Narges Kariminejad
57201980350
Publications - 10
Evaluation of early warning signals for soil erosion using remote sensing indices in northeastern Iran
Publication Name: Scientific Reports
Publication Date: 2025-12-01
Volume: 15
Issue: 1
Page Range: Unknown
Description:
Soil erosion represents a major challenge to natural resource conservation, causing land degradation, biodiversity loss, and diminished soil quality. This study explored the use of satellite imagery to evaluate the spatiotemporal risk of soil erosion in northeastern Iran. The ICONA model was applied to identify areas at severe erosion risk, while remote sensing indices (NDVI, NDSI, and TGSI) were employed to analyze erosion trends. NDVI is used to monitor vegetation health, NDSI detects soil salinity levels, and TGSI assesses topsoil grain size distribution, collectively providing critical insights into soil erosion risk in the study area. These indices, derived from the Google Earth Engine with a 30-meter spatial resolution and monthly temporal intervals (2003–2022), were assessed at 100 points, equally divided between eroded and non-eroded regions. Field data, including vegetation plots and soil profiles, were used to validate the remote sensing outputs. Early warning signals were analyzed through three statistical indices—autocorrelation coefficient, skewness, and standard deviation—using Kendall’s tau. Results revealed that 39.7% of the area falls under low erosion risk, 58.4% under medium risk, and 1.9% under severe risk. Significant breakpoints in NDSI and NDVI were identified in 2013, while TGSI showed no detectable change. Major shifts occurred near the Alagol, Almagol, and Ajigol wetlands and northern drylands. This study underscores the importance of integrating satellite data with field validation to improve soil management, protect biodiversity, and guide sustainable erosion mitigation strategies.
Open Access: Yes
Evaluation of Various Deep Learning Algorithms for Landslide and Sinkhole Detection from UAV Imagery in a Semi-arid Environment
Publication Name: Earth Systems and Environment
Publication Date: 2024-12-01
Volume: 8
Issue: 4
Page Range: 1387-1398
Description:
Sinkholes and landslides occur due to soil collapse in different slope types, often triggered by heavy rainfall, presenting challenges in the semi-arid Golestan province, Iran. This study primarily focuses on the detection of these phenomena. Recent advancements in unmanned aerial vehicle (UAV) image acquisition and the incorporation of deep learning (DL) algorithms have enabled the creation of semi-automated methods for highly detailed soil landform detection across large areas. In this study, we explored the efficacy of six state-of-the-art deep learning segmentation algorithms—DeepLab-v3+, Link-Net, MA-Net, PSP-Net, ResU-Net, and SQ-Net—applied to UAV-derived datasets for mapping landslides and sinkholes. Our most promising outcomes demonstrated the successful mapping of landslides with an F1-Score of 0.95% and sinkholes with an F1-Score of 89% in a challenging environment. ResUNet exhibited an outstanding Precision of 0.97 and Recall of 0.92, culminating in the highest F1-Score of 0.95, indicating the best landslide detection model. MA-Net and SQ-Net resulted in the highest F1-Score for sinkhole detection. Our study underscores the significant impact of DL segmentation algorithm selection on the accuracy of landslide and sinkhole detection tasks. By leveraging DL segmentation algorithms, the accuracy of both landslide and sinkhole detection tasks can be significantly improved, promoting better hazard management and enhancing the safety of the affected areas.
