Estimating Plant Traits of Grasslands from UAV-Acquired Hyperspectral Images: A Comparison of Statistical Approaches
<p>RGB ortho-mosaic of the experimental grassland plots on 15 May 2014, acquired using the Panasonic GX1 camera of the Wageningen UR Hyperspectral Mapping System (HYMSY).</p> "> Figure 2
<p>Map of different types and levels of fertilization applied on the experimental grassland plots. The 60 plots were split into four groups of 15 plots and for every group the treatments were applied as indicated in the table. The black line is a measurement rail which is also shown in <a href="#ijgi-04-02792-f001" class="html-fig">Figure 1</a>.</p> "> Figure 3
<p>The octocopter UAV Aerialtronics Altura AT8 v1A equipped with all necessary hardware and software tools for its control and programming.</p> "> Figure 4
<p>Influence of the type and the amount of fertilizer treatment on grassland traits and their standard deviations.</p> "> Figure 5
<p>Average and standard deviation of the spectra for the three different levels of organic fertilization (170, 230, and 340 kgN/ha) of the May and October harvest.</p> "> Figure 6
<p>Correlogram between spectral variables of the hyperspectral dataset and height (H), fresh biomass (FB), crude protein (CP), and metabolic energy (ME) for the May harvest.</p> "> Figure 7
<p>Scatterplot related to the influence of the type and the amount of fertilizer on selected narrow-band vegetation indices.</p> "> Figure 8
<p>Scatterplot of the best relationships between selected grassland traits and vegetation indices. The best results of the linear regression model for height, fresh matter yield, and crude protein were found in the integrated dataset of May and October, including both organic and inorganic fertilizers; the best result for Metabolic Energy was found instead in the May dataset, combining both organic and inorganic fertilized plots.</p> "> Figure 9
<p>Height variation within plots by applying the NDRE index on the acquired hyperspectral dataset of May. The plots with the lowest inorganic fertilization level (0 kgN/ha) are indicated with an arrow down and plots with the highest inorganic fertilization level (340 kgN/ha) are indicated with an arrow up.</p> "> Figure 10
<p>Metabolic energy variation within plots by applying the CI<sub>red-edge</sub> index on the acquired hyperspectral dataset of May.</p> "> Figure 11
<p>Scatterplot of the measured <span class="html-italic">vs.</span> predicted values for the best PLSR models presented for the integrated dataset of May and October and composed by both organic and inorganic fertilization plots (LOO = Leave-One-Out validation).</p> "> Figure 12
<p>PLSR coefficients for height, fresh matter yield, crude protein, and metabolic energy for the PLSR model of the integrated dataset of May and October, including both organic and inorganic fertilization plots.</p> ">
Abstract
:1. Introduction
- Compare two regression methods based on vegetation indices and the PLSR approach in order to choose the best strategy for predicting bio-physical and bio-chemical plant traits of grasslands;
- Investigate the influence of the amount and the type of fertilization on grassland traits and the resulting spectral curve;
- Evaluate the influence of the phenology of grasslands and the timing of spectral data collection on the established regression relations.
2. State of the Art of UAVs Applications
3. Material and Methods
3.1. Study Area and Field Data Collection
- Crude ash (CA): VDLUFA method book III, method No. 8.1.1
- Crude protein (CP): VDLUFA method book III, No.4.1.1
- Crude fiber (CF): VDLUFA method book III, No. 6.1.1
- Sodium (Na): VDLUFA method book III/6, No. 10.8.3
- Potassium (K): VDLUFA method book III/6, No. 10.8.3
- Metabolic energy (ME): ME was calculated from CA, CP, and CF as follows [50]:
- for harvest dates before 1 July:
- for harvest dates after 30 June:
- (1)
- all plots prepared with different levels of inorganic fertilizer for both May and October campaigns;
- (2)
- all the data of all plots arranged with both inorganic and organic fertilizer for both May and October campaigns;
- (3)
- this dataset takes into account all the May campaign data related to all plots arranged with different levels of inorganic and organic fertilizer.
