Hyperspectral Imaging with cost-sensitive learning for high-throughput screening of loblolly pine (Pinus Taeda L.) seedling for freeze tolerance


Loblolly pine (Pinus taeda L.) is a commercially important timber species planted across a wide temperature gradient in the southeastern United States. Ensuring the planting stock is suitably adapted to the growing environment is critical to achieve high productivity and survival. Long term field studies, although considered the most reliable method for assessing cold hardiness of loblolly pine, are extremely resource intensive and time consuming. The development of a high-throughput screening tool to characterize and classify freeze tolerance among different genetic entries of seedlings will facilitate the accurate deployment of highly productive and well-adapted families across the landscape. This study presents a novel approach using hyperspectral imaging to screen loblolly pine seedlings for freeze tolerance. A diverse population of 1549 seedlings raised in the nursery were subjected to an artificial mid-winter freeze using a freeze chamber. A custom-assembled hyperspectral imaging system was used for in-situ scanning the seedlings before and periodically after the freeze event, followed by visual scoring of the frozen seedlings. A hyperspectral data processing pipeline was developed to segment individual pine seedlings and extract the spectral data. Examination of spectral features of the seedlings revealed reductions of chlorophylls and water concentrations in the freeze-susceptible plants. Since the majority of seedlings were freeze-stressed, leading to severely class imbalance of the hyperspectral data, a cost-sensitive learning technique that aims to optimize a class-specific cost matrix in classification schemes was proposed for modeling the imbalanced hyperspectral data, classifying the seedlings into healthy and stressed phenotypes. Cost optimization was effective for boosting the classification accuracy compared to regular modeling that assigns equal costs to individual classes. Full-spectrum, cost-optimized support vector machine (SVM) models achieved the geometric classification accuracies of 75-78% before and within 10 days after the freeze event, and of up to 96% for the seedlings 41 days after the freeze even. The top portion of seedlings was more indicative of freeze events than middle and bottom portions, leading to better classification accuracies. Further, variable selection enabled significant reductions of wavelengths while achieving even better accuracies of up to 97% than full-spectrum SVM modeling. This study demonstrates that hyperspectral imaging will provide tree breeders with a valuable tool that offers improved efficiency and objectivity in characterizing and screening of freeze tolerance for loblolly pine.

Transactions of the ASABE (in press)