Pegah Khosravani

Pegah Khosravani

Department of Geosciences, Soil Science and Geomorphology, U...

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
29 May 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Hadi ShokatiHadi Shokati
Hadi Shokati
MMMahmoud Mashal
Mahmoud Mashal
ANAliakbar Noroozi
Aliakbar Noroozi
AAAli Akbar Abkar
Ali Akbar Abkar
SMSaham Mirzaei
Saham Mirzaei
Thomas ScholtenThomas Scholten
Thomas Scholten
Accurate spatiotemporal monitoring and modeling of soil moisture (SM) is of paramount importance for various applications ranging from food production to climate change adaptation. This study deals with modeling SM with the random forest (RF) algorithm using datasets comprising multispectral data from Sentinel-2, Landsat-8/9, and hyperspectral data from the CoSpectroCam sensor (CSC, licensed to AgriWatch BV, Enschede, The Netherlands) mounted on an unmanned aerial vehicle (UAV) in Iran. The model included nine bands from Landsat-8/9, 11 bands from Sentinel-2, and 1252 bands from the CSC (covering the wavelength range between 420 and 850 nm). The relative feature importance and band sensitivity to SM variations were analyzed. In addition, four indices, including the perpendicular index (PI), ratio index (RI), difference index (DI), and normalized difference index (NDI) were calculated from the different bands of the datasets, and their sensitivity to SM was evaluated. The results showed that the PI exhibited the highest sensitivity to SM changes in all datasets among the four indices considered. Comparisons of the performance of the datasets in SM estimation emphasized the superior performance of the UAV hyperspectral data (R2 = 0.87), while the Sentinel-2 and Landsat-8/9 data showed lower accuracy (R2 = 0.49 and 0.66, respectively). The robust performance of the CSC data is likely due to its superior spatial and spectral resolution as well as the application of preprocessing techniques such as noise reduction and smoothing filters. The lower accuracy of the multispectral data from Sentinel-2 and Landsat-8/9 can also be attributed to their relatively coarse spatial resolution compared to the CSC, which leads to pixel non-uniformities and impurities. Therefore, employing the CSC on a UAV proves to be a valuable technology, providing an effective link between satellite observations and ground measurements.

18 November 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Pegah KhosravaniPegah Khosravani
Pegah Khosravani
Ali Akbar MoosaviAli Akbar Moosavi
Ali Akbar Moosavi
MBMajid Baghernejad
Majid Baghernejad
NKNdiye Kebonye
Ndiye Kebonye
SMSeyed Roohollah Mousavi
Seyed Roohollah Mousavi
Thomas ScholtenThomas Scholten
Thomas Scholten
Soil aggregate stability (SAS) is needed to evaluate the soil’s resistance to degradation and erosion, especially in semi-arid regions. Traditional laboratory methods for assessing SAS are labor-intensive and costly, limiting timely and cost-effective monitoring. Thus, we developed cost-efficient wall-to-wall spatial prediction maps for two fundamental SAS proxies [mean weight diameter (MWD) and geometric mean diameter (GMD)], across a 5000-hectare area in Southwest Iran. Machine learning algorithms coupled with environmental and soil covariates were used. Our results showed that topographic covariates were the most influential covariates in predicting these SAS proxies. Overall, our SAS maps are valuable tools for sustainable soil and natural resource management, enabling decision-making for addressing potential soil degradation and promoting sustainable land use in semi-arid regions.

18 August 2024 in Land
Verified
Journal Article
Open access
PDF file
Pegah KhosravaniPegah Khosravani
Pegah Khosravani
MBMajid Baghernejad
Majid Baghernejad
Ruhollah Taghizadeh-MehrjardiRuhollah Taghizadeh-Mehrjardi
Ruhollah Taghizadeh-Mehrjardi
SMSeyed Roohollah Mousavi
Seyed Roohollah Mousavi
Ali Akbar MoosaviAli Akbar Moosavi
Ali Akbar Moosavi
Thomas ScholtenThomas Scholten
Thomas Scholten
(1) Background: The use of multiscale prediction or the optimal scaling of predictors can enhance soil maps by applying pixel size in digital soil mapping (DSM). (2) Methods: A total of 200, 50, and 129 surface soil samples (0–30 cm) were collected by the CLHS method in three different areas, namely, the Marvdasht, Bandamir, and Lapuee plains in southwest Iran. Then, four soil properties—soil organic matter (SOM), bulk density (BD), soil shear strength (SS), and mean weighted diameter (MWD)—were measured at each sampling point as representative attributes of soil physical and chemical quality. This study examined different-scale scenarios ranging from resampling the original 30 m digital elevation model and remote sensing indices to various pixel sizes, including 60 × 60, 90 × 90, 120 × 120, and up to 2100 × 2100 m. (3) Results: After evaluating 22 environmental covariates, 11 of them were identified as the most suitable candidates for predicting soil properties based on recursive feature elimination (RFE) and expert opinion methods. Furthermore, among different pixel size scenarios for SOM, BD, SS, and MWD, the highest accuracy was achieved at 1200 × 1200 m (R2 = 0.35), 180 × 180 m (R2 = 0.67), 1200 × 1200 m (R2 = 0.42), and 2100 × 2100 m (R2 = 0.34), respectively, in Marvdasht plain. (4) Conclusions: Adjusting the pixel size improves the capture of soil property variability, enhancing mapping precision and supporting effective decision making for crop management, irrigation, and land use planning.

