Khalil Gholamnia
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
Khalil Gholamnia has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Omid Ghorbanzadeh
Department of Geoinformatics—Z_GIS, University of Salzburg, Salzburg, Austria
12 shared publications - Thomas Blaschke
Department of Geoinformatics, University of Salzburg, Salzburg, Austria
8 shared publications - Hossein Tahmasebi Moghaddam
Department of Geography, Faculty of Human Sciences, University of Zanjan, Zanjan, Iran
3 shared publications - Jagannath Aryal
The University of Melbourne
3 shared publications - Pedram Ghamisi
Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Helmholtz Institute Freiberg for Resource Technology, Freiberg, Germany
3 shared publications - Thimmaiah Gudiyangada Nachappa
Department of Geoinformatics–Z_GIS, University of Salzburg, 5020 Salzburg, Austria
3 shared publications
Latest Publications
- Open Access
- 27 October 2026
- Published by Wiley in Transactions in GIS
- Vol. 30 (7)
Sustainable Land Suitability Assessment for Garden City Development in Zanjan's Urban Hinterland Using Machine Learning
In response to rapid urban expansion, population growth, and the need for sustainable land use, urban agriculture presents a viable strategy for enhancing food security and ecological balance in urban planning. This study aims to assess land suitability for garden city development in the urban hinterland zone of Zanjan. A hybrid framework integrating the Analytic Hierarchy Process (AHP) with two machine learning (ML) methods, Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost), was employed. A set of geospatial and environmental criteria, including slope, aspect, elevation, soil erosion, climatic variables (precipitation and temperature), and proximity to infrastructure and natural features, were analyzed to identify ecologically and socially suitable locations for garden city development. The standardized criteria were used as predictor variables, while expert‐informed suitability scores derived from the AHP framework served as reference values for model development. The results showed that the SVM and XGBoost models successfully learned the spatial suitability patterns represented by the expert‐informed AHP framework, achieving coefficients of determination of R 2 = 0.988 and R 2 = 0.977, respectively. These values indicate a high level of agreement between the ML predictions and the expert‐informed suitability patterns rather than independent predictive accuracy. The findings also revealed that distance from faults, access to urban infrastructure, and land slope were the most influential factors in determining suitable areas. The proposed hybrid framework demonstrates how expert knowledge and data‐driven learning can be integrated to support transparent and comprehensive land suitability assessment for garden city development in peri‐urban environments.
- 27 October 2026
- Published by Wiley in Transactions in GIS
- Vol. 30 (7)
Open AccessSustainable Land Suitability Assessment for Garden City Development in Zanjan's Urban Hinterland Using Machine Learning
In response to rapid urban expansion, population growth, and the need for sustainable land use, urban agriculture presents a viable strategy for enhancing food security and ecological balance in urban planning. This study aims to assess land suitability for garden city development in the urban hinterland zone of Zanjan. A hybrid framework integrating the Analytic Hierarchy Process (AHP) with two machine learning (ML) methods, Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost), was employed. A set of geospatial and environmental criteria, including slope, aspect, elevation, soil erosion, climatic variables (precipitation and temperature), and proximity to infrastructure and natural features, were analyzed to identify ecologically and socially suitable locations for garden city development. The standardized criteria were used as predictor variables, while expert‐informed suitability scores derived from the AHP framework served as reference values for model development. The results showed that the SVM and XGBoost models successfully learned the spatial suitability patterns represented by the expert‐informed AHP framework, achieving coefficients of determination of R 2 = 0.988 and R 2 = 0.977, respectively. These values indicate a high level of agreement between the ML predictions and the expert‐informed suitability patterns rather than independent predictive accuracy. The findings also revealed that distance from faults, access to urban infrastructure, and land slope were the most influential factors in determining suitable areas. The proposed hybrid framework demonstrates how expert knowledge and data‐driven learning can be integrated to support transparent and comprehensive land suitability assessment for garden city development in peri‐urban environments.
