022)

Add to Collection

Article Multidisciplinary Sciences

Machine learning-based estimation of riverine nutrient concentrations and associated uncertainties caused by sampling frequencies

Shengyue Chen et al.

Summary: In this study, machine learning models were used to estimate water quality, and the random forest model outperformed the support vector machine and back-propagation neural network models. Higher sampling frequency contributed to better model performance, and water temperature, electrical conductivity, and turbidity were identified as key indicators for nutrient estimation. The study highlights the importance of high-frequency data in machine learning model development.

PLOS ONE (2022)

Add to Collection

Article Engineering, Environmental

Algal bloom forecasting with time-frequency analysis: A hybrid deep learning approach

Muyuan Liu et al.

Summary: Researchers proposed a novel hybrid approach (WLSTM) to improve the prediction accuracy of traditional LSTM in algal bloom forecasting. By introducing advanced time-frequency wavelet analysis and conducting experiments in two different lakes, WLSTM outperformed other commonly used approaches and achieved high accuracy in predicting algal fluctuations and bloom levels.

WATER RESEARCH (2022)

Add to Collection

Article Engineering, Environmental

TLT: Recurrent fine-tuning transfer learning for water quality long-term prediction

Lin Peng et al.

Summary: This study introduces a deep learning model using transfer learning framework to improve the accuracy of long-term water quality prediction in data-constrained scenarios.

WATER RESEARCH (2022)

Add to Collection

Article Environmental Sciences

Improved predictive performance of cyanobacterial blooms using a hybrid statistical and deep-learning method

Hu Li et al.

Summary: The study considers combining statistical models with deep-learning models to better capture temporal patterns of highly dynamic observations. The proposed ARIMA-LSTM model shows promising potential to outperform current baseline models for predicting CyanoHABs in highly variable time-series observations. The predictive errors of mean absolute error and root mean square error were reduced significantly compared to the best baseline model.

ENVIRONMENTAL RESEARCH LETTERS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

A Comprehensive Survey on Transfer Learning

Fuzhen Zhuang et al.

Summary: Transfer learning aims to improve the performance of target learners by transferring knowledge from related source domains, reducing the reliance on target-domain data. This survey aims to systematize and summarize existing research studies in order to help readers understand the current status and ideas in the area of transfer learning.

PROCEEDINGS OF THE IEEE (2021)

Add to Collection

Article Environmental Sciences

Prediction of harmful algal blooms in large water bodies using the combined EFDC and LSTM models

Lei Zheng et al.

Summary: The research utilizes EFDC and LSTM models to predict Harmful algal blooms (HABs), achieving high-precision forecasting for chlorophyll-a in the next 1 to 3 time steps through data dimension reduction. This cost-effective method provides a reliable way for early detection of HABs.

JOURNAL OF ENVIRONMENTAL MANAGEMENT (2021)

Add to Collection

Review Engineering, Environmental

Machine learning in natural and engineered water systems

Ruixing Huang et al.

Summary: Machine learning has shown great potential in water resources management, being able to predict water quality indicators, solve emerging pollution problems, and effectively identify specific contaminants.

WATER RESEARCH (2021)

Add to Collection

Article Environmental Sciences

Transferring Hydrologic Data Across Continents - Leveraging Data-Rich Regions to Improve Hydrologic Prediction in Data-Sparse Regions

Kai Ma et al.

Summary: The study demonstrated the potential of transfer learning in transferring hydrological models between different continents, showing significantly improved performance in regions such as China and Chile. The benefits of transfer learning increased with more data available in the source data set and greater physiographic diversity.

WATER RESOURCES RESEARCH (2021)

Add to Collection

Article Environmental Sciences

Archetypes and Controls of Riverine Nutrient Export Across German Catchments

Pia Ebeling et al.

Summary: This study found that spatial heterogeneity of nutrient sources predominantly controls the variability of in-stream concentration dynamics among catchments, with agricultural land use leading to increased nitrate concentrations. Phosphate concentrations were related to point sources, while organic carbon levels were linked to the abundance of riparian wetlands.

WATER RESOURCES RESEARCH (2021)

Add to Collection

Article Engineering, Civil

Artificial intelligence modelling integrated with Singular Spectral analysis and Seasonal-Trend decomposition using Loess approaches for streamflow predictions

Halit Apaydin et al.

Summary: This study investigates the potential of combining artificial neural network methods with Singular Spectral Analysis (SSA) for predicting river streamflows in the Nallihan stream, Turkey. The results show that the hybrid SSA-based models outperformed standalone neural network models and improved the accuracy of flow predictions.

JOURNAL OF HYDROLOGY (2021)

Add to Collection

Article Engineering, Civil

Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting

Maryam Rahimzad et al.

Summary: Streamflow forecasting is crucial for water resource management, flood warning, and mitigation. This study compared the accuracy of four data-driven techniques in daily streamflow forecasting and found that the LSTM network outperformed other models in terms of NRMSE, E-H, E-L, and R values.

WATER RESOURCES MANAGEMENT (2021)

Add to Collection

Article Environmental Sciences

Regionalization for Ungauged Catchments - Lessons Learned From a Comparative Large-Sample Study

Sandra Pool et al.

Summary: This study compares 19 regionalization approaches in 671 gauged catchments in the United States and finds that the evaluation of predicted hydrograph varies depending on the regionalization method. Therefore, a multi-criteria evaluation is essential for a robust assessment of regionalization performance.

WATER RESOURCES RESEARCH (2021)

Add to Collection

Article Environmental Sciences

Predicting Water Temperature Dynamics of Unmonitored Lakes With Meta-Transfer Learning

Jared D. Willard et al.

