Model selection and timing of acquisition date impacts classification accuracy: A case study using hyperspectral imaging to detect white pine blister rust over time

2021 ◽  
Vol 191 ◽  
pp. 106555
Author(s):  
Marja Haagsma ◽  
Gerald F.M. Page ◽  
Jeremy S. Johnson ◽  
Christopher Still ◽  
Kristen M. Waring ◽  
...  
Keyword(s):  
Model Selection ◽  
Hyperspectral Imaging ◽  
Classification Accuracy ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Blister Rust ◽  
Over Time

scholarly journals Using Hyperspectral Imagery to Detect an Invasive Fungal Pathogen and Symptom Severity in Pinus strobiformis Seedlings of Different Genotypes

2020 ◽  
Vol 12 (24) ◽  
pp. 4041
Author(s):  
Marja Haagsma ◽  
Gerald F. M. Page ◽  
Jeremy S. Johnson ◽  
Christopher Still ◽  
Kristen M. Waring ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Classification Accuracy ◽  
Search Algorithm ◽  
Support Vector ◽  
P Value ◽  
Small Subset ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Bhattacharyya Distance ◽  
Blister Rust

Finding trees that are resistant to pathogens is key in preparing for current and future disease threats such as the invasive white pine blister rust. In this study, we analyzed the potential of using hyperspectral imaging to find and diagnose the degree of infection of the non-native white pine blister rust in southwestern white pine seedlings from different seed-source families. A support vector machine was able to automatically detect infection with a classification accuracy of 87% (κ = 0.75) over 16 image collection dates. Hyperspectral imaging only missed 4% of infected seedlings that were impacted in terms of vigor according to expert’s assessments. Classification accuracy per family was highly correlated with mortality rate within a family. Moreover, classifying seedlings into a ‘growth vigor’ grouping used to identify the degree of impact of the disease was possible with 79.7% (κ = 0.69) accuracy. We ranked hyperspectral features for their importance in both classification tasks using the following features: 84 vegetation indices, simple ratios, normalized difference indices, and first derivatives. The most informative features were identified using a ‘new search algorithm’ that combines both the p-value of a 2-sample t-test and the Bhattacharyya distance. We ranked the normalized photochemical reflectance index (PRIn) first for infection detection. This index also had the highest classification accuracy (83.6%). Indices such as PRIn use only a small subset of the reflectance bands. This could be used for future developments of less expensive and more data-parsimonious multispectral cameras.

Pruning to manage white pine blister rust in the southern Rocky Mountains

2011 ◽  
Author(s):  
Amanda Crump ◽  
William R. Jacobi ◽  
Kelly S. Burns ◽  
Brian E. Howell
Keyword(s):  
Rocky Mountains ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Southern Rocky Mountains ◽  
Blister Rust

Options for the management of white pine blister rust in the Rocky Mountain Region

2008 ◽  
Author(s):  
Kelly S. Burns ◽  
Anna W. Schoettle ◽  
William R. Jacobi ◽  
Mary F. Mahalovich
Keyword(s):  
Rocky Mountain ◽  
Mountain Region ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Blister Rust ◽  
Rocky Mountain Region

Thinning in mature eastern white pine: 43-year case study

2002 ◽  
Vol 78 (4) ◽  
pp. 539-549 ◽  
Author(s):  
Paul D Anderson ◽  
John C Zasada ◽  
Glen W Erickson ◽  
Zigmond A Zasada
Keyword(s):  
Genetic Diversity ◽  
Dna Analysis ◽  
Large Diameter ◽  
White Pine ◽  
Thinning Intensity ◽  
Pine Regeneration ◽  
Volume Production ◽  
Pine Stands ◽  
Over Time

