File(s) not publicly available

Prediction of macronutrients in plant leaves using chemometric analysis and wavelength selection

journal contribution
posted on 15.06.2021, 04:31 by Mohammad Malmir, Iman Tahmasbian, Zhihong Xu, Michael B Farrar, Shahla Hosseini Bai
Purpose: Fast and real-time prediction of leaf nutrient concentrations can facilitate decision-making for fertilisation regimes on farms and address issues raised with over-fertilisation. Cacao (Theobroma cacao L.) is an important cash crop and requires nutrient supply to maintain yield. This project aimed to use chemometric analysis and wavelength selection to improve the accuracy of foliar nutrient prediction. Materials and methods: We used a visible-near infrared (400–1000 nm) hyperspectral imaging (HSI) system to predict foliar calcium (Ca), potassium (K), phosphorus (P) and nitrogen (N) of cacao trees. Images were captured from 95 leaf samples. Partial least square regression (PLSR) models were developed to predict leaf nutrient concentrations and wavelength selection was undertaken. Results and discussion: Using all wavelengths, Ca (R = 0.76, RMSE = 0.28), K (R = 0.35, RMSE = 0.46), P (R = 0.75, RMSE = 0.019) and N (R = 0.73, RMSE = 0.17) were predicted. Wavelength selection increased the prediction accuracy of Ca (R = 0.79, RMSE = 0.27) and N (R = 0.74, RMSE = 0.16), while did not affect prediction accuracy of foliar K (R = 0.35, RMSE = 0.46) and P (R = 0.75, RMSE = 0.019). Conclusions: Visible-near infrared HSI has a good potential to predict Ca, P and N concentrations in cacao leaf samples, but K concentrations could not be predicted reliably. Wavelength selection increased the prediction accuracy of foliar Ca and N leading to a reduced number of wavelengths involved in developed models. 2 2 2 2 2 2 2 2 CV CV CV CV CV CV CV CV CV CV CV CV CV CV CV CV

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Volume

20

Issue

1

Start Page

249

End Page

259

eISSN

1614-7480

ISSN

1439-0108

Publisher

Springer

Language

en

Peer Reviewed

Yes

Open Access

No

Acceptance Date

23/07/2019

External Author Affiliations

University of the Sunshine Coast; Griffith University

Era Eligible

Yes

Journal

Journal of Soils and Sediments