Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area and Experimental Design
2.2. Data Collection
2.2.1. Image Data Acquisition
2.2.2. Field Measured Data Acquisition
2.3. Data Preprocessing
2.4. Feature Extraction
2.4.1. Vegetation Index Extraction
2.4.2. Texture Feature Extraction
2.4.3. Image Coverage Features
2.5. Machine Learning Algorithms
- (1)
- All image features and leaf water content data are normalized;
- (2)
- The dataset is randomly divided into two subsets, with 50% allocated to the training set and the remaining 50% to the test set;
- (3)
- Ten-fold cross-validation is applied to the training set. By performing multiple iterations of training and validation, the variability introduced by data partitioning is minimized, allowing for a more accurate evaluation of the model’s generalization ability and a reduction in overfitting risk. Finally, the optimal model is selected, and its performance in estimating leaf water content is assessed using the test set.
2.5.1. MLR Algorithm
2.5.2. RR Algorithm
2.5.3. RFR Algorithm
2.5.4. Particle Swarm Optimization Algorithm (PSO)
2.6. Evaluation Metrics
3. Results
3.1. Descriptive Statistics of Maize LWC
3.2. Correlation Analysis of Features
3.3. Explained Variance of Features and Lasso Selection
3.4. Estimation Results of Maize LWC Across Various Growth Stages
3.5. Comparison of Estimation Results Using Different Regression Models
4. Discussion
4.1. Comparison of Model Performance for LWC Estimation
4.2. Impact of Feature Selection and Comparison of Methods
4.3. Comparison of ResNet50 Feature Optimization in LWC Models Across Different Growth Stages
4.4. Comparative Analysis of Optimization Algorithms
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Wang, R.M.; He, N.; Li, S.G.; Li, X.; Li, M.X. Spatial variation and mechanisms of leaf water content in grassland plants at the biome scale: Evidence from three comparative transects. Sci. Rep. 2021, 11, 9281. [Google Scholar] [CrossRef]
- Trifilò, P.; Abate, E.; Petruzzellis, F.; Azzarà, M.; Nardini, A. Critical water contents at leaf, stem and root level leading to irreversible drought-induced damage in two woody and one herbaceous species. Plant Cell Environ. 2023, 46, 119–132. [Google Scholar] [CrossRef]
- Song, X.Y.; Zhou, G.S.; He, Q.J. Critical Leaf Water Content for Maize Photosynthesis under Drought Stress and Its Response to Rewatering. Sustainability 2021, 13, 7218. [Google Scholar] [CrossRef]
- Yang, F.F.; Liu, T.; Wang, Q.Y.; Du, M.Z.; Yang, T.L.; Liu, D.Z.; Li, S.J.; Liu, S.P. Rapid determination of leaf water content for monitoring waterlogging in winter wheat based on hyperspectral parameters. J. Integr. Agric. 2021, 20, 2613–2626. [Google Scholar] [CrossRef]
- Li, B.; Zhang, X.; Wang, R.; Mei, Y.; Ma, J.J. Leaf water status monitoring by scattering effects at terahertz frequencies. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 2021, 245, 118932. [Google Scholar] [CrossRef]
- Rezaei, M.; Ebrahimi, E.; Naseh, S.; Mohajerpour, M. A new 1.4-GHz soil moisture sensor. Measurement 2012, 45, 1723–1728. [Google Scholar] [CrossRef]
