1
|
The Influence of Aerial Hyperspectral Image Processing Workflow on Nitrogen Uptake Prediction Accuracy in Maize. REMOTE SENSING 2021. [DOI: 10.3390/rs14010132] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
Abstract
A meticulous image processing workflow is oftentimes required to derive quality image data from high-resolution, unmanned aerial systems. There are many subjective decisions to be made during image processing, but the effects of those decisions on prediction model accuracy have never been reported. This study introduced a framework for quantifying the effects of image processing methods on model accuracy. A demonstration of this framework was performed using high-resolution hyperspectral imagery (<10 cm pixel size) for predicting maize nitrogen uptake in the early to mid-vegetative developmental stages (V6–V14). Two supervised regression learning estimators (Lasso and partial least squares) were trained to make predictions from hyperspectral imagery. Data for this use case were collected from three experiments over two years (2018–2019) in southern Minnesota, USA (four site-years). The image processing steps that were evaluated include (i) reflectance conversion, (ii) cropping, (iii) spectral clipping, (iv) spectral smoothing, (v) binning, and (vi) segmentation. In total, 648 image processing workflow scenarios were evaluated, and results were analyzed to understand the influence of each image processing step on the cross-validated root mean squared error (RMSE) of the estimators. A sensitivity analysis revealed that the segmentation step was the most influential image processing step on the final estimator error. Across all workflow scenarios, the RMSE of predicted nitrogen uptake ranged from 14.3 to 19.8 kg ha−1 (relative RMSE ranged from 26.5% to 36.5%), a 38.5% increase in error from the lowest to the highest error workflow scenario. The framework introduced demonstrates the sensitivity and extent to which image processing affects prediction accuracy. It allows remote sensing analysts to improve model performance while providing data-driven justification to improve the reproducibility and objectivity of their work, similar to the benefits of hyperparameter tuning in machine learning applications.
Collapse
|
2
|
Prediction of Early Season Nitrogen Uptake in Maize Using High-Resolution Aerial Hyperspectral Imagery. REMOTE SENSING 2020. [DOI: 10.3390/rs12081234] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
The ability to predict spatially explicit nitrogen uptake (NUP) in maize (Zea mays L.) during the early development stages provides clear value for making in-season nitrogen fertilizer applications that can improve NUP efficiency and reduce the risk of nitrogen loss to the environment. Aerial hyperspectral imaging is an attractive agronomic research tool for its ability to capture spectral data over relatively large areas, enabling its use for predicting NUP at the field scale. The overarching goal of this work was to use supervised learning regression algorithms—Lasso, support vector regression (SVR), random forest, and partial least squares regression (PLSR)—to predict early season (i.e., V6–V14) maize NUP at three experimental sites in Minnesota using high-resolution hyperspectral imagery. In addition to the spectral features offered by hyperspectral imaging, the 10th percentile Modified Chlorophyll Absorption Ratio Index Improved (MCARI2) was made available to the learning models as an auxiliary feature to assess its ability to improve NUP prediction accuracy. The trained models demonstrated robustness by maintaining satisfactory prediction accuracy across locations, pixel sizes, development stages, and a broad range of NUP values (4.8 to 182 kg ha−1). Using the four most informative spectral features in addition to the auxiliary feature, the mean absolute error (MAE) of Lasso, SVR, and PLSR models (9.4, 9.7, and 9.5 kg ha−1, respectively) was lower than that of random forest (11.2 kg ha−1). The relative MAE for the Lasso, SVR, PLSR, and random forest models was 16.5%, 17.0%, 16.6%, and 19.6%, respectively. The inclusion of the auxiliary feature not only improved overall prediction accuracy by 1.6 kg ha−1 (14%) across all models, but it also reduced the number of input features required to reach optimal performance. The variance of predicted NUP increased as the measured NUP increased (MAE of the Lasso model increased from 4.0 to 12.1 kg ha−1 for measured NUP less than 25 kg ha−1 and greater than 100 kg ha−1, respectively). The most influential spectral features were oftentimes adjacent to each other (i.e., within approximately 6 nm), indicating the importance of both spectral precision and derivative spectra around key wavelengths for explaining NUP. Finally, several challenges and opportunities are discussed regarding the use of these results in the context of improving nitrogen fertilizer management.