3.2. UAV and Its Equipment
3.3. Hyperspectral Data Collection and Pre-Processing of Spectra
3.4. The Narrow-Band Vegetation Indices
Index | Formulation |
---|---|
MTCI | |
MCARI/OSAVI (Wu) | |
CIred edge | |
NDRE |
3.5. Partial Least Squares Regression (PLSR)
4. Results
4.1. Grassland Traits
Traits | Height | Fresh Biomass | Dry Matter Yield | Crude Ash | Crude Protein | Crude Fibre | Na | K | Metabolic Energy |
---|---|---|---|---|---|---|---|---|---|
Height | 1 | 0.92 | 0.89 | 0.59 | 0.32 | 0.76 | 0.19 | 0.68 | −0.72 |
Fresh Matter yield | 0.92 | 1 | 0.94 | 0.59 | 0.34 | 0.79 | 0.22 | 0.66 | −0.75 |
Dry Matter | 0.89 | 0.94 | 1 | 0.413 | 0.15 | 0.76 | 0.03 | 0.52 | −0.74 |
Crude Ash | 0.59 | 0.59 | 0.41 | 1 | 0.81 | 0.45 | 0.70 | 0.89 | −0.36 |
Crude Protein | 0.32 | 0.34 | 0.15 | 0.81 | 1 | 0.10 | 0.89 | 0.74 | 0.046 |
Crue Fibre | 0.76 | 0.79 | 0.76 | 0.45 | 0.10 | 1 | −0.017 | 0.059 | −0.98 |
Na | 0.19 | 0.22 | 0.03 | 0.70 | 0.89 | −0.017 | 1 | 0.57 | 0.14 |
K | 0.68 | 0.66 | 0.52 | 0.89 | 0.74 | 0.059 | 0.57 | 1 | −0.50 |
Metabolic Energy | −0.72 | −0.75 | −0.74 | −0.36 | 0.04 | −0.98 | 0.14 | −0.50 | 1 |
Statistics | Height (cm) | Fresh Biomass (kg/Plot) | Dry Matter Yield (dt/ha) | Crude Ash (g/kg) | Crude Protein (g/kg) | Crude Fibre (g/kg) | Na (g/kg) | K (g/kg) | Metabolic Energy (MJ) |
---|---|---|---|---|---|---|---|---|---|
Min | 23.9 | 11.4 | 24.1 | 79 | 88 | 200 | 0.2 | 21.9 | 10.2 |
Max | 40.9 | 28.1 | 50.7 | 101 | 164.3 | 247.5 | 1.5 | 28.1 | 10.9 |
Mean | 33.9 | 20.9 | 37.8 | 89.1 | 112.4 | 232.3 | 0.5 | 25.5 | 10.5 |
SD | 4.8 | 5 | 7.4 | 6.5 | 22.6 | 14.9 | 0.4 | 1.7 | 0.2 |
CV | 0.1 | 0.2 | 0.2 | 0.07 | 0.2 | 0.06 | 0.6 | 0.06 | 0.02 |
Statistics | Height (cm) | Fresh Biomass (kg/plot) | Dry Matter Yield (dt/ha) | Crude Ash (g/kg) | Crude Protein (g/kg) | Crude Fibre (g/kg) | Na (g/kg) | K (g/kg) | Metabolic Energy (MJ) |
---|---|---|---|---|---|---|---|---|---|
Min | 15 | 6.2 | 11.3 | 88 | 131 | 270 | 0.1 | 22.6 | 9.7 |
Max | 19.7 | 15.2 | 27.1 | 100 | 183 | 298 | 0.9 | 26.1 | 9.9 |
Mean | 18.1 | 10.6 | 18.6 | 93.6 | 150.4 | 279.3 | 0.5 | 24.6 | 9.8 |
SD | 1.4 | 2.6 | 4.5 | 3.5 | 15 | 8.6 | 0.3 | 1.2 | 0.06 |
CV | 0.08 | 0.2 | 0.2 | 0.03 | 0.1 | 0.03 | 0.6 | 0.05 | 0.006 |
Traits | Significance Level between Organic And Inorganic Fertilized (May) | Significance Level between Organic And Inorganic Fertilized (October) | Significance all Treatment Levels between May and October Data |
---|---|---|---|
Height | 0.35 | 0.67 | <0.001 |
Dry Matter | 0.25 | 0.57 | <0.001 |
Fresh matter yield | 0.31 | 0.62 | <0.001 |
Crude Ash | 0.77 | 0.72 | 0.082 |
Crude Protein | 0.56 | 0.69 | <0.001 |
Crude Fibre | 0.17 | 0.82 | <0.001 |
Na | 0.69 | 0.62 | 0.82 |
K | 0.65 | 0.13 | 0.23 |
Metabolic Energy | 0.08 | 0.69 | <0.001 |
4.2. Hyperspectral data
4.3. Narrow-Band Vegetation Indices
Plots May | Plots May and October | |||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Inorganic–Organic | Inorganic–Organic | |||||||||||||||
