Inverting the Leaf Area Index of summer maize through the application of optimization methods
Abstract
Abstract: The leaf area index (LAI) of summer maize plays a pivotal role in estimating biomass, photosynthetic potential, transpiration, and various other crucial vegetation parameters. It serves as a vital indicator for evaluating growth progress and predicting crop yields. Unmanned Aerial Vehicle (UAV) remote sensing has proven to be a rapid and non-destructive tool for monitoring the LAI of summer maize. The objective of this study is to enhance the accuracy of the LAI inversion model for summer maize by leveraging different optimization algorithms. To achieve this, we designed varying fertilization levels to create distinct canopy structures. We employed a UAV multi-spectral remote sensing system to obtain 19 vegetation indices, which were collected concurrently with ground-based LAI measurements throughout the growing season. In our investigation, we applied multiple linear regression (MLR), Support Vector Machine Regression (SVR), and Random Forest Regression Model (RF) to establish regression models between the vegetation indices of summer maize and LAI over the entire growth period. For hyperparameter optimization of the SVR and RF models, we employed the Particle Swarm Optimization algorithm (PSO), Whale Optimization Algorithm (WOA), and Grey Wolf Optimization Algorithm (GWO) to search for optimal combinations of hyperparameters. The results demonstrated that Difference Vegetation Index (DVI), Green-Blue Ratio Index (GBRI), Standard Greenness Index (NGI), Wide Dynamic Range Vegetation Index (WDRVI), and Vegetation Infrared Ratio Index (SR) exhibited high correlations with LAI. Furthermore, the accuracy of LAI estimation models was significantly improved through the application of optimization methods. Notably, the LAI estimation model established using SVR-GWO yielded the highest accuracy (R2=0.912, RMSE=0.607). In summary, the utilization of optimization algorithms has proven to be an effective approach in enhancing the precision of LAI estimation models, with promising applications in agricultural research and crop management.
Keywords: summer maize; multispectral remote sensing; leaf area index; vegetation index; inversion models; optimization methods
DOI: 10.33440/j.ijpaa.20230601.199
Citation: Bie X T, Jia P, Wang G B, Yang C L, Wang Q Y, Gu H Z, Shan C F and Lan Y B. Inverting the Leaf Area Index of summer maize through the application of optimization methods. Int J Precis Agric Aviat, 2023; 6(1): 1–8.
Full Text:
PDFReferences
Shailendra M. Internet of things enabled deep learning methods using unmanned aerial vehicles enabled integrated farm management. Heliyon, 2023, 9: e18659. DOI: 10.1016/j.heliyon.2023.e18659
Lan Y B, Zhao D N, Zhang Y F, et al. Exploration and development prospect of eco-unmanned farm modes. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(9): 312–327. (in Chinese with English abstract) DOI: 10.11975/j.issn.1002-6819.2021.09.036 http://www.tcsae.org
Xia T, Wu W B, ZHOU Yong, et al. An Estimation Method of Winter Wheat Leaf Area Index Based on HyperSpectral Data. Scientia Agricultura Sinica. 2012, 45(10): 2085–2092. DOI: 10.3864/j.issn.0578–1752.2012.110.022
Wu W B, Hong T S, Wang X P, et al. Advance in Ground-based LAI Measurement Methods. Journal of Huazhong Agricultural University. 2007, (02): 270–275. DOI: 10.13300/j.cnki.hnlkxb.2007.02.031
Yan G J, Hu R H, Luo J H, et al. Review of indirect methods for leaf area index measurement. Journal of Remote Sensing, 2016, 20(5): 958–978 DOI:10.11834/jrs.20166238
Li F Y? Huang H? Guan C Y?Review on measurement of crop leaf area. Journal of Hunan Agricultural University(Natural Sciences), 2021, 47(3)?274–282. DOI: 10.13331/j.cnki.jhau.2021.03.005
Xiong W C, Qiu Q, Chen T H, et al. Analysis of LAI Indirect Measurement Method. Journal of Anhui Agricultural Sciences, 2021, 47(03): 274–282. DOI: 10.13989/j.cnki.0517-6611.2013.15.094
Chen Q T, Jia L, Massimo M, et al. A numerical analysis of aggregation error in evapotranspiration estimates due to heterogeneity of soil moisture and leaf area index. Agricultural and Forest Meteorology, 2019, 269–270: 335–350. DOI: 10.1016/j.agrformet.2019.02.017
Meng J H, Zheng H G, Wang S X, et al. The feasibility analysis on satellite data based crop fungal toxin prediction. Remote Se-nsing Technology and Application?2023?38(3): 535–543. DOI: 10.11873/j.issn.1004?0323.2023.3.0535
Yang C, Yan G, Du S M, Li X D. Application Review of Unmanned Aerial Vehicle Remote Sensing Technology in Wheat Producti-on. Henan Science, 2021, 39(10): 1598–1602.
