Machine learning classification methods in hyperspectral data processing for agricultural applications

ABSTRACT

In agricultural applications hyperspectral imaging is used in cases where differences in spectral reflectance of the examined objects are small. However, the large amount of data generated by hyperspectral sensors requires advance processing methods. Machine learning approaches may play an important role in this task. They are known for decades, but they need high volume of data to compute accurate results. Until recently, the availability of hyperspectral data was a big drawback. It was first used in satellites, later in manned aircrafts and data availability from those platforms was limited because of logistics complexity and high price. Nowadays, hyperspectral sensors are available for unmanned aerial vehicles, which enabled to reach a high volume of data, thus overcoming these issues. This way, the aim of this paper is to present the status of the usage of machine learning approaches in the hyperspectral data processing, with a focus on agriculture applications. Nevertheless, there are not many studies available applying machine learning approach to hyperspectral data for agricultural applications. This apparent limitation was in fact the inspiration for making this survey. Preliminary results using UAV-based data are presented, showing the suitability of machine learning techniques in remote sensed data.

References

1. Sabale, S.P. and Jadhav, C.R. 2015. Hyperspectral Image Classification Methods in Remote Sensing - A Review. 2015InternationalConferenceonComputing Communication Control and Automation (Feb. 2015), 679--683.
2. Qiu, Q. et al. 2017. Survey of supervised classification techniques for hyperspectral images. Sensor Review. 37, 3 (Jun. 2017), 371--382.
3. Ghamisi, P. et al. 2017. Advanced Spectral Classifiers for Hyperspectral Images: A review. IEEE Geoscience and Remote Sensing Magazine. 5, 1 (Mar. 2017), 8--32.
4. Poojary, N. et al. 2015. Automatic target detection in hyperspectral image processing: A review of algorithms. 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) (Aug. 2015), 1991--1996.
5. Tarabalka, Y. 2010. Classification of hyperspectral data using spectral-spatial approaches. Institut National Polytechnique de Grenoble-INPG.
6. Young, M.E. 2002. From early child development to human development: Investing in our children's future. World Bank Publications.
7. Atzberger, C. 2013. Advances in Remote Sensing of Agriculture: Context Description, Existing Operational Monitoring Systems and Major Information Needs. Remote Sensing. 5, 2 (Feb. 2013), 949--981.
8. Liaghat, S. et al. 2010. A Review: The Role of Remote Sensing in Precision Agriculture. American Journal of Agricultural and Biological Sciences. 5, 1 (Mar. 2010), 50--55.
9. Uba, N.K. 2016. Land use and land cover classification using deep learning techniques. Arizona State University.
10. Elarab, M. 2015. The application of unmanned aerial vehicle to precision agriculture: Chlorophyll, nitrogen, and evapotranspiration estimation. Utah State University.
11. Karalasa, K. et al. 2015. Deep learning for multi-label land cover classification. SPIE Remote Sensing (2015), 96430Q---96430Q.
12. Prasad, S. et al. 2015. Introduction to the Issue on Advances in Hyperspectral Data Processing and Analysis. IEEE Journal of Selected Topics in Signal Processing. 9, 6 (Sep. 2015), 961--963.
13. Benediktsson, J.A. et al. 2012. Very High-Resolution Remote Sensing: Challenges and Opportunities {Point of View}. Proceedings of the IEEE. 100, 6 (Jun. 2012), 1907--1910.
14. Shippert, P. 2003. Introduction to hyperspectral image analysis. Online Journal of Space Communication. 3, (2003), 13.
15. Manolakis, D. et al. 2003. Hyperspectral image processing for automatic target detection applications. Lincoln Laboratory Journal. 14, 1 (2003), 79--116.
16. Yang, M. et al. 2015. Compressive hyperspectral imaging via adaptive sampling and dictionary learning. arXiv:1512.00901 {cs}. (Dec. 2015).
17. Geoinformatics|DigitalTextbookLibrary:2008. http://www.tankonyvtar.hu/en/tartalom/tamop425/0032_terinformatika/ch04s04.html. Accessed: 2018-02-06.
18. Adão, T. et al. 2017. Hyperspectral Imaging: A Review on UAV-Based Sensors, Data Processing and Applications for Agriculture and Forestry. Remote Sensing. 9, 11 (Oct. 2017), 1110.
19. Verleysen, M. et al. eds. 2013. Proceedings / 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013: Bruges, Belgium, April 24 - 25 - 26, 2013. Ciaco.
20. Adaptive Control Processes: 1961. https://press.princeton.edu/titles/101.html. Accessed: 2018-01-14.
21. Alajlan, N. et al. 2012. Fusion of supervised and unsupervised learning for improved classification of hyperspectral images. Information Sciences. 217, (Dec. 2012), 39--55.
