scholarly journals Spatially Explicit Large Area Biomass Estimation: Three Approaches Using Forest Inventory and Remotely Sensed Imagery in a GIS

Sensors ◽  
2008 ◽  
Vol 8 (1) ◽  
pp. 529-560 ◽  
Author(s):  
Michael Wulder ◽  
Joanne White ◽  
Richard Fournier ◽  
Joan Luther ◽  
Steen Magnussen
Keyword(s):  
Forest Inventory ◽  
Remotely Sensed ◽  
Biomass Estimation ◽  
Spatially Explicit ◽  
Large Area ◽  
Remotely Sensed Imagery

Supporting large-area, sample-based forest inventories with very high spatial resolution satellite imagery

2009 ◽  
Vol 33 (3) ◽  
pp. 403-423 ◽  
Author(s):  
Michael J. Falkowski ◽  
Michael A. Wulder ◽  
Joanne C. White ◽  
Mark D. Gillis
Keyword(s):  
Forest Inventory ◽  
Information Needs ◽  
High Spatial Resolution ◽  
Temporal Frequency ◽  
Forest Monitoring ◽  
Large Area ◽  
Remotely Sensed Imagery ◽  
Forest Inventories ◽  
Very High Spatial Resolution ◽  
Very High

Information needs associated with forest management and reporting requires data with a steadily increasing level of detail and temporal frequency. Remote sensing satellites commonly used for forest monitoring (eg, Landsat, SPOT) typically collect imagery with sufficient temporal frequency, but lack the requisite spatial and categorical detail for some forest inventory information needs. Aerial photography remains a principal data source for forest inventory; however, information extraction is primarily accomplished through manual processes. The spatial, categorical, and temporal information requirements of large-area forest inventories can be met through sample-based data collection. Opportunities exist for very high spatial resolution (VHSR; ie, <1 m) remotely sensed imagery to augment traditional data sources for large-area, sample-based forest inventories, especially for inventory update. In this paper, we synthesize the state-of-the-art in the use of VHSR remotely sensed imagery for forest inventory and monitoring. Based upon this review, we develop a framework for updating a sample-based, large-area forest inventory that incorporates VHSR imagery. Using the information needs of the Canadian National Forest Inventory (NFI) for context, we demonstrate the potential capabilities of VHSR imagery in four phases of the forest inventory update process: stand delineation, automated attribution, manual interpretation, and indirect attribute modelling. Although designed to support the information needs of the Canadian NFI, the framework presented herein could be adapted to support other sample-based, large-area forest monitoring initiatives.

Remotely sensed imagery revealing the effects of hurricanes Gustav and Ike on coastal Louisiana

Data Series ◽  
10.3133/ds566 ◽  
2010 ◽  
Author(s):  
John A. Barras ◽  
John C. Brock ◽  
Robert A. Morton ◽  
Laurinda J. Travers
Keyword(s):  
Remotely Sensed ◽  
Remotely Sensed Imagery ◽  
Coastal Louisiana

Map-guided interpretation of remotely-sensed imagery

1980 ◽  
Author(s):  
J. M. Tenenbaum ◽  
H. G. Barrow ◽  
R. C. Bolles ◽  
M. A. Fischler ◽  
H. C. Wolf
Keyword(s):  
Remotely Sensed ◽  
Remotely Sensed Imagery

scholarly journals Effects of Training Set Size on Supervised Machine-Learning Land-Cover Classification of Large-Area High-Resolution Remotely Sensed Data

2021 ◽  
Vol 13 (3) ◽  
pp. 368
Author(s):  
Christopher A. Ramezan ◽  
Timothy A. Warner ◽  
Aaron E. Maxwell ◽  
Bradley S. Price
Keyword(s):  
Machine Learning ◽  
Sample Size ◽  
Remotely Sensed ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Sample Sizes ◽  
Remotely Sensed Data ◽  
Large Area ◽  
Training Set ◽  
Set Size

The size of the training data set is a major determinant of classification accuracy. Nevertheless, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algorithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic object-based image analysis (GEOBIA) approach. GEOBIA, in which adjacent similar pixels are grouped into image-objects that form the unit of the classification, offers the potential benefit of allowing multiple additional variables, such as measures of object geometry and texture, thus increasing the dimensionality of the classification input data. The six supervised machine-learning algorithms are support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), single-layer perceptron neural networks (NEU), learning vector quantization (LVQ), and gradient-boosted trees (GBM). RF, the algorithm with the highest overall accuracy, was notable for its negligible decrease in overall accuracy, 1.0%, when training sample size decreased from 10,000 to 315 samples. GBM provided similar overall accuracy to RF; however, the algorithm was very expensive in terms of training time and computational resources, especially with large training sets. In contrast to RF and GBM, NEU, and SVM were particularly sensitive to decreasing sample size, with NEU classifications generally producing overall accuracies that were on average slightly higher than SVM classifications for larger sample sizes, but lower than SVM for the smallest sample sizes. NEU however required a longer processing time. The k-NN classifier saw less of a drop in overall accuracy than NEU and SVM as training set size decreased; however, the overall accuracies of k-NN were typically less than RF, NEU, and SVM classifiers. LVQ generally had the lowest overall accuracy of all six methods, but was relatively insensitive to sample size, down to the smallest sample sizes. Overall, due to its relatively high accuracy with small training sample sets, and minimal variations in overall accuracy between very large and small sample sets, as well as relatively short processing time, RF was a good classifier for large-area land-cover classifications of HR remotely sensed data, especially when training data are scarce. However, as performance of different supervised classifiers varies in response to training set size, investigating multiple classification algorithms is recommended to achieve optimal accuracy for a project.

Sign in / Sign up

Export Citation Format

Share Document