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.
