@misc{RudKaethnerGiesseretal.2018,
  author    = {Rud, R. and K{\"a}thner, Jana and Giesser, J. and Pasche, R. and Giebel, Antje and Selbeck, J{\"o}rn and Shenderey, C. and Fleury, D. and Zude-Sasse, Manuela and Alchanatis, Victor},
  title     = {Monitoring spatial variability in an apple orchard under different water regimes},
  series = {International Symposium on Sensing Plant Water Status - Methods and Applications in Horticultural Science},
  volume    = {1197},
  journal   = {International Symposium on Sensing Plant Water Status - Methods and Applications in Horticultural Science},
  publisher = {International Society for Horticultural Science},
  address   = {The Hague},
  isbn      = {978-94-62611-93-1},
  issn      = {0567-7572},
  doi       = {10.17660/ActaHortic.2018.1197.19},
  pages     = {139 -- 146},
  year      = {2018},
  abstract  = {Precision fruticulture addresses site or tree-adapted crop management. In the present study, soil and tree status, as well as fruit quality at harvest were analysed in a commercial apple (Malus × domestica 'Gala Brookfield'/Pajam1) orchard in a temperate climate. Trees were irrigated in addition to precipitation. Three irrigation levels (0, 50 and 100\%) were applied. Measurements included readings of apparent electrical conductivity of soil (ECa), stem water potential, canopy temperature obtained by infrared camera, and canopy volume estimated by LiDAR and RGB colour imaging. Laboratory analyses of 6 trees per treatment were done on fruit considering the pigment contents and quality parameters. Midday stem water potential (SWP), normalized crop water stress index (CWSI) calculated from thermal data, and fruit yield and quality at harvest were analysed. Spatial patterns of the variability of tree water status were estimated by CWSI imaging supported by SWP readings. CWSI ranged from 0.1 to 0.7 indicating high variability due to irrigation and precipitation. Canopy volume data were less variable. Soil ECa appeared homogeneous in the range of 0 to 4 mS m-1. Fruit harvested in a drought stress zone showed enhanced portion of pheophytin in the chlorophyll pool. Irrigation affected soluble solids content and, hence, the quality of fruit. Overall, results highlighted that spatial variation in orchards can be found even if marginal variability of soil properties can be assumed.},
  language  = {en}
}
@article{ErlerRiebeBeitzetal.2020,
  author    = {Erler, Alexander and Riebe, Daniel and Beitz, Toralf and L{\"o}hmannsr{\"o}ben, Hans-Gerd and Gebbers, Robin},
  title     = {Soil Nutrient Detection for Precision Agriculture Using Handheld Laser-Induced Breakdown Spectroscopy (LIBS) and Multivariate Regression Methods (PLSR, Lasso and GPR)},
  series = {Sensors},
  volume    = {20},
  journal   = {Sensors},
  number    = {2},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {1424-8220},
  doi       = {10.3390/s20020418},
  pages     = {17},
  year      = {2020},
  abstract  = {Precision agriculture (PA) strongly relies on spatially differentiated sensor information. Handheld instruments based on laser-induced breakdown spectroscopy (LIBS) are a promising sensor technique for the in-field determination of various soil parameters. In this work, the potential of handheld LIBS for the determination of the total mass fractions of the major nutrients Ca, K, Mg, N, P and the trace nutrients Mn, Fe was evaluated. Additionally, other soil parameters, such as humus content, soil pH value and plant available P content, were determined. Since the quantification of nutrients by LIBS depends strongly on the soil matrix, various multivariate regression methods were used for calibration and prediction. These include partial least squares regression (PLSR), least absolute shrinkage and selection operator regression (Lasso), and Gaussian process regression (GPR). The best prediction results were obtained for Ca, K, Mg and Fe. The coefficients of determination obtained for other nutrients were smaller. This is due to much lower concentrations in the case of Mn, while the low number of lines and very weak intensities are the reason for the deviation of N and P. Soil parameters that are not directly related to one element, such as pH, could also be predicted. Lasso and GPR yielded slightly better results than PLSR. Additionally, several methods of data pretreatment were investigated.},
  language  = {en}
}
@misc{ErlerRiebeBeitzetal.2019,
  author    = {Erler, Alexander and Riebe, Daniel and Beitz, Toralf and L{\"o}hmannsr{\"o}ben, Hans-Gerd and Gebbers, Robin},
  title     = {Soil Nutrient Detection for Precision Agriculture Using Handheld Laser-Induced Breakdown Spectroscopy (LIBS) and Multivariate Regression Methods (PLSR, Lasso and GPR)},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {815},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-44418},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-444183},
  pages     = {19},
  year      = {2019},
  abstract  = {Precision agriculture (PA) strongly relies on spatially differentiated sensor information. Handheld instruments based on laser-induced breakdown spectroscopy (LIBS) are a promising sensor technique for the in-field determination of various soil parameters. In this work, the potential of handheld LIBS for the determination of the total mass fractions of the major nutrients Ca, K, Mg, N, P and the trace nutrients Mn, Fe was evaluated. Additionally, other soil parameters, such as humus content, soil pH value and plant available P content, were determined. Since the quantification of nutrients by LIBS depends strongly on the soil matrix, various multivariate regression methods were used for calibration and prediction. These include partial least squares regression (PLSR), least absolute shrinkage and selection operator regression (Lasso), and Gaussian process regression (GPR). The best prediction results were obtained for Ca, K, Mg and Fe. The coefficients of determination obtained for other nutrients were smaller. This is due to much lower concentrations in the case of Mn, while the low number of lines and very weak intensities are the reason for the deviation of N and P. Soil parameters that are not directly related to one element, such as pH, could also be predicted. Lasso and GPR yielded slightly better results than PLSR. Additionally, several methods of data pretreatment were investigated.},
  language  = {en}
}