UAV hyperspectral image acquisition and processing, an application for nutrient estimation of rice in Vietnam

Luong Minh Khanh; Son Tong Si; Huong Mai; Huong To Thi Mai; Giang Tran Son; Binh Pham-Duc; Hien Phan; Canh Le Van; Lan Pham Thi; Ai Tong Thi Huyen

doi:10.15625/2615-9783/21306

Author affiliations

Authors

Minh Khanh Luong University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Tong Si Son University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Huong Mai University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Huong Thi Mai To University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Giang Son Tran University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Binh Pham-Duc University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Hien Phan University of Science and Technology of Hanoi (USTH), VAST, Hanoi, Vietnam
Le Van Canh Hanoi University of Mining and Geology (HUMG), Hanoi, Vietnam
Thi Lan Pham Hanoi University of Mining and Geology (HUMG), Hanoi, Vietnam
Tong Thi Huyen Ai Space Technology Institute (STI), VAST, Hanoi, Vietnam

DOI:

https://doi.org/10.15625/2615-9783/21306

Keywords:

Unmanned Aerial Vehicle, Hyperspectral remote sensing, Nutrient concentration, Vegetation indices

Abstract

Hyperspectral imagery obtained from Unmanned Aerial Vehicles (UAVs) is increasingly employed to investigate nutrient concentrations in vegetation. The deployment of a hyperspectral camera on a UAV, flight planning, image acquisition, preprocessing of hyperspectral data, and the subsequent estimation of nutrient concentrations in vegetation are facing challenges. These challenges manifest as geometric, spectral distortions, and the abundance of numerous spectral bands. This study seeks to guide on mitigating the impact of issues encountered during an experiment to estimate nutrient concentrations in rice leaves using UAV hyperspectral images. An industrial hexagonal drone equipped with a push-broom hyperspectral camera featuring 122 bands within the Visible to Near-Infrared (VIS-NIR) wavelength range (400-960 nm) is employed to collect data over a 1-hectare testing rice field. Models for estimating Leaf Phosphorus Concentration (LPC) and Leaf Potassium Concentration (LKC) are developed based on the correlation between hyperspectral images, characterized by a 3 cm spatial resolution, and 162 LPC and 162 LKC reference data points. Utilizing various vegetation indices for LPC and LKC estimation, the outcomes reveal that a combination of band wavelengths at 838 nm and 734 nm is effective for LPC estimation, yielding a Root Mean Square Error (RMSE) of 27.1%. Conversely, LKC estimation exhibits an RMSE of 38.8% with an insignificant correlation between LKC and the current wavelength ranges. Above all, this study is a primary example of the utilization of UAV hyperspectral data in precision agriculture in Vietnam.

Downloads

Download data is not yet available.

References

Adão T., J. Hruška, L. Pádua, J. Bessa, E. Peres, R. Morais, J. Sousa. 2017. Hyperspectral Imaging: A Review on UAV-Based Sensors, Data Processing and Applications for Agriculture and Forestry. Remote Sensing, 9(11), 1110.

Albayrak S., 2008. Use of Reflectance Measurements for the Detection of N, P, K, ADF and NDF Contents in Sainfoin Pasture. Sensors (Basel), 8(11), 7275–7286.

Brownlee J., 2020. Feature Importance and Feature Selection With XGBoost in Python. from https://machinelearningmastery.com/feature-importance-and-feature-selection-with-xgboost-in-python/.

Buresh R., 2022. Rice Knowledge Bank, Nitrogen (N) excess. from http://www.knowledgebank.irri.org/training/fact-sheets/nutrient-management/deficiencies-and-toxicities-fact-sheet/item/nitrogen-excess#:~:text=What%20it%20does,the%20strength%20of%20the%20stems.%20.

Campos-Soriano L., M. Bundo, M. Bach-Pages, S.F. Chiang, T.J. Chiou, B. San Segundo, 2020. Phosphate excess increases susceptibility to pathogen infection in rice. Mol Plant Pathol, 21(4), 555–570.

Chang, Chein-I., 2003. Hyperspectral Imaging: Techniques for Spectral Detection and Classification. New York: Kluwer Academic/Plenum Publishers.

Clauss K., M. Ottinger, P. Leinenkugel, C. Kuenzer, 2018. Estimating rice production in the Mekong Delta, Vietnam, utilizing time series of Sentinel-1 SAR data. International Journal of Applied Earth Observation and Geoinformation, 73, 574–585.

