4.7 Article

Airborne hyperspectral imaging of nitrogen deficiency on crop traits and yield of maize by machine learning and radiative transfer modeling

出版社

ELSEVIER
DOI: 10.1016/j.jag.2021.102617

关键词

Nitrogen; Photosynthetic capacity; Chlorophyll; Yield; Hyperspectral; Airborne; Radiative transfer model; Machine learning; Leaf; Canopy; Maize; Bioenergy crop

资金

  1. U.S. Department of Energy's Advanced Research Projects Agency-Energy (ARPA-E) SMARTFARM (MBC Lab) project
  2. NASA New Investigator Award
  3. NASA [NNX16AI56G, 80NSSC18K0170]
  4. USDA National Institute of Food and Agriculture (NIFA) Foundational Program award [2017-67013-26253, 2017-6800226789, 2017-67003-28703]
  5. NASA Jet Propulsion Laboratory award [1638464]
  6. NSF Macrosystems Biology grant [1638720]
  7. USDA Hatch award [WIS01874]
  8. U.S. Department of Energy's Advanced Research Projects Agency-Energy (ARPA-E) SMARTFARM (SYMFONI) project
  9. Illinois Discovery Partners Institute (DPI)
  10. Institute for Sustainability, Energy, and Environment (iSEE)
  11. College of Agricultural, Consumer and Environmental Sciences Future Interdisciplinary Research Explorations (ACES FIRE)
  12. Center for Digital Agriculture (CDA), University of Illinois at Urbana-Champaign

向作者/读者索取更多资源

The study shows that using hyperspectral imaging can accurately estimate critical crop traits, such as nitrogen, chlorophyll, and photosynthetic capacity, and evaluate the impact of nitrogen deficiency on crop yield. By combining process-based and data-driven approaches, it is possible to predict crop traits more effectively, facilitating precision agricultural management.
Nitrogen is an essential nutrient that directly affects plant photosynthesis, crop yield, and biomass production for bioenergy crops, but excessive application of nitrogen fertilizers can cause environmental degradation. To achieve sustainable nitrogen fertilizer management for precision agriculture, there is an urgent need for nondestructive and high spatial resolution monitoring of crop nitrogen and its allocation to photosynthetic proteins as that changes over time. Here, we used visible to shortwave infrared (400-2400 nm) airborne hyperspectral imaging with high spatial (0.5 m) and spectral (3-5 nm) resolutions to accurately estimate critical crop traits, i.e., nitrogen, chlorophyll, and photosynthetic capacity (CO2-saturated photosynthesis rate, V-max,V-27), at leaf and canopy scales, and to assess nitrogen deficiency on crop yield. We conducted three airborne campaigns over a maize (Zea mays L.) field during the growing season of 2019. Physically based soil-canopy Radiative Transfer Modeling (RTM) and data-driven approaches i.e. Partial-Least Squares Regression (PLSR) were used to retrieve crop traits from hyperspectral reflectance, with ground truth of leaf nitrogen, chlorophyll, V-max,V-27, Leaf Area Index (LAI), and harvested grain yield. To improve computational efficiency of RTMs, Random Forest (RF) was used to mimic RTM simulations to generate machine learning surrogate models RTM-RF. The results show that prior knowledge of soil background and leaf angle distribution can significantly reduce the illposed RTM retrieval. RTM-RF achieved a high accuracy to predict leaf chlorophyll content (R-2 = 0.73) and LAI (R-2 = 0.75). Meanwhile, PLSR exhibited better accuracy to predict leaf chlorophyll content (R-2 = 0.79), nitrogen concentration (R-2 = 0.83), nitrogen content (R-2 = 0.77), and V-max,V-27 (R-2 = 0.69) but required measured traits for model training. We also found that canopy structure signals can enhance the use of spectral data to predict nitrogen related photosynthetic traits, as combining RTM-RF LAI and PLSR leaf traits well predicted canopy-level traits (leaf traits x LAI) including canopy chlorophyll (R-2 = 0.80), nitrogen (R-2 = 0.85) and V-max,V-27 (R-2 = 0.82). Compared to leaf traits, we further found that canopy-level photosynthetic traits, particularly canopy V-max,V-27, have higher correlation with maize grain yield. This study highlights the potential for synergistic use of processbased and data-driven approaches of hyperspectral imaging to quantify crop traits that facilitate precision agricultural management to secure food and bioenergy production.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据