-
Quantum-Enhanced Vision Transformer for Flood Detection using Remote Sensing Imagery
Authors:
Soumyajit Maity,
Behzad Ghanbarian
Abstract:
Reliable flood detection is critical for disaster management, yet classical deep learning models often struggle with the high-dimensional, nonlinear complexities inherent in remote sensing data. To mitigate these limitations, we introduced a novel Quantum-Enhanced Vision Transformer (ViT) that synergizes the global context-awareness of transformers with the expressive feature extraction capabiliti…
▽ More
Reliable flood detection is critical for disaster management, yet classical deep learning models often struggle with the high-dimensional, nonlinear complexities inherent in remote sensing data. To mitigate these limitations, we introduced a novel Quantum-Enhanced Vision Transformer (ViT) that synergizes the global context-awareness of transformers with the expressive feature extraction capabilities of quantum computing. Using remote sensing imagery, we developed a hybrid architecture that processes inputs through parallel pathways, a ViT backbone and a quantum branch utilizing a 4-qubit parameterized quantum circuit for localized feature mapping. These distinct representations were fused to optimize binary classification. Results showed that the proposed hybrid model significantly outperformed a classical ViT baseline, increased overall accuracy from 84.48% to 94.47% and the F1-score from 0.841 to 0.944. Notably, the quantum integration substantially improved discriminative power in complex terrains for both class. These findings validate the potential of quantum-classical hybrid models to enhance precision in hydrological monitoring and earth observation applications.
△ Less
Submitted 13 March, 2026;
originally announced March 2026.
-
Estimating oil recovery factor using machine learning: Applications of XGBoost classification
Authors:
Alireza Roustazadeh,
Behzad Ghanbarian,
Frank Male,
Mohammad B. Shadmand,
Vahid Taslimitehrani,
Larry W. Lake
Abstract:
In petroleum engineering, it is essential to determine the ultimate recovery factor, RF, particularly before exploitation and exploration. However, accurately estimating requires data that is not necessarily available or measured at early stages of reservoir development. We, therefore, applied machine learning (ML), using readily available features, to estimate oil RF for ten classes defined in th…
▽ More
In petroleum engineering, it is essential to determine the ultimate recovery factor, RF, particularly before exploitation and exploration. However, accurately estimating requires data that is not necessarily available or measured at early stages of reservoir development. We, therefore, applied machine learning (ML), using readily available features, to estimate oil RF for ten classes defined in this study. To construct the ML models, we applied the XGBoost classification algorithm. Classification was chosen because recovery factor is bounded from 0 to 1, much like probability. Three databases were merged, leaving us with four different combinations to first train and test the ML models and then further evaluate them using an independent database including unseen data. The cross-validation method with ten folds was applied on the training datasets to assess the effectiveness of the models. To evaluate the accuracy and reliability of the models, the accuracy, neighborhood accuracy, and macro averaged f1 score were determined. Overall, results showed that the XGBoost classification algorithm could estimate the RF class with reasonable accuracies as high as 0.49 in the training datasets, 0.34 in the testing datasets and 0.2 in the independent databases used. We found that the reliability of the XGBoost model depended on the data in the training dataset meaning that the ML models were database dependent. The feature importance analysis and the SHAP approach showed that the most important features were reserves and reservoir area and thickness.
△ Less
Submitted 28 October, 2022;
originally announced October 2022.
-
Estimating oil and gas recovery factors via machine learning: Database-dependent accuracy and reliability
Authors:
Alireza Roustazadeh,
Behzad Ghanbarian,
Mohammad B. Shadmand,
Vahid Taslimitehrani,
Larry W. Lake
Abstract:
With recent advances in artificial intelligence, machine learning (ML) approaches have become an attractive tool in petroleum engineering, particularly for reservoir characterizations. A key reservoir property is hydrocarbon recovery factor (RF) whose accurate estimation would provide decisive insights to drilling and production strategies. Therefore, this study aims to estimate the hydrocarbon RF…
▽ More
With recent advances in artificial intelligence, machine learning (ML) approaches have become an attractive tool in petroleum engineering, particularly for reservoir characterizations. A key reservoir property is hydrocarbon recovery factor (RF) whose accurate estimation would provide decisive insights to drilling and production strategies. Therefore, this study aims to estimate the hydrocarbon RF for exploration from various reservoir characteristics, such as porosity, permeability, pressure, and water saturation via the ML. We applied three regression-based models including the extreme gradient boosting (XGBoost), support vector machine (SVM), and stepwise multiple linear regression (MLR) and various combinations of three databases to construct ML models and estimate the oil and/or gas RF. Using two databases and the cross-validation method, we evaluated the performance of the ML models. In each iteration 90 and 10% of the data were respectively used to train and test the models. The third independent database was then used to further assess the constructed models. For both oil and gas RFs, we found that the XGBoost model estimated the RF for the train and test datasets more accurately than the SVM and MLR models. However, the performance of all the models were unsatisfactory for the independent databases. Results demonstrated that the ML algorithms were highly dependent and sensitive to the databases based on which they were trained. Statistical tests revealed that such unsatisfactory performances were because the distributions of input features and target variables in the train datasets were significantly different from those in the independent databases (p-value < 0.05).
