Incorporation of water quality index models with machine learning-based techniques for real-time assessment of aquatic ecosystems.

Water quality index (WQI) is a well-established tool for assessing the overall quality of fresh inland-waters. However, the effectiveness of real-time assessment of aquatic ecosystems using the WQI is usually impacted by the absence of some water quality parameters in which their accurately in-situ measurements are impossible and face difficulties. Using a rich water quality dataset spanned from 1980 to 2023, we employed four machine learning-based models to estimate the British Colombia WQI (BCWQI) in the Lake Päijänne, Finland, without parameters like chemical oxygen demand (COD) and total phosphorus (TP). Measurement of both COD and TP is time-consuming, needs laboratory equipment and labor costs, and faces sampling-related difficulties. Our results suggest the machine learning-based models successfully estimate the BCWQI in Lake Päijänne when TP and COD are omitted from the dataset. The long-short term memory model is the least sensitive model to exclusion of COD and TP from inputs. This model with the coefficient of determination and root-mean squared error of 0.91 and 0.11, respectively, outperforms the support vector regression, random forest, and neural network models in real-time estimation of the BCWQI in Lake Päijänne. Incorporation of BCWQI with the machine learning-based models could enhance assessment of overall quality of inland-waters with a limited database in a more economical and time-saving way. Our proposed method is an effort to replace the traditional offline water quality assessment tools with a real-time model and improve understanding of decision-makers on the effectiveness of management practices on the changes in lake water quality.

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

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