- Deng, X.; Gu, H.N.; Yang, L.; Lyu, H.F.; Cheng, Y.G.; Pan, L.P.; Fu, Z.J.; Cui, L.Q.; Zhang, L. A method of electrical conductivity compensation in a low-cost soil moisture sensing measurement based on capacitance. Measurement 2020, 150, 107052. [Google Scholar] [CrossRef]
- Phang, S.K.; Chiang, T.; Happonen, A.; Chang, M. From Satellite to UAV-Based Remote Sensing: A Review on Precision Agriculture. IEEE Access 2023, 11, 127057–127076. [Google Scholar] [CrossRef]
- Attard, M.; Phillips, R.A.; Bowler, E.; Clarke, P.J.; Cubaynes, H.; Johnston, D.W.; Fretwell, P.T. Review of Satellite Remote Sensing and Unoccupied Aircraft Systems for Counting Wildlife on Land. Remote Sens. 2024, 16, 627. [Google Scholar] [CrossRef]
- Zhang, Z.X.; Zhu, L.X. A Review on Unmanned Aerial Vehicle Remote Sensing: Platforms, Sensors, Data Processing Methods, and Applications. Drones 2023, 7, 398. [Google Scholar] [CrossRef]
- Zhang, P.P.; Zhou, X.X.; Wang, Z.X.; Mao, W.; Li, W.X.; Yun, F.; Guo, W.S.; Tan, C.W. Using HJ-CC D image and PLS algorithm to estimate the yield of field-grown winter wheat. Sci. Rep. 2020, 10, 5173. [Google Scholar] [CrossRef]
- Jeong, S.; Ko, J.; Choi, J.; Xue, W.; Yeom, J.M. Application of an unmanned aerial system for monitoring paddy productivity using the GRAMI-rice model. Int. J. Remote Sens. 2018, 39, 2441–2462. [Google Scholar] [CrossRef]
- Liu, T.; Wang, J.L.; Wang, J.Y.; Zhao, Y.Y.; Wang, H.; Zhang, W.J.; Yao, Z.S.; Liu, S.P.; Zhong, X.C.; Sun, C.M. Research on the estimation of wheat AGB at the entire growth stage based on improved convolutional features. J. Integr. Agric. 2025, 24, 1403–1423. [Google Scholar] [CrossRef]
- Zhang, M.N.; Zhou, J.F.; Sudduth, K.A.; Kitchen, N.R. Estimation of maize yield and effects of variable-rate nitrogen application using UAV-based RGB imagery. Biosyst. Eng. 2020, 189, 24–35. [Google Scholar] [CrossRef]
- Zhang, Y.; Wu, J.B.; Wang, A.Z. Comparison of various approaches for estimating leaf water content and stomatal conductance in different plant species using hyperspectral data. Ecol. Indic. 2022, 142, 109278. [Google Scholar] [CrossRef]
- Wang, X.P.; Zhao, C.Y.; Guo, N.; Li, Y.H.; Jian, S.Q.; Yu, K. Determining the Canopy Water Stress for Spring Wheat Using Canopy Hyperspectral Reflectance Data in Loess Plateau Semiarid Regions. Spectrosc Lett. 2015, 48, 492–498. [Google Scholar] [CrossRef]
- Chen, S.B.; Chen, Y.W.; Chen, J.Y.; Zhang, Z.T.; Fu, Q.P.; Bian, J.; Cui, T.; Ma, Y.Z. Retrieval of cotton plant water content by UAV-based vegetation supply water index (VSWI). Int. J. Remote Sens. 2020, 41, 4389–4407. [Google Scholar] [CrossRef]
- Yang, N.; Zhang, Z.T.; Ding, B.B.; Wang, T.Y.; Zhang, J.R.; Liu, C.; Zhang, Q.Y.; Zuo, X.Y.; Chen, J.Y.; Cui, N.B.; et al. Evaluation of winter-wheat water stress with UAV-based multispectral data and ensemble learning method. Plant Soil 2024, 497, 647–668. [Google Scholar] [CrossRef]
- Shu, M.Y.; Dong, Q.Z.; Fei, S.P.; Yang, X.H.; Zhu, J.Y.; Meng, L.; Li, B.G.; Ma, Y.T. Improved estimation of canopy water status in maize using UAV-based digital and hyperspectral images. Comput. Electron. Agric. 2022, 197, 106982. [Google Scholar] [CrossRef]
