Sarah Farhadpour
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
Research Subjects
Sarah Farhadpour has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Aaron E. Maxwell
Department of Geology and Geography, West Virginia University, Morgantown, WV 26506, USA
5 shared publications - Farhad Hosseinali
Department of Surveying Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran
2 shared publications - Srinjoy Das
West Virginia University
2 shared publications Aaron E. Maxwell
West Virginia University
1 shared publicationBehnam Solouki
West Virginia University
1 shared publication- Hamed Khosravi
Department of Industrial and Management Systems Engineering West Virginia University Morgantown West Virginia USA
1 shared publication
Latest Publications
- 30 October 2026
- Published by Taylor & Francis in International Journal of Remote Sensing
- p. 1-46
SegFormer and SegFormer-UNet for anthropogenic geomorphic feature extraction from land surface parameters
1. Remotely sensed data combined with feature extraction and classification techniques are widely applied to geomorphic mapping tasks such as landslide susceptibility modelling (Azarafza et al. 202...
- 30 October 2026
- Published by Taylor & Francis in International Journal of Remote Sensing
- p. 1-46
SegFormer and SegFormer-UNet for anthropogenic geomorphic feature extraction from land surface parameters
1. Remotely sensed data combined with feature extraction and classification techniques are widely applied to geomorphic mapping tasks such as landslide susceptibility modelling (Azarafza et al. 202...
- Open Access
- 21 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2415
State-Space-Based Mamba and Convolutional Neural Network Integration for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters
Accurate and scalable extraction of geomorphic features from LiDAR-derived terrain data is important for environmental monitoring, land use planning, and geohazard assessment. Recent deep learning advances have introduced state-space models, such as Mamba, which can capture broad spatial dependencies with linear complexity and offer an alternative to conventional convolutional neural network (CNN)- or Transformer-based approaches. This study evaluates Mamba-based architectures for geomorphic segmentation across three landform types: agricultural terraces, mine benches, and valley fill faces. Using high spatial resolution terrain derivatives, or land surface parameters (LSPs), as an input feature space, we compare a pure Mamba–UNet, a hybrid architecture with a Mamba-based encoder and CNN decoder, and a baseline CNN-based UNet with a ResNet-34 encoder, each trained with frozen and unfrozen encoders. Results indicate that no single architecture was best across all tasks; however, the hybrid Mamba-CNN architecture provided the most consistent performance overall, improving spatial continuity and interior feature recovery for tasks requiring broad spatial context, although its advantage over the baseline UNet was modest and task-dependent, and boundary-level analysis indicated that CNN-based configurations delineated feature edges most precisely, while the randomly initialized UNet remained highly competitive and achieved the strongest results for some tasks. Further, Mamba-based encoders converge quickly and maintain strong performance when frozen, whereas CNN-based UNets benefit more from encoder fine-tuning.
- 21 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2415
Open AccessState-Space-Based Mamba and Convolutional Neural Network Integration for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters
Accurate and scalable extraction of geomorphic features from LiDAR-derived terrain data is important for environmental monitoring, land use planning, and geohazard assessment. Recent deep learning advances have introduced state-space models, such as Mamba, which can capture broad spatial dependencies with linear complexity and offer an alternative to conventional convolutional neural network (CNN)- or Transformer-based approaches. This study evaluates Mamba-based architectures for geomorphic segmentation across three landform types: agricultural terraces, mine benches, and valley fill faces. Using high spatial resolution terrain derivatives, or land surface parameters (LSPs), as an input feature space, we compare a pure Mamba–UNet, a hybrid architecture with a Mamba-based encoder and CNN decoder, and a baseline CNN-based UNet with a ResNet-34 encoder, each trained with frozen and unfrozen encoders. Results indicate that no single architecture was best across all tasks; however, the hybrid Mamba-CNN architecture provided the most consistent performance overall, improving spatial continuity and interior feature recovery for tasks requiring broad spatial context, although its advantage over the baseline UNet was modest and task-dependent, and boundary-level analysis indicated that CNN-based configurations delineated feature edges most precisely, while the randomly initialized UNet remained highly competitive and achieved the strongest results for some tasks. Further, Mamba-based encoders converge quickly and maintain strong performance when frozen, whereas CNN-based UNets benefit more from encoder fine-tuning.
