Sara Attarchi

Dr. Sara Attarchi

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
7 April 2021 in Environmental Monitoring and Assessment
Verified
Journal Article
Closed access
PDF file
MMMeysam Moharrami
Meysam Moharrami
MJMohammad Javanbakht
Mohammad Javanbakht
SASara Attarchi
Sara Attarchi

28 April 2014 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SASara Attarchi
Sara Attarchi
Richard GloaguenRichard Gloaguen
Richard Gloaguen
The objective of this study is to develop models based on both optical and L-band Synthetic Aperture Radar (SAR) data for above ground dry biomass (hereafter AGB) estimation in mountain forests. We chose the site of the Loveh forest, a part of the Hyrcanian forest for which previous attempts to estimate AGB have proven difficult. Uncorrected ETM+ data allow a relatively poor AGB estimation, because topography can hinder AGB estimation in mountain terrain. Therefore, we focused on the use of atmospherically and topographically corrected multispectral Landsat ETM+ and Advanced Land-Observing Satellite/Phased Array L-band Synthetic Aperture Radar (ALOS/PALSAR) to estimate forest AGB. We then evaluated 11 different multiple linear regression models using different combinations of corrected spectral and PolSAR bands and their derived features. The use of corrected ETM+ spectral bands and GLCM textures improves AGB estimation significantly (adjusted R2 = 0.59; RMSE = 31.5 Mg/ha). Adding SAR backscattering coefficients as well as PolSAR features and textures increase substantially the accuracy of AGB estimation (adjusted R2 = 0.76; RMSE = 25.04 Mg/ha). Our results confirm that topographically and atmospherically corrected data are indispensable for the estimation of mountain forest’s physical properties. We also demonstrate that only the joint use of PolSAR and multispectral data allows a good estimation of AGB in those regions.

25 April 2014 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SASara Attarchi
Sara Attarchi
Richard GloaguenRichard Gloaguen
Richard Gloaguen
Forest environment classification in mountain regions based on single-sensor remote sensing approaches is hindered by forest complexity and topographic effects. Temperate broadleaf forests in western Asia such as the Hyrcanian forest in northern Iran have already suffered from intense anthropogenic activities. In those regions, forests mainly extend in rough terrain and comprise different stand structures, which are difficult to discriminate. This paper explores the joint analysis of Landsat7/ETM+, L-band SAR and their derived parameters and the effect of terrain corrections to overcome the challenges of discriminating forest stand age classes in mountain regions. We also verified the performances of three machine learning methods which have recently shown promising results using multisource data; support vector machines (SVM), neural networks (NN), random forest (RF) and one traditional classifier (i.e., maximum likelihood classification (MLC)) as a benchmark. The non-topographically corrected ETM+ data failed to differentiate among different forest stand age classes (average classification accuracy (OA) = 65%). This confirms the need to reduce relief effects prior data classification in mountain regions. SAR backscattering alone cannot properly differentiate among different forest stand age classes (OA = 62%). However, textures and PolSAR features are very efficient for the separation of forest classes (OA = 82%). The highest classification accuracy was achieved by the joint usage of SAR and ETM+ (OA = 86%). However, this shows a slight improvement compared to the ETM+ classification (OA = 84%). The machine learning classifiers proved t o be more robust and accurate compared to MLC. SVM and RF statistically produced better classification results than NN in the exploitation of the considered multi-source data.

