Determining the Best Classification Algorithm in order to Estimate the Area under Date Palm Cultivation using LANDSAT 8 Satellite Imagery

Document Type : Research Article

Authors

• S. Rahnama ¹
• M. Maharlooei ¹
• M. A. Rostami ²
• H. Maghsoudi ¹

¹ Dept. of Mechanical Engineering of Biosystems, Shahid Bahonar University of Kerman, Kerman, Iran

² Agricultural Engineering Research Department, Kerman Agricultural and Resource Research and Education Center, AREEO, Kerman, Iran

https://doi.org/10.22067/jam.v9i2.67310

Abstract

Introduction
Date palm is one of the most valuable horticultural products in Iran, which includes 16% of non-oil exports to the world. Kerman province has the second rank for the cultivation area of date palm in Iran. Having information about the exact cultivated area has gained importance for further decision makings. To determine the cultivated area, organizations usually use census which has the disadvantages of high cost, wasting time and labor intensive. The aim of this research was to study the feasibility of using Landsat 8 OLI images to identify and classify the area under date palm cultivation. To accomplish this purpose, four supervised classification methods were evaluated.
Materials and Methods
The study area was in Bam region located at 200 km southeast of Kerman province. In this research, a total of 14 images of Landsat8 OLI satellite from the study area during fall and winter were downloaded from Landsat official web page. After preliminary inspections for interested classes (Date palm gardens, Lands covered with bare soil and forage crop fields), one of the images that was taken on Jan 14, 2017, was selected for further analysis. After initial corrections and processing, 32 images of alfalfa farms, 32 images of date palm gardens and 32 images of lands covered with bare soil, were selected using GPS data points collected in study area scouting. Shape files of all selected fields were created and utilized for supervised classification training set. The same process was also done for the unsupervised classification method.  To evaluate the classification methods confusion matrix and Kappa coefficient were used to determine the true and miss-classified area under date palm cultivation. It is worth mentioning that these factors alone cannot identify the most powerful method for classification and they just give us a general overview to choose acceptable methods among all available methods. To identify the most powerful method among selected methods, confusion matrix and investigating the pixel transfers between classes is the crucial method.
Results and Discussion
Results of classifications revealed that the overall classification accuracy by using NN, MLC, SVM, MDC, and K-Means were 99.10% (kappa 0.973), 98.77% (kappa 0.975), 98.66% (kappa 0.973), 98.52% (kappa 0.97), and 52.66% (kappa 0.31) respectively. Concerning the confusion matrix in the NN method, the percentage of producer accuracy error in date palm class was 0% and in user, accuracy error was 1.44%. In the review of other methods, the lowest producer accuracy error value in date palm class obtained by NN and SVM methods was 0% and the highest producer accuracy error belonged to MLC method which was 1.35%. Checking the recognition power of other classes showed that in the soil class, the highest producer accuracy error was 2.32% by MDC method and the least one was 0.64% by MLC. For forage class, the highest producer accuracy error was calculated 37.07% by SVM and the least accurate one was 4.92% by MDC. Although the K-Means method with Kappa Coefficient of 0.31 did not have a good classification quality, concerning classes and samples, it successfully could identify date palm according to selective samples with 100% accuracy. Results of calculated date palm area using supervised classification methods versus actual area measurements showed that NN and SVM methods with the coefficient of determination (R²) of 0.9995% and 0.9986% had the highest coefficients. K-Means method with R-square of 0.9228% had a good correlation.
In general, all supervised classification methods obtained acceptable results for distinguishing between date palm classes and two other classes. NN and SVM methods could successfully recognize date palm class. K-Means method also could recognize date palm class but the recognition included some errors such as dark clay soil textures which were classified as the date palm.
Conclusion
In general, overall accuracy and kappa Coefficient alone cannot identify the most powerful method for classifying and these methods just give us a general overview to choose an acceptable percentage of accuracy coefficients among available methods. After the initial selection, to identify the most powerful method of classification the pixel transfer calculations in a confusion matrix would be an acceptable technique.

Keywords

• Date palm
• Neural networks
• Support vector machines
• Supervised classification
• Unsupervised classification

20.1001.1.22286829.1398.9.2.6.7

References

1. Alavipanah, S. K. 2017. Application of Remote Sensing in the Earth sciences (soil). (In Farsi).

2. Alipour, F., M. H. Aghakhani, M. H. Abasspour-Fard. and A. Sepehr. 2014. Demarcation and Estimation of Agricultural Lands Using ETM+ Imagery Data (Case study: Astan Ghods Razavi Great Farm). Journal of Agricultural Machinery 4 (2): 244-254. (In Farsi).