MTCI | MCARI/OSAVI | CI RED-EDGE | NDRE | MTCI | MCARI/OSAVI | CI RED-EDGE | NDRE | |||||||||
R2 | RMSE | R2 | RMSE | R2 | RMSE | R2 | RMSE | R2 | RMSE | R2 | RMSE | R2 | RMSE | R2 | RMSE | |
Height | 0.45 | 2.62 | 0.56 | 3.32 | 0.39 | 3.90 | 0.58 | 3.25 | 0.4 | 6.52 | 0.599 | 5.38 | 0.598 | 5.40 | 0.4 | 6.40 |
Dry Matter | 0.47 | 2.94 | 0.51 | 3.86 | 0.43 | 4.35 | 0.57 | 3.85 | 0.36 | 5.19 | 0.57 | 4.29 | 0.53 | 4.66 | 0.38 | 5.06 |
Fresh matter yield | 0.36 | 3.82 | 0.45 | 5.19 | 0.30 | 5.57 | 0.46 | 4.85 | 0.35 | 8.86 | 0.55 | 7.31 | 0.47 | 7.62 | 0.38 | 8.70 |
Crude Ash | 0.07 | 4.54 | 0.25 | 5.76 | 0.036 | 6.53 | 0.14 | 6.15 | 0.0006 | 5.90 | 1E-05 | 5.90 | 0.040 | 5.78 | 0.0013 | 5.90 |
Crude Protein | 0.004 | 15.32 | 0.05 | 21.17 | 0.0019 | 21.96 | 0.04 | 21.27 | 0.13 | 24.75 | 0.14 | 24.62 | 0.30 | 22.22 | 0.084 | 25.36 |
Crude Fiber | 0.51 | 8.29 | 0.41 | 12.84 | 0.46 | 12.32 | 0.49 | 11.95 | 0.09 | 26.47 | 0.20 | 24.67 | 0.24 | 24.04 | 0.059 | 26.82 |
Na | 0.001 | 0.25 | 0.05 | 0.35 | 0.0024 | 0.36 | 0.13 | 0.36 | 0.001 | 0.33 | 0.015 | 0.32 | 0.0002 | 0.33 | 0.017 | 0.32 |
K | 0.18 | 1.18 | 0.31 | 1.53 | 0.12 | 1.73 | 0.28 | 1.56 | 0.27 | 1.39 | 0.32 | 1.35 | 0.20 | 1.46 | 0.31 | 1.36 |
Metabolic Energy | 0.51 | 0.12 | 0.42 | 1.18 | 0.50 | 0.17 | 0.46 | 0.18 | 0.07 | 0.37 | 0.19 | 0.35 | 0.22 | 0.34 | 0.05 | 0.38 |
4.4. Partial Least Squares Regression (PLSR)
Traits | Plots May | Plots May and October | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
Inorganic–Organic | Inorganic–Organic | |||||||||
R2 | RPD | RMSE | RMSELOO | LF | R2 | RPD | RMSE | RMSELOO | LF | |
Height | 0.7 | 2.22 | 2.29 | 2.71 | 3 | 0.86 | 4.0 | 2.13 | 3.15 | 6 |
Dry Matter yield | 0.63 | 1.97 | 3.81 | 4.48 | 3 | 0.83 | 3.78 | 2.95 | 4.48 | 6 |
Fresh Matter yield | 0.72 | 2.29 | 2.31 | 2.73 | 3 | 0.81 | 3.86 | 1.67 | 2.78 | 7 |
Crude Ash | 0.62 | 2.01 | 3.36 | 4.04 | 3 | 0.47 | 1.58 | 3.74 | 4.26 | 4 |
Crude Protein | 0.56 | 1.79 | 12.28 | 14.38 | 3 | 0.76 | 2.34 | 11.73 | 12.79 | 4 |
Crude Fibre | 0.46 | 2.08 | 6.07 | 12.16 | 5 | 0.78 | 2.48 | 11.21 | 12.75 | 4 |
Na | 0.39 | 2.19 | 0.16 | 0.28 | 5 | 0.21 | 1.26 | 0.26 | 0.28 | 4 |
K | 0.68 | 6.08 | 0.3 | 1.02 | 7 | 0.39 | 1.46 | 1.12 | 1.27 | 4 |
Metabolic Energy | 0.44 | 2.73 | 0.09 | 0.17 | 5 | 0.80 | 2.59 | 0.15 | 0.17 | 4 |
5. Discussion
6. Conclusions
Acknowledgments
Author Contributions
Conflicts of Interest
References
- White, R.; Murray, S.; Rohweder, M. Pilot Analysis of Global Ecosystems—Grassland Ecosystems; World Resources Institute: Washington, DC, USA, 2000. [Google Scholar]
- Hopkins, A.; Holz, B. Grassland for agriculture and nature conservation: Production, quality and multi-functionality. Agron. Res. 2006, 4, 3–20. [Google Scholar]
- Clevers, J.G.P.W.; van der Heijden, G.W.A.M.; Verzakov, S.; Schaepman, M.E. Estimating grassland biomass using SVM band shaving of hyperspectral data. Photogramm. Eng. Remote Sens. 2007, 73, 1141–1148. [Google Scholar] [CrossRef]