- Cheng, T.; Rivard, B.; Sánchez-Azofeifa, A.G.; Féret, J.B.; Jacquemoud, S.; Ustin, S.L. Predicting leaf gravimetric water content from foliar reflectance across a range of plant species using continuous wavelet analysis. J. Plant Physiol. 2012, 169, 1134–1142. [Google Scholar] [CrossRef]
- Ndlovu, H.S.; Odindi, J.; Sibanda, M.; Mutanga, O.; Clulow, A.; Chimonyo, V.; Mabhaudhi, T. A Comparative Estimation of Maize Leaf Water Content Using Machine Learning Techniques and Unmanned Aerial Vehicle (UAV)-Based Proximal and Remotely Sensed Data. Remote Sens. 2021, 13, 4091. [Google Scholar] [CrossRef]
- Niu, Y.X.; Han, W.T.; Zhang, H.H.; Zhang, L.Y.; Chen, H.P. Estimating fractional vegetation cover of maize under water stress from UAV multispectral imagery using machine learning algorithms. Comput. Electron. Agric. 2021, 189, 106414. [Google Scholar] [CrossRef]
- Wang, S.; Ning, Y.F.; Shi, H.M. A new uncertain linear regression model based on equation deformation. Soft Comput. 2021, 25, 12817–12824. [Google Scholar] [CrossRef]
- Wang, J.L.; Chen, C.; Wang, J.C.; Yao, Z.S.; Wang, Y.; Zhao, Y.Y.; Wu, F.; Han, D.W.; Yang, G.S.; Liu, T. NDVI Estimation Throughout the Whole Growth Period of Multi-Crops Using RGB Images and Deep Learning. Agronomy 2025, 15, 63. [Google Scholar] [CrossRef]
- Stamford, J.D.; Vialet-Chabrand, S.; Cameron, I.; Lawson, T. Development of an accurate low cost NDVI imaging system for assessing plant health. Plant Methods 2023, 19, 9. [Google Scholar] [CrossRef]
- Xu, H.Q. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. Int. J. Remote Sens. 2006, 27, 3025–3033. [Google Scholar] [CrossRef]
- Li, F.; Miao, Y.X.; Feng, G.H.; Yuan, F.; Yue, S.C.; Gao, X.W.; Liu, Y.Q.; Liu, B.; Ustine, S.L.; Chen, X.P. Improving estimation of summer maize nitrogen status with red edge-based spectral vegetation indices. Field Crops Res. 2014, 157, 111–123. [Google Scholar] [CrossRef]
- Jiang, L.; Kogan, F.N.; Guo, W.; Tarpley, J.D.; Mitchell, K.E.; Ek, M.B.; Tian, Y.H.; Zheng, W.Z.; Zou, C.Z.; Ramsay, B.H. Real-time weekly global green vegetation fraction derived from advanced very high resolution radiometer-based NOAA operational global vegetation index (GVI) system. J. Geophys. Res. Atmos. 2010, 115, D11114. [Google Scholar] [CrossRef]
- Xue, J.R.; Su, B.F. Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications. J. Sens. 2017, 2017, 1353691. [Google Scholar] [CrossRef]
- Huete, A.; Didan, K.; Miura, T.; Rodriguez, E.P.; Gao, X.; Ferreira, L.G. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens. Environ. 2002, 83, 195–213. [Google Scholar] [CrossRef]
- Haralick, R.M.; Shanmugam, K.; Dinstein, I.H. Textural features for image classification. IEEE Trans. Syst. Man Cybern. 1973, 6, 610–621. [Google Scholar] [CrossRef]
- Gitelson, A.A.; Kaufman, Y.J.; Stark, R.; Rundquist, D. Novel algorithms for remote estimation of vegetation fraction. Remote Sens. Environ. 2002, 80, 76–87. [Google Scholar] [CrossRef]
- Broge, N.H.; Leblanc, E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sens. Environ. 2001, 76, 156–172. [Google Scholar] [CrossRef]
- Mishra, S.; Mishra, D.R. Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters. Remote Sens. Environ. 2012, 117, 394–406. [Google Scholar] [CrossRef]