- Open Access
- 19 August 2026
- Published by Elsevier in Environmental and Sustainability Indicators
- Vol. 32
Multi-scenario machine learning–driven LUCC simulation and InVEST-based carbon sequestration assessment: A case study of metropolitan Prague, Czech Republic
- 19 August 2026
- Published by Elsevier in Environmental and Sustainability Indicators
- Vol. 32
Open AccessMulti-scenario machine learning–driven LUCC simulation and InVEST-based carbon sequestration assessment: A case study of metropolitan Prague, Czech Republic
- Open Access
- 13 August 2026
- Published by Springer Nature in Discover Cities
- Vol. 3 (1) , 162
Typology of transit-oriented development to promote sustainable urban structure
- 13 August 2026
- Published by Springer Nature in Discover Cities
- Vol. 3 (1) , 162
Open AccessTypology of transit-oriented development to promote sustainable urban structure
- Open Access
- 6 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 24280
Distinguishing compound and cumulative hazards using machine learning and fuzzy logic in multi-hazard susceptibility mapping
- 6 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 24280
Open AccessDistinguishing compound and cumulative hazards using machine learning and fuzzy logic in multi-hazard susceptibility mapping
- 9 June 2026
- Published by Springer Nature in Spatial Information Research
- Vol. 34 (4) , 35
Uncertainty-aware machine learning via Dempster–Shafer theory for wildfire susceptibility mapping
- 9 June 2026
- Published by Springer Nature in Spatial Information Research
- Vol. 34 (4) , 35
Uncertainty-aware machine learning via Dempster–Shafer theory for wildfire susceptibility mapping
- Open Access
- 18 May 2026
- Published by Elsevier in Environmental Modelling & Software
- Vol. 203
Comparative evaluation of DYNA-CLUE and a python-based machine learning framework for long-term land-use and land-cover simulation
- 18 May 2026
- Published by Elsevier in Environmental Modelling & Software
- Vol. 203
Open AccessComparative evaluation of DYNA-CLUE and a python-based machine learning framework for long-term land-use and land-cover simulation
- 11 February 2026
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 54 (4) , 1721-1736
Deforestation Monitoring in Zagros Oak Forests with Landsat time Series and the BFAST Spatial Algorithm
- 11 February 2026
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 54 (4) , 1721-1736
Deforestation Monitoring in Zagros Oak Forests with Landsat time Series and the BFAST Spatial Algorithm
- Open Access
Evaluating the Impact of Recursive Feature Elimination on Machine Learning Models for Predicting Forest Fire-Prone Zones
This study aimed to enhance the accuracy of forest fire susceptibility mapping (FSM) by innovatively applying recursive feature elimination (RFE) with an ensemble of machine learning models, specifically Support Vector Machine (SVM) and Random Forest (RF), to identify key fire factors. The fire zones were derived from MODIS satellite imagery from 2012 to 2017. Further validation of these data has been provided by field surveys and reviews of land records in rangelands and forests; a total of 326 fire points were determined in this study. Seventeen factors involving topography, geomorphology, meteorology, hydrology, and human factors were identified as being effective primary factors in triggering and spreading fires in the selected mountainous case study area. As a first step, the RFE models RF, Extra Trees, Gradient Boosting, and AdaBoost were used to identify important fire factors among all selected primary factors. The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM. Training and testing data were divided tenfold, and the model’s performance was evaluated using cross-validation. Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthew’s correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model.
Open AccessEvaluating the Impact of Recursive Feature Elimination on Machine Learning Models for Predicting Forest Fire-Prone Zones
This study aimed to enhance the accuracy of forest fire susceptibility mapping (FSM) by innovatively applying recursive feature elimination (RFE) with an ensemble of machine learning models, specifically Support Vector Machine (SVM) and Random Forest (RF), to identify key fire factors. The fire zones were derived from MODIS satellite imagery from 2012 to 2017. Further validation of these data has been provided by field surveys and reviews of land records in rangelands and forests; a total of 326 fire points were determined in this study. Seventeen factors involving topography, geomorphology, meteorology, hydrology, and human factors were identified as being effective primary factors in triggering and spreading fires in the selected mountainous case study area. As a first step, the RFE models RF, Extra Trees, Gradient Boosting, and AdaBoost were used to identify important fire factors among all selected primary factors. The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM. Training and testing data were divided tenfold, and the model’s performance was evaluated using cross-validation. Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthew’s correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model.
- Open Access
- 14 February 2022
- Published by Taylor & Francis in Big Earth Data
- Vol. 7 (4) , 961-985
The application of ResU-net and OBIA for landslide detection from multi-temporal Sentinel-2 images
Landslide detection is a hot topic in the remote sensing community, particularly with the current rapid growth in volume (and variety) of Earth observation data and the substantial progress of computer vision. Deep learning algorithms, especially fully convolutional networks (FCNs), and variations like the ResU-Net have been used recently as rapid and automatic landslide detection approaches. Although FCNs have shown cutting-edge results in automatic landslide detection, accuracy can be improved by adding prior knowledge through possible frameworks. This study evaluates a rule-based object-based image analysis (OBIA) approach built on probabilities resulting from the ResU-Net model for landslide detection. We train the ResU-Net model using a landslide dataset comprising landslide inventories from various geographic regions, including our study area and test the testing area not used for training. In the OBIA stage, we first calculate land cover and image difference indices for pre-and post-landslide multi-temporal images. Next, we use the generated indices and the resulting ResU-Net probabilities for image segmentation; the extracted landslide object candidates are then optimized using rule-based classification. In the result validation section, the landslide detection of the proposed integration of the ResU-Net with a rule-based classification of OBIA is compared with that of the ResU-Net alone. Our proposed approach improves the mean intersection-over-union of the resulting map from the ResU-Net by more than 22%.
