Prediction of Early Season Nitrogen Uptake in Maize Using High-Resolution Aerial Hyperspectral Imagery

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.

[1]  I. Helland ON THE STRUCTURE OF PARTIAL LEAST SQUARES REGRESSION , 1988 .

[2]  A. Brook,et al.  Spectral data source effect on crop state estimation by vegetation indices , 2018, Environmental Earth Sciences.

[3]  John E. Sawyer,et al.  Strengths and Limitations of Nitrogen Rate Recommendations for Corn and Opportunities for Improvement , 2018 .

[4]  A. Dobermann,et al.  Agroecosystems, Nitrogen-use Efficiency, and Nitrogen Management , 2002, Ambio.

[5]  Luca Bechini,et al.  Does remote and proximal optical sensing successfully estimate maize variables? A review , 2018, European Journal of Agronomy.

[6]  John R. Miller,et al.  Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture , 2004 .

[7]  S. Polasky,et al.  Land-use change and costs to rural households: a case study in groundwater nitrate contamination , 2014 .

[8]  D. Pannell Economic perspectives on nitrogen in farming systems: managing trade-offs between production, risk and the environment , 2017 .

[9]  James B. Burkholder,et al.  Absorption measurements of oxygen between 330 and 1140 nm , 1990 .

[10]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[11]  I. M. Scotford,et al.  Applications of Spectral Reflectance Techniques in Northern European Cereal Production: A Review , 2005 .

[12]  A. Huete A soil-adjusted vegetation index (SAVI) , 1988 .

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  M. C. Leirós,et al.  Dependence of mineralization of soil organic matter on temperature and moisture , 1999 .

[15]  D. Tilman,et al.  Global food demand and the sustainable intensification of agriculture , 2011, Proceedings of the National Academy of Sciences.

[16]  G. Robertson,et al.  Nitrogen in Agriculture: Balancing the Cost of an Essential Resource , 2009 .

[17]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[18]  P. Scharf SOIL AND PLANT TESTS TO PREDICT OPTIMUM NITROGEN RATES FOR CORN* , 2001 .

[19]  Earl D. Vories,et al.  Ground‐Based Canopy Reflectance Sensing for Variable‐Rate Nitrogen Corn Fertilization , 2010 .

[20]  Jan Willem Erisman,et al.  Consequences of human modification of the global nitrogen cycle , 2013, Philosophical Transactions of the Royal Society B: Biological Sciences.

[21]  Sylvie M. Brouder,et al.  Chlorophyll meter readings can predict nitrogen need and yield response of corn in the north-central USA , 2006 .

[22]  Sharon L. Qi,et al.  High Nitrate Concentrations in Some Midwest United States Streams in 2013 after the 2012 Drought. , 2016, Journal of environmental quality.

[23]  Li Wang,et al.  Evaluation of Leaf N Concentration in Winter Wheat Based on Discrete Wavelet Transform Analysis , 2019, Remote. Sens..

[24]  Carlos Costa,et al.  Comparison of Crop‐Based Indicators with Soil Nitrate Test for Corn Nitrogen Requirement , 2005 .

[25]  S. Polasky,et al.  The social costs of nitrogen , 2016, Science Advances.

[26]  Richard A. Johnson,et al.  A new family of power transformations to improve normality or symmetry , 2000 .

[27]  D. Mulla,et al.  Spatial and temporal variation in economically optimum nitrogen rate for corn , 2003 .

[28]  Roderic L. Jones,et al.  Absorption of solar radiation by water vapor in clear and cloudy skies: Implications for anomalous absorption , 2000 .

[29]  Sotirios Archontoulis,et al.  Development of a nitrogen recommendation tool for corn considering static and dynamic variables , 2019, European Journal of Agronomy.

[30]  E. Milton,et al.  The use of the empirical line method to calibrate remotely sensed data to reflectance , 1999 .

[31]  Jeffrey A. Coulter,et al.  Soil Texture and Precipitation Influence Optimal Time of Nitrogen Fertilization for Corn , 2019, Agronomy Journal.

[32]  Hui Shao,et al.  Active Optical Sensing of Spring Maize for In-Season Diagnosis of Nitrogen Status Based on Nitrogen Nutrition Index , 2016, Remote. Sens..

[33]  I. Matejovič Total nitrogen in plant material determinated by means of dry combustion : a possible alternative to determination by Kjeldahl digestion , 1995 .

[34]  Qing Zhu,et al.  Improving in-season nitrogen recommendations for maize using an active sensor , 2011 .

[35]  Richard T. Conant,et al.  Patterns and trends in nitrogen use and nitrogen recovery efficiency in world agriculture , 2013 .

[36]  Effects of fertilizer timing and variable rate N on nitrate–N losses from a tile drained corn-soybean rotation simulated using DRAINMOD-NII , 2019, Precision Agriculture.

[37]  Adam E. Dellinger,et al.  Nitrogen Recommendations for Corn: An On-The-Go Sensor Compared with Current Recommendation Methods , 2009 .

[38]  J. Peñuelas,et al.  The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status. , 1994 .

[39]  William R. Raun,et al.  Variability in Optimum Nitrogen Rates for Maize , 2016 .

[40]  Bruno Basso,et al.  Environmental and economic benefits of variable rate nitrogen fertilization in a nitrate vulnerable zone. , 2016, The Science of the total environment.

[41]  Daniel E. Kaiser,et al.  Soil sample timing, nitrogen fertilization, and incubation length influence anaerobic potentially mineralizable nitrogen , 2020, Soil Science Society of America Journal.

[42]  G. Robertson,et al.  Global metaanalysis of the nonlinear response of soil nitrous oxide (N2O) emissions to fertilizer nitrogen , 2014, Proceedings of the National Academy of Sciences.