Mu T Y, Zhao W, Hu X Y, et al. Rice lodging recognition method based on UAV remote sensing combined with the improved DeepLabV3+ model. Journal of China Agricultural University, 2022, 27(02): 143–154. DOI: 10.11841/J.ISSN.1007-4333.2022.02.14
Yang S Q, Lin F S, Xu P H, et al. Planting Row Detection of Multi-growth Winter Wheat Field Based on UAV Remote Sensing Image. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(02): 181–188. DOI: 10.6041/j.issn.1000-1298.2023.02.17
Li Q. Remote Sensing Monitoring of Wheat Growth Based on UAV Image Technology. Journal of Agricultural Mechanization Research,
, 44(05): 193–197. DOI: 10.13427/j.cnki.njyi.2022.05.035
Shao Y J, Tang Q X, Cui J P, et al. Cotton Leaf Area Index Estimation Combining UAV Spectral and Textural Features. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(06): 186–196. DOI: 10.6041/j. issn. 1000-1298.2023.06.019
Yang N, Zhou M, Chen H, et al. Estimation of Wheat Leaf Area Index and Yield Based on UAV RGB Images. Journal of Triticeae Crops. 2023, 43(07): 920–932. DOI: 10.7606. j.issn.1009-1041.2023.07.13
Shao G M, Wang Y J, Han W T. Estimation Method of Leaf Area Index for Summer Maize Using UAV-Based Multispectral Remote Sensing. Smart Agriculture, 2020, 2(3): 118–128. (in Chinese with English abstract) DOI: 10.12133/j.smartag.2020.2.3.202006-SA001
Zhang Y Q. Estimating Height and Leaf Area Index of Maize and Soybean Using UAV LiDAR. Fujian Agriculture and Forestry University. 2022
Ehteram M, Seifi A, Banadkooki F. Application of Machine Learning Models in Agricultural and Meteorological Sciences. Springer Nature Singapore, 2023: 23–32.
N. M.Hatta, Azlan M Z, Roselina S, et al. Recent studies on optimization method of Grey Wolf Optimiser (GWO): a review (2014–2017). Artificial Intelligence Review, 2018, 52: 2651–2683.
Xian H F, Che J X. Unified whale optimization algorithm based multi-kernel SVR ensemble learning for wind speed forecasting. Applied Soft Computing, 2022, 130: 109690.
Gao Y L, Yang Q W, Wang X F, et al. Overview of New Swarm Intelligent Optimization Algorithms. Journal of Zhengzhou Univ-ersity (Engineering Science). 2022, 43(03): 21–30. DOI: 10.13705/j.issn.1671-6833.2022.03.007
Han W T, Peng X S, Zhang L Y, et al. Summer Maize Yield Estimation Based on Vegetation Index Derived from Multi-temporal UAV Remote Sensing. Transactions of the Chinese Society for Agricultural Machinery. 2020, 51(01): 148–155. DOI: 10.6041/j.issn.1000-1298.2020.01.016
Jiang Y, Wang J, Hou C C, et al. Estimation of soybean leaf area index using UAV LiDAR and Sentinel-2 image data. Science of Surveying and Mapping. DOI: 10.16251/j.cnki.1009-2307.2023.04.019
Andrés V, Anatoly A. G, Anthony L. N, et al. Comparison of different vegetation indices for the remote assessment of green leaf area index of crops. Remote Sensing of Environment, 2011, 115: 3468–3478.
Liu W D, Xiang Y Q, Zheng L F, et al. Relationships between Rice LAI, CH.D and Hyperspectral Data. Journal of Remote Sensing, 2000, (04): 279–283.
Leng X, Hong Z Y. Neural Network Based on Spotted Hyena Optimizer for Forest LAI Retrieval. Journal of Southwest University(Natural Science Edition), 2022, 44(12): 176–185. DOI: 10.13718/j.cnki.xdzk.2022.12.018
Zhang J. Study on Estimation Model of Summer Maize Leaf Area Index Based on UAV Multispectral Image. Shanxi Agricultural University, 2022
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.