Bahman Jabbarian Amiri

This research delves into the efficacy of machine learning models in predicting water quality parameters within a catchment area, focusing on unraveling the significance of individual input variables. In order to manage water quality, it is necessary to determine the relationship between the physical attributes of the catchment, such as geological permeability and hydrologic soil groups, and in-stream water quality parameters. Water quality data were acquired from the Iran Water Resource Management Company (WRMC) through monthly sampling. For statistical analysis, the study utilized 5-year means (1998–2002) of water quality data. A total of 88 final stations were included in the analysis. Using machine learning methods, the paper gives relations for 11 in-stream water quality parameters: Sodium Adsorption Ratio (SAR), Na⁺, Mg²⁺, Ca²⁺, SO₄²⁻, Cl⁻, HCO³⁻, K⁺, pH, conductivity (EC), and Total Dissolved Solids (TDS). To comprehensively evaluate model performance, the study employs diverse metrics, including Pearson’s Linear Correlation Coefficient (R) and the mean absolute percentage error (MAPE). Notably, the Random Forest (RF) model emerges as the standout model across various water parameters. Integrating research outcomes enables targeted strategies for fostering environmental sustainability, contributing to the broader goal of cultivating resilient water ecosystems. As a practical pathway toward achieving a delicate balance between human activities and environmental preservation, this research actively contributes to sustainable water ecosystems.

Urban stormwater runoff has posed significant challenges in the face of urbanization and climate change, emphasizing the importance of trees in providing runoff reduction ecosystem services (RRES). However, the sustainability of RRES can be disturbed by urban landscape modification. Understanding the impact of landscape structure on RRES is crucial to manage urban landscapes effectively to sustain supply of RRES. So, this study developed a new approach that analyzes the relationship between the landscape structural pattern and the RRES in Tabriz, Iran. The provision of RRES was estimated using the i-Tree Eco model. Landscape structure-related metrics of land use and cover (LULC) were derived using FRAGSTATS to quantify the landscape structure. Stepwise regression analysis was used to assess the relationship between landscape structure metrics and the provision of RRES. The results indicated that throughout the city, the trees prevented 196854.15 m³ of runoff annually. Regression models (p ≤ 0.05) suggested that the provision of RRES could be predicted using the measures of the related circumscribing circle metric (0.889 ≤ r² ≤ 0.954) and the shape index (r² = 0.983) of LULC patches. The findings also revealed that the regularity or regularity of the given LULC patches’ shape could impact the patches’ functions, which, in turn, affects the provision of RRES. The landscape metrics can serve as proxies to predict the capacity of trees for potential RRES using the obtained regression models. This helps to allocate suitable LULC through optimizing landscape metrics and management guidance to sustain RRES.

River water quality can be affected by a range of factors, including both point and non-point sources of pollution. Of these factors, changes in land use and land cover are particularly significant, as they can alter the structure of the landscape and consequently impact water quality in rivers. To investigate the relationship between patch shapes, a measure of landscape structure, and river water quality at the catchment scale, this study utilized spatial data from 39 catchments in the southern basin of the Caspian Sea. This study employed stepwise multivariate regression modeling to explore how changes in landscape structure, which can be measured by landscape metrics including the shape index, the contiguity index, the fractal dimension index, the perimeter–area ratio, and the related circumscribing circle, impact water quality variables. Four regression models—linear, exponential, logarithmic, and power models—were evaluated, and the most appropriate model for each water quality variable was determined using the Akaike information criterion. To validate the models, three groups of accuracy metrics were employed, and Monte Carlo simulation was utilized to analyze the models’ behavior. This study found that landscape structure metrics could explain up to 71% and 82% of the variations in the measures of TDS and Mg, respectively, and the shape index, the contiguity index, and fractal metric were particularly significant in predicting water quality. Moreover, this study verified the accuracy of the models and revealed that changes in landscape structure, such as a decline in patch continuity and an increase in patch complexity, can impact river water quality. The findings of this study suggest optimizing landscape structure metrics in land use planning to reduce river pollution and improve water quality.

This study examines the effects of the change in the shape of landscape patches, known as landscape structure, on ecological susceptibility, which is defined using the object-oriented method. The aim is to determine whether ecological susceptibility is influenced by the shape of the landscape patches in the southern basin of the Caspian Sea. The multivariate linear regression approach is applied to discover the extent to which the mean, median, and weighted average of the landscape structure metrics can explain the total variations of the ecological susceptibility. To determine the optimal models, an intermodel comparison is conducted using the Akaike information criterion. Sensitivity and uncertainty analyses were performed to determine how sensitive ecological susceptibility is to changes in the variables of the models and how they behave under varying conditions. The models (0.64≥r2≥0.27, p ≤ 0.05) indicate that the landscape structure metrics can be applied to predict ecological susceptibility. Examining the mean, median, and weighted average of the landscape metrics in estimating ecological susceptibility also reveals that the models made by the mean and median values have less uncertainty than those developed by the weighted average. The results show that the regularity or irregularity in the shape of the landscape patches and the degree of contiguity of the land use/land cover patches can significantly affect ecological susceptibility. Closed deciduous broad-leaf forest patches, closed mixed forest patches, and open mixed forest patches can be considered crucial land use/land covers to estimate ecological susceptibility.

