ESTIMATION OF AREA SOWN AND SOWING DATES OF INSEASON RABI CROPS USING SENTINEL-2 TIME SERIES DATA
394 / 190
Authors
-
SANDEEP V.GAIKWAD*, AMOL D. VIBHUTE and KARBHARI V. KALE
Department of Computer Science & IT, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad - 431 004
Keywords:
Sown area estimation, sowing dates extraction, NDVI temporal profile, Sentinel 2, ISODATA classificationAbstract
An estimation of the area sown and sowing dates with their frequent updates in crop growing
season are crucial for devising the Nation’s food secuirty policies. These areas and dates were
estimated in India through a crop simulation model at a 5km X 5km grid across the states. Therefore,
a pilot study was conducted crop of sown area estimation, and sowing dates of rabi (post-rainy) crops
for 2017-2018 using nine (09) high-resolution Sentinel-2 images. These images were acquired from
October 1, 2017, to January 31, 2018 and were used to prepare the Satellite Image Time Series
(SITS) dataset. A new methodology was implemented using a time-series vegetation index at 10m
spatial resolution Sentinel-2 data to detect rabi crops’ growth in Vaijapur Tehsil of Maharastra.
Normalized Difference Vegetation Index (NDVI) was computed from the dataset, and further used for
a research study. A composite of 15 images was prepared for analysis of the temporal profile of NDVI.
The temporal profile trend starts from the emergence of crops and shows the maximum value at the
maturity state of crops. Furthermore, it starts decreasing and shows a minimum threshold value
>0.03 at the crop’s harvesting state. Additionally, it was correctly used to differentiate early, normal,
and late sown crops in the study area. Furthermore, sown area estimation was carried out by an
unsupervised ISODATA (Iterative Self-Organizing Data Analysis) algorithm. The overall accuracy was
88.39 with 0.84 kappa coefficient through the conducted experiment. Sentinel-2 is a suitable data
source for sown area estimation and sowing date extraction with acceptable accuracy.
References
1. Belgiu, M and Csillik, O. 2018. Sentinel-2
2. cropland mapping using pixel-based and
3. object-based time-weighted dynamic time
4. warping analysis. Remote Sensing of
5. Environment. 204: 509-523.
6. Bingfang, W and Qiangzi, L. 2004. Crop area
7. estimation using remote sensing on twostage
8. stratified sampling. International
9. Society for Photogrametry and Remote
10. Sensing (ISPRS). 20:12-23.
11. Bisht, P., Kumar, P., Yadav, M., Rawat, J. S.,
12. Sharma, M. P and Hooda, R. S. 2014.
13. Spatial dynamics for relative contribution of
14. cropping pattern analysis on environment
15. by integrating remote sensing and
16. GIS. International Journal of Plant
17. Production. 8(1):1735-8043.
18. Chakraborty, A., Seshasai, M. V. R and Dadhwal,
19. V. K. 2014. Geo-spatial analysis of the
20. temporal trends of Kharif crop phenology
21. metrics over India and its relationships with
22. rainfall parameters. Environmental
23. Monitoring and Assessment. 186(7):4531-
24. Clerici, N., Valbuena Calderon, C. A and Posada,
25. J. M. 2017. Fusion of Sentinel-1A and
26. Sentinel-2A data for land cover mapping: A
27. case study in the lower Magdalena region,
28. Colombia. Journal of Maps. 13(2):718-726.
29. De Beurs, K. M and Loffe, G. 2014. Use of
30. Landsat and MODIS data to remotely
31. estimate Russia’s sown area. Journal of
32. Land Use Science. 9(4):377-401.
33. Delgado Blasco, J. M., Foumelis, M., Stewart, C
34. and Hooper, A. 2019. Measuring urban
35. subsidence in the rome metropolitan area
36. (Italy) with sentinel-1 snap-stamps
37. persistent scatterer interferometry. Remote
38. Sensing. 11(2):129.
39. Gaikwad, S. V., Vibhute, A. D., Kale, K. V.,
40. Nalawade, D. B and Jadhav, M. B. 2018.
41. Design and development of ground truth
42. collection platform using android and leaflet
43. library. In: International Conference on
44. Recent Trends in Image Processing and
45. Pattern Recognition – Singapore. Springer.
46. pp.520-528.