Collapse
|
3
|
Meacham-Hensold K, Fu P, Wu J, Serbin S, Montes CM, Ainsworth E, Guan K, Dracup E, Pederson T, Driever S, Bernacchi C. Plot-level rapid screening for photosynthetic parameters using proximal hyperspectral imaging. JOURNAL OF EXPERIMENTAL BOTANY 2020; 71:2312-2328. [PMID: 32092145 PMCID: PMC7134947 DOI: 10.1093/jxb/eraa068] [Citation(s) in RCA: 40] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/10/2020] [Accepted: 02/10/2020] [Indexed: 05/20/2023]
Abstract
Photosynthesis is currently measured using time-laborious and/or destructive methods which slows research and breeding efforts to identify crop germplasm with higher photosynthetic capacities. We present a plot-level screening tool for quantification of photosynthetic parameters and pigment contents that utilizes hyperspectral reflectance from sunlit leaf pixels collected from a plot (~2 m×2 m) in <1 min. Using field-grown Nicotiana tabacum with genetically altered photosynthetic pathways over two growing seasons (2017 and 2018), we built predictive models for eight photosynthetic parameters and pigment traits. Using partial least squares regression (PLSR) analysis of plot-level sunlit vegetative reflectance pixels from a single visible near infra-red (VNIR) (400-900 nm) hyperspectral camera, we predict maximum carboxylation rate of Rubisco (Vc,max, R2=0.79) maximum electron transport rate in given conditions (J1800, R2=0.59), maximal light-saturated photosynthesis (Pmax, R2=0.54), chlorophyll content (R2=0.87), the Chl a/b ratio (R2=0.63), carbon content (R2=0.47), and nitrogen content (R2=0.49). Model predictions did not improve when using two cameras spanning 400-1800 nm, suggesting a robust, widely applicable and more 'cost-effective' pipeline requiring only a single VNIR camera. The analysis pipeline and methods can be used in any cropping system with modified species-specific PLSR analysis to offer a high-throughput field phenotyping screening for germplasm with improved photosynthetic performance in field trials.
Collapse
Affiliation(s)
- Katherine Meacham-Hensold
- Department of Plant Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
| | - Peng Fu
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
| | - Jin Wu
- Environmental & Climate Science Department, Brookhaven National Laboratory, Upton, New York, USA
- School of Biological Sciences, University of Hong Kong, Pokfulam, Hong Kong
| | - Shawn Serbin
- Environmental & Climate Science Department, Brookhaven National Laboratory, Upton, New York, USA
| | - Christopher M Montes
- Department of Plant Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
| | - Elizabeth Ainsworth
- Department of Plant Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- USDA ARS Global Change and Photosynthesis Research Unit, Urbana, IL, USA
| | - Kaiyu Guan
- Department of Natural Resources and Environmental Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- National Center of Supercomputing Applications, University of Illinois at Urbana-Champaign, Champaign, IL, USA
| | - Evan Dracup
- USDA ARS Global Change and Photosynthesis Research Unit, Urbana, IL, USA
| | - Taylor Pederson
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
| | - Steven Driever
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- Center for Crop Systems Analysis, Wageningen University, The Netherlands
| | - Carl Bernacchi
- Department of Plant Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA
- USDA ARS Global Change and Photosynthesis Research Unit, Urbana, IL, USA
| |
Collapse
|
4
|
Apell JN, McNeill K. Updated and validated solar irradiance reference spectra for estimating environmental photodegradation rates. ENVIRONMENTAL SCIENCE. PROCESSES & IMPACTS 2019; 21:427-437. [PMID: 30714584 DOI: 10.1039/c8em00478a] [Citation(s) in RCA: 31] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Irradiance reference spectra are used to calculate environmentally relevant photodegradation half-lives, but the currently used spectra were originally published in the 1980s with limited validation. The goal of this work is to provide updated irradiance reference spectra using the Simple Model of the Atmospheric Radiative Transfer of Sunshine (SMARTS). The SMARTS irradiance spectra were validated against measurements from several high-resolution spectroradiometers, and the updated irradiance reference spectra use current measurements for atmospheric species that can affect the irradiance that reaches the Earth's surface. These updated irradiance spectra are provided in 1 nm increments from 280 to 800 nm for 0° to 70° latitude at 10° increments in both the northern and southern hemisphere. Lastly, the influence of the input parameters on the modeled irradiance spectra was investigated. This work will allow users to calculate more accurate photodegradation half-lives using the updated irradiance reference spectra, and it also provides insight for users to calculate their own location- and time-specific irradiance spectra using SMARTS.
