HAHossein Amini

Hossein Amini

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hossein Amini has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Interpretable machine learning for river salinity dynamics in arid basins

    by Hossein Amini, Reza Shakeri, Narjes Ghaderi, Farshid Fakheri, Khosro Morovati, Banafsheh Zahraie, Reza Ahmadian

    Managing salinity in arid rivers is impeded by sparse monitoring, relying on low-frequency grab samples that miss hydrological event dynamics. Here, interpretable machine learning is applied to a 50-year monthly archive (1968–2018; Discharge, major ions, pH) from three stations on Iran’s Karkheh River. Gradient Boosting Regression achieves high predictive skill for Total Dissolved Solids (TDS)/Electrical Conductivity (EC) (test-set R 2 = 0.94/0.97; RMSE = 55 mg L −1 /56 µS cm −1 ), validated via time-aware cross-validation. SHAP-based feature attribution reveals that Na + and SO 4 –2 are the strongest contributors to TDS, while Na + and Cl − dominate EC, consistent with conservative salinity sources under baseflow conditions. A reduced-input decision tree (four predictors) retains R 2 = 0.81–0.87, enabling minimal-sensor monitoring. Flow-regime partitioning and STL (Seasonal-Trend decomposition using Locally estimated scatterplot smoothing)-detrended event composites reveal low-flow salinization and ion-specific post-flood recovery (Cl − : 1–2 months; Na + : 2–3 months), guiding targeted sampling. This framework extracts predictive power, process associations, and operational guidance from legacy grab-sample archives, scalable to data-limited basins worldwide.


  • Open Access

    Identification, characterization, and quantification of microplastics in water and sediments of high-altitude Himalayan Dal Lake

    by Yousuf Dar Jaffer, Raj Mukhopadhyay, Chittaranjan Raul, Hossien Amini, Irfan Bhat, Mukesh Bhendarkar, Shakir Ahmad Mir, Satyendra Kumar, Rajender Kumar Yadav

    Plastic debris is believed to be widespread in freshwater ecosystems globally. The present study aims to characterize, identify, and measure microplastic (MP) concentrations in Dal Lake, one of the most renowned high-altitude urban Himalayan lakes located at 1583 m above mean sea level and covering an area of 24 km2. Results revealed that the number of MPs in lake surface water and sediments ranged from 140 ± 20 to 846 ± 136 particles l−1 and 2616 ± 1016 to 12 966 ± 496 particles kg−1 dry weight, respectively. The relatively higher number of MPs in Dal Lake sediments indicates that sediments act as a silent trap, accumulating MPs over time. The MPs exhibited three morphological types, i.e. fragment, film, and line, indicating the fragmentation of bigger plastic particles. The most prevalent size fraction of MPs (90%) in both water and sediment was less than 500 µm. Count-based pollution level indexing indicated higher contamination in sediments (2.05 times that in surface water), placing the lake’s health at a high hazard level (category II). Domestic waste from urban areas, tourism activities, and road runoff can serve as potential pathways for MPs to enter the lake. To further explore the environmental patterns associated with MP abundance, we implemented a semi-supervised machine learning framework combining principal component analysis-based clustering and random forest classification. This approach revealed that variables such as total phosphorus, dissolved oxygen, and pH are key environmental indicators distinguishing MP-related clusters in Dal Lake. This study highlights the widespread presence of MPs in high-altitude freshwater ecosystems and emphasizes the significance of lake sediments in the entrapment of MPs. There is, therefore, an urgent need to implement plastic pollution mitigation strategies to protect the environment and public health of such vulnerable urban lake regions.

  • Open Access

    TDS Prediction with Wavelet Analysis and Trend-Seasonal Decomposition and Machine Learning Algorithms, Case Study: Karkheh River, Iran

    by Hossein Amini, Farshid Fakheri, Jaffer Yousuf Dar, Reza Shakeri, Hossein Nejati, Man Yue Lam, Banafsheh Zahraie, Reza Ahmadian

    Water quality assessment is definitely important, as the available water resources are highly stressed by population growth, climate change due to anthropogenic activities, and a significant change in consumption patterns. This study aims an innovative framework to predict the total dissolved solids (TDS) with more accuracy in the rivers, case study: “Karkheh River”, Iran, with the integration of signal analysis with machine learning algorithms. First, continuous wavelet transform (CWT) was applied to decompose the time series of water quality variables (e.g., Ca, HCO3, SO4, and Cl) into their trends, seasonality, and residuals, extracting features that capture temporal dynamics. These features served as input for non-linear machine learning models (XGBoost, Random Forest, Decision Tree) in differenct scenarios to compare which way of adding new feature would improve the model performance in terms of the TDS predictions. Adding new features characterized by only TDS signal analysis improved the TDS predictions and was compared with adding all variables signal characterization and compared with only using raw data to predict TDS level. Using a 50-year dataset from three different hydrometric stations, the models could achieve over 95% accuracy, and XGBoost outperformed others in terms of taking the advantage of the new extracted features from signals. The results indicates that signal-driven features significantly contribute to ccurately TDS prediction by 30% improvement in RMSE, and it can offer a scalable approach for real-time water quality monitoring in semi-arid river systems, which leads to a better early warning system for designing future mitigation strategies.