47. Gaikwad, S.V., Vibhute, A.D., Kale, K.V., Dhumal,
48. R.K., Nagne, A.D., Mehrotra, S.C., Varpe,
49. A.B and Surase, R.R. 2019. Drought
50. severity identification and classification of
51. the land pattern using Landsat 8 data based
52. on spectral indices and maximum likelihood
53. a l g o r i t h m . I n : M i c r o e l e c t r o n i c s ,
54. Electromagnetics and Telecommunications.-
55. Singapore. pp. 517-524.
56. Jakubauskas, M. E., Legates, D. R and Kastens,
57. J. H. 2002. Crop identification using
58. harmonic analysis of time-series AVHRR
59. NDVI data. Computers and Electronics in
60. Agriculture. 37(1-3): 127-139.
61. Kafira, V., Albanakis, K and Oikonomidis, D.
62. Flood susceptibility assessment using
63. GIS: An example from Kassandra Peninsula,
64. Halkidiki, Greece. Geology. pp. 287-308.
65. Kukawska, E., Lewiñski, S., Krupiñski, M.,
66. Malinowski, R., Nowakowski, A., Rybicki, M
67. and Kotarba, A. 2017. Multi-temporal
68. Sentinel-2 data-remarks and observations.
69. In: 2017 9th International Workshop on the
70. Analysis of Multi-temporal Remote Sensing
71. Images (MultiTemp). IEEE. pp.1-4.
72. Louis, J., Debaecker, V., Pflug, B., Main-Knorn,
73. M., Bieniarz, J., Mueller-Wilm, U and Gascon,
74. F. 2016. Sentinel-2 Sen2Cor: L2A processor
75. for users. In: Proceedings of Living Planet
76. Symposium 2016. Spacebooks Online. pp.
77. -8..
78. Mahdianpari, M., Salehi, B., Mohammadi
79. manesh, F., Homayouni, S and Gill, E. 2019.
80. The first wetland inventory map of
81. newfoundland at a spatial resolution of 10
82. m using sentinel-1 and sentinel-2 data on
83. the google earth engine cloud computing
84. platform. Remote Sensing. 11(1):43.
85. Malenovsky, Z., Rott, H., Cihlar, J., Schaepman,
86. M. E., García-Santos, G., Fernandes, R and
87. Berger, M. 2012. Sentinels for science:
88. Potential of Sentinel-1,-2, and-3 missions
89. for scientific observations of ocean,
90. cryosphere and land. Remote Sensing of
91. Environment. 120:91-101.
92. GoI.2016. Manual for drought management-
93. Department of Agriculture and Cooperation,
94. Ministry of Agriculture, Govt. of
95. India, New Delhi. Retrieved from the website
96. (http://agricoop.nic.in/sites/default/files/
97. Manual % 20 Drought % 202016.pdf) on
98. 12.2020.
99. Marj, A. F and Meijerink, A. M. 2011. Agricultural
100. drought forecasting using satellite images,
101. climate indices and artificial neural network.
102. International Journal of Remote Sensing.
103. (24): 9707-9719.
104. Muller-Wilm, U., Louis, J., Richter, R., Gascon,
105. Fand Niezette, M. 2013. Sentinel-2 level 2A
106. prototype processor: Architecture,
107. algorithms and first results. In: Proceedings
108. of the ESA Living Planet Symposium.
109. Edinburgh, UK. pp. 9-13.
110. Narayanamoorthy, A. 2013. Profitability in crops
111. cultivation in India: Some evidence from cost
112. of cultivation survey data. Indian Journal of
113. Agricultural Economics. 68(902-2016-
114. :104-121.
