Logo des Repositoriums

Auflistung nach Schlagwort "multispectral"

1 - 2 von 2
  • Konferenzbeitrag
    A coupled multitemporal UAV-based LiDAR and multispectral data approach to model dry biomass of maize
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Rettig, Robert; Storch, Marcel; Wittstruck, Lucas; Ansah, Christabel; Bald, Richard Janis; Richard, David; Trautz, Dieter; Jarmer, Thomas
    The presented approach attempts to highlight the capabilities of a data fusion approach that combines UAV LiDAR (RIEGL – miniVUX-1UAV) and multispectral data (Micasense – Altum) to assess the dry above ground biomass (AGB) for maize. The combined acquisition of both LiDAR and multispectral data not only supports estimates of AGB when fusing them, but also helps to evaluate phenological stage-specific modelling differences on the individual sensor data. A multiple linear regression was applied on the multisensorial UAV data from two appointments in 2021. The resulting R² of 0.87 and RMSE of 14.35 g/plant for AGB was then transferred to AGB in dt/ha.
  • Konferenzbeitrag
    Machine Learning on the estimation of Leaf Area Index
    (42. GIL-Jahrestagung, Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft, 2022) Afrasiabian, Yasamin; Mokhtari, Ali; Yu, Kang
    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.