30 October 2021 in Atmosphere
Verified
Journal Article
Open access
PDF file
NMNicholas Middleton
Nicholas Middleton
SKSaviz Sehat Kashani
Saviz Sehat Kashani
SASara Attarchi
Sara Attarchi
MRMehdi Rahnama
Mehdi Rahnama
SMSahar Tajbakhsh Mosalman
Sahar Tajbakhsh Mosalman
Dust storms represent one of the most severe, if underrated, natural hazards in drylands. This study uses ground observational data from meteorological stations and airports (SYNOP and METARs), satellite observations (MODIS level-3 gridded atmosphere daily products and CALIPSO) and reanalysis data (ERA5) to analyze the synoptic meteorology of a severe Middle Eastern dust storm in April 2015. Details of related socio-economic impacts, gathered largely from news media reports, are also documented. This dust storm affected at least 14 countries in an area of 10 million km2. The considerable impacts were felt across eight countries in health, transport, education, construction, leisure and energy production. Hospitals in Saudi Arabia, Qatar and the UAE experienced a surge in cases of respiratory complaints and ophthalmic emergencies, as well as vehicular trauma due to an increase in motor vehicle accidents. Airports in seven countries had to delay, divert and cancel flights during the dust storm. This paper is the first attempt to catalogue such dust storm impacts on multiple socio-economic sectors in multiple countries in any part of the world. This type of transboundary study of individual dust storm events is necessary to improve our understanding of their multiple impacts and so inform policymakers working on this emerging disaster risk management issue.

19 August 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
NKNafiseh Kakhani
Nafiseh Kakhani
MRMoien Rangzan
Moien Rangzan
AJAli Jamali
Ali Jamali
SASara Attarchi
Sara Attarchi
Seyed Kazem AlavipanahSeyed Kazem Alavipanah
Seyed Kazem Alavipanah
TSThomas Scholten
Thomas Scholten
Soil Organic Carbon (SOC) constitutes a fundamental component of terrestrial ecosystem functionality, playing a pivotal role in nutrient cycling, hydrological balance, and erosion mitigation. Precise mapping of SOC distribution is imperative for the quantification of ecosystem services, notably carbon sequestration and soil fertility enhancement. Digital soil mapping (DSM) leverages statistical models and advanced technologies, including machine learning (ML), to accurately map soil properties, such as SOC, utilizing diverse data sources like satellite imagery, topography, remote sensing indices, and climate series. Within the domain of ML, self-supervised learning (SSL), which exploits unlabeled data, has gained prominence in recent years. This study introduces a novel approach that aims to learn the geographical link between multimodal features via self-supervised contrastive learning, employing pretrained Vision Transformers (ViT) for image inputs and Transformers for climate data, before fine-tuning the model with ground reference samples. The proposed approach has undergone rigorous testing on two distinct large-scale datasets, with results indicating its superiority over traditional supervised learning models, which depends solely on labeled data. Furthermore, through the utilization of various evaluation metrics (e.g., RMSE, MAE, CCC, etc.), the proposed model exhibits higher accuracy when compared to other conventional ML algorithms like random forest and gradient boosting. This model is a robust tool for predicting SOC and contributes to the advancement of DSM techniques, thereby facilitating land management and decision-making processes based on accurate information.

18 November 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
RPRamin Papi
Ramin Papi
SASara Attarchi
Sara Attarchi
Ali Darvishi BolooraniAli Darvishi Boloorani
Ali Darvishi Boloorani
Najmeh Samani NeisaniNajmeh Samani Neisani
Najmeh Samani Neisani
Due to diverse hydroclimatic conditions and human interventions, the Middle East hosts a variety of active sources of sand and dust storms (SDS). Discrimination of different types of SDS sources is the most important factor for adopting optimal mitigation measures to combat SDS. This study employed a binary mask-based modeling framework to identify Middle East SDS sources. Accordingly, using time series of remotely sensed data of land surface and atmospheric aerosol parameters, SDS sources covering an area of 1 million Km2 were identified with an overall accuracy of 82.6%. Considering the type of land use and spatial-temporal changes in water bodies, SDS sources were categorized into seven types in terms of origin. Desert sources have the largest share (>79%), whereas hydrologic sources accounted for about 8.4%. The results showed that water bodies had a declining trend after 2000. The occurrence of two severe drought periods in 2000–2001 and 2007–2012 led to a 52% decrease in water bodies and a 14–37% increase in SDS emission compared to the pre-2000 period. The latter drought period also led to a sharp decrease in groundwater resources across the region. Our results revealed that natural circumstances and drought actively contribute to the depletion of water resources that led to the formation of SDS sources in the Middle East, while the role of anthropogenic factors is predominant in the case of hydrologic SDS sources.