Collapse
Affiliation(s)
- Jennifer N Apell
- Institute for Biogeochemistry and Pollutant Dynamics, ETH Zurich, Universitaetstrasse 16, 8092 Zurich, Switzerland.
| | | |
Collapse
|
5
|
Modeling Photosynthetically Active Radiation from Satellite-Derived Estimations over Mainland Spain. REMOTE SENSING 2018. [DOI: 10.3390/rs10060849] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
6
|
|
7
|
Kim E, Yeom MS. Structural Arrangement of Water Molecules around Highly Charged Nanoparticles: Molecular Dynamics Simulation. B KOREAN CHEM SOC 2014. [DOI: 10.5012/bkcs.2014.35.5.1501] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
8
|
Hänninen V, Salmi T, Halonen L. Acceptor Tunneling Motion and O−H Stretching Vibration Overtones of the Water Dimer. J Phys Chem A 2009; 113:7133-7. [DOI: 10.1021/jp901974z] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Vesa Hänninen
- Laboratory of Physical Chemistry, University of Helsinki, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 Helsinki, Finland
| | - Teemu Salmi
- Laboratory of Physical Chemistry, University of Helsinki, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 Helsinki, Finland
| | - Lauri Halonen
- Laboratory of Physical Chemistry, University of Helsinki, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 Helsinki, Finland
| |
Collapse
|
9
|
Salmi T, Hänninen V, Garden AL, Kjaergaard HG, Tennyson J, Halonen L. Calculation of the O−H Stretching Vibrational Overtone Spectrum of the Water Dimer. J Phys Chem A 2008; 112:6305-12. [DOI: 10.1021/jp800754y] [Citation(s) in RCA: 55] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Teemu Salmi
- Laboratory of Physical Chemistry, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 University of Helsinki, Finland, Department of Chemistry, University of Otago, P.O. Box 56, 9054 Dunedin, New Zealand, and Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, United Kingdom
| | - Vesa Hänninen
- Laboratory of Physical Chemistry, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 University of Helsinki, Finland, Department of Chemistry, University of Otago, P.O. Box 56, 9054 Dunedin, New Zealand, and Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, United Kingdom
| | - Anna L. Garden
- Laboratory of Physical Chemistry, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 University of Helsinki, Finland, Department of Chemistry, University of Otago, P.O. Box 56, 9054 Dunedin, New Zealand, and Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, United Kingdom
| | - Henrik G. Kjaergaard
- Laboratory of Physical Chemistry, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 University of Helsinki, Finland, Department of Chemistry, University of Otago, P.O. Box 56, 9054 Dunedin, New Zealand, and Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, United Kingdom
| | - Jonathan Tennyson
- Laboratory of Physical Chemistry, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 University of Helsinki, Finland, Department of Chemistry, University of Otago, P.O. Box 56, 9054 Dunedin, New Zealand, and Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, United Kingdom
| | - Lauri Halonen
- Laboratory of Physical Chemistry, P.O. Box 55 (A.I. Virtasen aukio 1), FIN-00014 University of Helsinki, Finland, Department of Chemistry, University of Otago, P.O. Box 56, 9054 Dunedin, New Zealand, and Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, United Kingdom
| |
Collapse
|
10
|
Collins WD, Lee-Taylor JM, Edwards DP, Francis GL. Effects of increased near-infrared absorption by water vapor on the climate system. ACTA ACUST UNITED AC 2006. [DOI: 10.1029/2005jd006796] [Citation(s) in RCA: 24] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
11
|
Sierk B. Field measurements of water vapor continuum absorption in the visible and near-infrared. ACTA ACUST UNITED AC 2004. [DOI: 10.1029/2003jd003586] [Citation(s) in RCA: 23] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
12
|
Kjaergaard HG, Robinson TW, Howard DL, Daniel JS, Headrick JE, Vaida V. Complexes of Importance to the Absorption of Solar Radiation. J Phys Chem A 2003. [DOI: 10.1021/jp035098t] [Citation(s) in RCA: 100] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
13
|
Pfeilsticker K, Lotter A, Peters C, Bosch H. Atmospheric detection of water dimers via near-infrared absorption. Science 2003; 300:2078-80. [PMID: 12829778 DOI: 10.1126/science.1082282] [Citation(s) in RCA: 134] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
Abstract
Weakly bonded pairs of water molecules (H2O)2, or water dimers (WDs), may play an important role in photochemistry and climate, but the overlap of most of its spectral features with the water monomer (WM) has made detection difficult. We report on WD absorption measurements by means of atmospheric long-path (18.34 kilometers) differential optical absorption spectroscopy of the near-infrared OH stretching mode 0>f 4>b overtone transition predicted to be located near 746 nanometers. Our observation is in reasonable agreement with the known thermochemistry, calculated and measured structure, and spectroscopy (band strength, shape, and width) of the WD. The observation implies that the WD 0>f 4>b band is located at 749.5 nanometers, with a full width at half maximum of approximately 19.4 wave numbers, and that its band strength ranges between 1.23 x 10(-22) and 5.25 x 10(-22) centimeters per molecule.
Collapse
Affiliation(s)
- K Pfeilsticker
- Institut für Umweltphysik, INF 229, University of Heidelberg, D-69120 Heidelberg, Germany
| | | | | | | |
Collapse
|