Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes
The fruit weight is an important guideline for breeders and farmers to increase marketable productions, although conventionally it requires destructive measurements. The combination of image-based phenotyping (IBP) approaches with multivariate analysis has the potential to further improve the line s...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/2/338 |
| _version_ | 1797299153345183744 |
|---|---|
| author | Muh Farid Muhammad Fuad Anshori Riccardo Rossi Feranita Haring Katriani Mantja Andi Dirpan Siti Halimah Larekeng Marlina Mustafa Adnan Adnan Siti Antara Maedhani Tahara Nirwansyah Amier M. Alfan Ikhlasul Amal Andi Isti Sakinah |
| author_facet | Muh Farid Muhammad Fuad Anshori Riccardo Rossi Feranita Haring Katriani Mantja Andi Dirpan Siti Halimah Larekeng Marlina Mustafa Adnan Adnan Siti Antara Maedhani Tahara Nirwansyah Amier M. Alfan Ikhlasul Amal Andi Isti Sakinah |
| author_sort | Muh Farid |
| collection | DOAJ |
| description | The fruit weight is an important guideline for breeders and farmers to increase marketable productions, although conventionally it requires destructive measurements. The combination of image-based phenotyping (IBP) approaches with multivariate analysis has the potential to further improve the line selection based on economical trait, like fruit weight. Therefore, this study aimed to evaluate the potential of image-derived phenotypic traits as proxies for individual fruits weight estimation using multivariate analysis. To this end, an IBP experimentation was carried out on five populations of low-land tomato. Specifically, the Mawar (M; 10 plants), Karina (K; 10 plants), and F2 generation cross (100 lines) samples were used to extract training data for the proposed estimation model, while data derived from M/K//K backcross population (35 lines) and F5 population (50 lines) plants were used for destructive and non-destructive validation, respectively. Several phenotypic traits were extracted from each imaged tomato fruit, including the slice and whole fruit area (FA), round (FR), width (FW), height (FH), and red (RI), green (GI) and blue index (BI), and used as inputs of a genetic- and multivariate-based method for non-destructively predicting its fresh weight (FFW). Based on this research, the whole FA has the greatest potential in predicting tomato FFW regardless to the analyzed cultivar. The relevant model exhibited high power in predicting FFW, as explained by <i>R</i><sup>2</sup>-adjusted, <i>R</i><sup>2</sup>-deviation and <i>RMSE</i> statistics obtained for calibration (81.30%, 0.20%, 3.14 g, respectively), destructive (69.80%, 0.90%, 4.46 g, respectively) and non-destructive validation (80.20%, 0.50%, 2.12 g, respectively). These results suggest the potential applicability of the proposed IBP approach in guiding field robots or machines for precision harvesting based on non-destructive estimations of fruit weight from image-derived area, thereby enhancing agricultural practices in lowland tomato cultivation. |
| first_indexed | 2024-03-07T22:45:29Z |
| format | Article |
| id | doaj.art-5e5894fba73a41af80f5494de148c644 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-07T22:45:29Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-5e5894fba73a41af80f5494de148c6442024-02-23T15:04:14ZengMDPI AGAgronomy2073-43952024-02-0114233810.3390/agronomy14020338Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland TomatoesMuh Farid0Muhammad Fuad Anshori1Riccardo Rossi2Feranita Haring3Katriani Mantja4Andi Dirpan5Siti Halimah Larekeng6Marlina Mustafa7Adnan Adnan8Siti Antara Maedhani Tahara9Nirwansyah Amier10M. Alfan Ikhlasul Amal11Andi Isti Sakinah12Department of Agronomy, Faculty of Agriculture, Hasanuddin University, Makassar 90245, IndonesiaDepartment of Agronomy, Faculty of Agriculture, Hasanuddin University, Makassar 90245, IndonesiaDepartment of Agriculture, Food, Environment and Forestry (DAGRI), University of Florence (UNIFI), Piazzale delle Cascine 18, 50144 Florence, ItalyDepartment of Agronomy, Faculty of Agriculture, Hasanuddin University, Makassar 90245, IndonesiaDepartment of Agronomy, Faculty of Agriculture, Hasanuddin University, Makassar 90245, IndonesiaDepartment of Agricultural Technology, Faculty of Agriculture, Hasanuddin University, Makassar 90245, IndonesiaFaculty of Vocational, Hasanuddin University, Makassar 90245, IndonesiaAgrotechnology Study Program, Faculty of Agriculture, Universitas Sembilanbelas November, Kolaka 93514, IndonesiaDepartment of Biology, State University of Makassar, Makassar 90222, IndonesiaAgrotechnology Study Program, Faculty of Agriculture, Hasanuddin University, Makassar 90245, IndonesiaAgrotechnology