Summary: Most environmental data come from well-monitored sites, making transferring knowledge to unmonitored sites a challenge in environmental sciences. A novel transfer-learning framework, meta-transfer learning (MTL), accurately predicts temperature in unmonitored lakes by borrowing models from well-monitored lakes. The approach demonstrates improved performance in predicting temperatures in unmonitored lakes, showing the potential of MTL for various unmonitored systems and environmental variables.

WATER RESOURCES RESEARCH (2021)

Add to Collection

Article Geosciences, Multidisciplinary

The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019

Jie Yang et al.

Summary: Land cover (LC) plays a crucial role in energy exchange and environmental impact. Rapid changes in land cover in China necessitate fine-scale monitoring. A new dataset, CLCD, based on Landsat data on the Google Earth Engine platform provides valuable insights into China's land cover dynamics from 1990 to 2019.

EARTH SYSTEM SCIENCE DATA (2021)

Add to Collection

Article Environmental Sciences

A Rainfall-Runoff Model With LSTM-Based Sequence-to-Sequence Learning

Zhongrun Xiang et al.

WATER RESOURCES RESEARCH (2020)

Add to Collection

Article Engineering, Environmental

Hydro-climatic drivers of land-based organic and inorganic particulate micropollutant fluxes: The regime of the largest river water inflow of the Mediterranean Sea

Hugo Delile et al.

WATER RESEARCH (2020)

Add to Collection

Article Environmental Sciences

Enhancing Streamflow Forecast and Extracting Insights Using Long-Short Term Memory Networks With Data Integration at Continental Scales

Dapeng Feng et al.

WATER RESOURCES RESEARCH (2020)

Add to Collection

Article Multidisciplinary Sciences

Deep learning and process understanding for data-driven Earth system science

Markus Reichstein et al.

NATURE (2019)

Add to Collection

Review Geosciences, Multidisciplinary

Anthropogenic stresses on the world's big rivers

Jim Best

NATURE GEOSCIENCE (2019)

Add to Collection

Article Limnology

Extreme precipitation and phosphorus loads from two agricultural watersheds

Stephen R. Carpenter et al.

LIMNOLOGY AND OCEANOGRAPHY (2018)

Add to Collection

Article Environmental Sciences

Applying high-frequency surrogate measurements and a wavelet-ANN model to provide early warnings of rapid surface water quality anomalies

Bin Shi et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2018)

Add to Collection

Review Environmental Sciences

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Chaopeng Shen

WATER RESOURCES RESEARCH (2018)

Add to Collection

Article Geosciences, Multidisciplinary

The Open-source Data Inventory for Anthropogenic CO2, version 2016 (ODIAC2016): a global monthly fossil fuel CO2 gridded emissions data product for tracer transport simulations and surface flux inversions

Tomohiro Oda et al.

EARTH SYSTEM SCIENCE DATA (2018)

Add to Collection

Article Geosciences, Multidisciplinary

Framework for developing hybrid process-driven, artificial neural network and regression models for salinity prediction in river systems

Jason M. Hunter et al.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2018)

Add to Collection

Article Engineering, Environmental

A novel single-parameter approach for forecasting algal blooms

Xi Xiao et al.

WATER RESEARCH (2017)

Add to Collection

Article Multidisciplinary Sciences

Comment: WorldPop, open data for spatial demography

Andrew J. Tatem

SCIENTIFIC DATA (2017)

Add to Collection

Article Water Resources

Discharge and nutrient uncertainty: implications for nutrient flux estimation in small streams

C. E. M. Lloyd et al.

HYDROLOGICAL PROCESSES (2016)

Add to Collection

Review Engineering, Environmental

Automatic High Frequency Monitoring for Improved Lake and Reservoir Management

Rafael Marce et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2016)

Add to Collection

Article Engineering, Civil

Potential application of wavelet neural network ensemble to forecast streamflow for flood management

K. S. Kasiviswanathan et al.

JOURNAL OF HYDROLOGY (2016)

Add to Collection

Review Environmental Sciences

Real-time monitoring of nutrients and dissolved organic matter in rivers: Capturing event dynamics, technological opportunities and future directions

Phillip J. Blaen et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2016)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Proactive management of estuarine algal blooms using an automated monitoring buoy coupled with an artificial neural network

Peter Coad et al.

ENVIRONMENTAL MODELLING & SOFTWARE (2014)

Add to Collection

Review Engineering, Civil

Applications of hybrid wavelet-Artificial Intelligence models in hydrology: A review

Vahid Nourani et al.

JOURNAL OF HYDROLOGY (2014)

Add to Collection

Article Geosciences, Multidisciplinary

Root mean square error (RMSE) or mean absolute error (MAE)? - Arguments against avoiding RMSE in the literature

T. Chai et al.

GEOSCIENTIFIC MODEL DEVELOPMENT (2014)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

Add to Collection

Article Multidisciplinary Sciences

Global threats to human water security and river biodiversity

C. J. Voeroesmarty et al.

NATURE (2010)

Add to Collection

Editorial Material Multidisciplinary Sciences

Climate change - Stationarity is dead: Whither water management?

P. C. D. Milly et al.

SCIENCE (2008)

Add to Collection

Article Environmental Sciences

Ensemble predictions of runoff in ungauged catchments

N McIntyre et al.

WATER RESOURCES RESEARCH (2005)

Add to Collection

Article Engineering, Civil

Recent advances in wavelet analyses: Part I. A review of concepts

D Labat

JOURNAL OF HYDROLOGY (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.