△ Less
Submitted 22 October, 2022;
originally announced October 2022.
-
Scale-Dependent Pedotransfer Functions Reliability for Estimating Saturated Hydraulic Conductivity
Authors:
Behzad Ghanbarian,
Vahid Taslimitehrani,
Yakov A. Pachepsky
Abstract:
Saturated hydraulic conductivity Ksat is a fundamental characteristic in modeling flow and contaminant transport in soils and sediments. Therefore, many models have been developed to estimate Ksat from easily measureable parameters, such as textural properties, bulk density, etc. However, Ksat is not only affected by textural and structural characteristics, but also by scale e.g., internal diamete…
▽ More
Saturated hydraulic conductivity Ksat is a fundamental characteristic in modeling flow and contaminant transport in soils and sediments. Therefore, many models have been developed to estimate Ksat from easily measureable parameters, such as textural properties, bulk density, etc. However, Ksat is not only affected by textural and structural characteristics, but also by scale e.g., internal diameter and height. Using the UNSODA database and the contrast pattern aided regression (CPXR) method, we recently developed scale-dependent pedotransfer functions to estimate Ksat from textural data, bulk density, and sample dimensions. The main objectives of this study were evaluating the proposed pedotransfer functions using a larger database, and comparing them with seven other models. For this purpose, we selected more than nineteen thousands soil samples from all around the United States. Results showed that the scale-dependent pedotransfer functions estimated Ksat more accurately than seven other models frequently used in the literature.
△ Less
Submitted 21 October, 2016;
originally announced October 2016.
-
Measurement Scale Effect on Prediction of Soil Water Retention Curve and Saturated Hydraulic Conductivity
Authors:
Behzad Ghanbarian,
Vahid Taslimitehrani,
Guozhu Dong,
Yakov A. Pachepsky
Abstract:
Soil water retention curve (SWRC) and saturated hydraulic conductivity (SHC) are key hydraulic properties for unsaturated zone hydrology and groundwater. In particular, SWRC provides useful information on entry pore-size distribution, and SHC is required for flow and transport modeling in the hydrologic cycle. Not only the SWRC and SHC measurements are time-consuming, but also scale dependent. Thi…
▽ More
Soil water retention curve (SWRC) and saturated hydraulic conductivity (SHC) are key hydraulic properties for unsaturated zone hydrology and groundwater. In particular, SWRC provides useful information on entry pore-size distribution, and SHC is required for flow and transport modeling in the hydrologic cycle. Not only the SWRC and SHC measurements are time-consuming, but also scale dependent. This means as soil column volume increases, variability of the SWRC and SHC decreases. Although prediction of the SWRC and SHC from available parameters, such as textural data, organic matter, and bulk density have been under investigation for decades, up to now no research has focused on the effect of measurement scale on the soil hydraulic properties pedotransfer functions development. In the literature, several data mining approaches have been applied, such as multiple linear regression, artificial neural networks, group method of data handling. However, in this study we develop pedotransfer functions using a novel approach called contrast pattern aided regression (CPXR) and compare it with the multiple linear regression method. For this purpose, two databases including 210 and 213 soil samples are collected to develop and evaluate pedotransfer functions for the SWRC and SHC, respectively, from the UNSODA database. The 10-fold cross-validation method is applied to evaluate the accuracy and reliability of the proposed regression-based models. Our results show that including measurement scale parameters, such as sample internal diameter and length could substantially improve the accuracy of the SWRC and SHC pedotransfer functions developed using the CPXR method, while this is not the case when MLR is used. Moreover, the CPXR method yields remarkably more accurate soil water retention curve and saturated hydraulic conductivity predictions than the MLR approach.
△ Less
Submitted 9 February, 2015;
originally announced February 2015.