- 14 February 2022
- Published by Taylor & Francis in Big Earth Data
- Vol. 7 (4) , 961-985
Open AccessThe application of ResU-net and OBIA for landslide detection from multi-temporal Sentinel-2 images
Landslide detection is a hot topic in the remote sensing community, particularly with the current rapid growth in volume (and variety) of Earth observation data and the substantial progress of computer vision. Deep learning algorithms, especially fully convolutional networks (FCNs), and variations like the ResU-Net have been used recently as rapid and automatic landslide detection approaches. Although FCNs have shown cutting-edge results in automatic landslide detection, accuracy can be improved by adding prior knowledge through possible frameworks. This study evaluates a rule-based object-based image analysis (OBIA) approach built on probabilities resulting from the ResU-Net model for landslide detection. We train the ResU-Net model using a landslide dataset comprising landslide inventories from various geographic regions, including our study area and test the testing area not used for training. In the OBIA stage, we first calculate land cover and image difference indices for pre-and post-landslide multi-temporal images. Next, we use the generated indices and the resulting ResU-Net probabilities for image segmentation; the extracted landslide object candidates are then optimized using rule-based classification. In the result validation section, the landslide detection of the proposed integration of the ResU-Net with a rule-based classification of OBIA is compared with that of the ResU-Net alone. Our proposed approach improves the mean intersection-over-union of the resulting map from the ResU-Net by more than 22%.
- Open Access
- 30 January 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 672
A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions
The effects of the spatial resolution of remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate the effects of coarse (Landsat 8 and SRTM) and medium (Sentinel-2 and ALOS) spatial resolution data on wildfire susceptibility prediction using random forest (RF) and support vector machine (SVM) models. In addition, we investigate the fusion of the predictions from the different spatial resolutions using the Dempster–Shafer theory (DST) and 14 wildfire conditioning factors. Seven factors are derived separately from the coarse and medium spatial resolution datasets for the whole forest area of the Guilan Province, Iran. All conditional factors are used to train and test the SVM and RF models in the Google Earth Engine (GEE) software environment, along with an inventory dataset from comprehensive global positioning system (GPS)-based field survey points of wildfire locations. These locations are evaluated and combined with coarse resolution satellite data, namely the thermal anomalies product of the moderate resolution imaging spectroradiometer (MODIS) for the period 2009 to 2019. We assess the performance of the models using four-fold cross-validation by the receiver operating characteristic (ROC) curve method. The area under the curve (AUC) achieved from the ROC curve yields 92.15% and 91.98% accuracy for the respective SVM and RF models for the coarse RS data. In comparison, the AUC for the medium RS data is 92.5% and 93.37%, respectively. Remarkably, the highest AUC value of 94.71% is achieved for the RF model where coarse and medium resolution datasets are combined through DST.
- 30 January 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 672
Open AccessA Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions
The effects of the spatial resolution of remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate the effects of coarse (Landsat 8 and SRTM) and medium (Sentinel-2 and ALOS) spatial resolution data on wildfire susceptibility prediction using random forest (RF) and support vector machine (SVM) models. In addition, we investigate the fusion of the predictions from the different spatial resolutions using the Dempster–Shafer theory (DST) and 14 wildfire conditioning factors. Seven factors are derived separately from the coarse and medium spatial resolution datasets for the whole forest area of the Guilan Province, Iran. All conditional factors are used to train and test the SVM and RF models in the Google Earth Engine (GEE) software environment, along with an inventory dataset from comprehensive global positioning system (GPS)-based field survey points of wildfire locations. These locations are evaluated and combined with coarse resolution satellite data, namely the thermal anomalies product of the moderate resolution imaging spectroradiometer (MODIS) for the period 2009 to 2019. We assess the performance of the models using four-fold cross-validation by the receiver operating characteristic (ROC) curve method. The area under the curve (AUC) achieved from the ROC curve yields 92.15% and 91.98% accuracy for the respective SVM and RF models for the coarse RS data. In comparison, the AUC for the medium RS data is 92.5% and 93.37%, respectively. Remarkably, the highest AUC value of 94.71% is achieved for the RF model where coarse and medium resolution datasets are combined through DST.