Plant Phenotyping using Probabilistic Topic Models: Uncovering the Hyperspectral Language of Plants

Wahabzada, Mirwaes; Mahlein, Anne-Katrin; Bauckhage, Christian; Steiner, Ulrike; Oerke, E. C.; Kersting, Kristian

doi:10.1038/srep22482

Cited by 100 publications

(61 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, decision-tree models are available now that allow farmers to differentiate between plant diseases based on optical information (4). Virtual fence technologies (5) allow cattle herd management based on remote-sensing signals and sensors or actuators attached to the livestock.…”

mentioning

confidence: 99%

Smart farming is key to developing sustainable agriculture

Walter¹,

Finger²,

Huber³

et al. 2017

Proc. Natl. Acad. Sci. U.S.A.

518

259

View full text Add to dashboard Cite

Agriculture has seen many revolutions, whether the domestication of animals and plants a few thousand years ago, the systematic use of crop rotations and other improvements in farming practice a few hundred years ago, or the "green revolution" with systematic breeding and the widespread use of man-made fertilizers and pesticides a few decades ago. We suggest that agriculture is undergoing a fourth revolution triggered by the exponentially increasing use of information and communication technology (ICT) in agriculture.Autonomous, robotic vehicles have been developed for farming purposes, such as mechanical weeding, application of fertilizer, or harvesting of fruits. The development of unmanned aerial vehicles with autonomous flight control (1), together with the development of lightweight and powerful hyperspectral snapshot cameras that can be used to calculate biomass development and fertilization status of crops (2, 3), opens the field for sophisticated farm management advice. Moreover, decision-tree models are available now that allow farmers to differentiate between plant diseases based on optical information (4). Virtual fence technologies (5) allow cattle herd management based on remote-sensing signals and sensors or actuators attached to the livestock.Taken together, these technical improvements constitute a technical revolution that will generate disruptive changes in agricultural practices. This trend holds for farming not only in developed countries but also in developing countries, where deployments in ICT (e.g., use of mobile phones, access to the Internet) are being adopted at a rapid pace and could become the game-changers in the future (e.g., in the form of seasonal drought forecasts, climate-smart agriculture).Such profound changes in practice come not only with opportunities but also big challenges. It is crucial to point them out at an early stage of this revolution to avoid "lock-ins": advocates and skeptics of technology need to engage in an open dialogue on the future development of farming in the digital era. Only if aspects of technology, diversity of crop and livestock systems, and networking and institutions (i.e. markets and policies), are considered jointly in the dialogue, should farming in the digital era be termed "smart farming." Ample OpportunitiesSmart farming reduces the ecological footprint of farming. Minimized or site-specific application of inputs, such as fertilizers and pesticides, in precision agriculture systems will mitigate leaching problems as well as the emission of greenhouse gases (6). With current ICT, it is possible to create a sensor network allowing for almost continuous monitoring of the farm. Similarly, theoretical and practical frameworks to connect the states of plants, animals, and soils with the needs for production inputs, such as water, fertilizer, and medications, are in reach with current ICT globally.Smart farming can make agriculture more profitable for the farmer. Decreasing resource inputs will save the farmer money and labor, and increased reliabi...

show abstract

mentioning

confidence: 99%

Smart farming is key to developing sustainable agriculture

Walter¹,

Finger²,

Huber³

et al. 2017

Proc. Natl. Acad. Sci. U.S.A.

518

259

View full text Add to dashboard Cite

show abstract

“…Spectral sensors measure the light reflected from the crop canopy [1]. During pathogen attack and disease development on the crop leaf, diseases establish a spectral fingerprint in the reflected leaf signature [8][9][10]. These shifts of the signature can be detected using spectral sensors, particularly in the electromagnetic spectrum from 400-2500 nm [11].…”

Section: Of 20mentioning

confidence: 99%

In-Field Detection of Yellow Rust in Wheat on the Ground Canopy and UAV Scale

Bohnenkamp

Behmann

Mahlein³

2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

The application of hyperspectral imaging technology for plant disease detection in the field is still challenging. Existing equipment and analysis algorithms are adapted to highly controlled environmental conditions in the laboratory. However, only real time information from the field scale is able to guide plant protection measures and to optimize the use of resources. At the field scale, many parameters such as the optimal measurement distance, informative feature sets, and suitable algorithms have not been investigated. In this study, the hyperspectral detection and quantification of yellow rust in wheat was evaluated using two measurement platforms: a ground-based vehicle and an unmanned aerial vehicle (UAV). Different disease development stages and disease severities were provided in a plot-based field experiment. Measurements were performed weekly during the vegetation period. Data analysis was performed by three prediction algorithms with a focus on the selection of optimal feature sets. In this context, the across-scale application of optimized feature sets, an approach of information transfer between scales, was also evaluated. Relevant aspects for an on-line disease assessment in the field integrating affordable sensor technology, sensor spatial resolution, compact analysis models, and fast evaluation have been outlined and reflected upon. For the first time, a hyperspectral imaging observation experiment of a plant disease was comparatively performed at two scales, ground canopy and UAV.

show abstract

“…However, similar solutions at the canopy level may be technically extremely challenging to implement and require extensive studies due to problems in tracking individual pixels or organs over time and in obtaining a clean spectral signal from objects with varying orientation. Existing approaches to make use of spectral, spatial and temporal information rely on automated and data-driven extraction of characteristic spectral features for diseased plants under controlled conditions (Thomas et al, 2018;Wahabzada et al, 2016Wahabzada et al, , 2015. Here, promising results were achieved using a non-imaging sensor and manual feature extraction.…”

Section: Context and Scopementioning

confidence: 99%

In-field detection and quantification of Septoria tritici blotch in diverse wheat germplasm using spectral-temporal features

Anderegg

Hund

Karisto

et al. 2019

Preprint

View full text Add to dashboard Cite

Hyperspectral remote sensing holds the potential to detect and quantify crop diseases in a rapid and noninvasive manner. Such tools could greatly benefit resistance breeding, but their adoption is hampered by i) a lack of specificity to disease-related effects and ii) insufficient robustness to variation in reflectance caused by genotypic diversity and varying environmental conditions, which are fundamental elements of resistance breeding.We hypothesized that relying exclusively on temporal changes in canopy reflectance during pathogenesis may allow to specifically detect and quantify crop diseases whilst minimizing the confounding effects of genotype and environment. To test this hypothesis, we collected time-resolved canopy hyperspectral reflectance data for 18 diverse genotypes on infected and disease-free plots and engineered spectral-temporal features representing this hypothesis.Our results confirm the lack of specificity and robustness of disease assessments based on reflectance spectra at individual time points. We show that changes in spectral reflectance over time are indicative of the presence and severity of septoria tritici blotch (STB) infections. Furthermore, the proposed time-integrated approach facilitated the delineation of disease from physiological senescence, which is pivotal for efficient selection of STB-resistant material under field conditions. A validation of models based on spectral-temporal features on a diverse panel of >300 wheat genotypes offered evidence for the robustness of the proposed method. This study demonstrates the potential of time-resolved canopy reflectance measurements for robust assessments of foliar diseases in the context of resistance breeding.

show abstract

Plant Phenotyping using Probabilistic Topic Models: Uncovering the Hyperspectral Language of Plants

Cited by 100 publications

References 47 publications

Smart farming is key to developing sustainable agriculture

Smart farming is key to developing sustainable agriculture

In-Field Detection of Yellow Rust in Wheat on the Ground Canopy and UAV Scale

In-field detection and quantification of Septoria tritici blotch in diverse wheat germplasm using spectral-temporal features

Contact Info

Product

Resources

About