A physically informed multi-scale deep neural network for estimating foliar nitrogen concentration in vegetation

Simple item page
dc.citation.volume130
dc.contributor.authorDehghan-Shoar MH
dc.contributor.authorKereszturi G
dc.contributor.authorPullanagari RR
dc.contributor.authorOrsi AA
dc.contributor.authorYule IJ
dc.contributor.authorHanly J
dc.date.accessioned2024-07-16T21:56:29Z
dc.date.available2024-07-16T21:56:29Z
dc.date.issued2024-05-28
dc.description.abstractThis study introduces a Physically Informed Deep Neural Network (PINN) that leverages spectral data and Radiative Transfer Model insights to improve nitrogen concentration estimation in vegetation, addressing the complexities of physical processes. Utilizing a comprehensive spectroscopy dataset from various species across dry/ground (n = 2010), leaf (n = 1512), and canopy (n = 6007) scales, the study identifies 13 spectral bands key for chlorophyll and protein quantification. Key bands at 2276 nm, 755 nm, 1526 nm, 2243 nm, and 734 nm emerged vital for accurate N% prediction. The PINN outperforms partial least squares regression and standard deep neural networks, achieving an R2 of 0.71 and an RMSE of 0.42 (%N) on an independent validation set. Results indicate dry/ground data performed best (R2 = 0.9, RMSE = 0.24 %N), with leaf and canopy data showing lower efficacy (R2 = 0.67, RMSE = 0.45 %N; R2 = 0.65, RMSE = 0.46 %N, respectively). This multi-scale approach provides insights into spectral and N% relationships, enabling precise estimation across vegetation types and facilitating the development of transferable models. The PINN offers a new avenue for analyzing remote sensing data, demonstrating the significant potential for accurate, scale-spanning N% estimation in vegetation. Further enriching our analysis, the inclusion of seasonal data significantly enhanced our model's performance in field spectroscopy, with notable improvements observed across summer, spring, autumn, and winter. This adjustment underlines the model's increased accuracy and predictive capability at the field spectroscopy scale, emphasizing the vital role of integrating environmental factors, including climatic and physiological aspects, in future research.
dc.description.confidentialfalse
dc.edition.editionJune 2024
dc.identifier.citationDehghan-Shoar MH, Kereszturi G, Pullanagari RR, Orsi AA, Yule IJ, Hanly J. (2024). A physically informed multi-scale deep neural network for estimating foliar nitrogen concentration in vegetation. International Journal of Applied Earth Observation and Geoinformation. 130.
dc.identifier.doi10.1016/j.jag.2024.103917
dc.identifier.eissn1872-826X
dc.identifier.elements-typejournal-article
dc.identifier.issn1569-8432
dc.identifier.number103917
dc.identifier.piiS1569843224002711
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/70199
dc.languageEnglish
dc.publisherElsevier B.V.
dc.publisher.urihttps://www.sciencedirect.com/science/article/pii/S1569843224002711
dc.relation.isPartOfInternational Journal of Applied Earth Observation and Geoinformation
dc.subjectDeep learning
dc.subjectSpectroscopy
dc.subjectNitrogen concentration estimation
dc.subjectRadiative transfer models
dc.subjectPhysically informed machine learning
dc.titleA physically informed multi-scale deep neural network for estimating foliar nitrogen concentration in vegetation
dc.typeJournal article
pubs.elements-id489167
pubs.organisational-groupCollege of Health
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Published version.pdf
Size:
4.83 MB
Format:
Adobe Portable Document Format
Description:
489167 PDF.pdf
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
9.22 KB
Format:
Plain Text
Description:
Download
Collections
Journal Articles