MOISTURE CONTENT DETECTION OF SOYBEAN GRAINS BASED ON HYPERSPECTRAL IMAGING DOI Open Access

Zhichang CHANG,

Man Chen, Gong Cheng

et al.

INMATEH Agricultural Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 562 - 570

Published: Dec. 18, 2024

Using hyperspectral imaging technology for rapid, non-destructive detection of soybean grain moisture content provides technical support high-quality harvesting. A total 90 samples grains from different varieties were collected, with images acquired in the wavelength range 900–1700 nm. The each sample was determined using direct drying method as specified GB 5009.3-2016. divided into a calibration set and prediction based on 4:1 ratio partitioning Joint X-Y Distance. Eight preprocessing methods applied to raw spectral data, including baseline correction, moving average, Savitzky-Golay filtering, normalization, standard normal variate transformation, multiple scatter first derivative, deconvolution. Feature wavelengths then extracted successive projections algorithm competitive adaptive reweighted sampling algorithm. Finally, partial least squares regression model predicting developed these feature wavelengths. results show that correlation coefficient root mean square error optimal 0.92 0.2371, respectively. spectrum inversion can precisely rapidly predict non-destructively, thereby determining timing mechanical harvesting enhancing quality harvesting, storage, processing.

Language: Английский

Poplar seedling varieties and drought stress classification based on multi-source, time-series data and deep learning DOI
Lu Wang, Huichun Zhang, Liming Bian

et al.

Industrial Crops and Products, Journal Year: 2024, Volume and Issue: 218, P. 118905 - 118905

Published: June 9, 2024

Language: Английский

Citations

7
Analyzing different phenotypic methods of soybean leaves under the high temperature stress with near-infrared spectroscopy, microscopic Image, and multispectral image DOI
Ying Deng,

Weizhi Yang,

Jiajia Li

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 234, P. 110281 - 110281

Published: March 15, 2025

Language: Английский

Citations

0
Integrating sensor fusion with machine learning for comprehensive assessment of phenotypic traits and drought response in poplar species DOI Creative Commons
Ziyang Zhou, Huichun Zhang, Liming Bian

et al.

Plant Biotechnology Journal, Journal Year: 2025, Volume and Issue: unknown

Published: March 30, 2025

Summary Increased drought frequency and severity in a warming climate threaten the health stability of forest ecosystems, influencing structure functioning forests while having far‐reaching implications for global carbon storage regulation. To effectively address challenges posed by drought, it is imperative to monitor assess degree stress trees timely accurate manner. In this study, gradient experiment was conducted with poplar as research object, multimodal data were collected subsequent analysis. A machine learning‐based monitoring model constructed, thereby enabling duration trees. Four processing methods, namely decomposition, layer fusion, feature fusion decision employed comprehensively evaluate monitoring. Additionally, potential new phenotypic features obtained different methods discussed. The results demonstrate that optimal learning model, constructed under exhibits best performance, average accuracy, precision, recall F1 score reaching 0.85, 0.86, 0.85 respectively. Conversely, novel derived through decomposition supplementary did not further augment precision. This indicates approach has clear advantages offers robust theoretical foundation practical guidance future tree response assessment.

Language: Английский

Citations

0
Capturing plant functional traits in coastal dunes using close-range remote sensing DOI Creative Commons
Giacomo Trotta, Marco Vuerich, Elisa Petrussa

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103159 - 103159

Published: April 1, 2025

Language: Английский

Citations

0
Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China DOI Creative Commons
Hongran Li,

Hui Zhao,

Chao Wei

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 84, P. 102854 - 102854

Published: Oct. 16, 2024

Language: Английский

Citations

2
Three-dimensional image recognition of soybean canopy based on improved multi-view network DOI
Xiaodan Ma, Wenkang Xu,

Haiou Guan

et al.

Industrial Crops and Products, Journal Year: 2024, Volume and Issue: 222, P. 119544 - 119544

Published: Sept. 4, 2024

Language: Английский

Citations

1
Automatic pine wilt disease detection based on improved YOLOv8 UAV multispectral imagery DOI Creative Commons

Shaoxiong Xu,

Wenjiang Huang, Dachen Wang

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102846 - 102846

Published: Oct. 1, 2024

Language: Английский

Citations

1
A novel feature extraction-selection technique for long lead time agricultural drought forecasting DOI
Mehdi Mohammadi Ghaleni, Mansour Moradi, Mahnoosh Moghaddasi

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132332 - 132332

Published: Nov. 1, 2024

Language: Английский

Citations

1
Phenotyping for Effects of Drought Levels in Quinoa Using Remote Sensing Tools DOI Creative Commons
Nerio E. Lupa-Condo,

Frans C. Lope-Ccasa,

Angel A. Salazar-Joyo

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(9), P. 1938 - 1938

Published: Aug. 28, 2024

Drought is a principal limiting factor in the production of agricultural crops; however, quinoa possesses certain adaptive and tolerance factors that make it potentially valuable crop under drought-stress conditions. Within this context, objective present study was to evaluate morphological physiological changes ten genotypes three irrigation treatments: normal irrigation, followed by recovery terminal drought stress. The experiments were conducted at UNSA Experimental Farm Majes, Arequipa, Peru. A series morphological, physiological, remote measurements taken, including plant height, dry biomass, leaf area, stomatal density, relative water content, selection indices, chlorophyll content via SPAD, multispectral imaging, reflectance spectroradiometry. results indicated there numerous conditions stress; yield variables total height reduced 69.86%, 62.69%, 27.16%, respectively; stress with these less pronounced reduction 21.10%, 27.43%, 17.87%, respectively, indicating some are adapted or tolerant both water-limiting (Accession 50, Salcedo INIA Accession 49). Remote sensing tools such as drones spectroradiometry generated reliable, rapid, precise data for monitoring phenotyping optimum timing collecting predicting impacts from 79–89 days after sowing (NDRE CREDG r Pearson 0.85).

Language: Английский

Citations

0
MOISTURE CONTENT DETECTION OF SOYBEAN GRAINS BASED ON HYPERSPECTRAL IMAGING DOI Open Access

Zhichang CHANG,

Man Chen, Gong Cheng

et al.

INMATEH Agricultural Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 562 - 570

Published: Dec. 18, 2024

Using hyperspectral imaging technology for rapid, non-destructive detection of soybean grain moisture content provides technical support high-quality harvesting. A total 90 samples grains from different varieties were collected, with images acquired in the wavelength range 900–1700 nm. The each sample was determined using direct drying method as specified GB 5009.3-2016. divided into a calibration set and prediction based on 4:1 ratio partitioning Joint X-Y Distance. Eight preprocessing methods applied to raw spectral data, including baseline correction, moving average, Savitzky-Golay filtering, normalization, standard normal variate transformation, multiple scatter first derivative, deconvolution. Feature wavelengths then extracted successive projections algorithm competitive adaptive reweighted sampling algorithm. Finally, partial least squares regression model predicting developed these feature wavelengths. results show that correlation coefficient root mean square error optimal 0.92 0.2371, respectively. spectrum inversion can precisely rapidly predict non-destructively, thereby determining timing mechanical harvesting enhancing quality harvesting, storage, processing.

Language: Английский

Citations

0