- 28 April 2026
- Published by Wiley in Earth Surface Processes and Landforms
- Vol. 51 (5) , e70295
A deep learning architecture and workflow for geomorphic feature extraction using digital terrain model‐derived land surface parameters
An architecture and workflow are proposed and described for extracting geomorphic features from digital terrain model (DTM)‐derived land surface parameters (LSPs) using deep learning (DL)‐based semantic segmentation and integration of LSP calculations into the model architecture to allow for tensor‐ and graphics processing unit (GPU)‐based computation within the DL framework. To characterize terrain patterns at multiple spatial scales, the input DTM can be generalized using Gaussian pyramids (GPs). The LSPs are then provided to the trainable component of the model. The workflow is explored using two examples: valley fill faces resulting from mountaintop removal surface coal mine reclamation, an example of anthropogenic geomorphic features, and sinkholes within a karst landscape, an example of natural geomorphic features. We compare three different, ‘U’‐shaped architectures as the trainable component of the architecture: a traditional, convolutional neural network (CNN)‐based UNet, UNet with a ConvNeXt‐based encoder and attention gates along the skip connections and UNet with a Mamba‐based encoder and a CNN‐based decoder. As a baseline, DL models are compared with a pixel‐based random forest (RF) model using the same LSP feature space. We document improved performance in comparison with the pixel‐based approach and minimal differences among the three DL architectures based on F1 scores. The inclusion of GPs did not have a large impact on predictive performance for either the RF‐ or DL‐based models. Calculating LSPs as part of the model architecture did not greatly increase the computational complexity of the model. Depending on the model configuration, incorporating the LSP calculations into the model architecture increased the number of floating‐point operations (FLOPs) and multiply–accumulate operations (MACs) by 2.8% to 17.6% and increased the saved model size by 1.2 MB. In practice, only DTM data, mapping extent(s) and example features need to be provided during the training process. Disk space usage is decreased by a factor of 6 when not using GPs and 31 when incorporating these multiscale representations. The workflow offers an efficient means to extract geomorphic features from DTMs and can support downstream modelling and research tasks. It has been made available in the R language via the geodl package and Python via the terrainseg package.
- 28 April 2026
- Published by Wiley in Earth Surface Processes and Landforms
- Vol. 51 (5) , e70295
A deep learning architecture and workflow for geomorphic feature extraction using digital terrain model‐derived land surface parameters
An architecture and workflow are proposed and described for extracting geomorphic features from digital terrain model (DTM)‐derived land surface parameters (LSPs) using deep learning (DL)‐based semantic segmentation and integration of LSP calculations into the model architecture to allow for tensor‐ and graphics processing unit (GPU)‐based computation within the DL framework. To characterize terrain patterns at multiple spatial scales, the input DTM can be generalized using Gaussian pyramids (GPs). The LSPs are then provided to the trainable component of the model. The workflow is explored using two examples: valley fill faces resulting from mountaintop removal surface coal mine reclamation, an example of anthropogenic geomorphic features, and sinkholes within a karst landscape, an example of natural geomorphic features. We compare three different, ‘U’‐shaped architectures as the trainable component of the architecture: a traditional, convolutional neural network (CNN)‐based UNet, UNet with a ConvNeXt‐based encoder and attention gates along the skip connections and UNet with a Mamba‐based encoder and a CNN‐based decoder. As a baseline, DL models are compared with a pixel‐based random forest (RF) model using the same LSP feature space. We document improved performance in comparison with the pixel‐based approach and minimal differences among the three DL architectures based on F1 scores. The inclusion of GPs did not have a large impact on predictive performance for either the RF‐ or DL‐based models. Calculating LSPs as part of the model architecture did not greatly increase the computational complexity of the model. Depending on the model configuration, incorporating the LSP calculations into the model architecture increased the number of floating‐point operations (FLOPs) and multiply–accumulate operations (MACs) by 2.8% to 17.6% and increased the saved model size by 1.2 MB. In practice, only DTM data, mapping extent(s) and example features need to be provided during the training process. Disk space usage is decreased by a factor of 6 when not using GPs and 31 when incorporating these multiscale representations. The workflow offers an efficient means to extract geomorphic features from DTMs and can support downstream modelling and research tasks. It has been made available in the R language via the geodl package and Python via the terrainseg package.
