Machine Learning for the Detection of Oil Spills in Satellite Radar Images

Abstract

During a project examining the use of machine learning techniques for oil spill detection, we encountered several essential questions that we believe deserve the attention of the research community. We use our particular case study to illustrate such issues as problem formulation, selection of evaluation measures, and data preparation. We relate these issues to properties of the oil spill application, such as its imbalanced class distribution, that are shown to be common to many applications. Our solutions to these issues are implemented in the Canadian Environmental Hazards Detection System (CEHDS), which is about to undergo field testing.

References

  1. Aha, D., Kibler, D., & Albert, M. (1991). Instance-Based Learning Algorithms. Machine Learning, 6(1), 37-66.

    Google Scholar 

  2. Aha, D. (1992). Generalizing from Case Studies: ACase Study. Proceedings of the Ninth International Conference on Machine Learning (pp. 1-10), Morgan Kaufmann.

  3. Brodley, C., & Smyth, P. (1995). The Process of Applying Machine Learning Algorithms. Working Notes for Applying Machine Learning in Practice: A Workshop at the Twelfth International Conference on Machine Learning, Technical Report AIC-95-023 (pp. 7-13), NRL, Navy Center for Applied Research in AI, Washington, DC.

    Google Scholar 

  4. Burl, M.C., Asker, L., Smyth, P., Fayyad, U.M., Perona, P., Crumpler, L., & Aubele, J. (this issue). Learning to Recognize Volcanoes on Venus. Machine Learning, 30, 165-194.

  5. Caruana, R. (1993). Multitask Learning: A Knowledge-based Source of Inductive Bias. Proceedings of the Tenth International Conference on Machine Learning (pp. 41-48), Morgan Kaufmann.

  6. Catlett, J. (1991). Megainduction: A Test Flight. Proceedings of the Eighth International Workshop on Machine Learning (pp. 596-599), Morgan Kaufmann.

  7. Cherkauer, K.J., & Shavlik, J.W. (1994). Selecting Salient Features for Machine Learning from Large Candidate Pools through Parallel Decision-Tree Construction. In Kitano, H. & Hendler, J. (Eds.), Massively Parallel Artificial Intelligence (pp. 102-136), AAAI Press/MIT Press.

  8. Clark, P. & Matwin, S. (1993). Using Qualitative Models to Guide Inductive Learning. Proceedings of the Tenth International Conference on Machine Learning (pp. 49-56), Morgan Kaufmann.

  9. Clearwater, S., & Stern, E. (1991). A Rule-Learning Program in High Energy Physics Event Classification. Comp. Physics Comm., 67, 159-182.

    Google Scholar 

  10. DeRouin, E., Brown, J., Beck, H., Fausett, L., & Schneider, M. (1991). Neural Network Training on Unequally Represented Classes. In Dagli, C.H., Kumara, S.R.T., & Shin, Y.C. (Eds.), Intelligent Engineering Systems Through Artificial Neural Networks, pp. 135-145, ASME Press.

  11. Dietterich, T.G., Hild, H., & Bakiri, G. (1995). A Comparison of ID3 and Backpropagation for English Text-to-Speech Mapping. Machine Learning, 18, 51-80.

    Google Scholar 

  12. Dietterich, T.G., Lathrop, R.H., & Lozano-Perez, T. (1997). Solving the Multiple-Instance Problem with Axis-Parallel Rectangles. Artificial Intelligence, 89(1-2), 31-71.

    Google Scholar 

  13. Ezawa, K.J., Singh, M., & Norton, S.W. (1996). Learning Goal Oriented Bayesian Networks for Telecommunications Management. Proceedings of the Thirteenth International Conference on Machine Learning (pp. 139-147), Morgan Kaufmann.

  14. Fawcett, T., & Provost, F. (1997). Adaptive Fraud Detection. Data Mining and Knowledge Discovery, 1(3), 291-316.

    Google Scholar 

  15. Fayyad, U.M., Weir, N., & Djorgovski, S. (1993). SKICAT: A Machine Learning System for Automated Cataloging of Large Scale Sky Surveys. Proceedings of the Tenth International Conference on Machine Learning (pp. 112-119), Morgan Kaufmann.

  16. Floyd, S., & Warmuth, M. (1995). Sample Compression, Learnability, and the Vapnik-Chervonenkis Dimension. Machine Learning, 21, 269-304.

