Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

A synthesis approach of vegetation indices for monitoring high-risk agricultural regions using UAV and satellite hyperspectral data

Document Type : Research Paper

Authors
Maryam Sadeghi 1
Hossein Fekrat 1
Hassan Emami 2
1 Ph.D Candidate, Department of remote sensing and GIS, Faculty of planning and environmental sciences, University of Tabriz, Tabriz, Iran
2 Associate professor, Department of surveing, Faculty of Marand engineering ,University of Tabriz,, Tabriz, Iran
10.22131/sepehr.2025.2050311.3116
Abstract
Extended abstract
 Introduction
Remote sensing (RS), which is commonly used to monitor crops, is regarded as one of the most important innovations for precision and intelligent agriculture. Numerous characteristics of vegetation and crops could be monitored using RS. Today, the advancement of unmanned aerial vehicle (UAV)-based remote sensing systems has advanced crop monitoring and precision agriculture. When compared to prior methods. Using UAVs to monitor crops provides excellent prospects for obtaining field data in a simple, quick, and cost-effective manner. The ability of UAVs to fly at low altitude provides images of objects with extremely high spatial resolution (i.e., a few millimeters). Because of the widespread application of remote sensing and UAVs in recent years, quantitative and qualitative monitoring of croplands has expanded dramatically. Nowadays, because the global agriculture sector is facing increasing challenges as a result of a variety of stressful factors such as natural resource depletion, environmental pollution, climate change, and crop diseases, crop monitoring is critical to planning and managing sustainable agriculture. Various approaches have been studied to identify crop stress caused by a variety of variables. In the event that each spectral index has distinct properties and cannot consider all plant attributes, all base index approaches in vegetation research and crop monitoring have employed plant indices individually. It is obvious that each spectral index expresses a portion of the characteristics of the vegetation cover and does not express other characteristics, so the combination of different vegetation groups covers the unique characteristics of each index and considers more vegetation cover characteristics. The objective of this research is to employ the combination of indices from various categories, such as greenness indices, growth indices, plant leaf pigments, and leaf surface moisture indices, together with hyperspectral and UAV remote sensing data, to monitor risky areas and crop stress. It attempts to provide answers to the following questions: How do the suggested composite indices perform in images with medium and low spatial resolution (Hyperion) and imagery with extremely high spatial resolution (UAV hyperspectral)? And to what degree do the suggested combined indices increase the accuracy of stress monitoring of crops when compared to individual indices?
 Methodology
Although assessing the health of crops is a challenging task, satellite imagery and data can be quite beneficial in this field. The objective of this research is to use a combination of indices from different groups to monitor risk and stress areas in crops using hyperspectral remote sensing and UAV data. The primary data sets utilized in this study are Hyperion hyperspectral image data with 242 spectral bands and medium spatial resolution (30 meters) and UAV hyperspectral image data with 270 spectral bands and high spatial resolution (0.43 m), which have been analyzed in two independent areas. In this study, sixteen independent indices were employed separately, followed by the suggested composite indices on satellite and UVA imagery. Then, by combining the vegetation indices of the crops of the study area in terms of risk tolerance, they were classified into four different classes: no stress, low stress, medium stress, and high stress, and the results obtained in each stage were combined with equal weights to construct the final map of crop-risky areas. The research validated the results by creating a land use map of the UAV image using ground truth data and using the support vector machine classification algorithm, which was then compared and analyzed with the research results.
Results and discussion
According to the findings of this study, around 55% and 47% of each analyzed region were at medium to high risk in the Hyperion and UAV hyperspectral images, respectively. The corn crop had the biggest area related to high stress, whereas the soybean crop (thin leaf) had the lowest area related to high stress. The proposed combined indexes' findings revealed that the combined indexes MRWA2 and MRWC2 had excellent accuracy in detecting risky products. The usage of the greenness index, modified red edge vegetable index of the water band, and anthocyanin index in the composite indices, which are not impacted by the product's features and only recognize regions where the product is stressed, could potentially be the cause of this. Furthermore, the suggested combined indices of SRWR and MRWR yielded nearly identical findings. Additionally, the study found that in the Hyperion hyperspectral image with medium and low spatial resolution (30 meters and less), the combined indices showed higher accuracy than individual indices when compared to the classification map. Overall, in the high-risk class, individual indicators have an error of 18%, and combined indicators have an error of 10%.  As a result, the use of combined indices in medium- and low-spatial-resolution imagery reduces crop risk calculation inaccuracy by 42%, enabling more precise monitoring of risk areas.
 Conclusion
The current study's findings revealed that the suggested combined indices can potentially be utilized to monitor the stress of applied products, depending on the kind and aim of research in the study and monitoring of various types of vegetation. Furthermore, the results demonstrate that the spatial resolution of UAV and satellite imaging performs differently in crop stress monitoring. In this approach, using composite indices in images with medium and low spatial resolution decreases the inaccuracy of calculating risky regions of crops by roughly 42% and allows for more accurate monitoring of the risk areas. On the contrary, the accuracy of the combined indices compared to the individual indices is slightly enhanced in the hyperspectral image of a high-resolution UAV, but there is no obvious gain.
Keywords
Stress of crops
UAV hyperspectral images
Hyperion
Vegetation indices

