Linking Grape Yield Performance to Remote Sensing Vegetation Indices: A Fusion of Sentinel Radar and Optical Imagery with Machine Learning Models

Document Type : Research Article

Authors

H. R. Maleki ¹

M. Khodamorad Pour ²

H. Mohammadi Monavar ¹

¹ Department of Bio-System Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran

² Department of Water Science and Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran

https://doi.org/10.22067/jam.2025.91357.1325

Abstract

Introduction
Remote sensing is considered a key management tool in precision agriculture, particularly for monitoring and identifying plant coverage. Grapes are among the most valuable horticultural crops, with Hamedan province accounting for approximately 7.3 % of Iran's total vineyard area. This study evaluates the accuracy of vineyard identification in Hamedan province using machine learning algorithms including support vector machine (SVM), minimum distance (MD), and random forest (RF) models along with normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) estimated from combined optical and radar images of Sentinel (Sentinel-1 and Sentinel-2). Based on the most accurate vineyard identification map, the maximum time series of NDVI and NDWI of the MODIS satellite in vineyards was estimated between 2007 and 2020, and their correlation with the actual yield of the grape crop was examined.
Materials and Methods
In this research, we first extracted images of pivotal remote sensing vegetation indicators, including NDVI and NDWI, from Sentinel-2 images in Hamedan province in 2020. The approach of addressing speckle noise through median pixels allowed for the acquisition of median radar images from Sentinel-1 over the designated study area. To create high-accurate images, spectral composition was used to combine these images with the NDVI and NDWI from Sentinel-2 images. Using these images, vineyard identification maps were generated through classification algorithms, including support vector machine, random forest, and minimum distance models. Training samples were used to train these algorithms. Samples from six land coverage classes involving vineyards, were collected using a combination of field observations and Google Earth imagery. Of these, 70% were used for training and 30% for testing the classification models. In order to assess the accuracy of the vineyard identification maps, indicators including overall accuracy and kappa coefficient were examined. Subsequently, the vineyard map with the highest assessment indicator was selected. Finally, using this accurate vineyard identification map, the maximum monthly NDVI and NDWI indices estimated from MODIS sensor images in the vineyards were calculated from 2007 to 2020, and their correlation with yields of the grape crop was computed using Pearson correlation.
Results and Discussion
Based on the comparison of different classification algorithms for distinguishing vineyards, random forest model along with NDVI and NDWI indices outperformed support vector machine and minimum distance models. With regard to accuracy, however, the random forest along with the NDWI has the best overall accuracy (95%) and kappa coefficient (0.95). The superior performance of NDWI is attributed to the high moisture levels in vineyards resulting from irrigation, as NDWI is particularly sensitive to variations in vegetation water content. The lower accuracy of vineyard identification using SVM and MD models can be linked to shadow effects caused by the canopy structure of grapevines, as well as imbalanced training data used for the support vector machine model. Correlation analysis of real grape yields with NDVI and NDWI of MODIS extracted from the highest accuracy vineyards map indicates NDVI (correlation coefficient 0.81) has a stronger linear relationship with yield than NDWI (correlation coefficient 0.75). This can be explained by NDVI's sensitivity to leaf chlorophyll changes, which results in a strong correlation with yield.
Conclusion
Vineyards can be accurately identified using machine learning algorithms and remote sensing vegetation indices derived from combined radar and optical satellite images. Furthermore, the strong correlation between NDVI and grape yield enable reliable yield prediction based on NDVI time series analysis. The outcomes of this study facilitate the identification of grape cultivation areas, improved water resourse management, the development of optimized irrigation strategies, pre-harvest yield estimation, and the exploration of export options.

Keywords

Minimum Distance model

NDVI index

NDWI index

Random Forest model

Support Vector Machine model

Subjects

• Digital, Smart, and Precision Agriculture

---

Authors retain the copyright. This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