- Adjorlolo, C.; Mutanga, O.; Choc, M.A. Predicting C3 and C4 grass nutrient variability using in situ canopy reflectance and partial least squares regression. Int. J. Remote Sens. 2015, 36, 1743–1761. [Google Scholar] [CrossRef]
- Clevers, J.G.; Kooistra, L. Using hyperspectral remote sensing data for retrieving canopy chlorophyll and nitrogen content. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 2012, 5, 574–583. [Google Scholar] [CrossRef]
- Cohen, W.B.; Maiersperger, T.K.; Gower, S.T.; Turner, D.P. An improved strategy for regression of biophysical variables and Landsat ETM+ data. Remote Sens. Environ. 2003, 84, 561–571. [Google Scholar] [CrossRef]
- Curran, P.J.; Dungan, J.L.; Peterson, D.L. Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: Testing the Kokaly and Clark methodologies. Remote Sens. Environ. 2001, 76, 349–359. [Google Scholar] [CrossRef]
- Hansen, P.M.; Schjoerring, J.K. Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sens. Environ. 2003, 86, 542–553. [Google Scholar] [CrossRef]
- Hinzman, L.D.; Bauer, M.E.; Daughtry, C.S.T. Effects of nitrogen fertilization on growth and reflectance characteristics of winter wheat. Remote Sens. Environ. 1986, 19, 47–61. [Google Scholar] [CrossRef]
- McMurtrey, J.E.; Chappelle, E.W.; Kim, M.S.; Meisinger, J.J.; Corp, L.A. Distinguishing nitrogen fertilization levels in field corn (Zea mays L.) with actively induced fluorescence and passive reflectance measurements. Remote Sens. Environ. 1994, 47, 36–44. [Google Scholar] [CrossRef]
- Weiss, M.; Baret, F. Evaluation of canopy biophysical variable retrieval performances from the accumulation of large swath satellite data. Remote Sens. Environ. 1999, 70, 293–306. [Google Scholar] [CrossRef]
- Wang, J.; Wang, T.; Skidmore, A.K.; Shi, T.; Wu, G. Evaluating Different Methods for Grass Nutrient Estimation from Canopy Hyperspectral Reflectance. Remote Sens. 2015, 7, 5901–5917. [Google Scholar] [CrossRef]
- Darvishzadeh, R.; Atzberger, C.; Skidmore, A.; Schlerf, M. Mapping grassland leaf area index with airborne hyperspectral imagery: A comparison study of statistical approaches and inversion of radiative transfer models. ISPRS J. Photogramm. Remote Sens. 2011, 66, 894–906. [Google Scholar] [CrossRef]
- Lee, K.S.; Cohen, W.B.; Kennedy, R.E.; Maiersperger, T.K.; Gower, S.T. Hyperspectral versus multispectral data for estimating leaf area index in four different biomes. Remote Sens. Environ. 2004, 91, 508–520. [Google Scholar] [CrossRef]
- Schlerf, M.; Atzberger, C.; Hill, J. Remote sensing of forest biophysical variables using HyMap imaging spectrometer data. Remote Sens. Environ. 2005, 95, 177–194. [Google Scholar] [CrossRef]
- Schaepman, M.E.; Ustin, S.L.; Plaza, A.J.; Painter, T.H.; Verrelst, J.; Liang, S. Earth system science related imaging spectroscopy—An assessment. Remote Sens. Environ. 2009, 113, S123–S137. [Google Scholar] [CrossRef]
