Machine Learning-Based Crop Yield Estimation using Geo-Referenced Survey Data and Satellite Data
32 / 37
Authors
-
Ayub Aktar
The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi
-
Prachi Misra Sahoo
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Pankaj Das
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Tauqueer Ahmad
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Ankur Biswas
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Saikath Das
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
Keywords:
Crop Yield Estimation;Crop Cutting Experiments;Vegetation indices;MachineLearning; Geo-referenced Survey Data;Horvitz Thompson.Abstract
The present study proposed an estimator for crop yield using machine learning techniques, remote sensing and geo-referenced survey data. Various
vegetation indices, including Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Normalized
Difference Red Edge (NDRE), Soil-Adjusted Vegetation Index (SAVI) and Modified Soil-Adjusted Vegetation Index (MSAVI), along with nearest
neighbour information, were employed as input variables. Machine learning models, specifically Random Forest (RF), Support Vector Regression
(SVR) and Gradient Boosting (GB), were utilized to predict crop yield based on varying sample sizes (10%, 20%, 30%, 40% and 50%) in CCE data of
Barabanki district, situated in Uttar Pradesh, India.The study results show proposed ML based estimators were consistently outperforming the existing
Horvitz Thompson (HT)estimator and the performance of estimators improves consistently with increase in sample size.
Downloads
References
1. Aktar, A. (2024). Crop yield estimation using machine learning
2. technique for geo-referenced survey data. Unpublished M.Sc.
3. Thesis, Graduate School, ICAR-IARI, New Delhi.
4. Banerjee, R., Bharti, Das, P. and Khan, S. (2024). Crop Yield Prediction
5. Using Artificial Intelligence and Remote Sensing Methods.
6. In Artificial Intelligence and Smart Agriculture: Technology
7. and Applications (pp. 103-117). Singapore: Springer Nature
8. Singapore.
9. Breiman, L. (1996). Bagging Predictors. Machine Learning, 24,
10. 123-140.
11. Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32.
12. Chamber, R. and Clark, R. (2012). An Introduction to Model-Based
13. Survey Sampling with Applications. Oxford Statistical Science
14. Series.
15. Das, P., Jha, G.K., Lama, A., Parsad, R. and Mishra, D. (2020).
16. Empirical mode decomposition-based support vector regression
17. for agricultural price forecasting. Indian Journal of Extension
18. Education, 56(2), 7-12.
19. Das, P., Jha, G.K., Lama, A. and Parsad, R. (2023). Crop yield prediction
20. using hybrid machine learning approach: a case study of lentil
21. (Lens culinaris Medik.). Agriculture, 13(3), 596.
22. Dong, J., Lu, H., Wang, Y., Ye, T. and Yuan, W. (2020). Estimating
23. winter wheat yield based on a light use efficiency model and
24. wheat variety data. ISPRS Journal of Photogrammetry and
25. Remote Sensing, 160, 18-32.
26. Friedman, J.H. and Fisher, N.I. (1999). Bump hunting in high
27. dimensional data. Statistics and Computing, 9(2), 123-143.
28. Gitelson, A.A., Kaufman, Y.J., Mark, N. and Merzlyak, M.N. (1996).
29. Use of a green channel in remote sensing of global vegetation from
30. EOS-MODIS. Remote Sensing of Environment, 58(3), 289-298.
31. Gulati, A. and Juneja, R. (2020). Indian agriculture towards 2030.
32. Ministry of Agriculture & Farmers Welfare, Government of India,
33. 1-27.
34. Hamer, W.B., Birr, T., Verreet, J.A., Duttmann, R. and Klink, H. (2020).
35. Spatio-temporal prediction of the epidemic spread of dangerous
36. pathogens using machine learning methods. ISPRS International
37. Journal of Geo-Information, 9(1), 44.
38. Han, J., Zhang, Z., Cao, J., Luo, Y., Zhang, L., Li, Z. and Zhang, J.
39. (2020). Prediction of winter wheat yield based on multi-source
40. data and machine learning in China. Remote Sensing, 12(2), 236.
