Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants

Mirwaes Wahabzada, Kristian Kersting, Christian Bauckhage, Christoph Roemer, Agim Ballvora, Francisco Pinto, Uwe Rascher, Jens Leon, Lutz Ploemer
Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, PMLR R10:851-861, 2012.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR10-wahabzada12a, title = {Latent {D}irichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants}, author = {Wahabzada, Mirwaes and Kersting, Kristian and Bauckhage, Christian and Roemer, Christoph and Ballvora, Agim and Pinto, Francisco and Rascher, Uwe and Leon, Jens and Ploemer, Lutz}, booktitle = {Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence}, pages = {851--861}, year = {2012}, editor = {de Freitas, Nando and Murphy, Kevin}, volume = {R10}, series = {Proceedings of Machine Learning Research}, month = {14--18 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r10/main/assets/wahabzada12a/wahabzada12a.pdf}, url = {https://proceedings.mlr.press/r10/wahabzada12a.html}, abstract = {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.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants %A Mirwaes Wahabzada %A Kristian Kersting %A Christian Bauckhage %A Christoph Roemer %A Agim Ballvora %A Francisco Pinto %A Uwe Rascher %A Jens Leon %A Lutz Ploemer %B Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2012 %E Nando de Freitas %E Kevin Murphy %F pmlr-vR10-wahabzada12a %I PMLR %P 851--861 %U https://proceedings.mlr.press/r10/wahabzada12a.html %V R10 %X 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. %Z Reissued by PMLR on 04 October 2026.
APA
Wahabzada, M., Kersting, K., Bauckhage, C., Roemer, C., Ballvora, A., Pinto, F., Rascher, U., Leon, J. & Ploemer, L.. (2012). Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R10:851-861 Available from https://proceedings.mlr.press/r10/wahabzada12a.html. Reissued by PMLR on 04 October 2026.

Related Material