24 December 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LHLing Hu
Ling Hu
Volker HochschildVolker Hochschild
Volker Hochschild
HNHarald Neidhardt
Harald Neidhardt
MSMichael Schultz
Michael Schultz
Pegah KhosravaniPegah Khosravani
Pegah Khosravani
Hadi ShokatiHadi Shokati
Hadi Shokati
Forest fires diminish forests’ ecological services, including carbon sequestration, water retention, air cooling, and recreation, while polluting the environment and endangering habitats. Despite considerable economic advancements, firefighting strategies remain less than optimal. This paper introduces the Bi-layer Predictive Ensemble (BIPE), an innovative machine learning model designed to enhance the accuracy and generalization of forest fire susceptibility mapping. BIPE integrates model-centric and data-driven strategies, employing automated methods such as 10-fold cross-validation and meta-learning to improve stability and generalization. During its 10-fold cross-validation, BIPE demonstrated excellent performance, with the Area Under the Curve (AUC) values ranging from 0.990 to 0.996 and accuracy levels consistently high, around 97%, underscoring its robust class separation ability and strong generalization across different datasets. Our results confirm that BIPE outperforms traditional high-performance models like Support Vector Machine (SVM), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), Deep Neural Network (DNN), and Convolutional Neural Network (CNN), showcasing its practical effectiveness and reliability on the data of nonlinear, high-dimensional, and complex interactions. Additionally, our forest fire susceptibility maps offer valuable complementary information for German forest fire management authorities, enhancing their ability to assess and manage fire risks more effectively.

15 May 2025
Verified
Conference Paper
Open access
Pegah KhosravaniPegah Khosravani
Pegah Khosravani
NKNdiye Kebonye
Ndiye Kebonye
MBMajid Baghernejad
Majid Baghernejad
Ali Akbar MoosaviAli Akbar Moosavi
Ali Akbar Moosavi
SMSeyed Roohollah Mousavi
Seyed Roohollah Mousavi
Thomas ScholtenThomas Scholten
Thomas Scholten
The carbon to nitrogen (C: N) ratio is essential for regulating soil nutrient content balance, directly influencing crop yields and microbial activity. Spatially explicit monitoring of this ratio in temperate regions remains important to fully understand its benefits. Therefore, we sought to understand the influencing factors of the C: N and map its spatial variability at 250 m/pixel across Germany. We applied n = 1687 surface soils obtained from the 2015 Land Use and Coverage Area Frame Survey (LUCAS) database coupled with key environmental covariates, including soil, climatic, human-related, topographic, and remote sensing data. A cubist machine learning model was used to relate the C: N ratio with these environmental covariates. Our analysis revealed that pH, elevation, latitude, and silt were among the top four important covariates, accounting for 76.6 % of the total variance in the C: N ratio. The Cubist model demonstrated acceptable predictive capabilities, with a root mean square error (RMSE) of 2.55 and a relatively low bias of 0.02. Our C: N prediction map indicated that the northwestern region of Germany exhibited high C: N ratio values ranging between 15 and 24. This range suggests conducive conditions that support soil microbial activity and greater nutrient availability. Furthermore, this region has high precipitation and NDVI values, corroborating our earlier point. Our findings emphasize the importance of soil, topography, and human activity in influencing the C: N ratio in temperate regions like Germany. Thus, understanding their roles in soil stoichiometry is crucial for developing effective land management strategies to enhance soil health and agricultural productivity.Keywords: Soil pH, Human Footprint, Nutrient Dynamics, Cubist Model, Climate Mitigation

14 March 2026
Verified
Conference Paper
Open access
Pegah KhosravaniPegah Khosravani
Pegah Khosravani
FFFlorian Carlo Fischer
Florian Carlo Fischer
DWDirk Wagner
Dirk Wagner
Thomas ScholtenThomas Scholten
Thomas Scholten
In the context of accelerating climate change, understanding how soil forms in some of the most extreme environments on Earth, such as the cold deserts of Antarctica, is critical. As ice-free areas expand, new substrates are exposed to pedogenesis, a process involving various biogeochemical reactions such as the accumulation of organic matter and the movement of substances within the soil profile. In order to gain a better understanding of these microscale pedogenic processes, it is important to comprehend how and why chemical and biological heterogeneity emerges in such harsh conditions.In this study, we combined microaggregate fractionation, chemical analyses, and correlative light and electron microscopy (CLEM) to identify early indicators of soil formation and microbial components in Antarctic soils. Bulk soils were fractionated into three microaggregate size classes (53–250 µm, 20–53 µm, < 20 µm), each further separated into free and occluded fractions, yielding six microaggregate fractions in addition to the bulk soil. All fractions underwent chemical analyses to determine elemental composition and key soil properties. CLEM was applied to detect and visualize microbial and organic components within the soil matrix. Energy-dispersive X-ray spectroscopy (EDX) complemented CLEM by revealing the spatial distribution of major elements and mineral phases.Results showed marked differences among microaggregate classes and between free and occluded fractions, highlighting chemical and biological microscale heterogeneity overlooked by bulk analyses. CLEM revealed organic matter and potential microbial structures within the soil matrix, while EDX highlighted patchy elemental distributions. Notably, the