Detection of potassium deficiency and momentary transpiration rate estimation at early growth stages using proximal hyperspectral imaging and extreme gradient boosting

Shahar Weksler*, Offer Rozenstein, Nadav Haish, Menachem Moshelion, Rony Wallach, Eyal Ben-Dor

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Potassium is a macro element in plants that is typically supplied to crops in excess throughout the season to avoid a deficit leading to reduced crop yield. Transpiration rate is a momentary physiological attribute that is indicative of soil water content, the plant’s water require-ments, and abiotic stress factors. In this study, two systems were combined to create a hyperspec-tral–physiological plant database for classification of potassium treatments (low, medium, and high) and estimation of momentary transpiration rate from hyperspectral images. PlantArray 3.0 was used to control fertigation, log ambient conditions, and calculate transpiration rates. In addi-tion, a semi-automated platform carrying a hyperspectral camera was triggered every hour to cap-ture images of a large array of pepper plants. The combined attributes and spectral information on an hourly basis were used to classify plants into their given potassium treatments (average accuracy = 80%) and to estimate transpiration rate (RMSE = 0.025 g/min, R2 = 0.75) using the advanced en-semble learning algorithm XGBoost (extreme gradient boosting algorithm). Although potassium has no direct spectral absorption features, the classification results demonstrated the ability to label plants according to potassium treatments based on a remotely measured hyperspectral signal. The ability to estimate transpiration rates for different potassium applications using spectral information can aid in irrigation management and crop yield optimization. These combined results are important for decision-making during the growing season, and particularly at the early stages when potassium levels can still be corrected to prevent yield loss.

Original languageEnglish
Article number958
Pages (from-to)1-19
Number of pages19
JournalSensors
Volume21
Issue number3
DOIs
StatePublished - 1 Feb 2021

Funding

FundersFunder number
Agricultural Research Or-ganization
Agricultural Research Organization
Israel Chemical Ltd.31010201
Remote Sensing Laboratory
European Cooperation in Science and Technology
Israel Science Foundation1780/18
Tel Aviv UniversityCA17134

    Keywords

    • Functional phenotyping
    • Hyperspectral remote sensing
    • Phenomics
    • Potassium
    • Reflectance
    • Transpiration rate
    • XGboost

    Fingerprint

    Dive into the research topics of 'Detection of potassium deficiency and momentary transpiration rate estimation at early growth stages using proximal hyperspectral imaging and extreme gradient boosting'. Together they form a unique fingerprint.

    Cite this