Employing hybrid deep learning for near-real-time forecasts of sensor-based algal parameters in a Microcystis bloom-dominated lake
Copyright © 2024 Elsevier B.V. All rights reserved..
Harmful cyanobacterial blooms (CyanoHABs) are increasingly impacting the ecosystem of lakes, reservoirs and estuaries globally. The integration of real-time monitoring and deep learning technology has opened up new horizons for early warnings of CyanoHABs. However, unlike traditional methods such as pigment quantification or microscopy counting, the high-frequency data from in-situ fluorometric sensors display unpredictable fluctuations and variability, posing a challenge for predictive models to discern underlying trends within the time-series sequence. This study introduces a hybrid framework for near-real-time CyanoHABs predictions in a cyanobacterium Microcystis-dominated lake - Lake Dianchi, China. The proposed model was validated using hourly Chlorophyll-a (Chl a) concentrations and algal cell densities. Our results demonstrate that applying decomposition-based singular spectrum analysis (SSA) significantly enhances the prediction accuracy of subsequent CyanoHABs models, particularly in the case of temporal convolutional network (TCN). Comparative experiments revealed that the SSA-TCN model outperforms other SSA-based deep learning models for predicting Chl a (R2 = 0.45-0.93, RMSE = 2.29-5.89 μg/L) and algal cell density (R2 = 0.63-0.89, RMSE = 9489.39-16,015.37 cells/mL) at one to four steps ahead predictions. The forecast of bloom intensities achieved a remarkable accuracy of 98.56 % and an average precision rate of 94.04 % ± 0.05 %. In addition, scenarios involving various input combinations of environmental factors demonstrated that water temperature emerged as the most effective driver for CyanoHABs predictions, with a mean RMSE of 2.94 ± 0.12 μg/L, MAE of 1.55 ± 0.09 μg/L, and R2 of 0.83 ± 0.01. Overall, the newly developed approach underscores the potential of a well-designed hybrid deep-learning framework for accurately predicting sensor-based algal parameters. It offers novel perspectives for managing CyanoHABs through online monitoring and artificial intelligence in aquatic ecosystems.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:922 |
|---|---|
| Enthalten in: |
The Science of the total environment - 922(2024) vom: 20. März, Seite 171009 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Lan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Cyanobacterial blooms |
|---|
| Anmerkungen: |
Date Completed 20.03.2024 Date Revised 20.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.scitotenv.2024.171009 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM368929647 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM368929647 | ||
| 003 | DE-627 | ||
| 005 | 20240320234357.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240229s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.scitotenv.2024.171009 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1337.xml |
| 035 | |a (DE-627)NLM368929647 | ||
| 035 | |a (NLM)38402991 | ||
| 035 | |a (PII)S0048-9697(24)01148-3 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Lan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Employing hybrid deep learning for near-real-time forecasts of sensor-based algal parameters in a Microcystis bloom-dominated lake |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 20.03.2024 | ||
| 500 | |a Date Revised 20.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2024 Elsevier B.V. All rights reserved. | ||
| 520 | |a Harmful cyanobacterial blooms (CyanoHABs) are increasingly impacting the ecosystem of lakes, reservoirs and estuaries globally. The integration of real-time monitoring and deep learning technology has opened up new horizons for early warnings of CyanoHABs. However, unlike traditional methods such as pigment quantification or microscopy counting, the high-frequency data from in-situ fluorometric sensors display unpredictable fluctuations and variability, posing a challenge for predictive models to discern underlying trends within the time-series sequence. This study introduces a hybrid framework for near-real-time CyanoHABs predictions in a cyanobacterium Microcystis-dominated lake - Lake Dianchi, China. The proposed model was validated using hourly Chlorophyll-a (Chl a) concentrations and algal cell densities. Our results demonstrate that applying decomposition-based singular spectrum analysis (SSA) significantly enhances the prediction accuracy of subsequent CyanoHABs models, particularly in the case of temporal convolutional network (TCN). Comparative experiments revealed that the SSA-TCN model outperforms other SSA-based deep learning models for predicting Chl a (R2 = 0.45-0.93, RMSE = 2.29-5.89 μg/L) and algal cell density (R2 = 0.63-0.89, RMSE = 9489.39-16,015.37 cells/mL) at one to four steps ahead predictions. The forecast of bloom intensities achieved a remarkable accuracy of 98.56 % and an average precision rate of 94.04 % ± 0.05 %. In addition, scenarios involving various input combinations of environmental factors demonstrated that water temperature emerged as the most effective driver for CyanoHABs predictions, with a mean RMSE of 2.94 ± 0.12 μg/L, MAE of 1.55 ± 0.09 μg/L, and R2 of 0.83 ± 0.01. Overall, the newly developed approach underscores the potential of a well-designed hybrid deep-learning framework for accurately predicting sensor-based algal parameters. It offers novel perspectives for managing CyanoHABs through online monitoring and artificial intelligence in aquatic ecosystems | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Cyanobacterial blooms | |
| 650 | 4 | |a Deep-learning modelling | |
| 650 | 4 | |a Early warning | |
| 650 | 4 | |a Interpretable framework | |
| 650 | 4 | |a Real-time monitoring | |
| 650 | 4 | |a Time series decomposition | |
| 700 | 1 | |a Shan, Kun |e verfasserin |4 aut | |
| 700 | 1 | |a Yi, Yang |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Hong |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Yanyan |e verfasserin |4 aut | |
| 700 | 1 | |a Xie, Mingjiang |e verfasserin |4 aut | |
| 700 | 1 | |a Zhou, Qichao |e verfasserin |4 aut | |
| 700 | 1 | |a Shang, Mingsheng |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The Science of the total environment |d 1972 |g 922(2024) vom: 20. März, Seite 171009 |w (DE-627)NLM000215562 |x 1879-1026 |7 nnns |
| 773 | 1 | 8 | |g volume:922 |g year:2024 |g day:20 |g month:03 |g pages:171009 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.scitotenv.2024.171009 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 922 |j 2024 |b 20 |c 03 |h 171009 | ||