Ecologia Balkanica

Permanent URI for this collection

https://doi.uni-plovdiv.bg/handle/store/4
p-ISSN: 1314-0213 / e-ISSN: 1313-9940

Browse

Browsing Ecologia Balkanica by Author "Basha, Lule"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Evaluating heavy metal pollution and health risks in river systems using Random Forest and XGBoost: Evidence from the Shkumbin River
    (Plovdiv University Press "Paisii Hilendarski", 2025-12-19) Shyti, Bederiana; Basha, Lule; Bekteshi, Lirim
    Surface water contamination by heavy metals poses significant ecological and health risks due to their persistence, bioaccumulation, and toxicity. This research evaluated the concentrations of cadmium (Cd), chromium (Cr), copper (Cu), iron (Fe), lead (Pb), and zinc (Zn) in river water samples and assessed their impact on the Heavy Metal Pollution Index (HPI). Descriptive statistics revealed substantial variation among sampling sites, with HPI values ranging from 2.15 to 21.94. Although Cd and Pb were generally present in low concentrations, their localized maxima indicated potential hot spots of contamination, whereas Fe and Zn showed higher overall levels. To identify the most influential predictors of HPI, two machine learning regression models, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), were implemented. The RF model explained more than 90% of the variance in HPI, with Cd, Zn, and Cr emerging as the most critical contributors. The XGBoost model achieved even higher predictive accuracy (R² = 0.998, RMSE = 0.76), confirming Cd and Cr as dominant predictors, together accounting for nearly 80% of the model’s explanatory power. These findings highlight the pivotal role of Cd and Cr in shaping HPI dynamics and demonstrate the utility of ensemble learning methods for environmental monitoring and risk assessment.
  • Thumbnail Image
    Item
    Physico-chemical parameters and PCA approach to assess river water quality – a case study (Albania)
    (Plovdiv University Press "Paisii Hilendarski", 2025-06-30) Hoxha, Belinda; Shyti, Bederiana; Papajani, Blerina; Mazrreku, Armela; Osmani, Marilda; Basha, Lule
    Water quality refers to the physical, chemical and biological characteristics of water that determine its suitability for a specific use, such as drinking, industry, irrigation or supporting aquatic life. It is assessed by comparing water’s properties against established standards for various uses. Factors influencing water quality include natural elements like weather and geology, and human activities like pollution and land use. Water Quality Index (WQI) is a widely used tool for summarizing and communicating water quality information. It is a valuable and unique statistical approach that consolidates the experimental results of various physicochemical parameters into a single comprehensive and practical term in order to represent the overall quality status of water. The aim of the study is to demonstrate the ability of statistical methods in water quality prediction, specifically by identifying the most important parameters that influence the Water Quality Index (WQI). This involves the use of statistical techniques to analyze water quality data and identify the main factors that influence the overall water quality, potentially leading to a more efficient and accurate water quality management. The study takes in consideration physico-chemical parameters analyzed in Shkumbini River in Albania. The laboratory data from six sampling points during four years are gathered and analyzed based on water quality standards and statistically with PCA (Principal Component Analysis). The chosen parameters to evaluate water quality are TDS, GH, BOD, pH, DO, Cl, HCO3- and thermotolerant coliforms, which are also used to monitor the suitability of the PCA method in the determination of WQI. The physico-chemical parameters were evaluated against international water standards. Additionally, the PCA method showed that the order of indicators determining the WQI depends on the distance between the variables and the origin. The study reveals that using the PCA method, the recommended nine parameters are sufficient to determine the WQI value, and the cumulative proportion of Component 1, Component 2 and Component 3 explains nearly 63% of the total variance.