Development of a low-cost portable device for pixel-wise leaf SPAD estimation and blade-level SPAD distribution visualization using color sensing

Tan, Lehao; Zhou, Lei; Zhao, Nan; He, Yong; Qiu, Zhengjun

doi:10.1016/j.compag.2021.106487

Cited by 15 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this study was conducted in a closed indoor environment, there exists a wide range of fields where image-based SPAD value prediction can be conducted, ranging from fields [28] to greenhouses [30]. The results of this study can be used in environments where the leaf color can be obtained under a stable light source, as in previous studies [18]. However, when images are acquired under unstable light environments, such as in the fields or in greenhouses, the accuracy of the SPAD value prediction becomes an issue.…”

Section: Discussionmentioning

confidence: 93%

“…In this study, it was found that the accuracy of SPAD value prediction was enhanced by using color information (e.g., RGB, HSL, and HSV) obtained from digital images and photographic environment information (color temperature and illuminance) as the model input. Previous studies have proposed methods to stabilize the light environment during photographic [18] and color-corrected images using color charts as color standards [28]. However, a method to stabilize the light environment at the time of photography can only predict SPAD values on an individual leaf basis, although it can provide a highly accurate SPAD value prediction.…”

Section: Discussionmentioning

confidence: 99%

“…In previous studies, algorithms such as Linear Regression [7], convolutional neural networks (CNN) [18], Support Vector Machines [3], Random Forests [3,19], XGBoost [19], and Generalized Linear Models (GLMs) [20] have been applied to predict SPAD values using color values measured by images and color chromatometers. Although leaf colors vary from crop to crop and direct comparisons of model performances are not possible, some algorithms have achieved high model performance in predicting SPAD values.…”

Section: Introductionmentioning

confidence: 99%

“…However, because the intensity of sunlight, for example, changes from moment to moment, the pixel values of an image may change spatiotemporally, even for the same subject. In response to this problem, machine learning was applied to predict SPAD values from pixel values using a photographic device that creates a stable light environment [18]. However, similar to conventional SPAD meters, this device can only measure the SPAD values of individual leaves.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves

Kamiwaki,

Fukuda

2023

Algorithms

View full text Add to dashboard Cite

This study aims to clarify the influence of photographic environments under different light sources on image-based SPAD value prediction. The input variables for the SPAD value prediction using Random Forests, XGBoost, and LightGBM were RGB values, HSL values, HSV values, light color temperature (LCT), and illuminance (ILL). Model performance was assessed using Pearson’s correlation coefficient (COR), Nash–Sutcliffe efficiency (NSE), and root mean squared error (RMSE). Especially, SPAD value prediction with Random Forests resulted in high accuracy in a stable light environment; CORRGB+ILL+LCT and CORHSL+ILL+LCT were 0.929 and 0.922, respectively. Image-based SPAD value prediction was effective under halogen light with a similar color temperature at dusk; CORRGB+ILL and CORHSL+ILL were 0.895 and 0.876, respectively. The HSL value under LED could be used to predict the SPAD value with high accuracy in all performance measures. The results supported the applicability of SPAD value prediction using Random Forests under a wide range of lighting conditions, such as dusk, by training a model based on data collected under different illuminance conditions in various light sources. Further studies are required to examine this method under outdoor conditions in spatiotemporally dynamic light environments.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves

Kamiwaki,

Fukuda

2023

Algorithms

View full text Add to dashboard Cite

show abstract

“…The value of SPDA is a reliable indicator that can represent the content of chlorophyll (Tan et al, 2021). The SPDA values and photosynthetic characteristics were different under LK and HK stresses.…”

Section: Potassium Affects Plant Growth and Mineral Nutrientsmentioning

confidence: 99%

Transcriptional and metabolic responses of apple to different potassium environments

Sun

Zhang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Potassium (K) is one of the most important macronutrients for plant development and growth. The influence mechanism of different potassium stresses on the molecular regulation and metabolites of apple remains largely unknown. In this research, physiological, transcriptome, and metabolite analyses were compared under different K conditions in apple seedlings. The results showed that K deficiency and excess conditions influenced apple phenotypic characteristics, soil plant analytical development (SPAD) values, and photosynthesis. Hydrogen peroxide (H2O2) content, peroxidase (POD) activity, catalase (CAT) activity, abscisic acid (ABA) content, and indoleacetic acid (IAA) content were regulated by different K stresses. Transcriptome analysis indicated that there were 2,409 and 778 differentially expressed genes (DEGs) in apple leaves and roots under K deficiency conditions in addition to 1,393 and 1,205 DEGs in apple leaves and roots under potassium excess conditions, respectively. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment showed that the DEGs were involved in flavonoid biosynthesis, photosynthesis, and plant hormone signal transduction metabolite biosynthetic processes in response to different K conditions. There were 527 and 166 differential metabolites (DMAs) in leaves and roots under low-K stress as well as 228 and 150 DMAs in apple leaves and roots under high-K stress, respectively. Apple plants regulate carbon metabolism and the flavonoid pathway to respond to low-K and high-K stresses. This study provides a basis for understanding the metabolic processes underlying different K responses and provides a foundation to improve the utilization efficiency of K in apples.

show abstract

Simultaneously predicting SPAD and water content in rice leaves using hyperspectral imaging with deep multi‐task regression and transfer component analysis

Zhai,

Wang,

Zhou

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDWater content and chlorophyll content are important indicators for monitoring rice growth status. Simultaneous detection of water content and chlorophyll content is of significance. Different varieties of rice show differences in phenotype, resulting in the difficulties of establishing a universal model. In this study, hyperspectral imaging was used to detect the Soil and Plant Analyzer Development (SPAD) values and water content of fresh rice leaves of three rice varieties (Jiahua 1, Xiushui 121 and Xiushui 134).RESULTSBoth partial least squares regression and convolutional neural networks were used to establish single‐task and multi‐task models. Transfer component analysis (TCA) was used as transfer learning to learn the common features to achieve an approximate identical distribution between any two varieties. Single‐task and multi‐task models were also built using the features of the source domain, and these models were applied to the target domain. These results indicated that for models of each rice variety the prediction accuracy of most multi‐task models was close to that of single‐task models. As for TCA, the results showed that the single‐task model achieved good performance for all transfer learning tasks.CONCLUSIONCompared with the original model, good and differentiated results were obtained for the models using features learned by TCA for both the source domain and target domain. The multi‐task models could be constructed to predict SPAD values and water content simultaneously and then transferred to another rice variety, which could improve the efficiency of model construction and realize rapid detection of rice growth indicators. © 2024 Society of Chemical Industry.

show abstract

Development of a low-cost portable device for pixel-wise leaf SPAD estimation and blade-level SPAD distribution visualization using color sensing

Cited by 15 publications

References 21 publications

Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves

Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves

Transcriptional and metabolic responses of apple to different potassium environments

Simultaneously predicting SPAD and water content in rice leaves using hyperspectral imaging with deep multi‐task regression and transfer component analysis

Contact Info

Product

Resources

About