Subjects

1- Asokan, A. and Anitha, J., (2019). Change detection techniques for remote sensing applications: A survey. Earth Science Informatics, 12: 143-160. doi: 10.1007/s12145-019-00380-5.
2- Azmat, A., Yasmin, H., Hassan, M.N., Nosheen, A., Naz, R., Sajjad, M., Ilyas, N. and Akhtar, M.N., (2020). Co-application of bio-fertilizer and salicylic acid improves growth, photosynthetic pigments and stress tolerance in wheat under drought stress. PeerJ, 8: e9960.doi: 10.7717/peerj.9960.
3- Bhattacharya, S., Halder, S., Nag, S., Roy, P.K. and Roy, M.B., (2021). Assessment of drought using multi-parameter indices. Advances in water resources management for sustainable use: 243-255. doi: 10.1007/978-981-33-6412-7_18.
4- D’Odorico, P., Schönbeck, L., Vitali, V., Meusburger, K., Schaub, M., Ginzler, C., Zweifel, R., Velasco, V.M.E., Gisler, J. and Gessler, A., (2021). Drone‐based physiological index reveals long‐term acclimation and drought stress responses in trees. Plant, Cell & Environment, 44(11): 3552-3570.doi: 10.1111/pce.14177.
5- Datt, B., (1999). A new reflectance index for remote sensing of chlorophyll content in higher plants: tests using Eucalyptus leaves. Journal of plant physiology, 154(1): 30-36. doi: 10.1016/S0176-1617(99)80314-9.
6- Eitel, J.U., Gessler, P.E., Smith, A.M. and Robberecht, R., (2006). Suitability of existing and novel spectral indices to remotely detect water stress in Populus spp. Forest Ecology and Management, 229(1-3): 170-182.doi: 10.1016/j.foreco.2006.03.027.
7- Gerhards, M., Schlerf, M., Mallick, K. and Udelhoven, T., (2019). Challenges and future perspectives of multi-/Hyperspectral thermal infrared remote sensing for crop water-stress detection: A review. Remote Sensing, 11(10): 1240.doi: 10.3390/rs11101240.
8- Gitelson, A.A., Merzlyak, M.N. and Chivkunova, O.B., (2001). Optical properties and nondestructive estimation of anthocyanin content in plant leaves. Photochemistry and photobiology, 74(1): 38-45 doi: 10.1562/0031-8655(2001)0740038OPANEO2.0.CO2.
9- Hu, L., Zhang, C., Zhang, M., Shi, Y., Lu, J. and Fang, Z., (2023). Enhancing FAIR data services in agricultural disaster: A review. Remote Sensing, 15(8): 2024. doi: 10.3390/rs15082024.
10- Hunt Jr, E.R., Doraiswamy, P.C., McMurtrey, J.E., Daughtry, C.S., Perry, E.M. and Akhmedov, B., (2013). A visible band index for remote sensing leaf chlorophyll content at the canopy scale. International journal of applied earth observation and Geoinformation, 21, 103-112.doi: 10.1016/j.jag.2012.07.020.
11- Isazade, v., ghanbari, A. and Kamran, K.V., (2022). Evaluation of spectral indices and extraction of constructed and non-constructed urban features and its comparison with ground surface temperature using Landsat 7 and 8 satellite images (Study area, Tehran). Geographical Planning of Space, 11(42): 23-39. doi:  10.30488/GPS.2021.243118.3283. [in Persian].
12- Kaufman, Y.J. and Tanre, D., (1992). Atmospherically resistant vegetation index (ARVI) for EOS-MODIS. IEEE transactions on Geoscience and Remote Sensing, 30(2): 261-270. doi: 10.1109/36.134076.
13- Kayet, N., Pathak, K., Chakrabarty, A., Singh, C., Chowdary, V., Kumar, S. and Sahoo, S., (2019). Forest health assessment for geo-environmental planning and management in hilltop mining areas using Hyperion and Landsat data. Ecological Indicators, 106: 105471. doi: 10.1016/j.ecolind.2019.105471.
14- Lu, H., Chen, Y., Huan, H. and Duan, N., (2022). Analyzing cultivated land protection behavior from the perspective of land fragmentation and farmland transfer: Evidence from farmers in rural China. Frontiers in Environmental Science, 10: 901097.doi: 10.3389/fenvs.2022.901097.
