The use of near infrared spectroscopy to predict foliar nutrient levels of hydroponically grown teak seedlings

Whittier, W. Andrew; Hodge, Gary R.; López, Julio Pérez; Saravitz, Carole H.; Acosta, Juan J.

doi:10.1177/09670335211025649

Cited by 4 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current study, it was found that the NIRS system had a very good potential to predict the K content of the dried and ground pistachio tree leaves ( R 2 > 0.80) from the NIR reflectance data. The performance of the model developed for the K content determination was observed to have similar success ( R 2 > 0.80) compared to other studies conducted using NIRS on different plant leaves (Gálvez‐Sola et al., 2015; Whittier et al., 2021; Yarce & Rojas, 2012). Predictions of Ca, Cu, Mg, and Fe concentrations also exhibit modest yet reasonable performance ( R 2 = 0.70–0.80), which is comparable to or even superior to certain NIRS‐utilizing studies (Cuq et al., 2020; Gálvez‐Sola et al., 2015; Sekerli et al., 2021a, 2021b; Whittier et al., 2021; Yarce & Rojas, 2012).…”

Section: Discussionsupporting

confidence: 62%

“…The performance of the model developed for the K content determination was observed to have similar success ( R 2 > 0.80) compared to other studies conducted using NIRS on different plant leaves (Gálvez‐Sola et al., 2015; Whittier et al., 2021; Yarce & Rojas, 2012). Predictions of Ca, Cu, Mg, and Fe concentrations also exhibit modest yet reasonable performance ( R 2 = 0.70–0.80), which is comparable to or even superior to certain NIRS‐utilizing studies (Cuq et al., 2020; Gálvez‐Sola et al., 2015; Sekerli et al., 2021a, 2021b; Whittier et al., 2021; Yarce & Rojas, 2012). However, this technique did not offer good results for the prediction of N, P, Zn, and Mn in the present study ( R 2 < 0.70).…”

Section: Discussionsupporting

confidence: 62%

See 1 more Smart Citation

Rapid and cost‐effective assessment of nutrients in pistachio (Pistacia vera L.) leaves through Fourier transform near‐infrared spectroscopy (FT‐NIRS)

Sekerli,

Buyuk,

Keskin

et al. 2024

J. Plant Nutr. Soil Sci.

View full text Add to dashboard Cite

BackgroundPistachio nuts provide many health benefits in human diet. Nutrient levels in plant leaves and fertilizer schedules are determined based on traditional soil and leaf chemical analyses. However, these methods require additional labor, time, and cost, which is why most farmers do not prefer them and cannot detect nutrient deficiencies in time. Fast, easy‐to‐use and low‐cost nutrient level assessment techniques are needed.AimThis study aims to explore the viability of near‐infrared reflectance spectroscopy (NIRS) as a fast, user friendly, and cost effective technique for evluating the major macro‐ and micronutrient contents of dried and ground pistachio leaf sample.MethodsThe feasibility of NIRS for estimating nutrient contents was investigated by analyzing samples from 200 pistachio trees. Dried and ground pistachio leaves were subjected to NIRS analysis. PLSR (Partial least square regression) analyses were performed to develop nutrient content prediction models using spectral information of samples.ResultsIt was found that the NIRS system had a very good potential to estimate the K, Ca, Cu, and Mg contents of the leaf samples (R2 > 0.80). It was also found that Fe and Mn concentrations could also be estimated with good accuracy (R2 = 0.70–0.80). However, the NIRS system did not give good results for the prediction of N, P, and Zn (R2 < 0.40).ConclusionIn conclusion, the NIRS system can be used to quickly, easily, and economically assess the K, Ca, Cu, Mg, Fe, and Mn contents of dried and ground pistachio leaves. This technique has the potential to improve nutrient management practices in pistachio farming within a sustainable and environmentally conscious framework. Fourier transform NIRS (FT‐NIRS) can provide valuable insights by complementing rather than replacing traditional chemical analysis. Laboratory analysis is still required for definitive nutrient content information, but FT‐NIRS can significantly reduce the reliance on such analysis, thereby mitigating the environmental impact caused by the excessive use of chemical fertilizers and minimizing the health risks to laboratory staff. In addition, the rapid information‐gathering capabilities of the FT‐NIRS can be emphasized.

show abstract

Section: Discussionsupporting

confidence: 62%

Section: Discussionsupporting

confidence: 62%

Rapid and cost‐effective assessment of nutrients in pistachio (Pistacia vera L.) leaves through Fourier transform near‐infrared spectroscopy (FT‐NIRS)