Open Access: Yes
Detection of sinkholes and landslides using deep-learning methods and UAV images
Publication Name: Watershed Engineering and Management
Publication Date: 2024-09-01
Volume: 16
Issue: 3
Page Range: 316-330
Description:
Introduction Landslides and sinkholes damage social, economic, and natural infrastructure. These processes have direct and indirect impacts on important infrastructure, including residential areas, and influence land use change and migration from rural to urban areas. Sinkholes and landslides occur when parts of a soil collapse mainly in more gentle or steeper slopes, which are often triggered by intensive rainfall. One of the main goals in sustainable land management is the identification and control of natural disasters, which on the one hand leads to the quantitative and qualitative improvement of production in the long term, and on the other hand, maintains the quality of the soil and prevents soil degradation. In order to manage better and more stable, it seems necessary to know how to change and identify different forms of erosion such as sinkholes and landslides. Sinkholes and landslides occur when parts of a soil collapse mainly in more gentle or steeper slopes, which are often triggered by intensive rainfall. Materials and methods Recent advances in acquiring images from unmanned aerial vehicles (UAV) (UAV) and deep learning (DL) methods inherited from computer vision have made it feasible to propose semi-automated soil landform detection methodologies for large areas at an unprecedented spatial resolution. In this study, we evaluate the potential of two cutting-edge DL deep learning segmentation models, the vanilla U-Net model, and the Attention Deep Supervision Multi-Scale U-Net model, applied to UAV-derived products, to map landslides and sinkholes in a semi-arid environment, the “Golestan Province” (north-east Iran). Results and discussion Landslides: The performance of the U-Net model shows that it has fewer false positives, but at the same time, it has missed many landslide cells. Meanwhile, the ADSMS U-Net model has performed better in detecting landslide cells, but it attributed many cases to incorrect predictions (which is explained by the low accuracy score). The best F1 score achieved for the ADSMS U-Net model is 0.68. Sinkholes: For all band combinations, the performances of ADSMS U-Net are better than those of the traditional U-Net model. The best overall scores by ADSMS U-Net were obtained when trained on the ALL data. Regarding the effectiveness of the various combinations evaluated in this study, we can observe the contradictory behaviors of the models. The traditional U-Net achieves the best performance using the RGB optical combination, while the ADSMS U-Net can leverage topographic derivative information and optical data, showing the best results with the ALL combination. Moreover, it is evident that the DSHC data alone provides the worst results for both models. In overall, the results show that the ability of ADSMS U-Net to predict landslides is closer to the ground reality compared to U-Net. This model identifies most of the landslides in the test sections. Also, for all combinations of sinkhole bands, ADSMS U-Net performs better than the U-Net model. The best overall scores were obtained by ADSMS U-Net when trained on ALL data. Conclusions Since this kind of soil erosion is the main origin of some major soil erosion including gully initiation and extension, applying new technology namely, UAV and deep learning is highly important and recommended. Our framework can successfully map landslides in a challenging environment (with an F1-score of 69 %), and topographical derivates from UAV-derived DSM decrease the capacity of mapping sinkholes and landslides of the models calibrated with optical data. Future research could explore the use of such an approach to map landslides and sinkholes over time to assess time-based changes in the formation and spread of natural hazards.
Open Access: Yes
Assessment of soil erosion through spatial analyzing of soil properties using statistical-based functions
Publication Name: Bio Web of Conferences
Publication Date: 2024-08-23
Volume: 125
Issue: Unknown
Page Range: Unknown
Description:
The significant geomorphological hazard of collapsed cavities (CC) causes notable environmental transformations. To address this issue, the pipe collapse pattern was examined using two statistical methods, the Density Correlation Function (DCF) and the Mark Coloration Function (MCF). Key predictor variables like organic carbon (OC), sodium adsorption ratio (SAR), and exchangeable sodium percentage (ESP) were utilized to comprehend their impact on spatial distribution over time. The study was found that lower OC levels increase susceptibility to CC, while higher SAR and ESP amounts enhance the potential for collapsed cavities. The methodology and discoveries of this research can offer valuable insights for land managers, stakeholders, and researchers.
Open Access: Yes
Analysis of early warning signal of land degradation risk based on time series of remote sensing data
Publication Name: Bio Web of Conferences
Publication Date: 2024-08-23
Volume: 125
Issue: Unknown
Page Range: Unknown
Description:
This study explores the spatio-temporal dynamics of the Normalized Difference Vegetation Index (NDVI) to detect early signs of land degradation. Utilizing high-resolution NDVI data from the Google Earth Engine, spanning from 2004 to 2023 with a 30-meter resolution, this research analyzes monthly variations. To illustrate these dynamics, the study focuses on Sabzevar County, located in northeastern Iran, which extends over 7,217 km2and is approximately 220 kilometers distant from Mashhad. Validation of the NDVI data was performed using field observations from strategically located vegetation plots. One square meter plots were systematically established along 100-meter transects (10 transects in total), where the vegetation coverage in each plot was quantitatively assessed by experts. Comprehensive statistical analysis incorporated Kendall's tie test, alongside measurements of autocorrelation, coefficient of variation, and standard deviation, using R software to assess the trends and intensities of NDVI changes. The findings revealed a critical breakpoint in 2020, with increases in all three statistical indices—autocorrelation 0.82, coefficient of variation 0.65, and standard deviation 0.58—indicative of accelerating degradation prior to this year. Furthermore, the intensity of NDVI changes varied significantly across the study area, ranging from 0.05 in central and northern regions to 0.76 in the western parts. This research underscores the value of integrating field data with remote sensing technology to provide a robust analytical tool for early detection of land degradation. This method enables precise, timely assessment and proactive management of vulnerable ecosystems, particularly in arid regions.
