Login | DPI Staff queries on depositing or searching to era.daf.qld.gov.au

Advances in the Study of Biochemical, Morphological and Physiological Traits of Wheat and Sorghum Crops in Australia Using Hyperspectral Data and Machine Learning

Share this record

Add to FacebookAdd to LinkedinAdd to XAdd to WechatAdd to Microsoft_teamsAdd to WhatsappAdd to Any

Export this record

View Altmetrics

Potgieter, A., Camino, C., Poblete, T., George-Jaeggli, B. and et, a. (2023) Advances in the Study of Biochemical, Morphological and Physiological Traits of Wheat and Sorghum Crops in Australia Using Hyperspectral Data and Machine Learning. In: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, 16-21 July 2023, Pasadena, Calif. USA.

Full text not currently attached. Access may be available via the Publisher's website or OpenAccess link.

Article Link: https://doi.org/10.1109/IGARSS52108.2023.10282230

Abstract

In this paper, we discuss the integration of systems such as multi-dimensional radiative transfer models (RTM) with deep learning (DL) algorithms to estimate plant biochemical, physiological, and morphological traits at canopy level using high-resolution hyperspectral imagery (361 bands in the 400-1000 nm spectral range). We applied the approaches to two case studies for dryland cropping in Australia (i.e., wheat and sorghum). Crop type averages for the early flight for leaf area index (LAI) varied between 2, for Canola, to as high as 4.3 for Lentils. Wheat and Barley had LAI of 4.1 and 3.8 (m 2 /m 2 ), respectively. Chlorophyll a+b (C a+b ) averages for emerged crops were 18, 41, 44, 51 and 59 μg/cm 2 for Faba beans, Wheat, Canola, Barley and Oats, respectively. The pigment Anthocyanin varied from 4.9 to 15.9 μg/cm 2 for Lentils and Canola, respectively. Similar patterns were observed in the Carotenoid (C x+c ) levels (as high as 16.5 μg/cm 2 for Oats). For sorghum plots, the integrated DL approaches showed significant high correlation in predicting sorghum LAI (R 2 = 0.84, RMSE = 0.65 m 2 /m 2 ) and C a+b (R 2 = 0.94, RMSE = 4.94 µgcm -2 ). The maximum velocity carboxylation rates (Vcmax) varied between 45-75 µmol m -2 s -1 . For both studied periods, we yielded a R 2 > 0.78 and RMSE <= 5.35 µmol m -2 s -1 , being the RMSE lower when using the modelled fluorescence emission for retrieving the Vcmax. In addition, we derived the solar induced fluorescence emission hyperspectral narrowband (5.8 nm) sensing and radiative transfer models (RTM).

Item Type:Conference or Workshop Item (Paper)
Corporate Creators:Department of Agriculture and Fisheries, Queensland
Business groups:Crop and Food Science
Keywords:AI Artificial Intelligence Deep Learning high-resolution hyperspectral imagery Remote sensing Agtech AgriTech
Subjects:Science > Botany > Genetics
Agriculture > Agriculture (General) > Special aspects of agriculture as a whole > Inventions
Agriculture > Agriculture (General) > Special aspects of agriculture as a whole > Remote sensing
Plant culture > Field crops > Sorghum
Plant culture > Field crops > Wheat
Technology > Technology (General) > Spectroscopy
Technology > Technology (General)
Live Archive:11 Mar 2024 06:02
Last Modified:12 Mar 2024 02:27

Repository Staff Only: item control page