Testing protocols for smoothing datasets of hydraulic variables acquired during unsteady flows DOI
Özlem Baydaroğlu, Marian Muste, Atiye Cikmaz

et al.

Hydrological Sciences Journal, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 18

Published: Aug. 19, 2024

Flood wave propagation involves complex flow variable dependencies. Continuous in-situ hydrograph peak magnitude and timing data provide the most relevant information for understanding these New acoustic instruments can produce experimental evidence by extracting usable signals from noisy datasets. This study presents a new screening protocol to smoothen streamflow unwanted influences noise generated perturbations observational fluctuations. The combines quantitative (statistical fitness parameters) qualitative (domain expert judgments) evaluations. It is tested with 18 smoothing methods identify optimal conditioning candidates. Sensitivity analyses assess validity, generality, scalability of procedures. goal this analysis set mathematical foundation empirical results that lead unified, general conclusions on principles or protocols unsteady flows propagating in open channels, formulating practical guidance future acquisition processing, using better support data-driven modeling efforts.

Language: Английский

A priori physical information to aid generalization capabilities of neural networks for hydraulic modeling DOI Creative Commons
Gianmarco Guglielmo, Andrea Montessori, Jean‐Michel Tucny

et al.

Frontiers in Complex Systems, Journal Year: 2025, Volume and Issue: 2

Published: Jan. 6, 2025

The application of Neural Networks to river hydraulics and flood mapping is fledgling, despite the field suffering from data scarcity, a challenge for machine learning techniques. Consequently, many purely data-driven have shown limited capabilities when tasked with predicting new scenarios. In this work, we propose introducing physical information into training phase in form regularization term. Whereas idea formally borrowed Physics-Informed Networks, proposed methodology does not necessarily resort PDEs, making it suitable scenarios significant epistemic uncertainties, such as hydraulics. method enriches content dataset appears highly versatile. It shows improved predictive controllable, synthetic hydraulic problem, even extrapolating beyond boundaries data-scarce Therefore, our study lays groundwork future employment on real datasets complex applications.

Language: Английский

Citations

2
Crop yield prediction based on reanalysis and crop phenology data in the agroclimatic zones DOI
Serhan Yeşilköy, İbrahim Demir

Theoretical and Applied Climatology, Journal Year: 2024, Volume and Issue: 155(7), P. 7035 - 7048

Published: June 11, 2024

Language: Английский

Citations

5
Modeling of Harmful Algal Bloom Dynamics and Integrated Web Framework for Inland Waters in Iowa DOI Creative Commons
Özlem Baydaroğlu, Serhan Yeşilköy,

Anchit Dave

et al.

EarthArXiv (California Digital Library), Journal Year: 2024, Volume and Issue: unknown

Published: May 2, 2024

Harmful algal blooms (HABs) are one of the major environmental concerns, as they have various negative effects on public health, recreational services, ecological balance, wildlife, fisheries, microbiota, water quality, and economics. HABs caused by many sources, such pollution based agricultural activities, wastewater treatment plant discharges, leakages from sewer systems, natural factors like pH light levels, climate change impacts. While causes recognized, it is unknown how toxin-producing algae develop well key processes components that contribute to their weight due distinct dynamics each lake variety unpredictability conditions influencing these dynamics. Modeling in a changing essential for achieving sustainable development goals regarding clean sanitation. However, lack consistent adequate data significant challenge all studies. In this study, we employed sparse identification nonlinear (SINDy) technique model microcystin, an toxin, utilizing dissolved oxygen quality metric evaporation meteorological parameter. SINDy novel approach combines regression machine learning methods reconstruct analytical representation dynamical system. Moreover, model-driven web-based interactive tool was created disseminate education, raise awareness HAB events, produce more effective solutions problems through what-if scenarios. This web platform allows tracking status lakes observing impact specific parameters harmful formation. Users can easily share images user-friendly platform, allowing others view lakes.

Language: Английский

Citations

4
A Contemporary Systematic Review of Cyberinfrastructure Systems and Applications for Flood and Drought Data Analytics and Communication DOI Creative Commons
Serhan Yeşilköy, Özlem Baydaroğlu, Nikhil Kumar Singh

et al.