3. Azizi, J., and S. Yazdani. 2007. Investigation Stability Income of Export Date of Iran. Journal of Agricultural Sciences 13: 1-19. (In Farsi).

4. Bannari, A., A. Pacheco, K. Staenz, H. McNairn, and K. Omari. 2006. Estimating and mapping crop residues cover on agricultural lands using hyperspectral and IKONOS data. Remote Sensing of Environment 104: 447-459.

5. Bruzzone, L., and B. Demir. 2014. A review of modern approaches to classification of remote sensing data. Pages 127-143. Land Use and Land Cover Mapping in Europe, Springer.

6. Büttner, G. 2014. CORINE land cover and land cover change products. Pages 55-74. Land Use and Land Cover Mapping in Europe, Springer.

7. Chen, Y., and P. Gong. 2013. Clustering based on eigenspace transformation-CBEST for efficient classification. ISPRS Journal of Photogrammetry and Remote Sensing 83: 64-80.

8. De Maesschalck, R., D. Jouan-Rimbaud, and D. L. Massart. 2000. The mahalanobis distance. Chemometrics and intelligent laboratory systems 50: 1-18.

9. Detailed results of in the country Agricultural General Census. 2015. Statistical Center of Iran. (In Farsi).

10. Fatemi-talab, S. R., M. Madani pour, and S. A. Hashemi. 2015. Estimating the land coverage changes in Rudsar Jungles using NN and MLC methods. Journal of Remote sensing and GIS in Natural Resources 6 (2). (In Farsi).

11. Fazeli-farsani, A., R. Ghazavi, and M. A. Farzaneh. 2015. Evaluation of land use classification algorithms using image integration method. Journal of Remote sensing and GIS in Natural Resources 6 (1). (In Farsi).

12. Frey, K. E., and L. C. Smith. 2007. How well do we know northern land cover? Comparison of four global vegetation and wetland products with a new ground‐truth database for West Siberia. Global Biogeochemical Cycles 21.

13. Fritz, S., L. See, and F. Rembold. 2010. Comparison of global and regional land cover maps with statistical information for the agricultural domain in Africa. International Journal of Remote Sensing 31: 2237-2256.

14. Ghebrezgabher, M. G., T. Yang, X. Yang, X. Wang, and M. Khan. 2016. Extracting and analyzing forest and woodland cover change in Eritrea based on landsat data using supervised classification. The Egyptian Journal of Remote Sensing and Space Science 19: 37-47.

15. Ghorbani, M. A., F. Azani, and L. Naghipour. 2016. Comparing SVM and other supervised classification methods in simulating rainfall and run-off. Research Journal of Aquifers Management 13.

16. Gomez, C., J. C. White, and M. A. Wulder. 2016. Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing 116: 55-72.

17. Gong, W., L. Yuan, W. Fan, X. Wang, and P. Stott. 2016. Comparison to supervised classification modelling in land use cover using Landsat 8 OLI data: an example in Miyun county of North China. Nature Environment and Pollution Technology 15: 243.

18. Huang, C., L. S. Davis, and J. R. Townshend. 2002. An assessment of support vector machines for land cover classification. International Journal of Remote Sensing 23: 725-749.

19. Hansen, M. C., A. Egorov, D. P. Roy, P. Potapov, J. Ju, S. Turubanova, I. Kommareddy, and T. R. Loveland. 2011. Continuous fields of land cover for the conterminous United States using Landsat data: First results from the Web-Enabled Landsat Data (WELD) project. Remote Sensing Letters 2: 279-288.

20. Hashemi Tangestani, M., S. Beyranvand, and M. H. Tayebi. 2013. Detection of changes in Bakhtegan lake at time intervals from 1956 to 2007. Journal of Environmental Studies 39: 189-199. (In Farsi).

21. Hussain, M., D. Chen, A. Cheng, H. Wei, and D. Stanley. 2013. Change detection from remotely sensed images: From pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing 80: 91-106.

22. Khan, A. A., N. Minallah, and S. Khan. 2015. on the performance of supervised classifiers for crop identification and estimation using multi-spectral imagery. Journal of Engineering and Applied Sciences 34.