  • Open Access

    Comparative analysis of correlation and causality inference in water quality problems with emphasis on TDS Karkheh River in Iran

    by Reza Shakeri, Hossein Amini, Farshid Fakheri, Man Yue Lam, Banafsheh Zahraie

    Water quality management is a critical aspect of environmental sustainability, particularly in arid and semi-arid regions such as Iran where water scarcity is compounded by quality degradation. This study delves into the causal relationships influencing water quality, focusing on Total Dissolved Solids (TDS) as a primary indicator in the Karkheh River, southwest Iran. Utilizing a comprehensive dataset spanning 50 years (1968–2018), this research integrates Machine Learning (ML) techniques to examine correlations and infer causality among multiple parameters, including flow rate (Q), Sodium (Na+), Magnesium (Mg2+), Calcium (Ca2+), Chloride (Cl−), Sulfate (SO4 2−), Bicarbonates (HCO3 −), and pH. For modeling the causation, the “Back door linear regression” approach has been considered which establishes a stable and interpretable framework in causal inference by focusing on clear assumptions. Predictive modeling was used to show the difference between correlation and causation along with interpretability modeling to make the predictive model transparent. Predictive modeling does not report the causality among the variables as it showed Mg is not contributing to the target (TDS) while the findings reveal that TDS is predominantly positive influenced by Mg, Na, Cl, Ca and SO4, with HCO3 and pH exerting negative (inverse) effects. Unlike correlations, causal relationships demonstrate directional and often unequal influences, highlighting Mg as a critical driver of TDS levels. This novel application of ML-based causal inference in water quality research provides a cost-effective and time-efficient alternative to traditional experimental methods. The results underscore the potential of ML-driven causal analysis to guide water resource management and policy-making. By identifying the key drivers of TDS, this study proposes targeted interventions to mitigate water quality deterioration. Moreover, the insights gained lay the foundation for developing early warning systems, ensuring proactive and sustainable water quality management in similar hydrological contexts.


  • Open Access

    Meanders on the Move: Can AI-Based Solutions Predict Where They Will Be Located?

    by Hossein Amini, Federico Monegaglia, Reza Shakeri, Marco Tubino, Guido Zolezzi

    Meandering rivers are complex geomorphic systems that play an important role in the environment. They provide habitat for a variety of plants and animals, help to filter water, and reduce flooding. However, meandering rivers are also susceptible to changes in flow, sediment transport, and erosion. These changes can be caused by natural factors such as climate change and human activities such as dam construction and agriculture. Studying meandering rivers is important for understanding their dynamics and developing effective management strategies. However, traditional methods such as numerical and analytical modeling for studying meandering rivers are time-consuming and/or expensive. Machine learning algorithms can be used to overcome these challenges and provide a more efficient and comprehensive way to study meandering rivers. In this study, we used machine learning algorithms to study the migration rate of simulated meandering rivers using semi-analytical model to investigate the feasibility of employing this new method. We then used machine learning algorithms such as multi-layer perceptron, eXtreme Gradient Boost, gradient boosting regressor, and decision tree to predict the migration rate. The results show ML algorithms can be used for prediction of migration rate, which in turn can predict the planform position.


  • Assessment of drought conditions and prediction by machine learning algorithms using Standardized Precipitation Index and Standardized Water-Level Index (case study: Yazd province, Iran)

