Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content
Non-invasive crop analysis through image-based methods holds great promise for applications in plant research, yet accurate and robust trait inference from images remains a critical challenge. Our study investigates the potential of AI model ensembling and hybridization approaches to infer sorghum c...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Journal Article |
| Language: | Inglés |
| Published: |
MDPI
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/158402 |
| _version_ | 1855537822398676992 |
|---|---|
| author | Hammouch, Hajar Patil, Suchitra Choudhary, Sunita El-Yacoubi, A. Mounim Masner, Jan Kholová, Jana Anbazhagan, Krithika Vanek, Jirí Qin, Huafeng Stoces, Michal Berbia, Hassan Jagarlapudi, Adinarayana Chandramouli, Magesh Mamidi, Srinivas Prasad, K.V.S.V. Baddam, Rekha |
| author_browse | Anbazhagan, Krithika Baddam, Rekha Berbia, Hassan Chandramouli, Magesh Choudhary, Sunita El-Yacoubi, A. Mounim Hammouch, Hajar Jagarlapudi, Adinarayana Kholová, Jana Mamidi, Srinivas Masner, Jan Patil, Suchitra Prasad, K.V.S.V. Qin, Huafeng Stoces, Michal Vanek, Jirí |
| author_facet | Hammouch, Hajar Patil, Suchitra Choudhary, Sunita El-Yacoubi, A. Mounim Masner, Jan Kholová, Jana Anbazhagan, Krithika Vanek, Jirí Qin, Huafeng Stoces, Michal Berbia, Hassan Jagarlapudi, Adinarayana Chandramouli, Magesh Mamidi, Srinivas Prasad, K.V.S.V. Baddam, Rekha |
| author_sort | Hammouch, Hajar |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Non-invasive crop analysis through image-based methods holds great promise for applications in plant research, yet accurate and robust trait inference from images remains a critical challenge. Our study investigates the potential of AI model ensembling and hybridization approaches to infer sorghum crop traits from RGB images generated via unmanned aerial vehicle (UAV). In our study, we cultivated 21 sorghum cultivars in two independent seasons (2021 and 2022) with a gradient of fertilizer and water inputs. We collected 470 ground-truth N measurements and captured corresponding RGB images with a drone-mounted camera. We computed five RGB vegetation indices, employed several ML models such as MLR, MLP, and various CNN architectures (season 2021), and compared their prediction accuracy for N-inference on the independent test set (season 2022). We assessed strategies that leveraged both deep and handcrafted features, namely hybridized and ensembled AI architectures. Our approach considered two different datasets collected during the two seasons (2021 and 2022), with the training set from the first season only. This allowed for testing of the models’ robustness, particularly their sensitivity to concept drifts, in the independent season (2022), which is fundamental for practical agriculture applications. Our findings underscore the superiority of hybrid and ensembled AI algorithms in these experiments. The MLP + CNN-VGG16 combination achieved the best accuracy (R2 = 0.733, MAE = 0.264 N% on an independent dataset). This study emphasized that carefully crafted AI-based models applied to RGB images can achieve robust trait prediction with accuracies comparable to the similar phenotyping tasks using more complex (multi- and hyper-spectral) sensors presented in the current literature. |
| format | Journal Article |
| id | CGSpace158402 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | MDPI |
| publisherStr | MDPI |
| record_format | dspace |
| spelling | CGSpace1584022025-12-08T10:29:22Z Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content Hammouch, Hajar Patil, Suchitra Choudhary, Sunita El-Yacoubi, A. Mounim Masner, Jan Kholová, Jana Anbazhagan, Krithika Vanek, Jirí Qin, Huafeng Stoces, Michal Berbia, Hassan Jagarlapudi, Adinarayana Chandramouli, Magesh Mamidi, Srinivas Prasad, K.V.S.V. Baddam, Rekha artificial intelligence machine learning crops nitrogen phenotyping Non-invasive crop analysis through image-based methods holds great promise for applications in plant research, yet accurate and robust trait inference from images remains a critical challenge. Our study investigates the potential of AI model ensembling and hybridization approaches to infer sorghum crop traits from RGB images generated via unmanned aerial vehicle (UAV). In our study, we cultivated 21 sorghum cultivars in two independent seasons (2021 and 2022) with a gradient of fertilizer and water inputs. We collected 470 ground-truth N measurements and captured corresponding RGB images with a drone-mounted camera. We computed five RGB vegetation indices, employed several ML models such as MLR, MLP, and various CNN architectures (season 2021), and compared their prediction accuracy for N-inference on the independent test set (season 2022). We assessed strategies that leveraged both deep and handcrafted features, namely hybridized and ensembled AI architectures. Our approach considered two different datasets collected during the two seasons (2021 and 2022), with the training set from the first season only. This allowed for testing of the models’ robustness, particularly their sensitivity to concept drifts, in the independent season (2022), which is fundamental for practical agriculture applications. Our findings underscore the superiority of hybrid and ensembled AI algorithms in these experiments. The MLP + CNN-VGG16 combination achieved the best accuracy (R2 = 0.733, MAE = 0.264 N% on an independent dataset). This study emphasized that carefully crafted AI-based models applied to RGB images can achieve robust trait prediction with accuracies comparable to the similar phenotyping tasks using more complex (multi- and hyper-spectral) sensors presented in the current literature. 2024-09-26 2024-11-01T14:21:53Z 2024-11-01T14:21:53Z Journal Article https://hdl.handle.net/10568/158402 en Open Access MDPI Hammouch, H., Patil, S., Choudhary, S., El-Yacoubi, M. A., Masner, J., Kholová, J., Anbazhagan, K., Vanek, J., Qin, H., Stoces, M., Berbia, H., Jagarlapudi, A., Chandramouli, M., Mamidi, S., Prasad, K. V. S. V., & Baddam, R. (2024). Hybrid-AI and model ensembling to exploit UAV-based RGB imagery: An evaluation of sorghum crops nitrogen content. Agriculture, 14(Nitrogen Content) |
| spellingShingle | artificial intelligence machine learning crops nitrogen phenotyping Hammouch, Hajar Patil, Suchitra Choudhary, Sunita El-Yacoubi, A. Mounim Masner, Jan Kholová, Jana Anbazhagan, Krithika Vanek, Jirí Qin, Huafeng Stoces, Michal Berbia, Hassan Jagarlapudi, Adinarayana Chandramouli, Magesh Mamidi, Srinivas Prasad, K.V.S.V. Baddam, Rekha Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content |
| title | Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content |
| title_full | Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content |
| title_fullStr | Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content |
| title_full_unstemmed | Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content |
| title_short | Hybrid-AI and Model Ensembling to Exploit UAV-Based RGB Imagery: An Evaluation of Sorghum Crop’s Nitrogen Content |
| title_sort | hybrid ai and model ensembling to exploit uav based rgb imagery an evaluation of sorghum crop s nitrogen content |
| topic | artificial intelligence machine learning crops nitrogen phenotyping |
| url | https://hdl.handle.net/10568/158402 |
| work_keys_str_mv | AT hammouchhajar hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT patilsuchitra hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT choudharysunita hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT elyacoubiamounim hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT masnerjan hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT kholovajana hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT anbazhagankrithika hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT vanekjiri hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT qinhuafeng hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT stocesmichal hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT berbiahassan hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT jagarlapudiadinarayana hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT chandramoulimagesh hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT mamidisrinivas hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT prasadkvsv hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent AT baddamrekha hybridaiandmodelensemblingtoexploituavbasedrgbimageryanevaluationofsorghumcropsnitrogencontent |