Das B., R.N. Sahoo, S. Pargal, G. Krishna, R. Verma, V. Chinnusamy, V.K. Sehgal, V.K. Gupta, 2017. Comparison of different uni- and multi-variate techniques for monitoring leaf water status as an indicator of water-deficit stress in wheat through spectroscopy. Biosystems Engineering, 160, 69–83.

Davies M., M.B. Stuart, M.J. Hobbs, A.J.S. McGonigle, J.R. Willmott, 2022. Image Correction and In Situ Spectral Calibration for Low-Cost, Smartphone Hyperspectral Imaging. Remote Sensing, 14(5), 1152.

Delavarpour N., C. Koparan, J. Nowatzki, S. Bajwa, X. Sun, 2021. A Technical Study on UAV Characteristics for Precision Agriculture Applications and Associated Practical Challenges. Remote Sensing, 13(6), 1204.

Dobermann A., T. Fairhurst, 2000. Rice: Nutrient Disorders & Nutrient Management, Potash & Phosphate Institute, East & Southeast Asia Programs. ISBN 981-04-2742-5.

Geladi P., J. Burger, T. Lestander, 2004. Hyperspectral imaging: calibration problems and solutions. Chemometrics and Intelligent Laboratory Systems, 72(2), 209–217.

Giba L., 2023. Elastic Net Regression Explained, Step by Step. from https://machinelearningcompass.com/machine_learning_models/elastic_net_regression/.

Gitelson A.A., O.B. Chivkunova, M.N. Merzlyak, 2009. Nondestructive estimation of anthocyanins and chlorophylls in anthocyanic leaves. Am. J. Bot., 96(10), 1861–1868.

Grahn H., P. Geladi, 2007. Techniques and Applications of Hyperspectral Image Analysis. Wiley & Sons, Ltd. https://doi.org/10.1002/9780470010884.

Granitto P.M., C. Furlanello, F. Biasioli, F. Gasperi, 2006. Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemometrics and Intelligent Laboratory Systems, 83(2), 83–90.

Hindersah R., A.M. Kalay, A. Talahaturuson, 2022. Rice yield grown in different fertilizer combination and planting methods: Case study in Buru Island, Indonesia. Open Agriculture, 7(1), 871–881.

Jiang C., X. Gao, L. Liao, N.P. Harberd, X. Fu, 2007. Phosphate starvation root architecture and anthocyanin accumulation responses are modulated by the gibberellin-DELLA signaling pathway in Arabidopsis. Plant Physiol, 145(4), 1460–1470.

Kumar D., 2024. A Complete understanding of LASSO Regression. from https://www.mygreatlearning.com/blog/understanding-of-lasso-regression/

Li H., K. He, Z. Zhang, Y. Hu, 2023. Molecular mechanism of phosphorous signaling inducing anthocyanin accumulation in Arabidopsis. Plant Physiology and Biochemistry, 196, 121–129.

Ling B., D.G. Goodin, E.J. Raynor, A. Joern, 2019. Hyperspectral Analysis of Leaf Pigments and Nutritional Elements in Tallgrass Prairie Vegetation. Frontiers in Plant Science, 10, 142. https://doi.org/10.3389/fpls.2019.00142.

Liu H., H. Zhu, Z. Li, G. Yang, 2019. Quantitative analysis and hyperspectral remote sensing of the nitrogen nutrition index in winter wheat. International Journal of Remote Sensing, 41(3), 858–881.

Lu J., W. Li, M. Yu, X. Zhang, Y. Ma, X. Su, X. Yao, T. Cheng, Y. Zhu, W. Cao, Y. Tian, 2020. Estimation of rice plant potassium accumulation based on non-negative matrix factorization using hyperspectral reflectance. Precision Agriculture, 22(1), 51–74.

Lu J., T. Yang, X. Su, H. Qi, X. Yao, T. Cheng, Y. Zhu, W. Cao, Y. Tian, 2019. Monitoring leaf potassium content using hyperspectral vegetation indices in rice leaves. Precision Agriculture, 21(2), 324–348.

