Multitask Learning of Alfalfa Nutritive Value from UAV-Based Hyperspectral Images. Feng, L., Zhang, Z., Ma, Y., Sun, Y., Du, Q., Williams, P., Drewry, J., & Luck, B. IEEE Geoscience and Remote Sensing Letters, Institute of Electrical and Electronics Engineers Inc., 2022. ![Multitask Learning of Alfalfa Nutritive Value from UAV-Based Hyperspectral Images [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.
@article{
title = {Multitask Learning of Alfalfa Nutritive Value from UAV-Based Hyperspectral Images},
type = {article},
year = {2022},
keywords = {Alfalfa,hyperspectral imagery,multitask learning,nutritive value,unmanned aerial vehicle (UAV)},
volume = {19},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
id = {e63eab8d-285d-3700-a469-a48b17041be1},
created = {2023-11-08T09:41:21.722Z},
accessed = {2023-11-08},
file_attached = {true},
profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2023-11-08T09:41:30.654Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
folder_uuids = {bc66e353-ef41-46d4-8108-778d5481c126,bd3c6f2e-3514-47cf-bc42-12db8b9abe45},
private_publication = {false},
abstract = {Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.},
bibtype = {article},
author = {Feng, Luwei and Zhang, Zhou and Ma, Yuchi and Sun, Yazhou and Du, Qingyun and Williams, Parker and Drewry, Jessica and Luck, Brian},
doi = {10.1109/LGRS.2021.3079317},
journal = {IEEE Geoscience and Remote Sensing Letters}
}
Downloads: 0
{"_id":"Zu2phkXxwjCes7wCS","bibbaseid":"feng-zhang-ma-sun-du-williams-drewry-luck-multitasklearningofalfalfanutritivevaluefromuavbasedhyperspectralimages-2022","author_short":["Feng, L.","Zhang, Z.","Ma, Y.","Sun, Y.","Du, Q.","Williams, P.","Drewry, J.","Luck, B."],"bibdata":{"title":"Multitask Learning of Alfalfa Nutritive Value from UAV-Based Hyperspectral Images","type":"article","year":"2022","keywords":"Alfalfa,hyperspectral imagery,multitask learning,nutritive value,unmanned aerial vehicle (UAV)","volume":"19","publisher":"Institute of Electrical and Electronics Engineers Inc.","id":"e63eab8d-285d-3700-a469-a48b17041be1","created":"2023-11-08T09:41:21.722Z","accessed":"2023-11-08","file_attached":"true","profile_id":"f1f70cad-e32d-3de2-a3c0-be1736cb88be","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2023-11-08T09:41:30.654Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"folder_uuids":"bc66e353-ef41-46d4-8108-778d5481c126,bd3c6f2e-3514-47cf-bc42-12db8b9abe45","private_publication":false,"abstract":"Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.","bibtype":"article","author":"Feng, Luwei and Zhang, Zhou and Ma, Yuchi and Sun, Yazhou and Du, Qingyun and Williams, Parker and Drewry, Jessica and Luck, Brian","doi":"10.1109/LGRS.2021.3079317","journal":"IEEE Geoscience and Remote Sensing Letters","bibtex":"@article{\n title = {Multitask Learning of Alfalfa Nutritive Value from UAV-Based Hyperspectral Images},\n type = {article},\n year = {2022},\n keywords = {Alfalfa,hyperspectral imagery,multitask learning,nutritive value,unmanned aerial vehicle (UAV)},\n volume = {19},\n publisher = {Institute of Electrical and Electronics Engineers Inc.},\n id = {e63eab8d-285d-3700-a469-a48b17041be1},\n created = {2023-11-08T09:41:21.722Z},\n accessed = {2023-11-08},\n file_attached = {true},\n profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2023-11-08T09:41:30.654Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n folder_uuids = {bc66e353-ef41-46d4-8108-778d5481c126,bd3c6f2e-3514-47cf-bc42-12db8b9abe45},\n private_publication = {false},\n abstract = {Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.},\n bibtype = {article},\n author = {Feng, Luwei and Zhang, Zhou and Ma, Yuchi and Sun, Yazhou and Du, Qingyun and Williams, Parker and Drewry, Jessica and Luck, Brian},\n doi = {10.1109/LGRS.2021.3079317},\n journal = {IEEE Geoscience and Remote Sensing Letters}\n}","author_short":["Feng, L.","Zhang, Z.","Ma, Y.","Sun, Y.","Du, Q.","Williams, P.","Drewry, J.","Luck, B."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/38d953eb-a60e-dbcf-3fd6-6dff52ca7a42/full_text.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"feng-zhang-ma-sun-du-williams-drewry-luck-multitasklearningofalfalfanutritivevaluefromuavbasedhyperspectralimages-2022","role":"author","keyword":["Alfalfa","hyperspectral imagery","multitask learning","nutritive value","unmanned aerial vehicle (UAV)"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":["alfalfa","hyperspectral imagery","multitask learning","nutritive value","unmanned aerial vehicle (uav)"],"search_terms":["multitask","learning","alfalfa","nutritive","value","uav","based","hyperspectral","images","feng","zhang","ma","sun","du","williams","drewry","luck"],"title":"Multitask Learning of Alfalfa Nutritive Value from UAV-Based Hyperspectral Images","year":2022}