Open Access: Yes
Land subsidence modeling and mapping in Darab region, Iran
Publication Name: Advanced Tools for Studying Soil Erosion Processes Erosion Modelling Soil Redistribution Rates Advanced Analysis and Artificial Intelligence
Publication Date: 2024-01-01
Volume: Unknown
Issue: Unknown
Page Range: 275-294
Description:
Land subsidence refers to the collapse of Earth's surface. This study aimed to model land subsidence using machine learning methods in the Darab region of Fars Province, which is recognized as one of the most critical provinces suffering from land subsidence in the country. Nineteen factors affecting the occurrence of land subsidence were selected as independent variables for the modeling process: slope degree, aspect, distance to rivers, stream density, elevation, land use, normalized difference vegetation index (NDVI), plan curvature, profile curvature, topographic wetness index, pH, electrical conductivity, mean annual rainfall, mean weight diameter (MWD), clay, silt, calcium carbonate equivalent (CCE), sodium content, and organic matter. Modeling was conducted using: artificial neural network (ANN), maximum entropy (MaxEnt), and support vector machine (SVM). The performance of algorithms was compared both individually and in combination. Validation results using the receiver operating characteristic (ROC) curve to identify landslide prone areas showed that land subsidence susceptibility maps produced by single MaxEnt model had highest accuracy, with area under the curve (AUC) of 0.92. According to the prioritization of effective factors, elevation and land use were determined to be the most crucial factors for land subsidence. The results of this spatial modeling of land subsidence susceptibility can greatly aid land allocation planning and water resource management in the study area.
Open Access: Yes
Susceptibility mapping for land subsidence and collapsed pipes in north-east Iran
Publication Name: Advanced Tools for Studying Soil Erosion Processes Erosion Modelling Soil Redistribution Rates Advanced Analysis and Artificial Intelligence
Publication Date: 2024-01-01
Volume: Unknown
Issue: Unknown
Page Range: 579-594
Description:
Land subsidence and collapsed pipes are considered among geomorphological hazards, causing significant damages annually in the form of direct and indirect costs. These hazards lead to notable changes in the landscape, land degradation, soil and water losses, and regional erosion and sedimentation. Consequently, the effective management of these hazards and the determination of relationships between their environmental factors for quantitative susceptibility assessment are of utmost importance. A trustworthy evaluation depends on the quality of available data and the selection of appropriate analytical and modeling methods. Given that no comprehensive study on land subsidence and collapsed pipes in Razavi Khorasan Province has been conducted so far and considering that the land degradation resulting from plain land subsidence and collapsed pipes are among the primary threatening hazards for the country and the province, particularly in recent years, the use of proper analytical and modeling methods for comprehensive and integrated management seems essential. This research was conducted using high-resolution satellite imagery in Razavi Khorasan Province. In this study, topographical and hydrological feature maps were prepared using a digital elevation model based on the boundaries of Razavi Khorasan Province. Physical and chemical tests were conducted on 624 soil samples collected throughout the province, and their raster maps were produced. Data pertaining to vegetation cover, land use maps, geology, and regional precipitation were also prepared and used as inputs for the models. The spatial locations of land subsidence and collapsed pipes across the province were identified in subsequent phases. Following this, using statistical and data mining methods, spatial modeling of the land subsidence and collapsed pipes was performed, and the best regional model for their evaluation was chosen. The AUC numerical value for both the support vector machine (SVM) and maximum entropy (ME) models ranges between 0.8 and 0.9, indicating an excellent evaluation of the models used in zoning the land subsidence. Ultimately, the ability to recognize the behavior and formation conditions of these hazards, to identify areas with greater susceptibility, to present a risk management model for land subsidence and collapsed pipes, and to distinguish critical and susceptible areas for land subsidence and collapsed pipes, along with their control methods, was provided. Notably, the SVM algorithm demonstrated superior efficacy in this study. The insights derived from identifying erosional structures of collapsed pipes and land subsidence and understanding their spatial interrelationships offer a robust foundation for devising timely and strategic management interventions in affected domains.