Mahajan G.R., R.N. Pandey, R.N. Sahoo, V.K. Gupta, S.C. Datta, D. Kumar, 2016. Monitoring nitrogen, phosphorus and sulphur in hybrid rice (Oryza sativa L.) using hyperspectral remote sensing. Precision Agriculture, 18(5), 736–761.

Nalepa J., M. Antoniak, M. Myller, P. Ribalta Lorenzo, M. Marcinkiewicz, 2020. Towards resource-frugal deep convolutional neural networks for hyperspectral image segmentation. Microprocessors and Microsystems, 73, 102994.

Nguyen D., K. Clauss, S. Cao, V. Naeimi, C. Kuenzer, W. Wagner, 2015. Mapping Rice Seasonality in the Mekong Delta with Multi-Year Envisat ASAR WSM Data. Remote Sensing, 7(12), 15868–15893.

Nieves-Cordones M., F. Aleman, V. Martinez, F. Rubio, 2014. K+ uptake in plant roots. The systems involved, their regulation and parallels in other organisms. J. Plant Physiol, 171(9), 688–695.

Phung H.-P., L.-D. Nguyen, N.-H. Thong, L.-T. Thuy, A.A. Apan, 2020. Monitoring rice growth status in the Mekong Delta, Vietnam using multitemporal Sentinel-1 data. Journal of Applied Remote Sensing, 14(01), 1.

Pinit S., N. Ruengchaijatuporn, S. Sriswasdi, T. Buaboocha, S. Chadchawan, J. Chaiwanon, 2022. Hyperspectral and genome-wide association analyses of leaf phosphorus status in local Thai indica rice. PLoS One, 17(4), e0267304.

Poona N.K., A. van Niekerk, R.L. Nadel, R. Ismail, 2016. Random Forest (RF) Wrappers for Waveband Selection and Classification of Hyperspectral Data. Applied Spectroscopy, 70(2), 322–333.

Pullanagari R., G. Kereszturi, I. Yule, 2018. Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression. Remote Sensing, 10(7), 1117.

Rodarmel C., J. Shan, 2002. Principal Component Analysis for Hyperspectral Image Classification. Surveying and Land Information Science, 62(2), 115–123.

Sanchez L., A. Ermolenkov, S. Biswas, E.M. Septiningsih, D. Kurouski, 2020. Raman Spectroscopy Enables Noninvasive and Confirmatory Diagnostics of Salinity Stresses, Nitrogen, Phosphorus, and Potassium Deficiencies in Rice. Front Plant Sci., 11, 573321.

Skiles S.M., C.P. Donahue, A.G. Hunsaker, J.M. Jacobs, 2023. UAV hyperspectral imaging for multiscale assessment of Landsat 9 snow grain size and albedo. Frontiers in Remote Sensing, 3, 1038287. Doi: 10.3389/frsen.2022.1038287.

Sruthi E.R., 2024. Understand Random Forest Algorithms With Examples (Updated 2024). Analytics Vidhya. From https://www.analyticsvidhya.com/blog/2021/06/understanding-random-forest/

Stuart B.H., 2021. Infrared Spectroscopy of Biological Applications: An Overview. Encyclopedia of Analytical Chemistry, 1–16.

Wallach O., 2022. Visualizing the World's Biggest Rice Producers. from https://www.visualcapitalist.com/worlds-biggest-rice-producers/#google_vignette.

Wang L., S. Chen, D. Li, C. Wang, H. Jiang, Q. Zheng, Z. Peng, 2021. Estimation of Paddy Rice Nitrogen Content and Accumulation Both at Leaf and Plant Levels from UAV Hyperspectral Imagery. Remote Sensing, 13(15), 2956.

Zhang X., T. Lin, J. Xu, X. Luo, Y. Ying, 2019. Deep Spectra: An end-to-end deep learning approach for quantitative spectral analysis. Analytica Chimica Acta, 1058, 48–57.

Zhang Y., T. Wang, Z. Li, T. Wang, N. Cao, 2023. Based on machine learning algorithms for estimating leaf phosphorus concentration of rice using optimized spectral indices and continuous wavelet transform." Front Plant Sci., 14, 1185915.

Zhang Z., D. Jiang, Q. Chang, Z. Zheng, X. Fu, K. Li, H. Mo, 2023. Estimation of Anthocyanins in Leaves of Trees with Apple Mosaic Disease Based on Hyperspectral Data. Remote Sensing, 15(7), 1732.