- Open Access
- 14 December 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (24) , 4670
Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
Semantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derived from digital terrain models (DTMs) as input predictor variables. However, the operationalization of these supervised classification methods is limited by a lack of large volumes of quality training data. This study explores the use of transfer learning, where information learned from another, and often much larger, dataset is used to potentially reduce the need for a large, problem-specific training dataset. Two anthropogenic geomorphic feature extraction problems are explored: the extraction of agricultural terraces and the mapping of surface coal mine reclamation-related valley fill faces. Light detection and ranging (LiDAR)-derived DTMs were used to generate LSPs. We developed custom transfer parameters by attempting to predict geomorphon-based landforms using a large dataset of digital terrain data provided by the United States Geological Survey’s 3D Elevation Program (3DEP). We also explored the use of pre-trained ImageNet parameters and initializing models using parameters learned from the other mapping task investigated. The geomorphon-based transfer learning resulted in the poorest performance while the ImageNet-based parameters generally improved performance in comparison to a random parameter initialization, even when the encoder was frozen or not trained. Transfer learning between the different geomorphic datasets offered minimal benefits. We suggest that pre-trained models developed using large, image-based datasets may be of value for anthropogenic geomorphic feature extraction from LSPs even given the data and task disparities. More specifically, ImageNet-based parameters should be considered as an initialization state for the encoder component of semantic segmentation architectures applied to anthropogenic geomorphic feature extraction even when using non-RGB image-based predictor variables, such as LSPs. The value of transfer learning between the different geomorphic mapping tasks may have been limited due to smaller sample sizes, which highlights the need for continued research in using unsupervised and semi-supervised learning methods, especially given the large volume of digital terrain data available, despite the lack of associated labels.
- 14 December 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (24) , 4670
Open AccessExploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
Semantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derived from digital terrain models (DTMs) as input predictor variables. However, the operationalization of these supervised classification methods is limited by a lack of large volumes of quality training data. This study explores the use of transfer learning, where information learned from another, and often much larger, dataset is used to potentially reduce the need for a large, problem-specific training dataset. Two anthropogenic geomorphic feature extraction problems are explored: the extraction of agricultural terraces and the mapping of surface coal mine reclamation-related valley fill faces. Light detection and ranging (LiDAR)-derived DTMs were used to generate LSPs. We developed custom transfer parameters by attempting to predict geomorphon-based landforms using a large dataset of digital terrain data provided by the United States Geological Survey’s 3D Elevation Program (3DEP). We also explored the use of pre-trained ImageNet parameters and initializing models using parameters learned from the other mapping task investigated. The geomorphon-based transfer learning resulted in the poorest performance while the ImageNet-based parameters generally improved performance in comparison to a random parameter initialization, even when the encoder was frozen or not trained. Transfer learning between the different geomorphic datasets offered minimal benefits. We suggest that pre-trained models developed using large, image-based datasets may be of value for anthropogenic geomorphic feature extraction from LSPs even given the data and task disparities. More specifically, ImageNet-based parameters should be considered as an initialization state for the encoder component of semantic segmentation architectures applied to anthropogenic geomorphic feature extraction even when using non-RGB image-based predictor variables, such as LSPs. The value of transfer learning between the different geomorphic mapping tasks may have been limited due to smaller sample sizes, which highlights the need for continued research in using unsupervised and semi-supervised learning methods, especially given the large volume of digital terrain data available, despite the lack of associated labels.
- Open Access
- 18 July 2024
- Published by California Digital Library (CDL) in EarthArXiv
geodl: An R package for geospatial deep learning semantic segmentation using torch and terra
Convolutional neural network (CNN)-based deep learning (DL) methods have transformed the analysis of geospatial, Earth observation, and geophysical data due to their ability to model spatial context information at multiple scales. Such methods are especially applicable to pixel-level classification, or semantic segmentation, tasks. A variety of R packages have been developed for processing and analyzing geospatial data. However, there are currently no packages available for implementing geospatial DL in the R language and data science environment. This paper introduces the geodl R package, which supports pixel-level classification applied to a wide range of geospatial or Earth science data that can be represented as multidimensional arrays where each channel or band holds a predictor variable. geodl is built on the torch package, which supports the implementation of DL using the R and C++ languages without the need for installing a Python/PyTorch environment. This greatly simplifies the software environment needed to implement DL in R. Using geodl, geospatial raster-based data with varying numbers of bands, spatial resolutions, and coordinate reference systems are read and processed using the terra package, which makes use of C++ and allows for processing raster grids that are too large to fit into memory. Training loops are implemented with the luz package. The geodl package provides utility functions for creating raster masks or labels from vector-based geospatial data and image chips and associated masks from larger files and extents. It also defines a torch dataset subclass for geospatial data for use with torch data loaders. UNet-based models are provided with a variety of optional ancillary modules or modifications. Common assessment metrics (i.e., overall accuracy, class-level recalls or producer’s accuracies, class-level precisions or user’s accuracies, and class-level F1-scores) are implemented along with a modified version of the unified focal loss framework, which allows for defining a variety of loss metrics using one consistent implementation and set of hyperparameters. Users can assess models using standard geospatial and remote sensing metrics and methods and use trained models to predict to large spatial extents.