- Dalponte, M.; Bruzzone, L.; Vescovo, L.; Gianelle, D. The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas. Remote Sens. Environ. 2009, 113, 2345–2355. [Google Scholar] [CrossRef]
- Capolupo, A.; Pindozzi, S.; Okello, C.; Fiorentino, N.; Boccia, L. Photogrammetry for environmental monitoring: The use of drones and hydrological models for detection of soil contaminated by copper. Sci. Total Environ. 2015, 514, 298–306. [Google Scholar] [CrossRef] [PubMed]
- Capolupo, A.; Pindozzi, S.; Okello, C.; Boccia, L. Indirect field technology for detecting areas object of illegal spills harmful to human health: Application of drones, photogrammetry and hydrological models. Geospat. Health. 2014, 8, 699–707. [Google Scholar] [CrossRef] [PubMed]
- Nex, F.; Remondino, F. UAV for 3D mapping applications: A review. Appl. Geomat. 2013, 6, 1–15. [Google Scholar] [CrossRef]
- Zhang, C.; Kovacs, J. The application of small unmanned aerial systems for precision agriculture: A review. Precis. Agric. 2012, 13, 693–712. [Google Scholar] [CrossRef]
- Roelofsen, H.D.; Bodegom, P.M.; Kooistra, L.; Witte, J.P.M. Predicting leaf traits of herbaceous species from their spectral characteristics. Ecol. Evol. 2014, 4, 706–719. [Google Scholar] [CrossRef] [PubMed]
- Thenkabail, P.S.; Smith, R.B.; de Pauw, E. Evaluation of narrowband and broadband vegetation indices for determining optimal hyperspectral wavebands for agricultural crop characterization. Photogramm. Eng. Remote Sens. 2002, 68, 607–621. [Google Scholar]
- Blackburn, G.A. Quantifying chlorophylls and caroteniods at leaf and canopy scales: An evaluation of some hyperspectral approaches. Remote Sens. Environ. 1998, 66, 273–285. [Google Scholar] [CrossRef]
- Broge, N.H.; Leblanc, E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sens. Environ. 2001, 76, 156–172. [Google Scholar] [CrossRef]
- Elvidge, C.D.; Chen, Z. Comparison of broad-band and narrow-band red and near-infrared vegetation indices. Remote Sens. Environ. 1995, 54, 38–48. [Google Scholar] [CrossRef]
- Mutanga, O.; Skidmore, A.K.; Kumar, L.; Ferwerda, J. Estimating tropical pasture quality at canopy level using band depth analysis with continuum removal in the visible domain. Int. J. Remote Sens. 2005, 26, 1093–1108. [Google Scholar] [CrossRef]
- Zhao, D.; Huang, L.; Li, J.; Qi, J. A comparative analysis of broadband and narrowband derived vegetation indices in predicting LAI and CCD of a cotton canopy. ISPRS J. Photogramm. Remote Sens. 2007, 62, 25–33. [Google Scholar] [CrossRef]
- Atzberger, C.; Jarmer, T.; Schlerf, M.; Kötz, B.; Werner, W. Spectroradiometric determination of wheat bio-physical variables: Comparison of different empirical-statistical approaches. In Proceedings of the 23rd EARSeL symposium of the Remote Sensing in Transitions, Ghent, Belgium, 2–5 June 2003.
