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

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
A Phenology-Dependent Analysis for Identifying Key Drought Indicators for Crop Yield based on Causal Inference and Information Theory DOI Creative Commons
Özlem Baydaroğlu, Serhan Yeşilköy, İbrahim Demir

et al.

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

Published: Aug. 29, 2024

Drought indicators, which are quantitative measurements of drought severity and duration, used to monitor predict the risk effects drought, particularly in relation sustainability agriculture water supplies. This research uses causal inference information theory discover index, is most efficient indicator for agricultural productivity a valuable metric estimating predicting crop yield. The connection between precipitation, maximum air temperature, indices corn soybean yield ascertained by cross convergent mapping (CCM), while transfer them determined through entropy (TE). conducted on rainfed lands Iowa, considering phenological stages crops. Based nonlinearity analysis using S-map, it that causality could not be carried out CCM due absence data. results intriguing as they uncover both precipitation temperature indices. analysis, with strongest relationship production SPEI-9m SPI-6m during silking period, SPI-9m doughing period. Therefore, these may considered effective predictors prediction models. study highlights need periods when production, differs two periods.

Language: Английский

Citations

2
Crop Yield Prediction DOI

P. Srinivas Karthik,

Bolloju Sanjith,

Betha Charan Satya Raj

et al.

Published: June 21, 2024

Language: Английский

Citations

1
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