References

1. Alex, E. C., Ramesh, K. V., & Sridevi, H. (2017). Quantification and understanding the observed changes in land cover patterns in Bangalore. International Journal of Civil Engineering and Technology, 8(4), 597-603.
2. Adam, E., Mutanga, O., & Odindi, J., & Abdel-Rahman, E. M. (2014). Land-use/cover classification in a heterogeneous coastal landscape using Rapid Eye imagery: Evaluating the performance of random forest and support vector machines classifiers. International Journal of Remote Sensing, 35, 3440-3458. https://doi.org/10.1080/01431161.2014.903435
3. Adugna, T., Xu, W., & Fan, J. (2022). Comparison of Random Forest and Support Vector Machine Classifiers for Regional Land Cover Mapping Using Coarse Resolution FY-3C Images. Remote Sensing, 14(3), https://doi.org/10.3390/rs14030574
4. Ahmad, F. (2012). Detection of change in vegetation cover using multi-spectral and multi-temporal information for district Sargodha, Pakistan. Sociedade & Natureza, 24(3), 557-571. https://doi.org/10.1590/S1982-45132012000300014
5. Arab, S. T., Noguchi, R., Matsushita, S., & Ahamed, T. (2021). Prediction of grape yields from time-series vegetation indices using satellite remote sensing and a machine-learning approach. Remote Sensing Applications: Society and Environment, 22, 1-14. https://doi.org/10.1016/j.rsase.2021.100485
6. Avalos, J. M. M., & Araujo, E. S. (2021). Optimization of Vineyard Water Management: Challenges Strategies, and Perspectives. Water, 13(6), 1-32. https://doi.org/10.3390/w13060746
7. Biau, G., & Scornet. E. (2016). A random forest guided tour. Test, 25(2), 197-227. https://doi.org/10.1007/s11749-016-0481-7
8. Borgogno-Mondino, E., & Lessio, A. (2018). A FFT-Based approach to explore periodicity of vines/soil properties in vineyard from time series of satellite-derived spectral indices. IEEE International Geoscience and Remote Sensing Symposium(pp. 9078-9081). https://doi.org/10.1109/igarss.2018.8519437
9. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
10. Brinkhoff, J., Vardanega, J., & Robson, A. J. (2019). Land Cover Classification of Nine Perennial Crops Using Sentinel-1 and -2 Data. Remote Sensing, 12(1), 1-26. https://org/10.3390/rs12010096
11. Bovolo, F., & Bruzzone, L. (2007). A split-based approach to unsupervised change detection in large-size multitemporal images: Application to tsunami-damage assessment. IEEE Transactions on Geoscience and Remote Sensing, 45(6), 1658-1670. https://doi.org/10.1109/tgrs.2007.895835
12. Basheer, S., Wang, X., Farooque, A. A., Nawaz, R. A., Liu, K., Adekanmbi, T., & Liu, S. (2022). Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques. Remote Sensing, 14(19), 1-18. https://doi.org/10.3390/rs14194978
13. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297. https://doi.org/10.1007/BF00994018
14. Filgueiras, R., Mantovani, E. C., Althoff, D., FernandesFilho, E. I., & Cunha, F. F. D. (2019). Crop NDVI monitoring based on sentinel 1. Remote Sensing, 11(12), 1-21. https://doi.org/10.3390/rs11121441
15. Faizizadeh, B. & Haydari, H. (2008). Estimation of vineyards cultivated area of in using SPOT5 satellite image. Journal of Geography and Planning, 14(27), 47-60. (in Persian). Retrieved from https://sid.ir/paper/203804/en
16. Ghayour, L., Neshat, A., Paryani, S., Shahabi, H., Shirzadi, A., Chen, W., Ansari, N. A., Geertsema, M., Amiri, M. P., Gholamnia, M., Dou, J., & Ahmad, A. (2021). Performance evaluation of sentinel-2 and landsat8 OLI data for land cover/use classification using a comparison between machine learning algorithms. Remote Sensing, 13(7), 1-21. https://doi.org/10.3390/rs13071349
17. Goa, B. (1996). NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing Environment, 58(3), 257-266. https://doi.org/10.1016/S0034-4257(96)00067-3
18. Gogtay, N. J., & Thatte, U. M. (2017). Principles of correlation analysis. Journal of the Association of Physicians of India, 65(3), 78-81. Retrieved from https://pubmed.ncbi.nlm.nih.gov/28462548/