- Curran, P.J. Remote sensing of foliar chemistry. Remote Sens. Environ. 1989, 30, 271–278. [Google Scholar] [CrossRef]
- De Jong, S.M.; Pebesma, E.J.; Lacaze, B. Above-ground biomass assessment of Mediterranean forests using airborne imaging spectrometry: The DAIS Peyne experiment. Int. J. Remote Sens. 2003, 24, 1505–1520. [Google Scholar] [CrossRef]
- Grossman, Y.L.; Ustin, S.L.; Jacquemoud, S.; Sanderson, E.W.; Schmuck, G.; Verdebout, J. Critique of stepwise multiple linear regression for the extraction of leaf biochemistry information from leaf reflectance data. Remote Sens. Environ. 1996, 56, 182–193. [Google Scholar] [CrossRef]
- Huang, Z.; Turner, B.J.; Dury, S.J.; Wallis, I.R.; Foley, W.J. Estimating foliage nitrogen concentration from HYMAP data using continuum removal analysis. Remote Sens. Environ. 2004, 93, 18–29. [Google Scholar] [CrossRef]
- Kokaly, R.F.; Clark, R.N. Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression. Remote Sens. Environ. 1999, 67, 267–287. [Google Scholar] [CrossRef]
- Kawamura, K.; Watanabe, N.; Sakanoue, S.; Lee, H.J.; Lim, J.; Yoshitoshi, R. Genetic algorithm-based partial least squares regression for estimating legume content in a grass-legume mixture using field hyperspectral measurements. Grassl. Sci. 2013, 59, 166–172. [Google Scholar] [CrossRef]
- Cho, M.A.; Skidmore, A.; Corsi, F.; van Wieren, S.E.; Sobhan, I. Estimation of green grass/herb biomass from airborne hyperspectral imagery using spectral indices and partial least squares regression. Int. J. Appl. Earth Observ. Geoinf. 2007, 9, 414–424. [Google Scholar] [CrossRef]
- Darvishzadeh, R.; Skidmore, A.; Schlerf, M.; Atzberger, C.; Corsi, F.; Cho, M. LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements. ISPRS J. Photogramm. Remote Sens. 2008, 63, 409–426. [Google Scholar] [CrossRef]
- Zhou, G.; Ambrosia, V.; Gasiewski, A.J.; Bland, G. Foreword to the special issue on Unmanned Airborne Vehicle (UAV) sensing systems for earth observations. IEEE Trans. Geosci. Remote Sens. 2009, 3, 687–689. [Google Scholar] [CrossRef]
- Pajares, G. Overview and current status of remote sensing applications based on Unmanned Aerial Vehicles (UAVs). J. Photogramm. Eng. Remote Sens. 2015, 81, 281–330. [Google Scholar] [CrossRef]
- Lelong, C.C.; Burger, P.; Jubelin, G.; Roux, B.; Labbé, S.; Baret, F. Assessment of unmanned aerial vehicles imagery for quantitative monitoring of wheat crop in small plots. Sensors 2008, 8, 3557–3585. [Google Scholar] [CrossRef]
- Nebiker, S.; Annen, A.; Scherrer, M.D. Oesch. A light-weight multispectral sensor for micro UAV—Opportunities for very high resolution airborne remote sensing. In Proceedings of the XXI ISPRS Congress, Beijing, China, 3–11 July 2008.
