Shaban Shataee

Prof. Shaban Shataee

Forestry, Gorgan University of Agricultural Sciences and Natural Resources, Gorgān, Golestān, Iran
orcid
Forestry, Remote sensing, GIS, Spatial modelling

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
16 April 2012 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
Shaban ShataeeShaban Shataee
Shaban Shataee
SKSyavash Kalbi
Syavash Kalbi
AFAsghar Fallah
Asghar Fallah
DPDieter Pelz
Dieter Pelz
In a small case study of mixed hardwood Hyrcanian forests of Iran, three non-parametric methods, namely k-nearest neighbour (k-NN), support vector machine regression (SVR) and tree regression based on random forest (RF), were used in plot-level estimation of volume/ha, basal area/ha and stems/ha using field inventory and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data. Relevant pre-processing and processing steps were applied to the ASTER data for geometric and atmospheric correction and for enhancing quantitative forest parameters. After collecting terrestrial information on trees in the 101 samples, the volume, basal area and tree number per hectare were calculated in each plot. In the k-NN implementation using different distance measures and k, the cross-validation method was used to find the best distance measure and optimal k. In SVR, the best regularized parameters of four kernel types were obtained using leave-one-out cross-validation. RF was implemented using a bootstrap learning method with regularized parameters for decision tree model and stopping. The validity of performances was examined using unused test samples by absolute and relative root mean square error (RMSE) and bias metrics. In volume/ha estimation, the results showed that all the three algorithms had similar performances. However, SVR and RF produced better results than k-NN with relative RMSE values of 28.54, 25.86 and 26.86 (m3 ha–1), respectively, using k-NN, SVR and RF algorithms, but RF could generate unbiased estimation. In basal area/ha and stems/ha estimation, the implementation results of RF showed that RF was slightly superior in relative RMSE (18.39, 20.64) to SVR (19.35, 22.09) and k-NN (20.20, 21.53), but k-NN could generate unbiased estimation compared with the other two algorithms used.

24 July 2017 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
ASAmir Safari
Amir Safari
Hormoz SohrabiHormoz Sohrabi
Hormoz Sohrabi
SPScott Powell
Scott Powell
Shaban ShataeeShaban Shataee
Shaban Shataee
Remote sensing of low biomass forests has challenges related to the contribution of soil and understory reflectance recorded by sensors, hampering accurate forest aboveground carbon (AGC) quantification. To improve Landsat-based AGC estimates in forests with low biomass, this study explored the use of multi-temporal Landsat 8 Operational Land Imager (OLI) derived spectral information in Zagros forests by testing four machine learning algorithms: support vector machine (SVM), boosted regression trees (BRT), random forest (RF) and multivariate adaptive regression splines (MARS). We selected two forest areas with different levels of human activity for AGC reference plots: un-degraded forest (UD) and highly-degraded forest (HD). The results of the study showed that the Landsat image acquired in the peak of the growing season (10 August) provided the best AGC estimates for the UD site, but that for the HD site, AGC estimates were not affected by the timing of the imagery. The comparison of different modelling methods demonstrated lower accuracies from BRT, considerably biased estimates from SVM, and generally robust results from the RF algorithm. Overall, the study demonstrated the utility of applying the free Landsat 8 OLI dataset to AGC estimation, in particular non-commercial forests in developing countries where little budget is allocated for management.

10 June 2010 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
JMJ. Mohammadi
J. Mohammadi
Shaban ShataeeShaban Shataee
Shaban Shataee
FYF. Yaghmaee
F. Yaghmaee
AMA. S. Mahiny
A. S. Mahiny

1 April 2020 in Remote Sensing of Environment
Verified
Journal Article
Closed access
MPMaryam Poorazimy
Maryam Poorazimy
Shaban ShataeeShaban Shataee
Shaban Shataee
RMRonald E. McRoberts
Ronald E. McRoberts
JMJahangir Mohammadi
Jahangir Mohammadi

13 May 2023 in Environment, Development and Sustainability
Verified
Journal Article
Open access
PDF file
NKNematollah Kohestani
Nematollah Kohestani
SRShafagh Rastgar
Shafagh Rastgar
GHGhodratolla Heydari
Ghodratolla Heydari
Shaban ShataeeShaban Shataee
Shaban Shataee
HAHamid Amirnejad
Hamid Amirnejad
The current paper aims to assess the effects of landscape change in a mountain river basin in the north of Iran through quantifying, mapping, and assessing carbon storage. The analyses were performed based on previous alterations in land use and land cover (LULC) (1988–2018) and on expected changes determined by three LULC alteration setups for 2048. The Landsat imagery from 2018, 2008, 1998, and 1988 was used for evaluating and predicting the spatiotemporal distributions of LULC changes. The future LULC image prediction has been generated using Land Change Modeler (LCM) module of TerrSet software for the years 2028, 2038, and 2048. Validation was carried out by overlaying the actual and projected to 2018 map. We integrated the Markov Chain (MC) and InVEST Carbon Storage and Sequestration (InVEST-CSS) models for simulating the ecosystem carbon storage and the long-term monetary valuation. In this process, we considered social costs/economic value because of the area’s loss and gain of stored carbon. The results show that forests and rangelands with good and poor conditions decreased by 631.2, 10,374, and 10,254 ha, respectively, from 1988 to 2018. Overall, modeling and mapping LULC changes showed a descending trend in forests (0.66%), agriculture (0.1%), and rangelands (4.1%) in 2048. In addition, carbon storage has already been lost by 9.9 million tons (76.98 ha−1) from 1988 to 8.8 million tons (68.86 ha−1) in 2018 and is expected to have an 8.4 million tons (65.25 ha−1) loss by 2048. Monitoring the economic value of carbon storage from 1988 to 2018 shows a loss of $US 15684338 (121.8 ha−1) and estimates a loss of $US6972622 (54.18 ha−1) by 2048. Therefore, spatiotemporal design of InVEST model by estimating the carbon value over time focuses on continuous monitoring actions for both the carbon pools dynamic and LULC pattern. This consideration causes reduction the uncertainty of estimated models and also increases the continuous cost of those changes. This will help government and decision makers for long-term and accurate carbon sequestration strategies for ecosystem.

31 May 2019 in Arabian Journal of Geosciences
Verified
Journal Article
Closed access
PDF file
STSamaneh Tajik
Samaneh Tajik
SAShamsollah Ayoubi
Shamsollah Ayoubi
JKJahangir Khajehali
Jahangir Khajehali
Shaban ShataeeShaban Shataee
Shaban Shataee