15- Maes, W.H. and Steppe, K., 2019. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends in plant science, 24(2): 152-164. doi: /10.1016/j.tplants.2018.11.007.
16- Masry, A., Furlong, M.J., Clarke, A.R. and Cunningham, J.P., (2018). An improved culturing method for opiine fruit fly parasitoids and its application to parasitoid monitoring in the field. Insect science, 25(1): 99-108.doi: 10.1111/1744-7917.12403.
17- Mohammadi, S., mirlotfi, M. and akbari, M., (2014). Sugarcane Irrigation Scheduling by Combining Remote Sensing Data and SWAP Model in Mirza-Kuchak-Khan Sugarcane Agro-Industry, Ahwaz, Iran. Journal of Water Research in Agriculture, 28(1): 39-50.doi: 10.22092/jwra.2015.101063. [in Persian].
18- Moharana, S. and Dutta, S., (2019). Estimation of water stress variability for a rice agriculture system from space-borne hyperion imagery. Agricultural Water Management, 213: 260-269. doi: 10.1016/j.agwat.2018.10.001.
19- Omran, E.-S.E., (2018). Remote estimation of vegetation parameters using narrowband sensor for precision agriculture in arid environment. Egyptian Journal of Soil Science, 58(1): 73-92.doi: 10.21608/EJSS.2018.5614.
20- Radočaj, D., Šiljeg, A., Marinović, R. and Jurišić, M., (2023). State of major vegetation indices in precision agriculture studies indexed in web of science: A review. Agriculture, 13(3): 707. doi:10.3390/agriculture13030707.
21- Solberg, E.G., Diener, E. and Robinson, M.D., (2004). Why are materialists less satisfied? Psychology and consumer culture: The struggle for a good life in a materialistic world (pp. 29–48). American Psychological Association. doi: 10.1037/10658-003.
22- Tayade, R., Yoon, J., Lay, L., Khan, A.L., Yoon, Y. and Kim, Y., (2022). Utilization of spectral indices for high-throughput phenotyping. Plants, 11(13): 1712. doi: 10.3390/plants11131712.
23- Thénot, F., Méthy, M. and Winkel, T., (2002). The Photochemical Reflectance Index (PRI) as a water-stress index. International Journal of Remote Sensing, 23(23): 5135-5139. doi: 10.1080/01431160210163100.
24- Vasconcelos, J.C.S., Speranza, E.A., Antunes, J.F.G., Barbosa, L.A.F., Christofoletti, D., Severino, F.J. and de Almeida Cançado, G.M., (2023). Development and Validation of a Model Based on Vegetation Indices for the Prediction of Sugarcane Yield. AgriEngineering, 5(2): 698-719. doi: 10.3390/agriengineering5020044.
25- Wan, L., Li, Y., Cen, H., Zhu, J., Yin, W., Wu, W., Zhu, H., Sun, D., Zhou, W. and He, Y., (2018). Combining UAV-based vegetation indices and image classification to estimate flower number in oilseed rape. Remote Sensing, 10(9): 1484.doi: 10.3390/rs10091484.
26- Wang, Z., Zhao, Z. and Yin, C., (2022). Fine crop classification based on UAV hyperspectral images and random forest. ISPRS International Journal of Geo-Information, 11(4): 252. doi: 10.3390/ijgi11040252.
27- Weiss, M., Jacob, F. and Duveiller, G., (2020). Remote sensing for agricultural applications: A meta-review. Remote sensing of environment, 236: 111402. doi: 10.1016/j.rse.2019.111402.
28- Wilson, N.R. and Norman, L.M., (2018). Analysis of vegetation recovery surrounding a restored wetland using the normalized difference infrared index (NDII) and normalized difference vegetation index (NDVI). International Journal of Remote Sensing, 39(10): 3243-3274. doi: 10.1080/01431161.2018.1437297.
29- Yousefi, M., mikaniki, J., Ashrafi, A. and Neysani Samani, N., (2018). Land use Change Detection and Modeling, Using Remote Sensing data, Markov Chains and Cellular Automata (Case Study: City of Bojnord). Geographical Planning of Space, 7(26): 1-16. [in Persian].
30- Zhong, Y., Hu, X., Luo, C., Wang, X., Zhao, J. and Zhang, L., (2020). WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF. Remote Sensing of Environment, 250: 112012. doi: 10.1016/j.rse.2020.112012