- Link, J.; Senner, D.; Claupein, W. Developing and evaluating an aerial sensor platform (ASP) to collect multispectral data for deriving management decisions in precision farming. Comput. Electron. Agric. 2013, 94, 20–28. [Google Scholar] [CrossRef]
- Colomina, I.; Molina, P. Unmanned aerial systems for photogrammetry and remote sensing: A review. ISPRS J. Photogramm. Remote Sens. 2014, 92, 79–97. [Google Scholar] [CrossRef]
- Salamí, E.; Barrado, C.; Pastor, E. UAV flight experiments applied to the remote sensing of vegetated areas. Remote Sens. 2014, 6, 11051–11081. [Google Scholar] [CrossRef] [Green Version]
- Vanamburg, L.K.; Trlica, M.J.; Hoffer, R.M.; Weltz, M.A. Ground based digital imagery for grassland biomass estimation. Int. J. Remote Sens. 2006, 27, 939–950. [Google Scholar] [CrossRef]
- Von Bueren, S.K.; Burkart, A.; Hueni, A.; Rascher, U.; Tuohy, M.P.; Yule, I.J. Deploying four optical UAV-based sensors over grassland: Challenges and limitations. Biogeosciences 2015, 12, 163–175. [Google Scholar] [CrossRef]
- Sakamoto, T.; Gitelson, A.A.; Nguy-Robertson, A.L.; Arkebauer, T.J.; Wardlow, B.D.; Suyker, A.E.; Verma, S.B.; Shibayama, M. An alternative method using digital cameras for continuous monitoring of crop status. Agric. For. Meteorol. 2012, 154, 113–126. [Google Scholar] [CrossRef]
- Kawamura, K.; Sakuno, Y.; Tanaka, Y.; Lee, H.J.; Lim, J.; Kurokawa, Y.; Watanabe, N. Mapping herbage biomass and nitrogen status in an Italian ryegrass (Lolium multiflorum L.) field using a digital video camera with balloon system. J. Appl. Remote Sens. 2011, 5. [Google Scholar] [CrossRef]
- Bassler, R. Die Chemische Untersuchung von Futtermitteln in VDLUFA Methodenbuch Band III/3, 1976 mit 3. Ergänzungslieferung 1993 und 6; VDLUFA-Verlag: Darmstadt, Germany, 2006. [Google Scholar]
- GFE (Ausschuss für Bedarfsnormen der Gesellschaft für Ernährungsphysiologie). Formeln zur Schätzung des Gehaltes an umsetzbarer Energie in Futtermitteln aus Aufwüchsen des Dauergrünlandes und Mais-Ganzpflanzen. Proc. Soc. Nutr. Physiol. 1998, 7, 141–150. [Google Scholar]
- Suomalainen, J.; Anders, N.; Iqbal, S.; Roerink, G.; Franke, J.; Wenting, P.; Hünniger, D.; Bartholomeus, H.; Becker, R.; Kooistra, L. A lightweight hyperspectral mapping system and photogrammetric processing chain for unmanned aerial vehicles. Remote Sens. 2014, 6, 11013–11030. [Google Scholar] [CrossRef]
- Schläpfer, D.; Odermatt, D. MODO—Modtran4 for Remote Sensing Applications; ReSe Applications Schläpfer: Wil, Switzerland, 2006; p. 78. [Google Scholar]
- Colomina, I.; Blàzquez, M.; Molina, P.; Parès, M.E.; Wis, M. Towards a new paradigm for high resolution low-cost photogrammetry and remote sensing. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2008, 37, 1201–1206. [Google Scholar]
- Triggs, W.; McLauchlan, P.; Hartley, R.; Fitzgibbon, A. Bundle adjustment—A modern synthesis. In Vision Algorithms: Theory and Practice; Triggs, W., Ziesserman, A., Sterliski, R., Eds.; Springer Verlag: Berlin, Germany, 2000; pp. 298–375. [Google Scholar]
- Gruen, A.; Beyer, H.A. System calibration through self calibration. In Calibration and Orientation of Cameras in Computer Vision; Gruen, A., Huang, T.S., Eds.; Springer: New York, NY, USA, 2001; pp. 163–194. [Google Scholar]
- Dash, J.; Curran, P.J. The MERIS terrestrial chlorophyll index. Int. J. Remote Sens. 2004, 25, 5403–5413. [Google Scholar] [CrossRef]
- Wu, C.; Niu, Z.; Tang, Q.; Huang, W. Estimating chlorophyll content from hyperspectral vegetation indices: Modeling and validation. Agric. For. Meteorol. 2008, 148, 1230–1241. [Google Scholar] [CrossRef]
- Gitelson, A.A.; Gritz, Y.; Merzlyak, M.N. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. J. Plant Physiol. 2003, 160, 271–282. [Google Scholar] [CrossRef] [PubMed]
- Gitelson, A.A.; Keydan, G.P.; Merzlyak, M.N. Three-band model for noninvasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves. Geophys. Res. Lett. 2006, 33, L11402. [Google Scholar] [CrossRef]
- Barnes, E.M.; Clarke, T.R.; Richards, S.E.; Colaizzi, P.D.; Haberland, J.; Kostrzewski, M.; Waller, P.; Choi, C.; Riley, E.; Thompson, T.; et al. Coincident detection of crop water stress, nitrogen status and canopy density using ground-based multispectral data. In Proceedings of the Fifth International Conference on Precision Agriculture, Bloomington, MN, USA, 16–19 July 2000.
