Application of remodeled water quality indices for the appraisal of water quality in a Himalayan lake

Natural and anthropogenic pollution influence the general hydrochemistry of freshwater sources. Effective management strategies need an accurate evaluation of the water quality parameters, and inferences extracted from the data should be based on the most appropriate statistical methods. Conventional water quality indices (WQI) being related to a large number of water quality parameters results in significant variability and analytical costs. The focus of this study was to develop a remodeled water quality index (WQI_min) based on the localized trends in water quality and demonstrate it to understand water quality variations of Dal Lake (a freshwater lake in the Himalayan region). Spatio-temporal changes and trends of 14 water quality parameters were investigated that were arbitrated from the samples collected at 11 sampling locations during the water quality monitoring across the Dal Lake from September 2017 to August 2020. The results signify that the general mean WQI value was 81.9, and seasonal average WQI values ranges from 79.44 to 84.55. The water quality showed seasonal variance, with lowest values in summer, succeeded by autumn and winter, and highest in spring. Moreover, the results from stepwise multiple regression analysis indicated that the WQI_min significantly correlates with six water quality parameters (ammonia, dissolved oxygen, chemical oxygen demand, temperature, turbidity, and nitrate) in Dal Lake. The WQI_min model predicted the water quality of the Dal Lake with a coefficient of determination (R²) value of 0.96, root mean square error (RMSE) value of 4.1, and percentage error (PE) of 5.3%. The developed WQI_min model can be applied as a cost-effective and efficacious approach to determine the water quality of fresh surface water bodies.

A two-layer nested heterogeneous ensemble learning predictive method for COVID-19 mortality

The COVID-19 epidemic has had a great adverse impact on the world, having taken a heavy toll, killing hundreds of thousands of people. In order to help the world better combat COVID-19 and reduce its death toll, this study focuses on the COVID-19 mortality. First, using the multiple stepwise regression analysis method, the factors from eight aspects (economy, society, climate etc.) that may affect the mortality rates of COVID-19 in various countries is examined. In addition, a two-layer nested heterogeneous ensemble learning-based prediction method that combines linear regression (LR), support vector machine (SVM), and extreme learning machine (ELM) is developed to predict the development trends of COVID-19 mortality in various countries. Based on data from 79 countries, the experiment proves that age structure (proportion of the population over 70 years old) and medical resources (number of beds) are the main factors affecting the mortality of COVID-19 in each country. In addition, it is found that the number of nucleic acid tests and climatic factors are correlated with COVID-19 mortality. At the same time, when predicting COVID-19 mortality, the proposed heterogeneous ensemble learning-based prediction method shows better prediction ability than state-of-the-art machine learning methods such as LR, SVM, ELM, random forest (RF), long short-term memory (LSTM) etc.

Simulating chlorophyll-a fluorescence changing rate and phycocyanin fluorescence by using a multi-sensor system in Lake Taihu, China

Algal pollution in water sources has posed a serious problem. Estimating algal concentration in advance saves time for drinking water plants to take measures and helps us to understand causal chains of algal dynamics. This paper explores the possibility of building a short-term algal early warning model with online monitoring systems. In this study, we collected high-frequency data for water quality and weather conditions in shallow and eutrophic Lake Taihu by an in situ multi-sensor system (BIOLIFT) combined with a weather station. Extracted chlorophyll-a from water samples and chlorophyll-a fluorescence differentiated according to different algal classeses verified that chlorophyll-a fluorescence continuously measured by BIOLIFT only represent chlorophyll-a of green algae and diatoms. Stepwise linear regression was used to simulate the chlorophyll-a fluorescence changing rate of green algae and diatoms together (ΔChl_a-f%) and phycocyanin fluorescence concentration (blue-green algae) on the water surface layer (CyanoS). The results show that nutrients (total N, NO₃-N, NH₄-N, total P) were not necessary parameters for short-term algal models. ΔChl_a-f % is greatly influenced by the seasons, so seasonal partition of data before modeling is highly recommended. CyanoS_max and ΔChl_a-f% were simulated by only using multi-sensor and meteorological data (R² = 0.73; 0.75). All the independent variables (wave, water temperature, relative humidity, depth, cloud cover) used in the model were measured online and predictable. Wave height is the most important independent variable in the shallow lake. This paper offers a new approach to simulate and predict the algal dynamics, which also can be applied in other surface water.

Multi-scale relationship between land use/land cover types and water quality in different pollution source areas in Fuxian Lake Basin

The spatial-temporal evolution of land use and land cover (LULC) and its multi-scale impact on the water environment is becoming highly significant in the LULC research field. The current research results show that the more significant scale impact on LULC and water quality in the whole basin and the riparian buffer scale is unclear. A consensus has not been reached about the optimal spatial scale problem in the relationship between the LULC and water quality. The typical lake basin of the Fuxian Lake watershed was used as the research area and the scale relationship between the LULC and water quality was taken as the research object. High resolution remote sensing images, archival resources of surveying, mapping and geographic information, and the monitoring data of water quality were utilized as the main data sources. Remote sensing and Geometric Information Technology were applied. A multi-scale object random forest algorithm (MSORF) was used to raise the classification accuracy of the high resolution remote sensing images from 2005 to 2017 in the basin and the multi-scale relationship between the two was discussed using the Pearson correlation analysis method. From 2005 to 2017, the water quality indicators (Chemical Oxygen Demand (COD), Total Phosphorous (TP), Total Nitrogen (TN)) of nine rivers in the lake's basin and the Fuxian Lake center were used as response variables and the LULC type in the basin was interpreted as the explanation variable. The stepwise selection method was used to establish a relationship model for the water quality of the water entering the lake and the significance of the LULC type was established at p < 0.05.The results show that in the seven spatial scales, including the whole watershed, sub-basin, and the riparian buffer zone (100 m, 300 m, 500 m, 700 m, and 1,000 m): (1) whether it is in the whole basin or buffer zone of different pollution source areas, impervious surface area (ISA), or other land and is positively correlated with the water quality and promotes it; (2) forestry and grass cover is another important factor and is negatively correlated with water quality; (3) cropping land is not a major factor explaining the decline in water quality; (4) the 300 m buffer zone of the river is the strongest spatial scale for the LULC type to affect the Chemical Oxygen Demand (COD). Reasonable planning for the proportion of land types in the riparian zone and control over the development of urban land in the river basin is necessary for the improvement of the urban river water quality. Some studies have found that the relationship between LULC and water quality in the 100 m buffer zone is more significant than the whole basin scale. While our study is consistent with the results of research conducted by relevant scholars in Aibi Lake in Xinjiang, and Erhai and Fuxian Lakes in Yunnan. Thus, it may be inferred that for the plateau lake basin, the 300 m riparian buffer is the strongest spatial scale for the LULC type to affect COD.