Sekerli,

Buyuk,

Keskin

et al. 2024

J. Plant Nutr. Soil Sci.

View full text Add to dashboard Cite

show abstract

“…Photos of S-deficient seedlings in greenhouses have been published (Goslin 1959;Murison 1960;Hacskaylo et al 1969;Erdmann 1979;Whittier 2018) but they have not been published when grown outside in bareroot nurseries (Benzian 1965a;Bengtson 1968;Truman 1972;Baer 1984;. This is likely due to use of sulphate fertilizers plus irrigation water containing S plus atmospheric deposition.…”

Section: Deficiency Symptomsmentioning

confidence: 99%

Use of sulphur in bareroot pine and hardwood nurseries

South

2023

REFOR

View full text Add to dashboard Cite

During the 20th century, managers at sandy nurseries utilized sulphur (S) to lower soil pH and mitigate the risk of iron deficiency. During that time, however, applying S as a fertilizer was a rare event. At many nurseries, S in rain and irrigation water was sufficient to avoid visual deficiency symptoms. The S status of soil and foliage was typically unknown, and many researchers did not test for S due to the additional cost. Consequently, S became the most neglected macronutrient. While a few nursery trials demonstrated that elemental S reduced damping-off and increased height growth, a majority showed no benefit after applying S at rates lower than 100 kg ha-1. Even so, by 1980, S-deficiencies occurred at bareroot nurseries in Alabama, Oklahoma, Virginia, Wisconsin, the United Kingdom, and likely in North Dakota and New York. The risk of a deficiency increases when N-only fertilizers are applied to seedbeds. Due to research, experience and the precautionary principle, several managers transitioned to using ammonium sulfate instead of, less expensive, N-only nitrogen fertilizers. After soil tests became affordable, managers began to ask questions about the need to apply S to seedbeds. Only a few hydroponic trials with small pine seedlings have been used to estimate “threshold” or “critical values” for foliar S. Since an initial 1,500 μg g-1 S value is “unreliable” for pine seedlings, some authors lowered the value to 1,100 μg g-1 and even as low as 500 μg g-1 S. Others ignore all estimates based on total S concentrations and, instead, monitor only foliar SO4 levels.

show abstract

“…However, most of the nutrient minerals of fruit trees are present in organic matter and combined with one of the abovementioned moieties, so quantitative and qualitative analyses of nutrients can be achieved indirectly by NIR spectroscopy. 10 For example, Whittier et al 11 used NIR spectroscopy to predict the foliar nutrient levels of hydroponically grown teak seedlings. Bedin et al 12 detected C, N, P, and K in poultry litter by NIR spectroscopy via support vector machine (SVM) and achieved good results.…”

Section: Introductionmentioning

confidence: 99%

A Novel Tran_NAS Method for the Identification of Fe- and Mg-Deficient Pear Leaves from N- and P-Deficient Pear Leaf Data

Jin

Wang

et al. 2022

ACS Omega

View full text Add to dashboard Cite

Trace element deficiency diagnosis plays a critical role in pear cultivation. However, high-quality diagnostic models are challenging to investigate, making it difficult to collect samples. Therefore, this manuscript developed a novel transfer learning method, named Tran_NAS, with a finetuning neural network that uses a neural architecture search (NAS) to transfer learning from nitrogen (N) and phosphorus (P) to iron (Fe) and magnesium (Mg) to diagnose pear leaf element deficiencies. The best accuracy of the transferred NAS model is 89.12%, which is 11% more than that of the model without the transfer of trace element-deficient samples. Meanwhile, Tran_NAS also has better performance on source datasets after comparing with different proportions of training sets. Finally, this manuscript summarizes the transfer model coincident characteristics, including the methods of batch normalization (BN) and dropout layers, which make the model more generalizable. This manuscript applies a symmetric homogeneous feature-based transfer learning method on NAS that is designed explicitly for near-infrared (NIR) data collected from nutrient-deficient pear leaves. The novel transfer learning method would be more effective for the micro-NIR spectrum of the nondestructive diagnosis.

show abstract

The use of near infrared spectroscopy to predict foliar nutrient levels of hydroponically grown teak seedlings

Cited by 4 publications

References 20 publications

Rapid and cost‐effective assessment of nutrients in pistachio (Pistacia vera L.) leaves through Fourier transform near‐infrared spectroscopy (FT‐NIRS)

Rapid and cost‐effective assessment of nutrients in pistachio (Pistacia vera L.) leaves through Fourier transform near‐infrared spectroscopy (FT‐NIRS)

Use of sulphur in bareroot pine and hardwood nurseries

A Novel Tran_NAS Method for the Identification of Fe- and Mg-Deficient Pear Leaves from N- and P-Deficient Pear Leaf Data

Contact Info

Product

Resources

About