Universität zu Köln

Lussem, Ulrike, Bolten, Andreas, Kleppert, Ireneusz, Jasper, Joerg, Gnyp, Martin Leon ORCID: 0000-0002-5702-4914, Schellberg, Juergen and Bareth, Georg (2022). Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning. Remote Sens., 14 (13). BASEL: MDPI. ISSN 2072-4292

Full text not available from this repository.

Abstract

Precise and timely information on biomass yield and nitrogen uptake in intensively managed grasslands are essential for sustainable management decisions. Imaging sensors mounted on unmanned aerial vehicles (UAVs) along with photogrammetric structure-from-motion processing can provide timely data on crop traits rapidly and non-destructively with a high spatial resolution. The aim of this multi-temporal field study is to estimate aboveground dry matter yield (DMY), nitrogen concentration (N%) and uptake (Nup) of temperate grasslands from UAV-based image data using machine learning (ML) algorithms. The study is based on a two-year dataset from an experimental grassland trial. The experimental setup regarding climate conditions, N fertilizer treatments and slope yielded substantial variations in the dataset, covering a considerable amount of naturally occurring differences in the biomass and N status of grasslands in temperate regions with similar management strategies. Linear regression models and three ML algorithms, namely, random forest (RF), support vector machine (SVM), and partial least squares (PLS) regression were compared with and without a combination of both structural (sward height; SH) and spectral (vegetation indices and single bands) features. Prediction accuracy was quantified using a 10-fold 5-repeat cross-validation (CV) procedure. The results show a significant improvement of prediction accuracy when all structural and spectral features are combined, regardless of the algorithm. The PLS models were outperformed by their respective RF and SVM counterparts. At best, DMY was predicted with a median RMSECV of 197 kg ha(-1), N% with a median RMSECV of 0.32%, and Nup with a median RMSECV of 7 kg ha(-1). Furthermore, computationally less expensive models incorporating, e.g., only the single multispectral camera bands and SH metrics, or selected features based on variable importance achieved comparable results to the overall best models.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Lussem, Ulrike UNSPECIFIED UNSPECIFIED UNSPECIFIED Bolten, Andreas UNSPECIFIED UNSPECIFIED UNSPECIFIED Kleppert, Ireneusz UNSPECIFIED UNSPECIFIED UNSPECIFIED Jasper, Joerg UNSPECIFIED UNSPECIFIED UNSPECIFIED Gnyp, Martin Leon UNSPECIFIED orcid.org/0000-0002-5702-4914 UNSPECIFIED Schellberg, Juergen UNSPECIFIED UNSPECIFIED UNSPECIFIED Bareth, Georg UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-670215
DOI:	10.3390/rs14133066
Journal or Publication Title:	Remote Sens.
Volume:	14
Number:	13
Date:	2022
Publisher:	MDPI
Place of Publication:	BASEL
ISSN:	2072-4292
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language HYPERSPECTRAL VEGETATION INDEXES; RISING PLATE METER; SWARD HEIGHT; RED-EDGE; NITROGEN CONCENTRATION; PRECISION AGRICULTURE; PLANT HEIGHT; BIOMASS; REFLECTANCE; ALGORITHMS Multiple languages Environmental Sciences; Geosciences, Multidisciplinary; Remote Sensing; Imaging Science & Photographic Technology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/67021