115. Nigam, R., Vyas, S. S., Bhattacharya, B. K., Oza,
116. M. P., Srivastava, S. S., Bhagia, N.,
117. Debajyoti, D and Manjunath, K. R. 2015.
118. Modelling temporal growth profile of
119. vegetation index from Indian geostationary
120. satellite for assessing in-season progress
121. of crop area. GI Science and Remote
122. Sensing. 52(6):723-745.
123. Patel, S., Prakash, S and Bhatt, B. 2015. An
124. assessment of Kalpana-1 rainfall product
125. for drought monitoring over India at
126. meteorological sub-division scale. Water
127. International. 40(4):689-702.
128. Sitokonstantinou, V., Papoutsis, I., Kontoes, C.,
129. Lafarga Arnal, A., Armesto Andrés, A. P and
130. Garraza Zurbano, J. A. 2018. Scalable
131. parcel-based crop identification scheme
132. using sentinel-2 data time-series for the
133. monitoring of the common agricultural
134. policy. Remote Sensing. 10(6): 911.
135. Smith, V. H and Glauber, J. W. 2012. Agricultural
136. insurance in developed countries: Where
137. have we been and where are we
138. going?. Applied Economic Perspectives and
139. Policy. 34(3):363-390.
140. Springenberg, J. T. 2015. Unsupervised and
141. semi-supervised learning with categorical
142. generative adversarial networks. arXiv
143. preprint arXiv:1511.06390.
144. Vanino, S., Nino, P., De Michele, C., Bolognesi,
145. S.F., D’Urso, G., Di Bene, C., Pennelli, B.,
146. Vuolo, F., Farina, R., Pulighe, G and Napoli,
147. R.2018. Capability of Sentinel-2 data for
148. estimating maximum evapotranspiration and
149. irrigation requirements for tomato crop in
150. Central Italy. Remote Sensing of
151. Environment. 215:452-470.
152. Vibhute, A. D., Dhumal, R. K., Nagne, A. D.,
153. Rajendra, Y. D., Kale, K. V and Mehrotra,
154. S. C. 2016. Analysis, classification, and
155. estimation of pattern for land of Aurangabad
156. region using high-resolution satellite image.
157. In: Proceedings of the Second International
158. Conference on Computer and
159. Communication Technologies, New Delhi.
160. Springer. pp. 413-427.
161. Vibhute, A. D., Kale, K., Gaikwad, S., Dhumal,
162. R. K., Nagne, A. D., Varpe, A. B and
163. Mehrotra, S.C. 2020. Classification of
164. complex environments using pixel level
165. fusion of satellite data. Multimedia Tools and
166. Applications.https://doi.org/10.1007/
167. s11042-020-08978-4.
168. Vyas, S., Nigam, R., Patel, N. K and Panigrahy,
169. S. 2013. Extracting regional pattern of wheat
170. sowing dates using multispectral and high
171. temporal observations from indian
172. geostationary satellite. Journal of the Indian
173. Society of Remote Sensing. 41(4):855-864.
174. Vyas, S. P., Oza, M. P and Dadhwal, V. K. 2005.
175. Multi-crop separability study of Rabi crops
176. using multi-temporal satellite data. Journal
177. of the Indian Society of Remote Sensing.
178. (1):75-76.
179. Zhang, T., Su, J., Liu, C., Chen, W. H., Liu, H and
180. Liu, G. 2017. Band selection in Sentinel-2
181. satellite for agriculture applications. In: 2017
182. rd International Conference on Automation
183. and Computing (ICAC). IEEE. pp. 1-6.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The author owns the article's copyright until the article is accepted for publication. After acceptance, the author(s) assigns the article's copyright jointly to both the authors and the Publishers of the Journal of Research ANGRAU (ANGRAU) and licensed under a Creative Commons Attribution-Non Commercial-Share Alike 4.0 International License.
