Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation
Spectral analysis is a widely used method for monitoring photosynthetic capacity. However, vegetation indices-based linear regression exhibits insufficient utilization of spectral information, while full spectra-based traditional machine learning has limited representational capacity (partial least...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1499875/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543768119967744 |
|---|---|
| author | Xianzhi Deng Xiaolong Hu Liangsheng Shi Chenye Su Jinmin Li Shuai Du Shenji Li |
| author_facet | Xianzhi Deng Xiaolong Hu Liangsheng Shi Chenye Su Jinmin Li Shuai Du Shenji Li |
| author_sort | Xianzhi Deng |
| collection | DOAJ |
| description | Spectral analysis is a widely used method for monitoring photosynthetic capacity. However, vegetation indices-based linear regression exhibits insufficient utilization of spectral information, while full spectra-based traditional machine learning has limited representational capacity (partial least squares regression) or uninterpretable (convolution). In this study, we proposed a deep learning model with enhanced interpretability based on attention and vegetation indices calculation for global spectral feature mining to accurately estimate photosynthetic capacity. We explored the ability of the model to uncover the optimal vegetation indices form and illustrated its advantage over traditional methods. Furthermore, we verified that power compression was an effective method for spectral processing. Our results demonstrated that the new model outperformed traditional models, with an increase in the coefficient of determination (R2) of 0.01-0.43 and a decrease in root mean square error (RMSE) of 1.58-12.48 μmol m-2 s-1. The best performance of our model in R2 was 0.86 and 0.81 for maximum carboxylation rate (Vcmax) and maximum electron transport rate (Jmax), respectively. The photosynthesis-sensitive spectral bands identified by our model were predominantly in the visible range. The most sensitive vegetation indices form discovered by our model was Reflectancenear−infrared+Reflectancegreen/blueReflectancenear−infrared×Reflectancered. Our model provides a new framework for interpreting spectral information and accurately estimating photosynthetic capacity. |
| format | Article |
| id | doaj-art-8220327886744853aefa25f341952907 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-8220327886744853aefa25f3419529072025-01-13T06:10:46ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-01-011510.3389/fpls.2024.14998751499875Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimationXianzhi Deng0Xiaolong Hu1Liangsheng Shi2Chenye Su3Jinmin Li4Shuai Du5Shenji Li6State Key Laboratory of Water Resources Engineering And Management, Wuhan University, Wuhan, Hubei, ChinaState Key Laboratory of Water Resources Engineering And Management, Wuhan University, Wuhan, Hubei, ChinaState Key Laboratory of Water Resources Engineering And Management, Wuhan University, Wuhan, Hubei, ChinaState Key Laboratory of Water Resources Engineering And Management, Wuhan University, Wuhan, Hubei, ChinaState Key Laboratory of Water Resources Engineering And Management, Wuhan University, Wuhan, Hubei, ChinaState Key Laboratory of Water Resources Engineering And Management, Wuhan University, Wuhan, Hubei, ChinaUrban Operation Management Center of Hengsha Township, Shanghai, ChinaSpectral analysis is a widely used method for monitoring photosynthetic capacity. However, vegetation indices-based linear regression exhibits insufficient utilization of spectral information, while full spectra-based traditional machine learning has limited representational capacity (partial least squares regression) or uninterpretable (convolution). In this study, we proposed a deep learning model with enhanced interpretability based on attention and vegetation indices calculation for global spectral feature mining to accurately estimate photosynthetic capacity. We explored the ability of the model to uncover the optimal vegetation indices form and illustrated its advantage over traditional methods. Furthermore, we verified that power compression was an effective method for spectral processing. Our results demonstrated that the new model outperformed traditional models, with an increase in the coefficient of determination (R2) of 0.01-0.43 and a decrease in root mean square error (RMSE) of 1.58-12.48 μmol m-2 s-1. The best performance of our model in R2 was 0.86 and 0.81 for maximum carboxylation rate (Vcmax) and maximum electron transport rate (Jmax), respectively. The photosynthesis-sensitive spectral bands identified by our model were predominantly in the visible range. The most sensitive vegetation indices form discovered by our model was Reflectancenear−infrared+Reflectancegreen/blueReflectancenear−infrared×Reflectancered. Our model provides a new framework for interpreting spectral information and accurately estimating photosynthetic capacity.https://www.frontiersin.org/articles/10.3389/fpls.2024.1499875/fullhyperspectral dataspectral sensitive bandvegetation indexphotosynthetic capacitydeep learningpower compression |
| spellingShingle | Xianzhi Deng Xiaolong Hu Liangsheng Shi Chenye Su Jinmin Li Shuai Du Shenji Li Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation Frontiers in Plant Science hyperspectral data spectral sensitive band vegetation index photosynthetic capacity deep learning power compression |
| title | Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation |
| title_full | Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation |
| title_fullStr | Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation |
| title_full_unstemmed | Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation |
| title_short | Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation |
| title_sort | deep learning enabled exploration of global spectral features for photosynthetic capacity estimation |
| topic | hyperspectral data spectral sensitive band vegetation index photosynthetic capacity deep learning power compression |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1499875/full |
| work_keys_str_mv | AT xianzhideng deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation AT xiaolonghu deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation AT liangshengshi deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation AT chenyesu deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation AT jinminli deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation AT shuaidu deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation AT shenjili deeplearningenabledexplorationofglobalspectralfeaturesforphotosyntheticcapacityestimation |