19. Gu, Y., Brown, J. F., Verdin, J. P., & Wardlow, B. (2007). A five‐year analysis of MODIS NDVI and NDWI for grassland drought assessment over the central Great Plains of the United States. Geophysical Research Letters,34(6). https://doi.org/10.1029/2006GL029127
20. Hartling, S., Sagan, V., Sidike, P., Maimaitijiang, M., & Carron, J. (2019). Urban tree species classification using a WorldView-2/3 and LiDAR data fusion approach and deep learning. Sensors, 19(6), 1284. https://doi.org/10.3390/s19061284
21. Holben, B. N. (1986). Characteristics of maximum-value composite images from temporal AVHRR data. International Journal of Remote Sensing, 7(11), 1417-1434. https://doi.org/10.1080/01431168608948945
22. Huang, J., Chen, D., & Cosh, M.H. (2009). Sub-pixel reflectance unmixing in estimating vegetation water content and dry biomass of corn and soybeans cropland using normalized difference water index (NDWI) from satellites. Intenational Journal of Remote Sensing, 30(80), 2075-2104. https://doi.org/10.1080/01431160802549245
23. Immitzer, M., Vuolo, F., & Atzberger, C. (2016). First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe. Remote Sensing, 8(3), 166. https://doi.org/10.3390/rs8030166
24. Junges, A. H., Fontana, D. C., Anzanello, R., & Bremm, C. (2017). Normalized difference vegetation index obtained by ground-based remote sensing to characterize vine cycle in Rio Grande do Sul, Brazi. Ciencia E Agrotecnologia, 41(5), 543-553. https://doi.org/10.1590/1413-70542017415049016
25. Karimi, N., Sheshangosht, S., & Eftekhari, M. (2022). Crop type detection using an object-based classification method and multi-temporal Landsat satellite images. Paddy Water Environment, 20(3), 395-412. https://doi.org/10.1007/s10333-022-00901-x
26. Keria, H., Bensaci, E., Zoubiri, A., & Ben Si Said, Z. (2024). Long-term dynamics of remote sensing indicators to monitor the dynamism of ecosystems in arid and semi-arid areas: contributions to sustainable resource management. Journal of Water and Climate Change, 15(4), 1532-1550. https://doi.org/10.2166/wcc.2024.409
27. Kumar, L., & Mutanga, O. (2018). Google Earth Engine Applications Since Inception: Usage, Trends, and Potential. Remote Sensing, 10(10), 1509. https://doi.org/10.3390/rs10101509
28. Lewis, H. G., & Brown, M. (2001). A generalized confusion matrix for assessing area estimates from remotely sensed data. International Journal of Remote Sensing, 22(16), 3223-3235. https://doi.org/10.1080/01431160152558332
29. Liaw, A., & Wiener, M. (2002). Classification and Regression by RandomForest. R News, 2, 18-22. Retrieved from https://journal.r-project.org/articles/RN-2002-022/RN-2002-022.pdf
30. Lopez-Martinez, C., & Fabregas, X. (2002). Modeling and reduction of SAR interferometric phase noise in the wavelet domain. IEEE Transactions on Geoscience and Remote Sensing, 40(12), 2553-2566. https://doi.org/10.1109/tgrs.2002.806997
31. Lu, S., Xuan, J., Zhang, T., Bai, X., Tian, F., & Ortega-Farias, S. (2022). Effect of the shadow pixels on evapotranspiration inversion of vineyard: A high-resolution UAV-based and ground-based remote sensing measurements. Remote Sensing, 14(9), 2259. https://doi.org/10.3390/rs14092259
32. Mirzaei, M., Abbasi, M., Marofi, S., Solgi, E., & Karimi, R. (2018). Spectral discrimination of important orchard species using hyperspectral indices and artificial intelligence approaches, Journal of RS and GIS for Natural Resources, 9(2), 76-92. (in Persian). Retrieved from https://sanad.iau.ir/Journal/girs/Article/902480
33. MohamadiManavar, H., & Zibazadeh, S. (2022). Distinguishing rain-fed and irrigated crops in Hamadan province using spectral indices of satellite images. Journal of Agricultural Machinery, 12(4), 529-542. (in Persian with English abstract). https://doi.org/10.22067/jam.2021.69074.1022
34. Nematollahi, H., Ashourloo, D., Alimohammadi, A., Khodabandehloo, & Radiom, S. (2018). Development and application of crop and field condition indices using time-series satellite images of Sentinel-2. Iranian Journal of Remote Sensing & amp: GIS. 10(3), 105-122. (in Persian with English abstract). Retrieved from https://gisj.sbu.ac.ir/article_96575.html