Environmental Research Communications, Journal Year: 2024, Volume and Issue: 6(10), P. 102003 - 102003

Published: Oct. 1, 2024

Abstract Hydrometeorological disasters, including floods and droughts, have intensified in both frequency severity recent years. This trend underscores the critical role of timely monitoring, accurate forecasting, effective warning systems facilitating proactive responses. Today’s information offer a vast intricate mesh data, encompassing satellite imagery, meteorological metrics, predictive modeling. Easily accessible to general public, these cyberinfrastructures simulate potential disaster scenarios, serving as invaluable aids decision-making processes. review collates key literature on water-related systems, underscoring transformative impact emerging Internet technologies. These advancements promise enhanced flood drought timeliness greater preparedness through improved management, analysis, visualization, data sharing. Moreover, aid hydrometeorological predictions, foster development web-based educational platforms, support frameworks, digital twins, metaverse applications contexts. They further bolster scientific research development, enrich climate change vulnerability strengthen associated cyberinfrastructures. article delves into prospective developments realm natural pinpointing primary challenges gaps current highlighting intersections with future artificial intelligence solutions.

Language: Английский

Citations

4
Predicting Harmful Algal Blooms Using Explainable Deep Learning Models: A Comparative Study DOI Open Access
Bekir Zahit Demiray, Omer Mermer, Özlem Baydaroğlu

et al.

Water, Journal Year: 2025, Volume and Issue: 17(5), P. 676 - 676

Published: Feb. 26, 2025

Harmful algal blooms (HABs) have emerged as a significant environmental challenge, impacting aquatic ecosystems, drinking water supply systems, and human health due to the combined effects of activities climate change. This study investigates performance deep learning models, particularly Transformer model, there are limited studies exploring its effectiveness in HAB prediction. The chlorophyll-a (Chl-a) concentration, commonly used indicator phytoplankton biomass proxy for occurrences, is target variable. We consider multiple influencing parameters—including physical, chemical, biological quality monitoring data from stations located west Lake Erie—and employ SHapley Additive exPlanations (SHAP) values an explainable artificial intelligence (XAI) tool identify key input features affecting HABs. Our findings highlight superiority especially Transformer, capturing complex dynamics parameters providing actionable insights ecological management. SHAP analysis identifies Particulate Organic Carbon, Nitrogen, total phosphorus critical factors predictions. contributes development advanced predictive models HABs, aiding early detection proactive management strategies.

Language: Английский

Citations

0
Rain-on-snow climatology and its impact on flood risk in snow-dominated regions of Türkiye DOI
Serhan Yeşilköy, Özlem Baydaroğlu

Theoretical and Applied Climatology, Journal Year: 2025, Volume and Issue: 156(5)

Published: April 11, 2025

Language: Английский

Citations

0
Harmful algal bloom prediction using empirical dynamic modeling DOI
Özlem Baydaroğlu

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 959, P. 178185 - 178185

Published: Dec. 22, 2024

Language: Английский

Citations

1
Harrmful Algal Bloom Prediction using Emprical Dynamic Modelling DOI Creative Commons
Özlem Baydaroğlu

EarthArXiv (California Digital Library), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 2, 2024

Harmful Algal Blooms (HABs) can originate from a variety of reasons, including water pollution coming agriculture, effluent treatment plants, sewage system leaks, pH and light levels, the consequences climate change. In recent years, HAB events have become serious environmental problem, paralleling population growth, agricultural development, increasing air temperatures, declining precipitation. Hence, it is crucial to identify mechanisms responsible for formation harmful algal blooms (HABs), accurately assess their short- long-term impacts, quantify variations based on projections developing accurate action plans effectively managing resources. This present study utilizes empirical dynamic modeling (EDM) predict chlorophyll-a (chl-a) concentration Lake Erie. method characterized by its nonlinearity nonparametric nature. EDM has significant benefit in that surpasses constraints conventional statistical through use data-driven attractor reconstruction. Chl-a critical commonly used parameter prediction events. Erie an inland body experiences frequent phenomena as result location. With MAPE 4.31%, RMSE 6.24, coefficient determination 0.98, showed exceptional performance. These findings suggest underlying dynamics chl-a changes be well captured model.

Language: Английский

Citations

0
Testing protocols for smoothing datasets of hydraulic variables acquired during unsteady flows DOI
Özlem Baydaroğlu, Marian Muste, Atiye Cikmaz

et al.

Hydrological Sciences Journal, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 18

Published: Aug. 19, 2024

Flood wave propagation involves complex flow variable dependencies. Continuous in-situ hydrograph peak magnitude and timing data provide the most relevant information for understanding these New acoustic instruments can produce experimental evidence by extracting usable signals from noisy datasets. This study presents a new screening protocol to smoothen streamflow unwanted influences noise generated perturbations observational fluctuations. The combines quantitative (statistical fitness parameters) qualitative (domain expert judgments) evaluations. It is tested with 18 smoothing methods identify optimal conditioning candidates. Sensitivity analyses assess validity, generality, scalability of procedures. goal this analysis set mathematical foundation empirical results that lead unified, general conclusions on principles or protocols unsteady flows propagating in open channels, formulating practical guidance future acquisition processing, using better support data-driven modeling efforts.

Language: Английский

Citations

0