Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants
This work addresses the need for data-driven, objective drought stress indices in agriculture, offering a scalable complement to expert-based methods, though it is incremental as it builds on existing LDA approaches.
The study tackled the problem of discovering spectral drought stress indices from hyperspectral imaging by treating it as an unsupervised labeling problem at massive scale, using a novel online variational Bayes algorithm for latent Dirichlet allocation with convolved Dirichlet regularizer, which scales to large datasets and finds spectral topics that align with plant physiological knowledge in a fraction of the time compared to existing methods.
Understanding the adaptation process of plants to drought stress is essential in improving management practices, breeding strategies as well as engineering viable crops for a sustainable agriculture in the coming decades. Hyper-spectral imaging provides a particularly promising approach to gain such understanding since it allows to discover non-destructively spectral characteristics of plants governed primarily by scattering and absorption characteristics of the leaf internal structure and biochemical constituents. Several drought stress indices have been derived using hyper-spectral imaging. However, they are typically based on few hyper-spectral images only, rely on interpretations of experts, and consider few wavelengths only. In this study, we present the first data-driven approach to discovering spectral drought stress indices, treating it as an unsupervised labeling problem at massive scale. To make use of short range dependencies of spectral wavelengths, we develop an online variational Bayes algorithm for latent Dirichlet allocation with convolved Dirichlet regularizer. This approach scales to massive datasets and, hence, provides a more objective complement to plant physiological practices. The spectral topics found conform to plant physiological knowledge and can be computed in a fraction of the time compared to existing LDA approaches.