Saeed Saroei; Ali Asghar Darvishsefat; Manochehr Namiranian
Abstract
Estimating the biomass values in forests stands through remote sensing is important. It has been reported that the major reasons of uncertainty are the lack of concurrency in satellite data and field information as well as the use of global allometric equations for estimating the weight of biomass of ...
Read More
Estimating the biomass values in forests stands through remote sensing is important. It has been reported that the major reasons of uncertainty are the lack of concurrency in satellite data and field information as well as the use of global allometric equations for estimating the weight of biomass of forest trees inside the country. Minimizing the above problems and the investigation of data performance in developing appropriate model for estimating the forest biomass in the Bankoll region of Karazan District of Sirvan County in Ilam province using Sentinel-1 satellite data in 27th of June, 2017 was the main goal of this study. Average size of the trees crown in 53 rectangular plots related to the coppice growth form with dimensions of 30×30 mwhich during 23 may 2017 to 10 June 2017 through applying DGPS by RTK method have been implemented on the ground were entered in the process of estimation the value of biomass. The average harvested field biomass was 10.63 Mg ha-1. After extraction of radar features, those features which had the greatest correlation with the values of biomass were selected using genetic algorithm by two models including K-Nearest Neighbor (K-NN) regression and Support-Vector Regression (SVR), then the most appropriate combination was identified and the biomass values were modelled. Models were validated using 26 test plots. Correlation of features obtained from radar data and the value of biomass indicated that features of VH، Mean VV، Mean VV GLCM (Correlation) and Mean VH GLCM (Dissimilarity) had the greatest sensitivity towards the value of biomass. Using regression models indicated that SVR model (Relative RMSE of 0.08) was more precise compared with K-NN regression (relative RMSE of 0.10). The best combination in the use of K-NN regression model with a relative RMSE of almost 0.99 Mg ha-1 (equal to 10%) and the coefficient of determination (R2) of 0.22 and the best combination when using SVR model was a relative RMSE of 0.87 Mg ha-1 (equal to 8%) and the R2 of 0.14. The results indicated that the final models, obtained from the optimal features extracted from radar data in the wavelength of C band and used parametric and non-parametric regressional methods in this research, were not abled to improve the saturated effect in data for estimation of biomass in the studied forests and it was not resulted in presenting an estimating model with an acceptable accuracy.
M Rajabpour Rahmati; A.A Darvishsefat; N Baghdadi; Manochehr Namiranian; Nosrat ollah Zargham
Volume 7, Issue 4 , November 2015, , Pages 85-98
Abstract
Forest volume as an important factor in forest management was aimed to be measured in mountainous forests in the North of Iran using spaceborne LiDar. Two missions of GLAS (L3K and L3I) were preprocessed to remove inappropriate waveforms. Several waveform metrics including waveform extent (Wext), lead ...
Read More
Forest volume as an important factor in forest management was aimed to be measured in mountainous forests in the North of Iran using spaceborne LiDar. Two missions of GLAS (L3K and L3I) were preprocessed to remove inappropriate waveforms. Several waveform metrics including waveform extent (Wext), lead edge extent (Hlead), trail edge extent (Htrail) and quartile heights (H25, H50, H75 and H100) were extracted. Principal component analysis (PCA) was also applied to reduce noises from waveform signals and produce new components (PCs). In order to decrease the effect of terrain slope on waveforms, terrain index (TI) describing topographic information was extracted from a digital elevation model (DEM). Forest stand volume was measured on 60 circle plots with diameter of 70 m for developing volume models and their validation. Multiple regression and artificial neural network models were built based on two sets of variables including waveform metrics and PCs. Generally, both multiple regression and neural network methods produced approximately the same result. A neural network combining three first PCs of PCA and Wext estimated forest volume with an RMSE and of 119.9 m and 0.73, respectively (RMSE%=26.6). Interesting points regards to this model is employing PCs and Wext as input variables which are not affected by terrain slope, achieving slightly better accuracy without adding any ancillary data (DEM), and showing better performance in short sparse stands in comparison with other developed models.
