Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery
Accurate and efficient estimation of biochemical traits, including leaf index area (LAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC), is crucial for crop growth monitoring in agricultural management. Recent advancements in unmanned aerial vehicle (UAV) multispectral remote s...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375524001862 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846124922502381568 |
|---|---|
| author | Changsai Zhang Yuan Yi Lijuan Wang Shuo Chen Pei Li Shuxia Zhang Yong Xue |
| author_facet | Changsai Zhang Yuan Yi Lijuan Wang Shuo Chen Pei Li Shuxia Zhang Yong Xue |
| author_sort | Changsai Zhang |
| collection | DOAJ |
| description | Accurate and efficient estimation of biochemical traits, including leaf index area (LAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC), is crucial for crop growth monitoring in agricultural management. Recent advancements in unmanned aerial vehicle (UAV) multispectral remote sensing have enabled fast and cost-effective measurements of these traits. However, traditional statistical regression models trained on specific datasets lack scalability and transferability across practical field conditions without retraining. This study proposed an efficient physics-informed transfer learning model (PITL) for winter wheat biochemical traits estimation from UAV multispectral data. The PITL integrates the strengths of physical radiative transfer simulations and deep neural network architectures through transfer learning to improve the estimation of biochemical traits from UAV multispectral data. The PITL was tested with convolutional neural network (CNN), deep neural network (DNN), and long short-term memory (LSTM) architectures. Results indicated that PITLDNN had better accuracy than PITLCNN and PITLLSTM models in predicting LAI (R2=0.94, RMSE = 0.32 m2/m2), LCC (R2=0.81, RMSE = 5.20 μg/cm2) and CCC (R2=0.928, RMSE = 0.2 g/m2). Moreover, PITLDNN demonstrated higher capability in computational efficiency, making it suitable for processing large volumes of UAV multispectral data in crop growth monitoring applications. Furthermore, PITL's integration of radiative transfer knowledge with labeled field data yielded higher predictive accuracy compared to physically-based inversion model, pure data-driven deep neural network approaches, and hybrid models. This study highlighted the performance of PITLDNN in accurately and efficiently quantifing biochemical traits from UAV multispectral data, thereby providing timely and accurate information for guiding crop growth monitoring applications. |
| format | Article |
| id | doaj-art-064c48e3ef8a40919d895537e3106420 |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-064c48e3ef8a40919d895537e31064202024-12-13T11:07:56ZengElsevierSmart Agricultural Technology2772-37552024-12-019100581Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imageryChangsai Zhang0Yuan Yi1Lijuan Wang2Shuo Chen3Pei Li4Shuxia Zhang5Yong Xue6School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaJiangsu Xuhuai Regional Institute of Agricultural Science, Xuzhou 221131, ChinaSchool of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Mathematics and Statistics, Jiangsu Normal University, Xuzhou 221116, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China; School of Computing and Mathematics, College of Science and Engineering, University of Derby, Kedleston Road, Derby DE22 1GB, UK; Corresponding author.Accurate and efficient estimation of biochemical traits, including leaf index area (LAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC), is crucial for crop growth monitoring in agricultural management. Recent advancements in unmanned aerial vehicle (UAV) multispectral remote sensing have enabled fast and cost-effective measurements of these traits. However, traditional statistical regression models trained on specific datasets lack scalability and transferability across practical field conditions without retraining. This study proposed an efficient physics-informed transfer learning model (PITL) for winter wheat biochemical traits estimation from UAV multispectral data. The PITL integrates the strengths of physical radiative transfer simulations and deep neural network architectures through transfer learning to improve the estimation of biochemical traits from UAV multispectral data. The PITL was tested with convolutional neural network (CNN), deep neural network (DNN), and long short-term memory (LSTM) architectures. Results indicated that PITLDNN had better accuracy than PITLCNN and PITLLSTM models in predicting LAI (R2=0.94, RMSE = 0.32 m2/m2), LCC (R2=0.81, RMSE = 5.20 μg/cm2) and CCC (R2=0.928, RMSE = 0.2 g/m2). Moreover, PITLDNN demonstrated higher capability in computational efficiency, making it suitable for processing large volumes of UAV multispectral data in crop growth monitoring applications. Furthermore, PITL's integration of radiative transfer knowledge with labeled field data yielded higher predictive accuracy compared to physically-based inversion model, pure data-driven deep neural network approaches, and hybrid models. This study highlighted the performance of PITLDNN in accurately and efficiently quantifing biochemical traits from UAV multispectral data, thereby providing timely and accurate information for guiding crop growth monitoring applications.http://www.sciencedirect.com/science/article/pii/S2772375524001862Radiative transfer modelTransfer learningUAV multispectralLeaf area indexPlant phenotyping |
| spellingShingle | Changsai Zhang Yuan Yi Lijuan Wang Shuo Chen Pei Li Shuxia Zhang Yong Xue Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery Smart Agricultural Technology Radiative transfer model Transfer learning UAV multispectral Leaf area index Plant phenotyping |
| title | Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery |
| title_full | Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery |
| title_fullStr | Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery |
| title_full_unstemmed | Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery |
| title_short | Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery |
| title_sort | efficient physics informed transfer learning to quantify biochemical traits of winter wheat from uav multispectral imagery |
| topic | Radiative transfer model Transfer learning UAV multispectral Leaf area index Plant phenotyping |
| url | http://www.sciencedirect.com/science/article/pii/S2772375524001862 |
| work_keys_str_mv | AT changsaizhang efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery AT yuanyi efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery AT lijuanwang efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery AT shuochen efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery AT peili efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery AT shuxiazhang efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery AT yongxue efficientphysicsinformedtransferlearningtoquantifybiochemicaltraitsofwinterwheatfromuavmultispectralimagery |