41. Huete, A.R. (1988). A soil-adjusted vegetation index (SAVI). Remote
42. Sensing of Environment, 25(3), 295-309.
43. Jaikla, R., Auephanwiriyakul, S. and Jintrawet, A. (2008). Rice yield
44. prediction using a support vector regression method. In 2008 5th
45. International Conference on Electrical Engineering/Electronics,
46. Computer, Telecommunications and Information Technology, 1,
47. 29-32.
48. Jeong, J.H., Resop, J.P., Mueller, N.D., Fleisher, D.H., Yun, K., Butler,
49. E.E. and Kim, S. H. (2016). Random forests for global and
50. regional crop yield predictions. PloS One, 11(6), e0156571.
51. Khosla, E., Dharavath, R. and Priya, R. (2020). Crop yield prediction
52. using aggregated rainfall-based modular artificial neural networks and support vector regression. Environment, Development and
53. Sustainability, 22(6), 5687-5708.
54. Li, J., Alvarez, B., Siwabessy, J., Tran, M., Huang, Z., Przeslawski, R.
55. and Nichol, S. (2017). Application of random forest, generalised
56. linear model and their hybrid methods with geostatistical
57. techniques to count data: Predicting sponge species richness.
58. Environmental Modelling and Software, 97, 112-129.
59. Mahmoudzadeh, H., Matinfar, H.R., Taghizadeh-Mehrjardi, R. and
60. Kerry, R. (2020). Spatial prediction of soil organic carbon using
61. machine learning techniques in western Iran. Geoderma Regional,
62. 21, e00260.
63. Meng, Y., Yang, M., Liu, S., Mou, Y., Peng, C. and Zhou, X. (2021).
64. Quantitative assessment of the importance of bio-physical drivers
65. of land cover change based on a random forest method. Ecological
66. Informatics, 61, 101204.
67. Naveen, G.P., Sahoo, P.M., Das, P., Ahmad, T. and Biswas, A. (2024).
68. Random forest spatial interpolation techniques for crop yield
69. estimation at district level. Journal Of the Indian Society of
70. Agricultural Statistics, 78(1), 9–19.
71. Nigam, A., Garg, S., Agrawal, A. and Agrawal, P. (2019). Crop yield
72. prediction using machine learning algorithms. In 2019 Fifth
73. International Conference on Image Information Processing ,
74. 125-130.
75. Noorunnahar, M., Chowdhury, A.H. and Mila, F.A. (2023). A tree based
76. eXtreme Gradient Boosting (XGBoost) machine learning model
77. to forecast the annual rice production in Bangladesh. PloS One,
78. 18(3), e0283452.
79. Ohashi, O. and Torgo, L. (2012). Spatial interpolation using multiple
80. regression. International Conference on Data Mining, 2,
81. 1044-1049.
82. Royall, R.M. (1970). On finite population sampling theory under certain
83. linear regression models. Biometrika, 57(2), 377-387.
84. Sahoo, P.M., Rai, A., Ahmad, T., Singh, R. and Handique, B.K. (2012).
85. Estimation of acreage under paddy crop in Jaintia Hills district of
86. Meghalaya using Remote sensing and GIS.International Journal
87. of Agricultural and Statistical Sciences, 8(1), 193-202.
88. Sukhatme, P.V., Sukhatme, B.V., Sukhatme, S. and Asok, C. (1984).
89. Sampling Theory of Surveys with Applications. Indian Society
90. of Agricultural Statistics, New Delhi, Indiaand IOWA State
91. University Press Ames, USA.
92. Valliant, R., Dorfman, A.H. and Royall, R.M. (2000). Finite Population
93. Sampling and Inference: A Prediction Approach. John Wiley,
94. New York.
95. Vapnik, V. (1998). The Support Vector Method of Function Estimation.
96. Springer, Boston, MA.
97. Voitik, A., Kravchenko, V., Pushka, O., Kutkovetska, T., Shchur, T.
98. and Kocira, S. (2023). Comparison of NDVI, NDRE, MSAVI and
99. NDSI indices for early diagnosis of crop problems. Agricultural
100. Engineering, 27(1), 47-57.
101. Yang, F., Liu, Y., Yan, J., Guo, L., Tan, J., Meng, X. and Feng, H.
102. (2024). Winter wheat yield estimation with colourindex fusion
103. texture feature. Agriculture, 14(4), 581.
104. Wu, C. and Thompson, M.E. (2020). Sampling Theory and Practice.