35. Negri, R. G., Dutra, L. V., Sant'Anna, S. J. S., & Lu, D. (2016). Examining region-based methods for land cover classification using stochastic distances. International Journal of Remote Sensing, 37(8), 1902-1921. https://doi.org/10.1080/01431161.2016.1165883
36. Pal, S., Pandey, S. K., Sharma, S. K., & Nair, R. (2022). Land use and land cover classification of Jabalpur district using minimum distance classifier. The Pharma Innovation, 11(11), 1161-1163. Retrieved from https://www.thepharmajournal.com/archives/2022/vol11issue11S/PartO/S-11-11-148-831.pdf
37. Pal, M., & Mather, P. M. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007-1011. https://doi.org/10.1080/01431160512331314083
38. Pearson, K. (1896). Mathematical contributions to the theory of evolution III. Regression, heredity and panmixia. Philosophical Transactions of the Royal Society of London. Series A, 187, 253-318. https://doi.org/10.1098/rsta.1896.0007
39. Phiri, D., Simwanda, M., Salekin, S., Nyirenda, V. R., Murayama, Y., & Ranagalage, M. (2020). Sentinel-2 data for land cover/use mapping: A review. Remote sensing, 12(14), https://doi.org/10.3390/rs12142291
40. Robinson, N. P., Allred, B. W., Jones, M. O., Moreno, A., Kimball, J. S., Naugle, D. E., Erickson. T. A., & Richardson, A. D. (2017). A Dynamic Landsat Derived Normalized Difference Vegetation Index (NDVI) Product for the Conterminous United States. Remote Sensing, 9(8), 64-77. https:/doi.org/10.3390/rs9080863
41. Sekertekin, A., & Zadbagher, E. (2021). Simulation of future land surface temperature distribution and evaluating surface urban heat island based on impervious surface area. Ecological Indicators, 122, 1-11. https://doi.org/10.1016/j.ecolind.2020.107230
42. Tomas, P., Samuel, O. F., Dongryeol, R. (2018). Automatic Coregistration Algorithm to Remove Canopy Shaded Pixels in UAV-Borne Thermal Images to Improve the Estimation of Crop Water Stress Index of a Drip-Irrigated Cabernet Sauvignon Vineyard. Sensors, 18, 397. https://doi.org/10.3390/s18020397
43. Tucker, C. J. (1979). Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8(2), 127-150. https://doi.org/10.1016/0034-4257(79)90013-0
44. Torres, R., Snoeij, P., Geudtner, D., Bibby, D., Davidson, M., Attema, E. & Rostan, F. (2012). GMES Sentinel-1 mission. Remote sensing of Environment, 120, 9-24. https://doi.org/10.1016/j.rse.2011.05.028
45. Vélez, S., Barajas, E., Blanco, P., Rubio, J. A., & Castrillo, D. (2021). Spatio-temporal analysis of satellite imagery (NDVI) to identify terroir and vineyard yeast differences according to appellation of origin (AOP) and biogeographic origin. Multidisciplinary Scientific Journal,4(3), 244-256. https://doi.org/10.3390/j4030020
46. Vintrou, E., Desbrosse, A., Begue, A., Traore, S., Baron, C., & Lo seen, D. (2012). Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products. International Journal of Applied Earth Observation and Geoinformation, 14(1), 83-93. https://doi.org/10.1016/j.jag.2011.06.010
47. Wacker, A. G., & Landgrebe, D. A. (1972). Minimum Distance Classification in Remote Sensing. LARS Technical Reports. Paper 25, 1-20. Retrieved from https://docs.lib.purdue.edu/larstech/25/
48. Yu, H., & Kim, S. (2012). SVM Tutorial: Classification, Regression and Ranking. Handbook of Natural Computing, 1, 479-506. https://doi.org/10.1007/978-3-540-92910-9_15
49. Zare Khormizi, H., Ghafarian Malamiri, H. R, & Mortaz, M. (2020). Evaluation of supervised classification capability of Landsat-8 and Sentinel-2A Satellite images in determining type and area of Pistachio Cultivars. Journal of Rs and Gis for natural Resources, 11(1), 84-103. (in Persian with English abstract). Retrieved from https://srb.sanad.iau.ir/en/Article/902735
50. Zhao, L., Li, Q., Zhang, Y., Wang, H., & Du, X. (2019). Integrating the Continuous Wavelet Transform and a Convolutional Neural Network to Identify Vineyard Using Time Series Satellite Images. Remote Sensing, 11(22), 2641. https://doi.org/10.3390/rs11222641
51. Zhu, Z., & Woodcock, C. E. (2012). Object-based cloud and cloud shadow detection in Landsat imagery.