    Google Scholar 

  17. Hart, P.E. (1968). The Condensed Nearest Neighbor Rule. IEEE Transactions on Information Theory, IT-14, 515-516.

    Google Scholar 

  18. Haverkamp, D., Tsatsoulis, C., & Gogineni, S. (1994). The Combination of Algorithmic and Heuristic Methods for the Classification of Sea Ice Imagery. Remote Sensing Reviews, 9, 135-159.

    Google Scholar 

  19. Heerman, P. D., & Khazenie, N. (1992). Classification of Multispectral Remote Sensing Data using a backpropagation Neural Network. IEEE Trans. of Geoscience and Remote Sensing, 30, 81-88.

    Google Scholar 

  20. Holte, R. C., Acker, L., & Porter, B.W. (1989). Concept Learning and the Problem of Small Disjuncts. Proceedings of the International Joint Conference on Artificial Intelligence (pp. 813-818), Morgan Kaufmann.

  21. Honda, T., Motizuki, H., Ho, T.B., & Okumura, M. (1997). Generating Decision Trees from an Unbalanced Data Set. In van Someren, M., & Widmer, G. (Eds.), Poster papers presented at the 9th European Conference on Machine Learning (pp. 68-77).

  22. Hovland, H. A., Johannessen, J. A., & Digranes, G. (1994). Slick Detection in SAT Images. Proceedings of IGARSS'94 (pp. 2038-2040).

  23. Ioerger, T.R., Rendell, L.A., & Subramaniam, S. (1995). Searching for Representations to Improve Protein Sequence Fold-Class Prediction. Machine Learning, 21, 151-176.

    Google Scholar 

  24. Keeney, R.L., & Raiffa, H. (1993). Decisions with Multiple Objectives: Preferences and Value Tradeoffs, Cambridge University Press.

  25. Kohavi, R., & John, G.H. (to appear). Wrappers for Feature Subset Selection. Artificial Intelligence (special issue on relevance).

  26. Kohavi, R., & John, G.H. (1995). Automatic Parameter Selection by Minimizing Estimated Error. Proceedings of the Twelfth International Conference on Machine Learning (pp. 304-312), Morgan Kaufmann.

  27. Kononenko, I., & Bratko, I. (1991). Information-Based Evaluation Criterion for Classifier' Performance. Machine Learning, 6, 67-80.

    Google Scholar 

  28. Kubat, M., Holte, R., & Matwin, S. (1997). Learning when Negative Examples Abound. Machine Learning: ECML-97, Lecture Notes in Artificial Intelligence 1224 (pp. 146-153), Springer.

  29. Kubat, M., & Matwin, S. (1997). Addressing the Curse of Imbalanced Training Sets: One-Sided Sampling. Proceedings of the Fourteenth International Conference on Machine Learning (pp. 179-186), Morgan Kaufmann.

  30. Kubat, M., Pfurtscheller, G., & Flotzinger D. (1994). AI-Based Approach to Automatic Sleep Classification. Biological Cybernetics, 79, 443-448.

    Google Scholar 

  31. Kubat, M., & Widmer, G. (Eds.) (1996). Proceedings of the ICML'96 Pre-Conference Workshop on Learning in Context-Sensitive Domains.

  32. Langley, P., & Simon, H.A. (1995). Applications of Machine Learning and Rule Induction. Communications of the ACM, 38(11), 55-64.

    Google Scholar 

  33. Lee, Y., Buchanan, B.G., & Aronis, J.M. (this issue). Learning Rules to Predict Rodent Carcinogenicity. Machine Learning, 30, 217-240.

  34. Lewis, D., & Catlett, J. (1994). Heterogeneous Uncertainty Sampling for Supervised Learning. Proceedings of the Eleventh International Conference on Machine Learning (pp. 148-156), Morgan Kaufmann.

  35. Lewis, D., & Gale, W. (1994). A Sequential Algorithm for Training Text Classifiers. Proceedings of the Seventeenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 3-12), Springer-Verlag.

  36. Lubinsky, David (1994). Bivariate Splits and Consistent Split Criteria in Dichotomous Classification Trees. Ph.D. thesis, Computer Science, Rutgers University.

  37. Murphy, P., & Aha, D. (1994). UCIRepository of Machine Learning Databases (machine-readable data repository). University of California, Irvine.

    Google Scholar 

  38. Ossen, A., Zamzow, T., Oswald, H., & Fleck, E. (1994). Segmentation of Medical Images Using Neural-Network Classifiers. Proceedings of the International Conference on Neural Networks and Expert Systems in Medicine and Healthcare (NNESMED'94) (pp. 427-432).

