Saeid Pourmorad

Dr. Saeid Pourmorad

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SPSaeid Pourmorad
Saeid Pourmorad
MKMostafa Kabolizadeh
Mostafa Kabolizadeh
Luca Antonio DimuccioLuca Antonio Dimuccio
Luca Antonio Dimuccio
Artificial Intelligence (AI) methods, including Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference Systems (ANFISs), Support Vector Machines (SVMs), Deep Learning (DL), Genetic Programming (GP) and Hybrid Algorithms, have proven to be important tools for accurate groundwater level (GWL) modelling. Through an analysis of the results obtained in numerous articles published in high-impact journals during 2001–2023, this comprehensive review examines each method’s capabilities, their combinations, and critical considerations about selecting appropriate input parameters, using optimisation algorithms, and considering the natural physical conditions of the territories under investigation to improve the models’ accuracy. For example, ANN takes advantage of its ability to recognise complex patterns and non-linear relationships between input and output variables. In addition, ANFIS shows potential in processing diverse environmental data and offers higher accuracy than alternative methods such as ANN, SVM, and GP. SVM excels at efficiently modelling complex relationships and heterogeneous data. Meanwhile, DL methods, such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs), are crucial in improving prediction accuracy at different temporal and spatial scales. GP methods have also shown promise in modelling complex and nonlinear relationships in groundwater data, providing more accurate and reliable predictions when combined with optimisation techniques and uncertainty analysis. Therefore, integrating these methods and optimisation techniques (Hybrid Algorithms), tailored to specific hydrological and hydrogeological conditions, can significantly increase the predictive capability of GWL models and improve the planning and management of water resources. These findings emphasise the importance of thoroughly understanding (a priori) the functionalities and capabilities of each potentially beneficial AI-based methodology, along with the knowledge of the physical characteristics of the territory under investigation, to optimise GWL predictive models.

30 January 2021 in Lithology and Mineral Resources
Verified
Journal Article
Closed access
PDF file
SPSaeid Pourmorad
Saeid Pourmorad
RHReza Mousavi Harami
Reza Mousavi Harami
ASAli Solgi
Ali Solgi
MAMohsen Aleali
Mohsen Aleali
The alluvial-fan sediments play a very important role in mineral reserves and underground water resources, though a comprehensive study on such sediments, especially from a geochemical point of view, is still lacking. In this research, a total of 22 particularly important alluvial fans across the Khuzestan Plain in the southwestern Iran were studied through field surveys, petrographic evaluations, and geochemical assessments. These investigations included particle size distribution studies, microscopic observation of 193 samples, subsurface study of 60 boreholes along 10 different sections, facies analysis on 46 different sections, and comprehensive geochemical studies through XRD, XRF, ICP Mass, and wet chemical analyses. Based on these studies, the sediments were found to be dominantly composed of gravel, muddy sand, silt, and clay. The sediments exhibited good roundness and good to fair sorting. The most abundant oxide in the study area being MgO followed by SiO2, Al2O3, and Fe2O3. According to the studies, most of the samples fell in the range of iron-bearing sandstones with rare cases of iron-bearing shales. Investigation of the geochemical indices showed the long sediment transport path from the source, humid climate, and moderate to extensive weathering of the deposit. The depositional setting was found to be dominantly an active continental margin and, to a lesser extent, a continental island arc. Investigating of the studied sediments provenance indicate a felsic to slightly basic source rock. The environmental studies were indicative of relatively low contamination of the region and abundance of rare earth elements including Y, Sc, Nd, La, and Ce, and the abundance of heavy elements including Cr, Zn, Pb, and Cd. Based on the mineralogical studies on the samples, the inter-grain cement in both gravel and conglomerate particles was found to be composed of calcite.

17 November 2021 in Lithology and Mineral Resources
Verified
Journal Article
Closed access
PDF file
SPSaeid Pourmorad
Saeid Pourmorad
AJAmir Jokar
Amir Jokar
SJShakura Jahan
Shakura Jahan
The use of key beds in the cap rocks of the oil reservoirs is crucial. Lack of awareness of these key beds will have serious risks and damages. The Gachsaran oil field is located 220 km southwest of Ahwaz-Iran. The former caprock consists of six key beds (A, B, C, D, E, and F). At the time of writing this paper these key beds are being used during excavations and drilling to determine the site of casing points. What has made utilizing these key beds during excavations difficult however, is use of diamond drill bits which results in the shattering of excavated samples. As such, it has become challenging to learn more about these key beds through studying petrographic thin sections in microscopy. These key beds were observed during the investigation at the drill sites. Later, the excavated samples were studied in the Energy-Dispersive X-ray Spectroscopy (EDS) machine, using a semi-quantitative method to analyze the elemental differences in those key beds. In addition to the identification of various lithological and diagenetic properties of the caprock, this study leads to the introduction of four new key beds based on geochemical properties. Some of the most important differences within the formation include those between the caprock anhydrite and the non-caprock anhydrite, namely the presence of potassium and titanium and the absence of chlorine and sodium in the caprock section. The four new key beds introduced from this study using elemental differences were named as key beds-1, 2, 3, and 4.