Scaling models is one of the challenges for water resource planning and management, with the aim of bringing the developed models into practice by applying them to predict water quality and quantity for catchments that lack sufficient data. For this study, we evaluated artificial neural network (ANN) training algorithms to predict the water quality index in a source catchment. Then, multiple linear regression (MLR) models were developed, using the predicted water quality index of the ANN training algorithms and water quality variables, as dependent and independent variables, respectively. The most appropriate MLR model has been selected on the basis of the Akaike information criterion, sensitivity and uncertainty analyses. The performance of the MLR model was then evaluated by a variable aggregation and disaggregation approach, for upscaling and downscaling proposes, using the data from four very large- and three large-sized catchments and from eight medium-, three small- and seven very small-sized catchments, where they are located in the southern basin of the Caspian Sea. The performance of seven artificial neural network training algorithms, including Quick Propagation, Conjugate Gradient Descent, Quasi-Newton, Limited Memory Quasi-Newton, Levenberg–Marquardt, Online Back Propagation, and Batch Back Propagation, has been evaluated to predict the water quality index. The results show that the highest mean absolute error was observed in the WQI, as predicted by the ANN LM training algorithm; the lowest error values were for the ANN LMQN and CGD training algorithms. Our findings also indicate that for upscaling, the aggregated MLR model could provide reliable performance to predict the water quality index, since the r² coefficient of the models varies from 0.73 ± 0.2 for large catchments, to 0.85 ± 0.15 for very large catchments, and for downscaling, the r² coefficient of the disaggregated MLR model ranges from 0.93 ± 0.05 for very large catchments, to 0.97 ± 0.02 for medium catchments. Therefore, scaled models could be applied to catchments that lack sufficient data to perform a rapid assessment of the water quality index in the study area.

Most studies that address the relationship between socio-economic characteristics and soil erosion focus on the effects of soil erosion on socio-economic conditions at different levels, from global to smallholder. Few, if any, efforts are made to address the influence of socio-economic variables on the soil erosion rate as an indicator of landscape degradation. The present study was carried out using spatial data from 402 catchments that cover Poland, to find out how socio-economic variables, which include area-weighted average income per capita (PLN km⁻²), area-weighted average gross domestic product (PLN km⁻²), population density (person km⁻²), and human development index can drive the soil erosion rate (kg ha⁻¹ yr⁻¹), along with annual precipitation, soil and geomorphological variables that include soil organic carbon content, soil water content, clay ratio, stream gradient, and terrain slope. The results showed that the soil erosion rate is indirectly driven by the socio-economic variables in the study catchments, as it is alleviated by increasing population density, the area-weighted average gross domestic product, and the human development index. Furthermore, analyzing the incremental relationship between soil erosion rate and the area-weighted average of socio-economic variables revealed that no uniform change can be observed in the relationship between the area-weighted average socio-economic variables and soil erosion in the study catchments.

The present study investigated the effects of changes in landscape configuration on river water quality, which is calculated by chemical export coefficients, using spatial data onto 31 catchments in the southwestern part of the Caspian Sea basin by applying stepwise multivariate regression models. The water quality modeling has been carried out applying the chemical export coefficients of sulfate, bicarbonate, chlorine, calcium, magnesium, and sodium, and eight landscape metrics (including interspersion juxtaposition index, percentage of like adjacencies, aggregation index, clumpiness index, normalized landscape shape index, patch cohesion index, landscape division index, and splitting index), by which landscape configuration is analyzed. The results indicated that the sulfate (0.25 ± 0.33 gr ha⁻¹yr⁻¹), bicarbonate (0.61 ± 0.87 gr ha⁻¹ yr⁻¹), chlorine (0.17 ± 0.23 gr ha⁻¹ yr⁻¹), calcium (0.16 ± 0.21 gr ha⁻¹ yr⁻¹), magnesium (0.05 ± 0.07 gr ha⁻¹ yr⁻¹), and sodium (0.16 ± 0.21 gr ha⁻¹ yr⁻¹) are annually exported from the study catchments into the rivers. The change in landscape configuration has significantly explained the chemical export coefficients of sulfate, bicarbonate, chlorine, calcium, magnesium, and sodium. The findings showed the cohesion and coherence of the permanently irrigated land patches resulting in the discontinuity of the broad-leaved forest and grassland ecosystems degraded river water quality.

In this study, the soil erosion regulation ecosystem services of the CORINE land use/ land cover types along with soil intrinsic features and geomorphological factors were examined by using the soil erosion data of 327 catchments in Poland, with a mean area of 510 ± 330 km², applying a multivariate regression modeling approach. The results showed that soil erosion is accelerated by the discontinuous urban fabric (r = 0.224, p ≤ 0.01), by construction sites (r = 0.141, p ≤ 0.05), non-irrigated arable land (r = 0.237, p ≤ 0.01), and is mitigated by coniferous forest (r = −0.322, p ≤ 0.01), the clay ratio (r = −0.652, p ≤ 0.01), and the organic content of the soil (r = −0.622, p ≤ 0.01). The models also indicated that there is a strong relationship between soil erosion and the percentage of land use/land cover types (r² = [0.62, 0.82, 0.83, 0.74]), i.e., mixed forest, non-irrigated arable land, fruit trees and berry plantations, broad-leaf forest, sport and leisure facilities, construction sites, and mineral extraction sites. The findings show that the soil erosion regulation ecosystem service is sensitive to broadleaf forests, rainfed agriculture, soil water content, terrain slope, drainage network density, annual precipitation, the clay ratio, the soil carbon content, and the degree of sensitivity increases from the broadleaf forest to the soil carbon content.

In this study we investigated the performance of the Tank hydrologic model in predicting rainfall–runoff using a descriptive–analytical approach, i…