1
|
Liao S, Wu Y, Hu X, Weng S, Hu Y, Zheng L, Lei Y, Tang L, Wang J, Wang H, Qiu M. Detection of apple fruit damages through Raman spectroscopy with cascade forest. Spectrochim Acta A Mol Biomol Spectrosc 2023; 296:122668. [PMID: 37001262 DOI: 10.1016/j.saa.2023.122668] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/01/2022] [Revised: 03/16/2023] [Accepted: 03/23/2023] [Indexed: 06/19/2023]
Abstract
Apple fruit damages seriously cause product and economic losses, infringe consumer rights and interests, and have harmful effects on human and livestock health. In this study, Raman spectroscopy (RS) and cascade forest (CForest) were adopted to determine apple fruit damages. First, the RS spectra of healthy, bruised, Rhizopus-infected, and Botrytis-infected apples were measured. Spectral changes and band attribution were analyzed. Different modeling methods were combined with various pre-processing and dimension reduction methods to construct recognition models. Among all models, CForest constructed with full spectra processed by Savitsky-Golay smoothing obtained the best performance with accuracies of 100%, 91.96%, and 92.80% in the training, validation, and test sets (ACCTE). And the modeling time is reduced to 1/3 of the full-spectra model with a similar ACCTE of 91.56% after principal component analysis. Overall, RS and CForest provided a non-destructive, rapid, and accurate identification of apple fruit damages and could be used in disease recognition and safety assurance of other fruits.
Collapse
Affiliation(s)
- Suyin Liao
- School of Electrical Engineering and Automation, Anhui University, 111 Jiulong Road, Hefei, China
| | - Yehang Wu
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Xujin Hu
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Shizhuang Weng
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Yimin Hu
- Hefei Institutes of Physical Science, Chinese Academy of Sciences, 350 Shushanhu Road, Hefei 230031, China
| | - Ling Zheng
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Yu Lei
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Le Tang
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Jinghong Wang
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China
| | - Haitao Wang
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, 111 Jiulong Road, Hefei, China.
| | - Mengqing Qiu
- Hefei Institutes of Physical Science, Chinese Academy of Sciences, 350 Shushanhu Road, Hefei 230031, China.
| |
Collapse
|
2
|
Abstract
Birds active in apple orchards in south-eastern Australia can contribute positively (e.g., control crop pests) or negatively (e.g., crop damage) to crop yields. Our study is the first to identify net outcomes of these activities, using six apple orchards, varying in management intensity, in south-eastern Australia as a study system. We also conducted a predation experiment using real and artificial codling moth (Cydia pomonella) larvae (a major pest in apple crops). We found that: (1) excluding birds from branches of apple trees resulted in an average of 12.8% more apples damaged by insects; (2) bird damage to apples was low (1.9% of apples); and (3) when trading off the potential benefits (biological control) with costs (bird damage to apples), birds provided an overall net benefit to orchard growers. We found that predation of real codling moth larvae was higher than for plasticine larvae, suggesting that plasticine prey models are not useful for inferring actual predation levels. Our study shows how complex ecological interactions between birds and invertebrates affect crop yield in apples, and provides practical strategies for improving the sustainability of orchard systems.
Collapse
Affiliation(s)
- Rebecca K Peisley
- School of Environmental Sciences, Charles Sturt University, Albury, New South Wales, Australia; Institute for Land, Water and Society, Charles Sturt University, Albury, New South Wales, Australia
| | - Manu E Saunders
- Institute for Land, Water and Society, Charles Sturt University , Albury , New South Wales , Australia
| | - Gary W Luck
- Institute for Land, Water and Society, Charles Sturt University , Albury , New South Wales , Australia
| |
Collapse
|