- Mu, S.J.; Yang, H.F.; Li, J.L.; Chen, Y.Z.; Gang, C.C.; Zhou, W.; Ju, W.M. Spatio-temporal dynamics of vegetation coverage and its relationship with climate factors in Inner Mongolia, China. J. Geogr. Sci. 2013, 23, 231–246. [Google Scholar] [CrossRef]
- Lee, H.; Wang, J.F.; Leblon, B. Using Linear Regression, Random Forests, and Support Vector Machine with Unmanned Aerial Vehicle Multispectral Images to Predict Canopy Nitrogen Weight in Corn. Remote Sens. 2020, 12, 2071. [Google Scholar] [CrossRef]
- Yasin, A.; Amin, M.; Qasim, M.; Muse, A.H.; Soliman, A.B. More on the Ridge Parameter Estimators for the Gamma Ridge Regression Model: Simulation and Applications. Math. Probl. Eng. 2022, 2022, 6769421. [Google Scholar] [CrossRef]
- Ali, M.; Prasad, R.; Xiang, Y.; Yaseen, Z.M. Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts. J. Hydrol. 2020, 584, 124647. [Google Scholar] [CrossRef]
- Chen, W.N.; Zhang, J.; Chung, H.; Zhong, W.L.; Wu, W.G.; Shi, Y.H. A Novel Set-Based Particle Swarm Optimization Method for Discrete Optimization Problems. IEEE Trans. Evol. Comput. 2010, 14, 278–300. [Google Scholar] [CrossRef]
- Liu, T.; Yang, T.L.; Zhu, S.L.; Mou, N.N.; Zhang, W.J.; Wu, W.; Zhao, Y.Y.; Yao, Z.S.; Sun, J.J.; Chen, C.; et al. Estimation of wheat biomass based on phenological identification and spectral response. Comput. Electron. Agric. 2024, 222, 109076. [Google Scholar] [CrossRef]
Vegetation Index | Definition | Reference |
---|---|---|
Excess Green Index (EXG) | EXG = | [24] |
Normalized Difference Vegetation Index (NDVI) | NDVI = | [25] |
Normalized Difference Water Index (NDWI) | NDWI = | [26] |
Normalized Difference Red-Edge (NDRE) | NDRE = | [27] |
Green Vegetation Index (GVI) | GVI = | [28] |
Soil-Adjusted Vegetation Index (SAVI) | SAVI = | [29] |
Enhanced Vegetation Index (EVI) | EVI = | [30] |
Green-Normalized Difference Vegetation Index (GNDVI) | GNDVI = | [31] |
Optimized Soil Adjusted Vegetation Index (OSAVI) | OSAVI = | [29] |
Triangular Vegetation Index (TVI) | TVI = | [32] |
Normalized Difference Chlorophyll Index (NDCI) | NDCI = | [33] |
Stage | BBCH | Avg. | Max | Min | STDEV | CV | Med. | Skewness | Sample Size |
---|---|---|---|---|---|---|---|---|---|
Seedling | 12 | 76.9 | 88.2 | 69.6 | 2.27 | 3.14 | 77.2 | 0.34 | 90 |
Jointing | 31 | 67.5 | 72.6 | 60.8 | 2.49 | 3.46 | 67.1 | 0.15 | 90 |
Booting | 45 | 75.9 | 80.3 | 60.9 | 2.98 | 4.16 | 75.0 | 0.20 | 90 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, Y.; Wang, J.; Li, J.; Wang, J.; Xu, H.; Liu, T.; Wang, J. Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features. Plants 2025, 14, 973. https://doi.org/10.3390/plants14060973
Wang Y, Wang J, Li J, Wang J, Xu H, Liu T, Wang J. Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features. Plants. 2025; 14(6):973. https://doi.org/10.3390/plants14060973
Chicago/Turabian StyleWang, Yuchen, Jianliang Wang, Jiayue Li, Jiacheng Wang, Hanzeyu Xu, Tao Liu, and Juan Wang. 2025. "Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features" Plants 14, no. 6: 973. https://doi.org/10.3390/plants14060973
APA StyleWang, Y., Wang, J., Li, J., Wang, J., Xu, H., Liu, T., & Wang, J. (2025). Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features. Plants, 14(6), 973. https://doi.org/10.3390/plants14060973