- 18 July 2024
- Published by California Digital Library (CDL) in EarthArXiv
Open Accessgeodl: An R package for geospatial deep learning semantic segmentation using torch and terra
Convolutional neural network (CNN)-based deep learning (DL) methods have transformed the analysis of geospatial, Earth observation, and geophysical data due to their ability to model spatial context information at multiple scales. Such methods are especially applicable to pixel-level classification, or semantic segmentation, tasks. A variety of R packages have been developed for processing and analyzing geospatial data. However, there are currently no packages available for implementing geospatial DL in the R language and data science environment. This paper introduces the geodl R package, which supports pixel-level classification applied to a wide range of geospatial or Earth science data that can be represented as multidimensional arrays where each channel or band holds a predictor variable. geodl is built on the torch package, which supports the implementation of DL using the R and C++ languages without the need for installing a Python/PyTorch environment. This greatly simplifies the software environment needed to implement DL in R. Using geodl, geospatial raster-based data with varying numbers of bands, spatial resolutions, and coordinate reference systems are read and processed using the terra package, which makes use of C++ and allows for processing raster grids that are too large to fit into memory. Training loops are implemented with the luz package. The geodl package provides utility functions for creating raster masks or labels from vector-based geospatial data and image chips and associated masks from larger files and extents. It also defines a torch dataset subclass for geospatial data for use with torch data loaders. UNet-based models are provided with a variety of optional ancillary modules or modifications. Common assessment metrics (i.e., overall accuracy, class-level recalls or producer’s accuracies, class-level precisions or user’s accuracies, and class-level F1-scores) are implemented along with a modified version of the unified focal loss framework, which allows for defining a variety of loss metrics using one consistent implementation and set of hyperparameters. Users can assess models using standard geospatial and remote sensing metrics and methods and use trained models to predict to large spatial extents.
- Top Cited PapersOpen Access
- 15 April 2024
- Published by Elsevier in Decision Analytics Journal
- Vol. 11
A cluster-based human resources analytics for predicting employee turnover using optimized Artificial Neural Networks and data augmentation
- 15 April 2024
- Published by Elsevier in Decision Analytics Journal
- Vol. 11
Top Cited PapersOpen AccessA cluster-based human resources analytics for predicting employee turnover using optimized Artificial Neural Networks and data augmentation
- Top Cited PapersOpen Access
- 30 January 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (3) , 533
Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices
Evaluating classification accuracy is a key component of the training and validation stages of thematic map production, and the choice of metric has profound implications for both the success of the training process and the reliability of the final accuracy assessment. We explore key considerations in selecting and interpreting loss and assessment metrics in the context of data imbalance, which arises when the classes have unequal proportions within the dataset or landscape being mapped. The challenges involved in calculating single, integrated measures that summarize classification success, especially for datasets with considerable data imbalance, have led to much confusion in the literature. This confusion arises from a range of issues, including a lack of clarity over the redundancy of some accuracy measures, the importance of calculating final accuracy from population-based statistics, the effects of class imbalance on accuracy statistics, and the differing roles of accuracy measures when used for training and final evaluation. In order to characterize classification success at the class level, users typically generate averages from the class-based measures. These averages are sometimes generated at the macro-level, by taking averages of the individual-class statistics, or at the micro-level, by aggregating values within a confusion matrix, and then, calculating the statistic. We show that the micro-averaged producer’s accuracy (recall), user’s accuracy (precision), and F1-score, as well as weighted macro-averaged statistics where the class prevalences are used as weights, are all equivalent to each other and to the overall accuracy, and thus, are redundant and should be avoided. Our experiment, using a variety of loss metrics for training, suggests that the choice of loss metric is not as complex as it might appear to be, despite the range of choices available, which include cross-entropy (CE), weighted CE, and micro- and macro-Dice. The highest, or close to highest, accuracies in our experiments were obtained by using CE loss for models trained with balanced data, and for models trained with imbalanced data, the highest accuracies were obtained by using weighted CE loss. We recommend that, since weighted CE loss used with balanced training is equivalent to CE, weighted CE loss is a good all-round choice. Although Dice loss is commonly suggested as an alternative to CE loss when classes are imbalanced, micro-averaged Dice is similar to overall accuracy, and thus, is particularly poor for training with imbalanced data. Furthermore, although macro-Dice resulted in models with high accuracy when the training used balanced data, when the training used imbalanced data, the accuracies were lower than for weighted CE. In summary, the significance of this paper lies in its provision of readers with an overview of accuracy and loss metric terminology, insight regarding the redundancy of some measures, and guidance regarding best practices.
