Search for: All records

Hyperspectral imaging allows for rapid, non-destructive and objective assessments of crop health. Narrowband-hyperspectral data was used to select wavelength regions that can be exploited to identify wheat infected with soil-borne mosaic virus. First, leaf samples were scanned in the lab to investigate spectral differences between healthy and diseased leaves, including non-symptomatic and symptomatic areas within a diseased leaf. The potential of 84 commonly used vegetation indices to find infection was explored. A machine-learning approach was used to create a classification model to automatically separate pixels into symptomatic, non-symptomatic and healthy classes. The success rate of the model was 69.7% using the full spectrum. It was very encouraging that by using a subset of only four broad bands, sampled to simulate a data set from a much simpler and less costly multispectral camera, accuracy increased to 71.3%. Next, the classification models were validated on field data. Infection in the field was successfully identified using classifiers trained on the entire spectrum of the hyperspectral data acquired in a lab setting, with the best accuracy being 64.9%. Using a subset of wavelengths, simulating multispectral data, the accuracy dropped by only 3 percentage points to 61.9%. This research shows the potential of using lab scans to train classifiers to be successfully applied in the field, even when simultaneously reducing the hyperspectral data to multispectral data.

 

Streams are complex where biology, hydrology, and atmospheric processes are all important. Because quantifying and modeling of these systems can be challenging, many teams go directly to prescribed restoration treatments and principles. Restoration on the Middle Fork of the John Day River in Oregon, USA, shows how a project that was designed according to widely accepted restoration principles may lead to outcomes contrary to one of the project's stated goals: reducing peak temperatures for endangered salmonids on the site. This study employed the most sophisticated equipment available for stream temperature monitoring, including approximately 1 million independent hourly measurements in the 2‐week period considered. These data were collected along the river channel with fiber optic–distributed temperature sensing and were used to quantify thermal dynamics. These observations were paired with a physically based stream temperature model which was then employed to predict temperature change from design alternatives. Restored‐reach impact on peak temperature was directly correlated with the air–water interfacial area and the percentage of effective shade (R² > 0.99). The increase in air–water area of the proposed design was predicted to increase daytime stream temperature by as much as 0.5°C upon completion of the work. Shade from riparian vegetation was found to potentially mitigate stream temperature increases, though only after decades of growth. A moderately dense canopy of 5 m tall trees blocking 17% of daily shortwave solar radiation is predicted to mitigate predicted temperature increases over the 1,800 m reach but also increases nighttime temperatures due to blocking of long‐wave radiation. These outcomes may not be intuitive to restoration practitioners and show how quantitative analysis can benefit the design of a project. This is significant in an area where riparian vegetation has been difficult to reestablish. Without quantitative analysis, restoration efforts can lead to outcomes opposite to stated goals and may be costly and disruptive interventions to fragile stream systems.

 

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.