11 November 2022 in Lithology and Mineral Resources
Verified
Journal Article
Closed access
PDF file
SPSaeid Pourmorad
Saeid Pourmorad
SASamira Abbasi
Samira Abbasi
NPNilanchal Patel
Nilanchal Patel
AMAshutosh Mohanty
Ashutosh Mohanty
Improper use of alluvial aquifers and declining water levels in these aquifers have led to significant attention to the search for other groundwater sources in karst areas and hard formations. Iran is one of the countries that has a very high percentage of karst in the world and the study and tracing of karst are very important in this country. In this research, eight effective factors in karstification are identified and categorized into two groups and the relevant information layers are prepared. The first group includes average annual rainfall, type of geological formations, the density of fractures, and density of the fracture site. The second group, which is of secondary importance, includes the average annual temperature, the density of canals, slope, and type of vegetation. After preparing the information layers, quantitative parameters based on fuzzy logic and qualitative parameters were standardized by the rasterization method. The importance and weight of each of the effective factors were determined from two methods viz. Analytic Hierarchy Process (AHP) and the Fuzzy Hierarchical Analysis Process (FAHP). After multiplying the standard maps with their respective weights, they were overlaid, and finally, karst potential maps were generated. Maps were generated from the two weighting methods based on the subsurface and surface hydrogeological-geomorphological diagrams. Karst features such as Karen, dissolution cavities, depressions, caves, dry valleys, reservoir rocks of springs and water exploitation wells, and Calcareous limbs were ascertained, which indicates that the results of the FAHP method are more consistent with the existing conditions in the region. The final map was divided into five classes in terms of the karst potential, viz. very high, high, medium, low, and no potential.

20 January 2024 in Doklady Earth Sciences
Verified
Journal Article
Closed access
PDF file
SAS. Abbasi
S. Abbasi
HAH. Amanipoor
H. Amanipoor
SBS. Battaleb-Looie
S. Battaleb-Looie
SPSaeid Pourmorad
Saeid Pourmorad
JKJ. Darvishi Khatoni
J. Darvishi Khatoni
SBS. Battalblooie
S. Battalblooie
Geochemical data and accurate statistics are critical in environmental studies to identify sources of soil contamination and reduce costs. A comprehensive understanding of investigation methods and data interpretation is a current challenge. This study presents innovative techniques for investigating soil contamination that can be applied worldwide. Using sediment samples from the southern region of Iran, we analysed 38 samples with X-ray fluorescence (XRF) and inductively coupled plasma mass spectrometry (ICP-MS). Statistical analysis, including descriptive statistics, Kolmogorov-Smirnov test (K-S), correlation coefficients, cluster and factor analyses, was performed using SPSS software. Cluster analysis revealed two primary element sources: lithogenic and anthropogenic, likely from the Karun River, the Gachsaran Formation, and contamination from nearby oil platforms. The pollution indices showed moderate pollution values for Mg, Sr, Cr, Ni, Pr, and Cd. Geochemical indices RI, PLI, Igeo, EF, Cf, and NIPI assessed the extent of pollution. Integration of sedimentary and geochemical data identified the source of sand particles as reworked Neogene deposits and silt from marl layers in upstream evaporites. These techniques have potential global applications.

7 April 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SPSaeid Pourmorad
Saeid Pourmorad
VGValerie Graw
Valerie Graw
ARAndreas Rienow
Andreas Rienow
Luca Antonio DimuccioLuca Antonio Dimuccio
Luca Antonio Dimuccio
Satellite remote sensing has become essential for water quality assessment across inland and coastal environments, with rapid improvements in recent years. Significant advances have been made in detecting optically active parameters (such as chlorophyll-a, suspended matter, and turbidity), showing consistently strong performance across multiple studies. Specifically, the median validation performance (R2) derived from the quantitative synthesis indicates R2 = 0.82 for chlorophyll-a (interquartile range—IQR: 0.75–0.90), R2 = 0.80 for total suspended matter (IQR: 0.78–0.85), and R2 = 0.88 for turbidity (IQR: 0.85–0.90). Conversely, the retrieval of optically inactive parameters (such as nutrients like total phosphorus and total nitrogen) remains more context dependent. It exhibits moderate, more variable results, with median R2 = 0.68 (IQR: 0.64–0.74) for total phosphorus and R2 = 0.75 (IQR: 0.70–0.80) for total nitrogen. These findings clearly illustrate the varying success of retrievals of optically active and inactive parameters and underscore the inherent difficulties of indirect estimation methods. However, high reported accuracy has yet to translate into transferable, uncertainty-informed, and operational monitoring systems. This gap stems from structural issues in validation design, physics integration, uncertainty management, and multi-sensor compatibility rather than data limitations alone. We present a PRISMA-guided, distribution-aware quantitative synthesis of 152 peer-reviewed studies (1980–2025), based on a systematic search protocol, to evaluate satellite-based retrievals of both optically active and inactive parameters. Instead of simply averaging performance, we analyse the empirical distributions of validation metrics, considering the validation protocol, sensor type, parameter category, degree of physics integration, and uncertainty quantification. The synthesis demonstrates that validation strategy often influences reported results more than the algorithm class itself, with accuracy inflated under non-independent cross-validation methods and notable variability between studies concealed by mean-based reports. Across four decades, four persistent structural challenges remain: limited transferability across sites and sensors beyond calibration areas; weak or implicit physical integration in many data-driven models; lack of or inconsistency in uncertainty quantification; and fragmented multi-sensor harmonisation that restricts operational scalability. To address these issues, we introduce two evidence-based coding frameworks: a physics-integration taxonomy (P0–P4) and an uncertainty-quantification hierarchy (U0–U4). Applying these frameworks shows that most studies remain focused on low-to-moderate levels of physics integration and primarily consider uncertainty at the prediction stage, with limited attention to upstream sources throughout the observation and inference process. Building on this structured synthesis, we propose a transferable, physics-informed, and uncertainty-aware conceptual framework that links model architecture, validation robustness, and probabilistic uncertainty to well-founded design principles. By shifting satellite water quality modelling from isolated algorithm demonstrations towards integrated, evidence-based system design, this study promotes scalable, decision-grade environmental monitoring amid the accelerating impacts of climate change.