- Geladi, P.; Kowalski, B.R. Partial least-squares regression: A tutorial. Anal. Chim. Acta 1986, 185, 1–17. [Google Scholar] [CrossRef]
- Farifteh, J.; van der Meer, F.; Atzberger, C.; Carranza, E.J.M. Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN). Remote Sens. Environ. 2007, 110, 59–78. [Google Scholar] [CrossRef]
- Kooistra, L.; Salas, E.A.L.; Clevers, J.; Wehrens, R.; Leuven, R.; Nienhuis, P.H.; Buydens, L.M.C. Exploring field vegetation reflectance as an indicator of soil contamination in river floodplains. Environ. Pollut. 2004, 127, 281–290. [Google Scholar] [CrossRef]
- Abdi, H. Partial least squares regression and projection on latent structure regression (PLS Regression). Wiley Interdiscip. Rev. Comput. Stat. 2010, 2, 97–106. [Google Scholar] [CrossRef]
- Reddersen, B.; Fricke, T.; Wachendorf, M. Effects of sample preparation and measurement standardization on the NIRS calibration quality of nitrogen, ash and NDFom content in extensive experimental grassland biomass. Anim. Feed Sci. Tech. 2013, 183, 77–85. [Google Scholar] [CrossRef]
- Williams, P.; Norris, K. Near-Infrared Technology in the Agricultural and Food Industries, 2nd ed.; American Association of Cereal Chemists: St. Paul, MN, USA, 2001. [Google Scholar]
- Serbin, S.P.; Singh, A.; McNeil, B.E.; Kingdon, C.C.; Townsend, P.A. Spectroscopic determination of leaf morphological and biochemical traits for northern temperate and boreal tree species. Ecol. Appl. 2014, 24, 1651–1669. [Google Scholar] [CrossRef]
- Mevik, B.H.; Wehrens, R. The pls package: Principal component and partial least squares regression in R. J. Stat. Softw. 2007, 18, 1–23. [Google Scholar] [CrossRef]
- Knoblauch, C.; Watson, C.; Becker, R.; Berendonk, C.; Wichern, F. Influence of nitrogen fertilisation on carbon and nitrogen mineralisation, microbial biomass and soil respiration in grassland soils. In Proceedings of the 18th Nitrogen Workshop, Lisbon, Portugal, 30 June–3 July 2014.
- Donath, T.W.; Hölzel, N.; Bissels, S.; Otte, A. Perspectives for incorporating biomass from non-intensively managed temperate flood-meadows into farming systems. Agric. Ecosyst. Environ. 2004, 104, 439–451. [Google Scholar] [CrossRef]
© 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Capolupo, A.; Kooistra, L.; Berendonk, C.; Boccia, L.; Suomalainen, J. Estimating Plant Traits of Grasslands from UAV-Acquired Hyperspectral Images: A Comparison of Statistical Approaches. ISPRS Int. J. Geo-Inf. 2015, 4, 2792-2820. https://doi.org/10.3390/ijgi4042792
Capolupo A, Kooistra L, Berendonk C, Boccia L, Suomalainen J. Estimating Plant Traits of Grasslands from UAV-Acquired Hyperspectral Images: A Comparison of Statistical Approaches. ISPRS International Journal of Geo-Information. 2015; 4(4):2792-2820. https://doi.org/10.3390/ijgi4042792
Chicago/Turabian StyleCapolupo, Alessandra, Lammert Kooistra, Clara Berendonk, Lorenzo Boccia, and Juha Suomalainen. 2015. "Estimating Plant Traits of Grasslands from UAV-Acquired Hyperspectral Images: A Comparison of Statistical Approaches" ISPRS International Journal of Geo-Information 4, no. 4: 2792-2820. https://doi.org/10.3390/ijgi4042792