Open Access: Yes
Soil pipe pattern dynamics and illustration of the erosional landforms from a geomorphological perspective
Publication Name: Advanced Tools for Studying Soil Erosion Processes Erosion Modelling Soil Redistribution Rates Advanced Analysis and Artificial Intelligence
Publication Date: 2024-01-01
Volume: Unknown
Issue: Unknown
Page Range: 59-72
Description:
The primary objective of this research was to analyze the spatial pattern and interactions of dendritic rill channels and surface/subsurface channels (pipes)/collapsed pipes. To achieve this, photogrammetry drones were employed on over 70ha in the protected region of Takhtsoltan in Razavi Khorasan Province. This approach pinpointed areas impacted by erosions from subsurface channels (pipes)/collapsed pipes and dendritic rill channels and surfaces. Subsequent field visits documented 76 instances of subsurface channels (pipes)/collapsed pipes and 58 dendritic rill channels and surfaces, using orthophotos derived from the aerial drone images. In the analytical phase, topographical, hydrological, soil, and biological factors were examined as independent variables, whereas the types of erosion from subsurface channels (pipes)/collapsed pipes and dendritic rill channels were viewed as dependent variables. Spatial patterns of the subsurface channels (pipes)/collapsed pipes and dendritic rill channels were discerned using univariate functions. Further, bivariate functions were deployed to probe the interrelations, revealing that the distribution pattern of the study area's subsurface channels (pipes)/collapsed pipes is predominantly clustered, in contrast to the dispersed spatial pattern of the dendritic rill channels. This analysis also confirmed significant positive correlations between dendritic rill channel erosions and subsurface channels (pipes)/collapsed pipes. Ultimately, by identifying the erosional landforms of subsurface channels (pipes)/collapsed pipes and dendritic rill channels and understanding the spatial and processual relationships between them, a deeper insight into the natural processes inherent in their spatial structure was achieved, paving the way for devising suitable strategies for their timely management.
Open Access: Yes
Review of multihazards research with the basis of soil erosion
Publication Name: Advanced Tools for Studying Soil Erosion Processes Erosion Modelling Soil Redistribution Rates Advanced Analysis and Artificial Intelligence
Publication Date: 2024-01-01
Volume: Unknown
Issue: Unknown
Page Range: 295-306
Description:
Soil erosion is a primary geomorphic process that may result in hazards and significant socioeconomic losses. These processes occur mainly through the surface and subsurface flows. We conducted a systematic literature review on the quantitative attribution analysis of soil erosion, presenting state-of-the-art erosion processes and demonstrating the relative importance of soil erosion as a natural hazard responsible for land degradation and desertification. This explains why a multidisciplinary approach is needed to understand how erosion occurs and what factors are involved. This justifies the multihazard analysis and the need to model the erosion processes. Knowledge of the quantitative elements of soil erosion measurement combined with the consideration of multiple risk assessments can help develop conceptual models of slope hydrology and soil erosion that can help decision-makers determine an appropriate early warning system design policy. Filling these gaps will guide us to increase our knowledge of surface and subsurface erosion, thereby helping us to better explore the changing landscape for improvement and develop strategies and effective soil erosion control techniques. However, more research is required to better explore the morphology and connectivity of soil erosion, their subsurface watershed, and behavior, as well as several challenges, opportunities, and strategies facing the analysis of soil erosion.
Open Access: Yes
Assessment of soil erosion patterns in Maharloo watershed using remote sensing techniques and early warning signals
Publication Name: Journal of Arid Environments
Publication Date: 2026-02-01
Volume: 232
Issue: Unknown
Page Range: Unknown
Description:
This study assessed the soil erosion dynamics in Iran's Maharloo watershed using remote sensing indices (Normalized Difference Vegetation Index (NDVI), Normalized Difference Salinity Index (NDSI), and Topsoil Grain Size Index (TGSI)) and machine learning models (RF, SVM, and BRT). Landsat 8 satellite images (2005–2024) were processed via the Google Earth Engine, with field validation ensuring accuracy. Among the indices, TGSI (R2 = 0.86), NDSI (R2 = 0.89), and NDVI (R2 = 0.87) showed the strongest correlations with ground data (Rain, Soil and Vegetation). The RF outperformed the other models (AUC = 0.89), identifying the central and western regions as warning erosion zones. Breakpoint analysis revealed abrupt changes in NDVI and NDSI (2013), while early warning signals (autocorrelation, variance, and skewness) indicated an escalating erosion warning, particularly near wetlands and rainfed fields. Spatial trends highlighted significant NDVI declines (Kendall's τ = 0.69) in wetland peripheries and NDSI increased (τ = 0.52) in northern farmlands. These findings underscore the efficacy of integrating machine learning and remote sensing for erosion monitoring, providing actionable insights for land management and conservation strategies.
Open Access: Yes
