Modelling impacts of climate change and anthropogenic activities on inflows and sediment loads of wetlands: case study of the Anzali wetland

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: April 3, 2023

Understanding the effects of climate change and anthropogenic activities on hydrogeomorpholgical parameters in wetlands ecosystems is vital for designing effective environmental protection control protocols these natural capitals. This study develops methodological approach to model streamflow sediment inputs under combined land use / cover (LULC) changes using Soil Water Assessment Tool (SWAT). The precipitation temperature data from General Circulation Models (GCMs) different Shared Socio-economic Pathway (SSP) scenarios (i.e., SSP1-2.6, SSP2-4.5, SSP5-8.5) are downscaled bias-corrected with Euclidean distance method quantile delta mapping (QDM) case Anzali wetland watershed (AWW) Iran. Land Change Modeler (LCM) adopted project future LULC at AWW. results indicate that air across AWW will decrease increase, respectively, SSP5-8.5 scenarios. Streamflow loads reduce sole influence SSP2-4.5 An increase load inflow was observed changes, this mainly due projected increased deforestation urbanization findings suggest densely vegetated regions, located zones steep slope, significantly prevents large high input Under by 2100, total reach 22.66, 20.83, 19.93 million tons scenarios, respectively. highlight without any robust interventions, degrade ecosystem partly-fill basin, resulting resigning Montreux record list Ramsar Convention Wetlands International Importance.

Language: Английский

---

Anzali Wetland Crisis: Unraveling the Decline of Iran's Ecological Gem

Journal of Geophysical Research Atmospheres, Journal Year: 2024, Volume and Issue: 129(4)

Published: Feb. 12, 2024

Abstract The wetland loss rate in Iran is faster than the global average. Comprehending shrinkage Iranian wetlands and identifying underlying drivers of these changes essential for safeguarding their ecosystems' health services. This study proposes a novel gray‐box modeling framework to quantify effects climate change anthropogenic activities on wetlands, by combining process‐based machine learning models. developed model utilized project Anzali coastal simulating complex interaction between meteorological, hydrological, sea water level characteristics, surface area. Our aggregates Soil Water Assessment Tool model, 12 General Circulation Models Coupled Model Intercomparison Project Phase 6, Landsat imagery, Long Short‐Term Memory till 2100. A comprehensive range Land Use/Cover scenarios are analyzed. results show that will seasonally desiccate 2058, mainly due increasing air temperature, reduction precipitation inflow, excessive sediment loading wetland, decline Caspian Sea level. For optimistic scenarios, where no considered, gradually diminish become seasonal waterbody outcomes this highlight desiccation has profound implications regional‐scale ecological balance, ecosystem function, public health, local economy. Robust environmental interventions sustainable development strategies urgently needed mitigate detrimental impacts wetland.

Language: Английский

---

Evaluation of water quality indexes with novel machine learning and SHapley Additive ExPlanation (SHAP) approaches

Journal of Water Process Engineering, Journal Year: 2024, Volume and Issue: 58, P. 104789 - 104789

Published: Jan. 17, 2024

Language: Английский

---

Marine waters assessment using improved water quality model incorporating machine learning approaches

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 344, P. 118368 - 118368

Published: June 24, 2023

In marine ecosystems, both living and non-living organisms depend on "good" water quality. It depends a number of factors, one the most important is quality water. The index (WQI) model widely used to assess quality, but existing models have uncertainty issues. To address this, authors introduced two new WQI models: weight based weighted quadratic mean (WQM) unweighted root squared (RMS) models. These were in Bay Bengal, using seven indicators including salinity (SAL), temperature (TEMP), pH, transparency (TRAN), dissolved oxygen (DOX), total oxidized nitrogen (TON), molybdate reactive phosphorus (MRP). Both ranked between "fair" categories, with no significant difference models' results. showed considerable variation computed scores, ranging from 68 88 an average 75 for WQM 70 76 72 RMS. did not any issues sub-index or aggregation functions, had high level sensitivity (R2 = 1) terms spatio-temporal resolution waterbodies. study demonstrated that approaches effectively assessed waters, reducing improving accuracy score.

Language: Английский

---

Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 904, P. 166960 - 166960

Published: Sept. 9, 2023

Language: Английский

---

Research on the factors influencing nanofiltration membrane fouling and the prediction of membrane fouling

Journal of Water Process Engineering, Journal Year: 2024, Volume and Issue: 59, P. 104876 - 104876

Published: Feb. 7, 2024

Language: Английский

---

Efficient data-driven machine learning models for scour depth predictions at sloping sea defences

Frontiers in Built Environment, Journal Year: 2024, Volume and Issue: 10

Published: Feb. 9, 2024

Seawalls are critical defence infrastructures in coastal zones that protect hinterland areas from storm surges, wave overtopping and soil erosion hazards. Scouring at the toe of sea defences, caused by wave-induced accretion bed material imposes a significant threat to structural integrity infrastructures. Accurate prediction scour depths is essential for appropriate efficient design maintenance structures, which serve mitigate risks failure through scouring. However, limited guidance predictive tools available estimating scouring sloping structures. In recent years, Artificial Intelligence Machine Learning (ML) algorithms have gained interest, although they underpin robust models many engineering applications, such yet be applied prediction. Here we develop present ML-based predicting seawall. Four ML algorithms, namely, Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Neural Networks (ANNs), Support Vector Regression (SVMR) utilised. Comprehensive physical modelling measurement data utilised validate models. A Novel framework feature selection, importance, hyperparameter tuning adopted pre- post-processing steps In-depth statistical analyses proposed evaluate performance The results indicate minimum 80% accuracy across all tested this study overall, SVMR produced most accurate predictions with Coefficient Determination ( r 2 ) 0.74 Mean Absolute Error (MAE) value 0.17. algorithm also offered computationally among tested. methodological can datasets rapid assessment facilitating model-informed decision-making.

Language: Английский

---

Machine learning prediction of wave characteristics: Comparison between semi-empirical approaches and DT model

Ocean Engineering, Journal Year: 2023, Volume and Issue: 286, P. 115583 - 115583

Published: Aug. 19, 2023

Language: Английский

---

Hybrid machine learning models for prediction of daily dissolved oxygen

Journal of Water Process Engineering, Journal Year: 2023, Volume and Issue: 54, P. 103957 - 103957

Published: June 27, 2023

Language: Английский

---

A multi-fidelity deep operator network (DeepONet) for fusing simulation and monitoring data: Application to real-time settlement prediction during tunnel construction

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108156 - 108156

Published: March 6, 2024

Ground settlement prediction during mechanized tunneling is of paramount importance and remains a challenging research topic. Typically, two paradigms are existing: physics-driven approach utilizing numerical simulation models for prediction, data-driven employing machine learning techniques to learn mappings between influencing factors the settlement. To integrate advantages both approaches assimilate data from different sources, we propose multi-fidelity deep operator network (DeepONet) framework, leveraging recently developed methods. The presented framework comprises components: low-fidelity subnet that captures fundamental ground patterns obtained finite element simulations, high-fidelity learns nonlinear correlation real engineering monitoring data. A pre-processing strategy causality adopted consider spatio-temporal characteristics tunnel excavation. results show proposed method can effectively capture physical information provided by simulations accurately fit measured (R2 around 0.9) as well. Notably, even when dealing with very limited noisy (with 50% error), model robust, achieving satisfactory R2>0.8. In comparison, R2 score pure simulation-based only 0.2. utilization transfer significantly reduces training time 20 min within 30 s, showcasing potential our real-time construction.

Language: Английский

---