    by Reza Shakeri, Hossein Amini, Farshid Fakheri, Hamed Ketabchi

    Drought as a natural phenomenon has always been a serious threat to regions with hot and dry climates. One of the major effects of drought is the drop in groundwater level. This paper focused on the SPI (Standardized Precipitation Index) and SWI (Standardized Water-Level Index) to assess meteorological and hydrological drought, respectively. In the first part, we used different time frames of SPI (3, 6, 12, and 24 months) to investigate drought in Yazd, a dry province in the center of Iran for 29 years (1990–2018). Then, in the second part, the relationship between SPI and SWI was investigated in the three aquifers of Yazd by some rain gauge stations and the closest observation wells to them. In addition to using SPI and SWI, we also used different machine learning (ML) algorithms to predict drought conditions including linear model and six non-linear models of K_Nearest_Neighbors, Gradient_Boosting, Decision_Tree, XGBoost, Random_Forest, and Neural_Net. To evaluate the accuracy of the mentioned models, three statistical indicators including Score, RMSE, and MAE were used. Based on the results of the first part, Yazd province has changed from mild wet to mild drought in terms of meteorological drought (the amount of rainfall according to SPI), and this condition can worsen due to climate change. The models used in ML showed that SPI-6 (score ave = 0.977), SPI-3 (score ave = 0.936), SPI-24 (score ave = 0.571), and SPI-12 (score ave = 0.413) indices had the highest accuracy, respectively. The models of Neural_Net (score ave = 0.964–RMSE ave = 0.020–MAE ave = 0.077) and Gradient_Boosting (score ave = 0.551–RMSE ave = 0.124–MAE ave = 0.248) had the highest and lowest accuracy in prediction of the SPI in all four-time scales. Based on the results of the second part, about the SWI, Random_Forest model (score = 0.929–RMSE = 0.052–MAE = 0.150) and model of Neural_Net (score = 0.755–RMSE = 0.235–MAE = 0.456) had the highest and lowest accuracy, respectively. Also, hydrological drought (reduction of the groundwater level) of the region has been much more severe, and according to the low correlation coefficient of average SPI and SWI (R2 = 0.14), we found that the uncontrolled pumping wells, as a main factor than a shortage of rainfall, have aggravated the hydrological drought, and this region is at risk of becoming a more arid region in the future.


  • Open Access

    The prediction of the Migration rate of meandering rivers using Machine learning models

    by Hossein Amini, Federico Monegaglia, Marco Tubino, Guido Zolezzi

    River meandering is the natural process that many lowland rivers undergo as a consequence of the alternation of bank erosion and accretion, which leads to the typical shape of the so-called meandering rivers. During the last decades, numerous modelling studies have been developed to reproduce their planform dynamics and to predict their future evolution. Most of these modelling approaches are physics-based, meaning that they solve the mathematical equations of shallow water open channel flow and fluvial sediment transport. Other types of modelling are very rare. Recent advances in artificial intelligence have led to promising results in many fields of science but their potential seems to have been so far rather unexplored in the prediction of meandering rivers morphodynamics. In this study, we have developed machine learning (hereinafter ML) models to compute the meander lateral migration rate based on training dataset: once the model has been trained with known migration rates and curvature values at two consecutive time steps, it is used to predict migration rates at the following time step. To this aim, the train and test dataset is coming from the outputs of a semi-analytical meander morphodynamic model which provides simulated evolving meandering planforms (described through the spatial curvature distribution) and migration rates computed through the excess near bank velocity. Such migration has been considered as the “Target” in the present study. The results for different models such as linear regression, feedforward neural network, SVM, and XGBoost were compared. It indicates that the “XGBoost” model with approximately 80 percent of accuracy in the prediction of the next time step, has the best result among them. This is just an opening chapter for the usage of ML in morphodynamics of meandering rivers and with advanced methods, there will be promising results ahead.

  • Open Access

    A model-based classification of confined meandering rivers

    by Hossein Amini, Federico Monegaglia, Stefano Lanzoni, Guido Zolezzi, Marco Tubino

    Confined meandering rivers are bounded between valleys and they are limited in their lateral migration compared to free meandering ones. In this study, we designed a model-based analysis to investigate types of confined meandering rivers. To simulate cases, we used the model developed by (Bogoni et al. 2017) based on a semi-analytical solution for flow and bed morphology ((Zolezzi and Seminara 2001). According to the result of (Lewin and Brindle 1977) the categorization of this type of meandering river should be based on the potential of evolution. We defined a confinement ratio as the ratio between the confined valley width and the meander belt width that the river would theoretically reach without geological confinement. Such unconfined meander belt width has been computed through long-term morphodynamic model simulations. This differs from previous work (Camporeale et al. 2005), semi-empirically suggesting an unconfined meander belt being nearly 3 times the modeled, linearly most unstable, intrinsic meander length. Our results indicate the existence of four different types of confined meandering rivers, which represents the most important point of this work. Compared to previous work, our classification adds a new class and reclassifies one of the previous types. Our proposed classes are; “Moderately confined condition” for confinement ratio in the range 0.1-1, “Strongly confined condition” for confinement ratio in the range 0.03-0.1. For a smaller confinement ratio than 0.03 we obtain a low sinuosity, single thread river, and for a confinement ratio greater than 1, we retrieve a free meandering river. Preliminary testing of our model-based classification with data from real confined meandering rivers shows promising results.