A white pine (Pinus strobus L.) stand at the western margin of the species range, approximately 125 years of age at present, was thinned in 1953 from 33.5 m2 ha-1 to target residual basal areas of 18.4, 23.0, 27.5, and 32.1 m2 ha-1 . Repeated measurement over the following 43-years indicated that the greatest total volume production and the greatest number of large diameter trees occurred in the unit of highest residual density. Over time, the distribution of stems was predominantly random although mortality between 1979 and 1996 resulted in a tendency for clumping in the 23.0 and 27.5 m2 ha-1 treatments. DNA analysis indicated that thinning intensity had little effect on the genetic diversity of residual white pine. This study suggests that mature white pine stands in northern Minnesota may be managed at relatively high densities without loss of productivity. However, regardless of overstory density, there was little or no white pine regeneration occurring in this stand. Key words: thinning, growth, genetic diversity, molecular markers, spatial pattern, regeneration

Risk of white pine blister rust to limber pine in Colorado and Wyoming, USA

2013 ◽  
Vol 44 (1) ◽  
pp. 21-38 ◽  
Author(s):  
H. S. J. Kearns ◽  
W. R. Jacobi ◽  
R. M. Reich ◽  
R. L. Flynn ◽  
K. S. Burns ◽  
...  
Keyword(s):  
White Pine Blister Rust ◽  
White Pine ◽  
Limber Pine ◽  
Blister Rust

scholarly journals Compounding effects of white pine blister rust, mountain pine beetle, and fire threaten four white pine species

Ecosphere ◽  
2020 ◽  
Vol 11 (10) ◽  
Author(s):  
Joan C. Dudney ◽  
Jonathan C. B. Nesmith ◽  
Matthew C. Cahill ◽  
Jennifer E. Cribbs ◽  
Dan M. Duriscoe ◽  
...  
Keyword(s):  
Mountain Pine Beetle ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Blister Rust ◽  
Mountain Pine ◽  
Pine Beetle ◽  
Pine Species

scholarly journals STUDIES ON WHITE PINE BLISTER RUST IN NOVA SCOTIA

1953 ◽  
Vol 29 (3) ◽  
pp. 267-272 ◽  
Author(s):  
W. K. McGinn ◽  
A. G. Davidson
Keyword(s):  
Nova Scotia ◽  
Control Measure ◽  
Systematic Search ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Clear Cutting ◽  
Blister Rust ◽  
Pine Regeneration ◽  
Show Evidence ◽  
Cutting Operation

Studies were undertaken in Nova Scotia to determine (i) the effect of different cutting practices on the establishment of a RIBES population and of white pine regeneration, (ii) whether blister rust is a major factor in retarding the establishment of white pine regeneration, and (iii) the feasibility and cost of RIBES eradication as a direct control measure against blister rust. No relationship was found to exist between RIBES establishment and the degree of cutting. Uncut softwood stands, where white pine is the predominant species, show evidence of producing a future pine crop. Forest types supporting white pine appear to offer the best opportunities for pine reproduction where a clear-cutting operation has given the stand maximum opening. Results of the present study to date do not show that blister rust is a major factor in retarding the establishment of white pine regeneration. To eradicate RIBES from the study area by a complete systematic search required 1 man-hour per acre. Because of the small number of RIBES plants found and of the tendency for them to occur consistently in moist, low-lying habitats, a complete systematic search for these plants appears to be unnecessary. It is suggested that one man, trained to recognize RIBES and their probable location, could cover large forest tracts with a minimum of time expended in searching localities unlikely to support these plants.

scholarly journals Whitebark pine mortality related to white pine blister rust, mountain pine beetle outbreak, and water availability

Ecosphere ◽  
2016 ◽  
Vol 7 (12) ◽  
Author(s):  
Erin Shanahan ◽  
Kathryn M. Irvine ◽  
David Thoma ◽  
Siri Wilmoth ◽  
Andrew Ray ◽  
...  
Keyword(s):  
Water Availability ◽  
Mountain Pine Beetle ◽  
Whitebark Pine ◽  
White Pine Blister Rust ◽  
White Pine ◽  
Blister Rust ◽  
Mountain Pine ◽  
Pine Beetle
Sign in / Sign up

Export Citation Format

Share Document