In the agriculture economy, understanding of spatial crop growing pattern is significant to agricultural structure adjustment and regional food safety policy. The phenlogical profile of crop can reflect a real trend of crop growth and therefore have been used to interpret seasonal crop growing patterns. Accurate identification of potato growing areas from other crop is not so easy because of their similar characteristics in the proposed study area. This study proposed a method to precisely predict the spatial potato crop growing pattern in the potato bowl districts of West Bengal by using 16-day composite MODIS NDVI data (MOD13Q1) in the potato cropping year of 2012-13 and 2013-14. Based on time series NDVI data and vast knowledge of field investigation a threshold value was set to build decision trees to pick up the potato crop as well as to eliminate the other crops. As a result, the potato crop area was successfully segregated from the multi-temporal NDVI data. Both predicted potato growing areas derived from MODIS NDVI data and the actual potato growing area is deployed for evaluation and the results give a satisfactory accuracy in both potato cropping year of 2012-13 and 2013-14. This result demonstrated that MODIS NDVI data are potentially good data source for spatial potato crop growing area extraction.

Potato Crop, Crop Phenology, MODIS, NDVI, Decision Trees

[1] A. Huete, K. Didan, T. Miura, E. Rodriguez, P. E, X. Gao, and L. G. Ferreira, “Overview of the radiometric and biophysical performance of the MODIS vegetation indices”, Remote Sensing of Environment, vol. 83, pp. 195–213, 2002.
[2] A. Chitradevi, S. Vijayalakshmi, “Random Forest for Multitemporal and Multiscale Classification of Remote Sensing Satellite Imagery”, International Journal of Computer Sciences and Engineering, Vol. 4, Issue. 2, pp. 59-65, 2016.
[3] B.D. Wardlow, J.H. Kastens, S.L. Egbert, “Using USDA crop progress data for the evaluation of greenup onset date calculated from MODIS 250-meter data”, Photogrammetric Engineering and Remote Sensing, vol. 72, pp. 1225−1234, 2006.
[4] B.D. Wardlow, S.L. Egbert and J.H. Kastens, “Analysis of time-series MODIS 250 m vegetation index data for crop classification in the US Central Great Plains”, Remote Sensing of Environment, vol. 108, pp. 290−310, 2007.
[5] B.D. Wardlow and S.L. Egbert, “Large-area crop mapping using time-series MODIS 250 m NDVI data: An assessment for the U.S. Central Great Plains”, Remote Sens. Environ., vol. 112, no. 3, pp. 1096–1116, 2008.
[6] B. Huang, H. Zhang, H. Song, J. Wang and C. Song, “fusion of remote-sensing imagery: generating simultaneously high-resolution synthetic spatial–temporal–spectral earth observations”, Remote Sens. Lett., vol. 4, pp. 561–569, 2013.
[7] C.O. Justice, J.B.G. Townshend, E.F. Vermote, E. Masuoka, R.E. Wolfe, N. Saleous, D.P. Roy and J.T. Morisette, “An overview of MODIS land data processing and product status”, Remote Sens. Environ, vol. 83, pp. 3–15, 2002.
[8] G. Hmimina, E. Dufrêne, J.Y. Pontailler, N. Delpierre, M. Aubinet, B. Caquet, A. De Grandcourt, B. Burban, C. Flechard, A. Granier, P. Gross, B. Heinesch, B. Longdoz, C. Moureaux, J.M. Ourcival, S. Rambal, L. Saint André, and K. Soudani, “Evaluation of the potential of MODIS satellite data to predict vegetation phenology in different biomes: An investigation using ground-based NDVI measurements”, Remote Sens. Environ., vol. 132, pp. 145–158, 2013.
[9] H. Zhang, J. Chen, B. Huang, H. Song and Y. Li, “Reconstructing seasonal variation of Landsat vegetation index related to leaf area index by fusing with MODIS data”, IEEE J. Select. Topics Appl. Earth Observ. Remote Sens, vol. 1, pp. 1–11, 2013.
[10] M. Zhang, Z. Qin, X. Liu and S. Ustin, “Detection of stress in tomatoes indiced by late blight disease in California, USA, using hyperspectral remote sensing”, International Journal of Applied Earth Observation and Geoinformation, vol. 4, no. 4, pp. 295-310, 2003.
[11] Ramesh K.N, Meenavathi M.B, "Agriculture Crop Area mapping in images acquired using Low Altitude Remote Sensing", International Journal of Computer Sciences and Engineering, Vol.6, Issue. 1, pp. 55-62, 2018.
[12] T. Sakamoto, M. Yokozawa, H. Toritani, M. Shibayama, N. Ishitsuka, and H. Ohno, “A crop phenology detection method using time-series MODIS data”, Remote Sens. Environ., vol. 96, no. 3–4, pp. 366–374, 2005.
[13] T. Sakamoto, N. Van Nguyen, H. Ohno, N. Ishitsuka, and M. Yokozawa, “Spatio-temporal distribution of rice phenology and cropping systems in the Mekong Delta with special reference to the seasonal water flow of the Mekong and Bassac rivers”, Remote Sens. Environ., vol. 100, no. 1, pp. 1–16, 2006.
[14] W.B. Wu, P. Yang, H.J. Tang, Q.B. Zhou, Z.X. Chen, and R. Shibasaki, “Characterizing Spatial Patterns of Phenology in Cropland of China Based on Remotely Sensed Data”, Agric. Sci. China, vol. 9, no. 1, pp. 101–112, 2010.
[15] X. Zhang, M. A. Friedl, C. Schaaf, “Global Vegetation Phenology from Moderate Resolution Imaging Spectroradiometer (MODIS): Evaluation of Global Patterns and Comparison with in situ Measurements”, Journal of Geo-physical Research, vol. 111: G04017, 2006.