A Novel Multi-Index Approach For Crop Health Analysis Using PCA-Derived Spectral Weights

Shivani S. Bhosle; Dr. Prapti D. Deshmukh

doi:10.29284/5hhgsf68

Authors

Shivani S. Bhosle Research Fellow, Dr.G.Y.Pathrikar College of Computer Science and Information Technology, MGM University ,Chhatrapti Sambhajinagr, Maharashtra
Dr. Prapti D. Deshmukh Pricipal, Dr.G.Y.Pathrikar College of Computer Science and Information Technology, MGM University ,Chhatrapti Sambhajinagr, Maharashtra

DOI:

https://doi.org/10.29284/5hhgsf68

Keywords:

Crop Health Analysis, PCA, NDVI, Sentinel-2A

Abstract

For precision agriculture, resource optimization, and sustainable farm management, prompt and correct crop health assessment is vital. Conventional vegetation indexes like NDVI and EVI offer insightful observations, yet they usually fall short of portraying the whole spectrum of physiological and structural conditions seen in several crops and habitats. By means of Principal Component Analysis (PCA), this study introduces a novel Multi-Vegetation Health Index (MVHI) integrating five complementary spectral indices—NDVI, EVI, SAVI, GNDVI, and NDRE—to derive objective statistical weights. Thirteen scenes from June–December 2024 from Sentinel-2A surface reflectance imagery were preprocessed using cloud filtering, spatial point extraction, and temporal index computation at field sites in Mahalaxmikheda village, Maharashtra. MVHI was built from the first principal component, which accounted for 82.30% of total spectral variation, hence confirming great information compression and index strength. Accuracy assessment using one-way ANOVA shown significant discriminatory ability across independently defined crop health groupings (F = 211.50, p < 0.001), with a large effect size (η² = 0.522). Comparative ANOVA results demonstrated that MVHI offers a balanced alternative to highly sensitive individual indices such NDRE and GNDVI. Spatial mapping of MVHI revealed clear gradients of crop vigor and stress, hence supporting its applicability for field-scale monitoring and agronomic decision-making. MVHI turns out to be a trustworthy, data-driven and whole crop health indicator fit for operational remote sensing and scientific study purposes.

References

1. Omia, E., Bae, H., Park, E., Kim, M. S., Baek, I., Kabenge, I., & Cho, B. K. (2023). Remote sensing in field crop monitoring: A comprehensive review of sensor systems, data analyses and recent advances. Remote Sensing, 15(2), 354.

2. Brewer, K., Clulow, A., Sibanda, M., Gokool, S., Naiken, V., & Mabhaudhi, T. (2022). Predicting the chlorophyll content of maize over phenotyping as a proxy for crop health in smallholder farming systems. Remote Sensing, 14(3), 518.

3. Yu, H., Kong, B., Hou, Y., Xu, X., Chen, T., & Liu, X. (2022). A critical review on applications of hyperspectral remote sensing in crop monitoring. Experimental Agriculture, 58, e26.

4. Vidican, R., Mălinaș, A., Ranta, O., Moldovan, C., Marian, O., Ghețe, A., ... & Cătunescu, G. M. (2023). Using remote sensing vegetation indices for the discrimination and monitoring of agricultural crops: A critical review. Agronomy, 13(12), 3040.

5. Wu, B., Zhang, M., Zeng, H., Tian, F., Potgieter, A. B., Qin, X., ... & Loupian, E. (2023). Challenges and opportunities in remote sensing-based crop monitoring: A review. National Science Review, 10(4), nwac290.

6. Maryana, S., Herdiyeni, Y., Wahjuni, S., & Santosa, E. (2025). UAV-Based Segmentation and Correlation Analysis of Vegetation Indices for Cassava Crop Health Assessment. JOIV: International Journal on Informatics Visualization, 9(4), 1381. https://doi.org/10.62527/joiv.9.4.3078

7. Kumar, S., Ghosh, S. S., Mandal, D., Bhattacharya, A., Porwal, A., & Karthikeyan, L. (2025). Enhancing Vegetation Monitoring: A Proposal for a Sentinel-2 Based Vegetation Health Index. https://doi.org/10.20944/preprints202501.1235.v1

8. Sellami, M., Albrizio, R., Colovic, M., Hamze, M., Cantore, V., Todorovic, M., Piscitelli, L., & Stellacci, A. M. (2022). Selection of Hyperspectral Vegetation Indices for Monitoring Yield and Physiological Response in Sweet Maize under Different Water and Nitrogen Availability. Agronomy, 12(2), 489. https://doi.org/10.3390/agronomy12020489

9. Sharma, A., & Guest. (n.d.). Principal component analysis (pca) in the evaluation of vegetation indices derived from time-series remote sensing data: a review.

10. Li, J., Wu, Z., Hu, Z., Li, Z., Wang, Y., & Molinier, M. (2021). Deep learning based thin cloud removal fusing vegetation red edge and short wave infrared spectral information for Sentinel-2A imagery. Remote Sensing, 13(1), 157.

11. Nagy, D., Warshavsky, Z., & Hughes, L. H. (2021, July). Improved Image Aggregation for Large-Scale Cloud-Free Image Creation. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (pp. 3889-3892). IEEE.

12. Vera-Esmeraldas, A., Pizarro-Oteíza, S., Labbé, M., Rojo, F., & Salazar, F. (2025). UAV-Based Spectral and Thermal Indices in Precision Viticulture: A Review of NDVI, NDRE, SAVI, GNDVI, and CWSI. Agronomy, 15(11), 2569.

13. de Oliveira, J. F., de Alcântara, J. F., Santana, D. C., Teodoro, L. P. R., Baio, F. H. R., Coradi, P. C., ... & Teodoro, P. E. (2023). Spectral variables as criteria for selection of soybean genotypes at different vegetative stages. Remote Sensing Applications: Society and Environment, 32, 101026.

14. Khunrattanasiri, W. (2023). Application of remote sensing vegetation indices for forest cover assessments. In Concepts and Applications of Remote Sensing in Forestry (pp. 153-166). Singapore: Springer Nature Singapore.

15. Melnyk, O., & Brunn, A. (2025). Analysis of Spectral Index Interrelationships for Vegetation Condition Assessment on the Example of Wetlands in Volyn Polissya, Ukraine. earth, 6(2), 28.

16. Uddin, M. P., Mamun, M. A., & Hossain, M. A. (2021). PCA-based feature reduction for hyperspectral remote sensing image classification. IETE Technical Review, 38(4), 377-396.

17. Flynn, K. C., Lee, T., Endale, D., Franzluebbers, A., Ma, S., & Zhou, Y. (2021). Assessing remote sensing vegetation index sensitivities for tall fescue (Schedonorus arundinaceus) plant health with varying endophyte and fertilizer types: A case for improving poultry manuresheds. Remote Sensing, 13(3), 521.