TY - GEN
T1 - Machine Learning on the estimation of Leaf Area Index
AU - Afrasiabian, Yasamin
AU - Mokhtari, Ali
AU - Yu, Kang
N1 - Publisher Copyright:
© 2022 Gesellschaft fur Informatik (GI). All rights reserved.
PY - 2022
Y1 - 2022
N2 - The Leaf Area Index (LAI) is an important indicator in agriculture that can be considered a reliable plant growth parameter. The objective of this study is to make use of two different machine learning algorithms including Support Vector Machine (SVM), and Random Forest (RF) to improve the estimation of leaf area index using multispectral, thermal, and hyperspectral data. The results showed that RF was the best model to improve the accuracy of the LAI estimation compared to the simple linear regression (previous study) and SVM (R2 = 0.91 for RF and R2 = 0.87 for SVM). To evaluate the effects of spectral portions on LAI estimation without calculating the spectral indices, (SI) we inputted each pair of spectral bands for training and testing both RF and SVM. It was found that the best correlation was lower compared to use SIs. However, R2 variations were more homogeneous across the whole spectrum, which suggests that even by using multispectral broadband bands in RF and SVM, a good correlation will be achieved.
AB - The Leaf Area Index (LAI) is an important indicator in agriculture that can be considered a reliable plant growth parameter. The objective of this study is to make use of two different machine learning algorithms including Support Vector Machine (SVM), and Random Forest (RF) to improve the estimation of leaf area index using multispectral, thermal, and hyperspectral data. The results showed that RF was the best model to improve the accuracy of the LAI estimation compared to the simple linear regression (previous study) and SVM (R2 = 0.91 for RF and R2 = 0.87 for SVM). To evaluate the effects of spectral portions on LAI estimation without calculating the spectral indices, (SI) we inputted each pair of spectral bands for training and testing both RF and SVM. It was found that the best correlation was lower compared to use SIs. However, R2 variations were more homogeneous across the whole spectrum, which suggests that even by using multispectral broadband bands in RF and SVM, a good correlation will be achieved.
KW - Leaf Area Index
KW - Random Forest
KW - Support Vector Machine
KW - hyperspectral
KW - multispectral
KW - thermal
UR - http://www.scopus.com/inward/record.url?scp=85128170919&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85128170919
T3 - Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)
SP - 21
EP - 26
BT - Informatik in der Land-, Forst- und Ernahrungswirtschaft - Fokus
A2 - Gandorfer, Markus
A2 - Hoffmann, Christa
A2 - El Benni, Nadja
A2 - Cockburn, Marianne
A2 - Anken, Thomas
A2 - Floto, Helga
PB - Gesellschaft fur Informatik (GI)
T2 - 42. Jahrestagung 2022 der Gesellschaft fur Informatik in der Land-, Forst- und Ernahrungswirtschaft: Was bedeutet Kunstliche Intelligenz fur die Agrar- und Ernahrungswirtschaft, GIL 2022 - 42nd Annual Conference 2022 of the Society for Information Technology in Agriculture, Forestry and Food Industry: What does Artificial Intelligence mean for the Agricultural and Food industry, GIL 2022
Y2 - 21 February 2022 through 22 February 2022
ER -