  39. Pazzani, M., Merz, C., Murphy, P., Ali, K., Hume, T., & Brunk, C. (1994). Reducing Misclassification Costs. Proceedings of the Eleventh International Conference on Machine Learning (pp. 217-225), Morgan Kaufmann.

  40. Pfurtscheller, G., Flotzinger, D., & Kalcher, J. (1992). Brain-Computer Interface-A New Communication Device for Handicapped Persons. In Zagler, W. (Ed.), Computer for Handicapped Persons: Proceedings of the Third International Conference (pp. 409-415).

  41. Provost, F.J., & Buchanan, B.G. (1995). Inductive Policy: The Pragmatics of Bias Selection. Machine Learning, 20(1/2), 35-62.

    Google Scholar 

  42. Provost, F.J., & Fawcett, T. (1997). Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions. Proceedings of the Third International Conference on Knowledge Discovery and Data Mining (pp. 43-48).

  43. Quinlan, J.R. (1993). C4.5: Programs for Machine Learning. Morgan Kaufmann.

  44. Riddle, P., Segal, R., & Etzioni, O. (1994). Representation Design and Brute-Force Induction in a Boeing Manufacturing Domain. Applied Artificial Intelligence, 8, 125-147.

    Google Scholar 

  45. Rieger, A. (1995). Data Preparation for Inductive Learning in Robotics. Proceedings of the IJCAI-95 workshop on Data Engineering for Inductive Learning (pp. 70-78).

  46. Saitta, L., Giordana, A., & Neri, F. (1995). What Is the “Real World”?. Working Notes for Applying Machine Learning in Practice: A Workshop at the Twelfth International Conference on Machine Learning, Technical Report AIC-95-023 (pp. 34-40), NRL, Navy Center for Applied Research in AI, Washington, DC.

    Google Scholar 

  47. Shapiro, A.D. (1987). Structured Induction in Expert Systems. Addison-Wesley.

  48. Skalak, D. (1994). Prototype and Feature Selection by Sampling and Random Mutation Hill Climbing Algorithms. Proceedings of the Eleventh International Conference on Machine Learning (pp. 293-301), Morgan Kaufmann.

  49. Solberg, A.H.S., & Solberg, R. (1996). A Large-Scale Evaluation of Features for Automatic Detection of Oil Spills in ERS SAR Images. IEEE Symp. Geosc. Rem. Sens (IGARSS) (pp. 1484-1486).

  50. Solberg, A.H.S., & Volden, E. (1997). Incorporation of Prior Knowledge in Automatic Classification of Oil Spills in ERS SAR Images. IEEE Symp. Geosc. Rem. Sens (IGARSS) (pp. 157-159).

  51. Swets, J.A. (1988). Measuring the Accuracy of Diagnostic Systems. Science, 240, 1285-1293.

    Google Scholar 

  52. Tomek, I. (1976). Two Modifications of CNN. IEEE Transactions on Systems, Man and Cybernetics, SMC-6, 769-772.

    Google Scholar 

  53. Turney, P. (1995). Data Engineering for the Analysis of Semiconductor Manufacturing Data. Proceedings of the IJCAI-95 workshop on Data Engineering for Inductive Learning (pp. 50-59).

  54. Turney, P. (1993). Exploiting Context when Learning to Classify. Proceedings of the European Conference on Machine Learning (pp. 402-407), Springer-Verlag.

  55. van Rijsbergen, C.J. (1979). Information Retrieval (second edition), Butterworths.

  56. Venables, W.N., & Ripley, B.D. (1994). Modern Applied Statistics with S-Plus. Springer-Verlag.

  57. von Winterfeldt, D., & Edwards, W. (1986). Decision Analysis and Behavioral Research. Cambridge University Press.

  58. Widmer, G., & Kubat, M. (1996). Learning in the Presence of Concept Drift and Hidden Contexts. Machine Learning, 23, 69-101.

    Google Scholar 

  59. Zhang, J. (1992). Selecting Typical Instances in Instance-Based Learning. Proceedings of the Ninth International Machine Learning Workshop (pp. 470-479), Morgan Kaufmann.

Download references

Author information

Affiliations

Authors

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Kubat, M., Holte, R.C. & Matwin, S. Machine Learning for the Detection of Oil Spills in Satellite Radar Images. Machine Learning 30, 195–215 (1998). https://doi.org/10.1023/A:1007452223027

Download citation

  • Inductive learning
  • classification
  • radar images
  • methodology