Study Program, Graduate School, Hasanuddin University, Makassar 90245, IndonesiaAgrotechnology Study Program, Graduate School, Hasanuddin University, Makassar 90245, IndonesiaAgricultural Science Study Program, Graduate School, Hasanuddin University, Makassar 90245, IndonesiaThe fruit weight is an important guideline for breeders and farmers to increase marketable productions, although conventionally it requires destructive measurements. The combination of image-based phenotyping (IBP) approaches with multivariate analysis has the potential to further improve the line selection based on economical trait, like fruit weight. Therefore, this study aimed to evaluate the potential of image-derived phenotypic traits as proxies for individual fruits weight estimation using multivariate analysis. To this end, an IBP experimentation was carried out on five populations of low-land tomato. Specifically, the Mawar (M; 10 plants), Karina (K; 10 plants), and F2 generation cross (100 lines) samples were used to extract training data for the proposed estimation model, while data derived from M/K//K backcross population (35 lines) and F5 population (50 lines) plants were used for destructive and non-destructive validation, respectively. Several phenotypic traits were extracted from each imaged tomato fruit, including the slice and whole fruit area (FA), round (FR), width (FW), height (FH), and red (RI), green (GI) and blue index (BI), and used as inputs of a genetic- and multivariate-based method for non-destructively predicting its fresh weight (FFW). Based on this research, the whole FA has the greatest potential in predicting tomato FFW regardless to the analyzed cultivar. The relevant model exhibited high power in predicting FFW, as explained by <i>R</i><sup>2</sup>-adjusted, <i>R</i><sup>2</sup>-deviation and <i>RMSE</i> statistics obtained for calibration (81.30%, 0.20%, 3.14 g, respectively), destructive (69.80%, 0.90%, 4.46 g, respectively) and non-destructive validation (80.20%, 0.50%, 2.12 g, respectively). These results suggest the potential applicability of the proposed IBP approach in guiding field robots or machines for precision harvesting based on non-destructive estimations of fruit weight from image-derived area, thereby enhancing agricultural practices in lowland tomato cultivation.https://www.mdpi.com/2073-4395/14/2/338digital imagingfruit predictionnon-destructive validationregression analysis<i>Solanum lycopersicum</i> |
| spellingShingle | Muh Farid Muhammad Fuad Anshori Riccardo Rossi Feranita Haring Katriani Mantja Andi Dirpan Siti Halimah Larekeng Marlina Mustafa Adnan Adnan Siti Antara Maedhani Tahara Nirwansyah Amier M. Alfan Ikhlasul Amal Andi Isti Sakinah Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes Agronomy digital imaging fruit prediction non-destructive validation regression analysis <i>Solanum lycopersicum</i> |
| title | Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes |
| title_full | Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes |
| title_fullStr | Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes |
| title_full_unstemmed | Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes |
| title_short | Combining Image-Based Phenotyping and Multivariate Analysis to Estimate Fruit Fresh Weight in Segregation Lines of Lowland Tomatoes |
| title_sort | combining image based phenotyping and multivariate analysis to estimate fruit fresh weight in segregation lines of lowland tomatoes |
| topic | digital imaging fruit prediction non-destructive validation regression analysis <i>Solanum lycopersicum</i> |
| url | https://www.mdpi.com/2073-4395/14/2/338 |
| work_keys_str_mv | AT muhfarid combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT muhammadfuadanshori combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT riccardorossi combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT feranitaharing combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT katrianimantja combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT andidirpan combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT sitihalimahlarekeng combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT marlinamustafa combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT adnanadnan combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT sitiantaramaedhanitahara combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT nirwansyahamier combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT malfanikhlasulamal combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes AT andiistisakinah combiningimagebasedphenotypingandmultivariateanalysistoestimatefruitfreshweightinsegregationlinesoflowlandtomatoes |