- 30 January 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (3) , 533
Top Cited PapersOpen AccessSelecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices
Evaluating classification accuracy is a key component of the training and validation stages of thematic map production, and the choice of metric has profound implications for both the success of the training process and the reliability of the final accuracy assessment. We explore key considerations in selecting and interpreting loss and assessment metrics in the context of data imbalance, which arises when the classes have unequal proportions within the dataset or landscape being mapped. The challenges involved in calculating single, integrated measures that summarize classification success, especially for datasets with considerable data imbalance, have led to much confusion in the literature. This confusion arises from a range of issues, including a lack of clarity over the redundancy of some accuracy measures, the importance of calculating final accuracy from population-based statistics, the effects of class imbalance on accuracy statistics, and the differing roles of accuracy measures when used for training and final evaluation. In order to characterize classification success at the class level, users typically generate averages from the class-based measures. These averages are sometimes generated at the macro-level, by taking averages of the individual-class statistics, or at the micro-level, by aggregating values within a confusion matrix, and then, calculating the statistic. We show that the micro-averaged producer’s accuracy (recall), user’s accuracy (precision), and F1-score, as well as weighted macro-averaged statistics where the class prevalences are used as weights, are all equivalent to each other and to the overall accuracy, and thus, are redundant and should be avoided. Our experiment, using a variety of loss metrics for training, suggests that the choice of loss metric is not as complex as it might appear to be, despite the range of choices available, which include cross-entropy (CE), weighted CE, and micro- and macro-Dice. The highest, or close to highest, accuracies in our experiments were obtained by using CE loss for models trained with balanced data, and for models trained with imbalanced data, the highest accuracies were obtained by using weighted CE loss. We recommend that, since weighted CE loss used with balanced training is equivalent to CE, weighted CE loss is a good all-round choice. Although Dice loss is commonly suggested as an alternative to CE loss when classes are imbalanced, micro-averaged Dice is similar to overall accuracy, and thus, is particularly poor for training with imbalanced data. Furthermore, although macro-Dice resulted in models with high accuracy when the training used balanced data, when the training used imbalanced data, the accuracies were lower than for weighted CE. In summary, the significance of this paper lies in its provision of readers with an overview of accuracy and loss metric terminology, insight regarding the redundancy of some measures, and guidance regarding best practices.
- Open Access
- 18 October 2019
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLII-4/W18, 387-393
PUBLIC PARTICIPATION IN GIS VIA MOBILE APPLICATIONS FOR CRISIS MANAGEMENT PROCESS: A CASE STUDY OF AN EARTHQUAKE, TEHRAN, IRAN
The effects of earthquakes on societies are greater than what most people think. These effects range from structural damages to economic impacts and fatalities. An earthquake only lasts for a few seconds and the aftershocks may continue for days, but the damage does continue for years. The lack of integrated and automated tools for estimating resources needed in the aftermath of an earthquake during the disaster response phase motivate the design and implementation of a comprehensive, interactive, and user-friendly model. The objective of this research is to use geospatial analyses for examining vulnerable areas and evaluating the hazard of building damage by earthquake. Hence, the effective parameters of damage are identified and by using the fuzzy inference, the degree of damage in the study area is determined. Subsequently, with the provision of internet service in a troubled region, it is possible to collect voluntary information from people in the region using their mobile smartphones. For this purpose, an app in the Android Studio environment has been developed for convenience and sending the exact location of the affected sites. Moreover, the result of this research identified areas with a high priority for relief and optimal use of time, especially in the early hours of the crisis.
- 18 October 2019
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLII-4/W18, 387-393
Open AccessPUBLIC PARTICIPATION IN GIS VIA MOBILE APPLICATIONS FOR CRISIS MANAGEMENT PROCESS: A CASE STUDY OF AN EARTHQUAKE, TEHRAN, IRAN
The effects of earthquakes on societies are greater than what most people think. These effects range from structural damages to economic impacts and fatalities. An earthquake only lasts for a few seconds and the aftershocks may continue for days, but the damage does continue for years. The lack of integrated and automated tools for estimating resources needed in the aftermath of an earthquake during the disaster response phase motivate the design and implementation of a comprehensive, interactive, and user-friendly model. The objective of this research is to use geospatial analyses for examining vulnerable areas and evaluating the hazard of building damage by earthquake. Hence, the effective parameters of damage are identified and by using the fuzzy inference, the degree of damage in the study area is determined. Subsequently, with the provision of internet service in a troubled region, it is possible to collect voluntary information from people in the region using their mobile smartphones. For this purpose, an app in the Android Studio environment has been developed for convenience and sending the exact location of the affected sites. Moreover, the result of this research identified areas with a high priority for relief and optimal use of time, especially in the early hours of the crisis.