22. Alonso, M.C. et al. 2011. Consequences of the Hughes phenomenon on some classification techniques. Proceedings of the ASPRS 2001 annual conference (2011), 1--5.
23. Camps-Valls, G. et al. 2014. Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods. IEEE Signal Processing Magazine. 31, 1 (Jan. 2014), 45--54.
24. Plaza, A. et al. 2009. Recent advances in techniques for hyperspectral image processing. Remote Sensing of Environment. 113, (Sep. 2009), S110--S122.
25. Gheyas, I.A. and Smith, L.S. 2010. Feature subset selection in large dimensionality domains. Pattern Recognition. 43, 1 (Jan. 2010), 5--13.
26. Salimi, A. et al. 2017. Using a Feature Subset Selection method and Support Vector Machine to address curse of dimensionality and redundancy in Hyperion hyperspectral data classification. The Egyptian Journal of Remote Sensing and Space Science. (Mar. 2017).
27. Shafri, H.Z.M. 2016. Machine Learning in Hyperspectral and Multispectral Remote Sensing Data Analysis. Artificial Intelligence Science and Technology. WORLD SCIENTIFIC. 3--9.
28. Mitchell, T.M. 1997. Machine Learning. McGraw-Hill, Inc.
29. Huang, X. and Jensen, J.R. 1997. A machine-learning approach to automated knowledge-base building for remote sensing image analysis with GIS data. Photogrammetric engineering and remote sensing. 63, 10 (1997), 1185--1193.
30. Linden, S. van der et al. 2007. Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines. Journal of Applied Remote Sensing. 1, 1 (Oct. 2007), 013543.
31. Shang, X. 2013. Evaluating the capability of machine-learning algorithms and object-oriented classification techniques using hyperspectral remote sensing for the discrimination of Australian native forest species in southeastern Australia. University of Wollongong Thesis Collection 1954--2016. (Jan. 2013).
32. Honkavaara, E. et al. 2012. HYPERSPECTRAL REFLECTANCE SIGNATURES AND POINT CLOUDS FOR PRECISION AGRICULTURE BY LIGHT WEIGHT UAV IMAGING SYSTEM. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. I-7, (Jul. 2012), 353--358.
33. Petersson, H. et al. 2016. Hyperspectral image analysis using deep learning #x2014; A review. 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) (Dec. 2016), 1--6.
34. LeCun, Y. et al. 2015. Deep learning. Nature. 521, 7553 (May 2015), 436.
35. Mou, L. et al. 2017. Deep Recurrent Neural Networks for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing. 55, 7 (Jul. 2017), 3639--3655.
36. Zhang, L. et al. 2016. Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art. IEEE Geoscience and Remote Sensing Magazine. 4, 2 (Jun. 2016), 22--40.
37. Ball, J.E. et al. 2018. Special Section Guest Editorial: Feature and Deep Learning in Remote Sensing Applications. Journal of Applied Remote Sensing. 11, 4 (Jan. 2018), 042601.
38. Zhu, X.X. et al. 2017. Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources. IEEE Geoscience and Remote Sensing Magazine. 5, 4 (Dec. 2017), 8--36.
39. 10 Breakthrough Technologies 2013: 2013. https://www.technologyreview.com/lists/technologies/2013/.Accessed: 2018-01-15.
40. Yalcin, H. 2017. Plant phenology recognition using deep learning: Deep-Pheno. 2017 6th International Conference on Agro-Geoinformatics (Aug. 2017), 1--5.
41. Liu, Z.-Y. et al. 2010. Application of neural networks to discriminate fungal infection levels in rice panicles using hyperspectral reflectance and principal components analysis. Computers and Electronics in Agriculture. 72, 2 (Jul. 2010), 99--106.
42. Yeh, Y.-H.F. et al. 2013. A Comparison of Machine Learning Methods on Hyperspectral Plant Disease Assessments. IFAC Proceedings Volumes. 46, 4 (2013), 361--365.
43. Singh, A. et al. 2016. Machine Learning for High-Throughput Stress Phenotyping in Plants. Trends in Plant Science. 21, 2 (Feb. 2016), 110--124.
44. Dutta, R. et al. 2015. Interactive visual big data analytics for large area farm biosecurity monitoring: i-EKbase system. Proceedings of the 4th International Conference on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications-Volume 41 (2015), 9--18.
45. Fletcher, R.S. and Turley, R.B. 2017. Employing Canopy Hyperspectral Narrowband Data and Random Forest Algorithm to Differentiate Palmer Amaranth from Colored Cotton. American Journal of Plant Sciences. 08, 12 (Nov. 2017), 3258.
46. Ashourloo, D. et al. 2016. An Investigation Into Machine Learning Regression Techniques for the Leaf Rust Disease Detection Using Hyperspectral Measurement. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 9, 9 (Sep. 2016), 4344--4351.
47. Ronneberger, O. et al. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 {cs}. (May 2015).

Index Terms

• Information systems

  • Information systems applications

    • Decision support systems

      • Data analytics

    • Process control systems

    • Spatial-temporal systems

      • Geographic information systems