23. Khatami, R., G. Mountrakis, and S. V. Stehman. 2016. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research. Remote Sensing of Environment 177: 89-100.

24. Kirchhof, W., P. Haberäcker, E. Krauth, G. Kritikos, and R. Winter. 1980. A rapid method to generate spectral theme classification of Landsat imagery. Acta Astronautica 7: 243-253.

25. Kumar, P., D. K. Gupta, V. N. Mishra, and R. Prasad. 2015. Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data. International Journal of Remote Sensing 36: 1604-1617.

26. Lillesand, T., R. W. Kiefer, and J. Chipman. 2014. Remote sensing and image interpretation. John Wiley & Sons.

27. Loveland, T. R., B. C. Reed, J. F. Brown, D. O. Ohlen, Z. Zhu, L. Yang, and J. W. Merchant. 2000. Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data. International Journal of Remote Sensing 21: 1303-1330.

28. NASA. 2017. Landsat Project Description. https://landsat.usgs.gov/landsat-project-statistics.

29. Pal, M., and P. Mather. 2006. Some issues in the classification of DAIS hyperspectral data. International Journal of Remote Sensing 27: 2895-2916.

30. Petropoulos, G. P., K. P. Vadrevu, G. Xanthopoulos, G. Karantounias, and M. Scholze. 2010. A comparison of spectral angle mapper and artificial neural network classifiers combined with Landsat TM imagery analysis for obtaining burnt area mapping. Sensors 10: 1967-1985.

31. Powers, D. M. 2011. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation.

32. Powers, D. M. 2012. The problem with kappa. Pages 345-355. Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics: Association for Computational Linguistics.

33. Radoux, J., C. Lamarche, E. Van Bogaert, S. Bontemps, C. Brockmann, and P. Defourny. 2014. Automated training sample extraction for global land cover mapping. Remote Sensing 6: 3965-3987.

34. Richards, J. A. 1999. Remote sensing digital image analysis. Springer.

35. Rostami, M. A., and H. Afzali. 2016. Remote Sensing of Residue Management in Farms using Landsat 8 Sensor Imagery. Journal of Agricultural Machinery 7 (2): 388-400. (In Farsi).

36. Rostami, M. A., M. H. Raoufat, A. A. Jafari, M. Loghavi, M. Kasraei, and S. M. R. Nazemsadat. 2014. Monitoring of Conservation Tillage and Tillage Intensity by Ground and Satellite Imagery. Journal of Agricultural Machinery 4 (2): 255-265. (In Farsi).

37. Sammut, C., and G. I. Webb. 2011. Encyclopedia of machine learning. Springer Science & Business Media.

38. Shahosseini, R., S. Homayouni, and M. R. Sarajian. 2009. classification remote sensing images using support vector machines. Geometric. (In Farsi).

39. Shao, Y., and R. S. Lunetta. 2012. Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points. ISPRS Journal of Photogrammetry and Remote Sensing 70: 78-87.

40. Tewkesbury, A. P., A. J. Comber, N. J. Tate, A. Lamb, and P. F. Fisher. 2015. A critical synthesis of remotely sensed optical image change detection techniques. Remote Sensing of Environment 160: 1-14.

41. Vapnik V. 1995. The nature of statistical learning theory, Springer-Verlag, New York. 314 pp.

42. Wanga, Q., B. Chena, J. Wang, F. Wanga, H. Hana, S. Li, K. Wang, C. Xiaod, and J. Daid. 2015. Four supervised classification methods for monitoring cotton field of verticillium wilt using TM image. Journal of Animal and Plant Sciences 25: 5-12.

43. Wulder, M. A., J. C. White, M. Cranny, R. J. Hall, J. E. Luther, A. Beaudoin, D. G. Goodenough, and J. A. Dechka. 2008a. Monitoring Canada’s forests. Part 1: Completion of the EOSD land cover project. Canadian Journal of Remote Sensing 34: 549-562.

44. Wulder, M. A., J. C. White, S. N. Goward, J. G. Masek, J. R. Irons, M. Herold, W. B. Cohen, T. R. Loveland, and C. E. Woodcock. 2008b. Landsat continuity: Issues and opportunities for land cover monitoring. Remote Sensing of Environment 112: 955-969.

45. Zobeiry, M., and A. R. Majd. 2013. An Introduction to Remote Sensing Technology and natural resources. University of Tehran press. (In Farsi).