prikaz prve stranice dokumenta Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat
  Preuzmi
PDF 3.56 MB
Znanstveni rad - Izvorni znanstveni rad
Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat
Remote Sensing, 5 (2025), ¨17!; 1-24. https://doi.org/10.3390/rs17050929
Skendžić, Sandra; Novak, Hrvoje; Zovko, Monika; Pajač Živković, Ivana; Lešić, Vinko; Maričević, Marko; Lemić, Darija

Citirajte ovaj rad

Skendžić, S., Novak, H., Zovko, M., Pajač Živković, I., Lešić, V., Maričević, M. i Lemić, D. (2025). Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat. Remote Sensing, 5. (¨17!), 1-24. doi: 10.3390/rs17050929

Skendžić, Sandra, et al. "Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat." Remote Sensing, vol. 5, br. ¨17!, 2025, str. 1-24. https://doi.org/10.3390/rs17050929

Skendžić, Sandra, Hrvoje Novak, Monika Zovko, Ivana Pajač Živković, Vinko Lešić, Marko Maričević i Darija Lemić. "Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat." Remote Sensing 5, br. ¨17! (2025): 1-24. https://doi.org/10.3390/rs17050929

Skendžić, S., et al. (2025) 'Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat', Remote Sensing, 5(¨17!), str. 1-24. doi: 10.3390/rs17050929

Skendžić S, Novak H, Zovko M, Pajač Živković I, Lešić V, Maričević M, i sur.. Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat. Remote Sensing [Internet]. 05.03.2025. [pristupljeno 18.03.2025.];5(¨17!):1-24. doi: 10.3390/rs17050929

S. Skendžić, et al., "Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat", Remote Sensing, vol. 5, br. ¨17!, str. 1-24, Ožujak 2025. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:168:993023. [Citirano: 18.03.2025.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:168:993023
Prijavite se u repozitorij kako biste mogli spremiti objekt u svoju listu.
Podaci o radu
Naslov (engleski)Hyperspectral Canopy Reflectance and Machine Learning for Threshold-Based Classification of Aphid-Infested Winter Wheat
AutorSandra Skendžić
AutorHrvoje Novak
AutorMonika Zovko
AutorIvana Pajač Živković
AutorVinko Lešić
AutorMarko Maričević
AutorDarija Lemić
Autorova ustanovaSveučilište u Zagrebu
Agronomski fakultet
(Poljoprivredna zoologija)
Autorova ustanovaSveučilište u Zagrebu
Fakultet elektrotehnike i računarstva
(Zavod za automatiku i računalno inženjerstvo)
Znanstveno / umjetničko
područje, polje i grana		BIOTEHNIČKE ZNANOSTI
Poljoprivreda (agronomija)
Fitomedicina
Sažetak (engleski)
Aphids are significant pests of winter wheat, causing damage by feeding on plant sap and reducing crop yield and quality. This study evaluates the potential of hyperspectral remote sensing (350–2500 nm) and machine learning (ML) models for classifying healthy and aphid-infested wheat canopies. Field-based hyperspectral measurements were conducted at three growth stages - T1 (stem elongation–heading), T2 (flowering), and T3 (milky grain development) - with infestation levels categorized according to established economic thresholds (ET) for each growth stage. Spectral data were analyzed using Uniform Manifold Approximation and Projection (UMAP); vegetation indices; and ML classification models, including Logistic Regression (LR), k-Nearest Neighbors (KNNs), Support vector machines (SVMs), Random Forest (RF), and Light Gradient Boosting Machine (LGBM). The classification models achieved high performance, with F1-scores ranging from 0.88 to 0.99, and SVM and RF consistently outperforming other models across all input datasets. The best classification results were obtained at T2 with an F1-score of 0.98, while models trained on the full spectrum dataset showed the highest overall accuracy. Among vegetation indices, the Modified Triangular Vegetation Index, MTVI (rpb = −0.77 to −0.82), and Triangular Vegetation Index, TVI (rpb = −0.66 to −0.75), demonstrated the strongest correlations with canopy condition. These findings underscore the utility of canopy spectra and vegetation indices for detecting aphid infestations above ET levels, allowing for a clear classification of wheat fields into “treatment required” and “no treatment required” categories. This approach provides a precise and timely decision making tool for insecticide application, contributing to sustainable pest management by enabling targeted interventions, reducing unnecessary pesticide use, and supporting effective crop protection practices.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objavePrihvaćen za objavljivanje
Vrsta recenzijeRecenziran - međunarodna recenzija
Verzija publikacijeZavršna verzija rukopisa prihvaćena za objavljivanje (postprint)
Naslov časopisaRemote Sensing
Brojčani podacivol. 5, br. ¨17!, str. 1-24, 929
BPC0 EUR
e-ISSN2072-4292
DOIhttps://doi.org/10.3390/rs17050929
URN:NBNurn:nbn:hr:168:993023
Datum objave elektroničkog izdanja2025-03-05
ProjektŠifra: KK.05.1.1.02.0031
Naziv (hrvatski): Napredna i prediktivna poljoprivreda za otpornost klimatskim promjenama
Naziv (engleski): Advanced and predictive agriculture for resilience to climate change
Kratica: AgroSPARC
Voditelj: Vinko Lešić
Pravna nadležnost: eu
Financijer: Europska unija
Linija financiranja: European Regional Development Fund
URL dokumentahttps://www.mdpi.com/2072-4292/17/5/929
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Zaštićeno autorskim pravom.
Datum i vrijeme pohrane2025-03-10 09:24:23