Spatial distributions and associations of main tree species in a spruce-fir forest in the Changbai Mountains area in northeastern China

2014 ◽  
Vol 34 (16) ◽  
Author(s):  
杨华 YANG Hua ◽  
李艳丽 LI Yanli ◽  
沈林 SHEN Lin ◽  
亢新刚 KANG Xingang
Keyword(s):  
Tree Species ◽  
Northeastern China ◽  
Changbai Mountains ◽  
Spatial Distributions

scholarly journals Mapping Tree Species Composition Using OHS-1 Hyperspectral Data and Deep Learning Algorithms in Changbai Mountains, Northeast China

Forests ◽  
2019 ◽  
Vol 10 (9) ◽  
pp. 818
Author(s):  
Yanbiao Xi ◽  
Chunying Ren ◽  
Zongming Wang ◽  
Shiqing Wei ◽  
Jialing Bai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Tree Species ◽  
Classification Accuracy ◽  
Learning Algorithms ◽  
Spectral Characteristics ◽  
Great Influence ◽  
Hyperspectral Images ◽  
Changbai Mountains ◽  
Species Classification ◽  
Tree Species Classification

The accurate characterization of tree species distribution in forest areas can help significantly reduce uncertainties in the estimation of ecosystem parameters and forest resources. Deep learning algorithms have become a hot topic in recent years, but they have so far not been applied to tree species classification. In this study, one-dimensional convolutional neural network (Conv1D), a popular deep learning algorithm, was proposed to automatically identify tree species using OHS-1 hyperspectral images. Additionally, the random forest (RF) classifier was applied to compare to the algorithm of deep learning. Based on our experiments, we drew three main conclusions: First, the OHS-1 hyperspectral images used in this study have high spatial resolution (10 m), which reduces the influence of mixed pixel effect and greatly improves the classification accuracy. Second, limited by the amount of sample data, Conv1D-based classifier does not need too many layers to achieve high classification accuracy. In addition, the size of the convolution kernel has a great influence on the classification accuracy. Finally, the accuracy of Conv1D (85.04%) is higher than that of RF model (80.61%). Especially for broadleaf species with similar spectral characteristics, such as Manchurian walnut and aspen, the accuracy of Conv1D-based classifier is significantly higher than RF classifier (87.15% and 71.77%, respectively). Thus, the Conv1D-based deep learning framework combined with hyperspectral imagery can efficiently improve the accuracy of tree species classification and has great application prospects in the future.

scholarly journals Soil nutrients influence spatial distributions of tropical tree species

2007 ◽  
Vol 104 (3) ◽  
pp. 864-869 ◽  
Author(s):  
Robert John ◽  
James W. Dalling ◽  
Kyle E. Harms ◽  
Joseph B. Yavitt ◽  
Robert F. Stallard ◽  
...  
Keyword(s):  
Soil Nutrients ◽  
Tree Species ◽  
Tropical Tree ◽  
Spatial Distributions ◽  
Tropical Tree Species

A transition matrix growth model for uneven-aged mixed-species forests in the Changbai Mountains, northeastern China

New Forests ◽  
2005 ◽  
Vol 29 (3) ◽  
pp. 221-231 ◽  
Author(s):  
Qingyu Hao ◽  
Fanrui Meng ◽  
Yuping Zhou ◽  
Jingxin Wang
Keyword(s):  
Growth Model ◽  
Transition Matrix ◽  
Northeastern China ◽  
Changbai Mountains ◽  
Mixed Species

The Determination of Nitrate Reductase Activity of Leaves to the Dominant Species in Forest Community of Northern Aspect of Changbai Mountains

2011 ◽  
Vol 183-185 ◽  
pp. 900-904
Author(s):  
Yu Wen Li ◽  
Yun Jie Wu
Keyword(s):  
Nitrate Reductase ◽  
Tree Species ◽  
Reductase Activity ◽  
Forest Community ◽  
High Yield ◽  
Changbai Mountains ◽  
Ecological Situation ◽  
Nr Activity

This paper addresses the application of improvement in vivo of traditional method for determination of nitrate reductase (NR) activity of leaves to dominant tree species in forest community of northern aspect of Changbai Mountains. It describes the NR activity of tree species related to the shade-endurance and shows that the intolerance tree species has higher NR activity. The NR of a species is also related to the ecological situation of the sites. Tree species with higher NR activities should be selected for breeding of fast growing and high yield tree species.

scholarly journals Numerical Simulations of Spatial Distributions and Diurnal Variations of Low-Level Jets in China during Early Summer

2014 ◽  
Vol 27 (15) ◽  
pp. 5747-5767 ◽  
Author(s):  
Yu Du ◽  
Qinghong Zhang ◽  
Yi-leng Chen ◽  
Yangyang Zhao ◽  
Xu Wang
Keyword(s):  
Boundary Layer ◽  
Diurnal Variation ◽  
Tarim Basin ◽  
Southern China ◽  
Early Summer ◽  
Northeastern China ◽  
Diurnal Variations ◽  
Spatial Distributions ◽  
Model Data ◽  
Low Level Jets

Abstract The detailed spatial distributions and diurnal variations of low-level jets (LLJs) during early summer (May–July) in China are documented using 2006–11 hourly model data from the Weather Research and Forecasting (WRF) Model with a 9-km horizontal resolution. It was found that LLJs frequently occur in the following regions of China: the Tarim basin, northeastern China, the Tibetan Plateau (TP), and southern China. The LLJs over China are classified into two types: boundary layer jets (BLJs, below 1 km) and synoptic-system-related LLJs (SLLJs, within 1–4 km). The LLJs in the Tarim basin and the TP are mainly BLJs. The SLLJs over southern China and northeastern China are associated with the mei-yu front and northeast cold vortex (NECV), respectively. The BLJs in all regions show pronounced diurnal variations with maximum occurrences at nighttime or in the early morning, whereas diurnal variations of SLLJs vary, depending on the location. From the analysis of model data, the diurnal variation of BLJs is mainly caused by inertial oscillation at nighttime and vertical mixing in the boundary layer during daytime. Over northeastern China, SLLJ occurrences show little diurnal variation. Over southern China, two diurnal modes of SLLJs, propagation and stationary, exist and have seasonal variations, which is generally consistent with diurnal variations of precipitation.

Sign in / Sign up

Export Citation Format

Share Document