Abstract
Geospatial information systems (GIS) support decision making and situational awareness in a wide variety of applications. These systems often require large amounts of labeled data to be displayed in a way that is easy to use and understand. Manually editing these information displays can be extremely time-consuming for an analyst. Algorithms have been designed to alleviate some of this work by automatically generating map displays or digitizing features. However, these systems regularly make mistakes, requiring analysts to verify and correct their output. This human-in-the-loop process of validating the algorithm’s labels can provide a means to continuously improve a model over time by using interactive machine learning (IML). This process allows for systems that can function with little or no training data and as the features continue to evolve. Such systems must also account for the strengths and limitations of both the analysts and underlying algorithms to avoid unnecessary frustration, encourage adoption, and increase productivity of the human-machine team. In this chapter, we introduce three examples of how IML has been used in GIS systems for airfield change detection, geographic region digitization and digital map editing. We also describe several considerations for designing IML workflows to ensure that the analyst and system complement one another, resulting in increased productivity and quality of the GIS output. Finally, we will consider new challenges that arise when applying IML to the complex task of automatic map labeling.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balboa, J.L.G., López, F.J.A.: Generalization-oriented road line classification by means of an artificial neural network. Geoinformatica 12(3), 289–312 (2008)
Bastani, F., et al.: Machine-assisted map editing. In: Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 23–32 (2018)
Bourgin, D.D., Peterson, J.C., Reichman, D., Russell, S.J., Griffiths, T.L.: Cognitive model priors for predicting human decisions. In: International conference on machine learning, pp. 5133–5141. PMLR (2019)
Do Nascimento, H.A., Eades, P.: User hints for map labeling. J. Vis. Lang. Comput. 19(1), 39–74 (2008)
Fleetwood, M.D., Byrne, M.D.: Modeling the visual search of displays: a revised act-r model of icon search based on eye-tracking data. Hum. Comput. Interact. 21(2), 153–197 (2006)
Karsznia, I., Sielicka, K.: When traditional selection fails: How to improve settlement selection for small-scale maps using machine learning. ISPRS Int. J. Geo-Inf. 9(4), 230 (2020)
Lohrenz, M.C., Trafton, J.G., Beck, M.R., Gendron, M.L.: A model of clutter for complex, multivariate geospatial displays. Hum. Factors 51(1), 90–101 (2009)
Michael, C.J., Acklin, D., Scheuerman, J.: On interactive machine learning and the potential of cognitive feedback. In: 2nd Workshop on Deep Models and Artificial Intelligence for Defense Applications (2020)
Michael, C.J., Dennis, S.M., Maryan, C., Irving, S., Palmston, M.L.: A general framework for human-machine digitization of geographic regions from remotely sensed imagery. In: Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL 2019 (2019)
Munro, R.: Human-in-the-loop Machine Learning. O’REILLY MEDIA, Newton (2020)
Opach, T., Korycka-Skorupa, J., Karsznia, I., Nowacki, T., Golebiowska, I., Rod, J.: Visual clutter reduction in zoomable proportional point symbol maps. Cartography Geog. Inf. Sci. 46(4), 347–367 (2019)
Paik, J., Pirolli, P.: Act-r models of information foraging in geospatial intelligence tasks. Comput. Math. Organ. Theory 21(3), 274–295 (2015)
Ruprecht, B., et al.: Concept learning based on human interaction and explainable AI. In: SPIE Defense and Commercial Sensing (2021)
Salvucci, D.D.: Modeling driver behavior in a cognitive architecture. Hum. Factors 48(2), 362–380 (2006)
Saran, A., Zhang, R., Short, E.S., Niekum, S.: Efficiently guiding imitation learning algorithms with human gaze. arXiv preprint arXiv:2002.12500 (2020)
Stoter, J., et al.: Methodology for evaluating automated map generalization in commercial software. Comput. Environ. Urban Syst. 33(5), 311–324 (2009)
Trafton, J.G., Hiatt, L.M., Brumback, B., McCurry, J.M.: Using cognitive models to train big data models with small data. In: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1413–1421 (2020)
Weibel, R., Keller, S., Reichenbacher, T.: Overcoming the knowledge acquisition bottleneck in map generalization: The role of interactive systems and computational intelligence. In: Frank, A.U.., Kuhn, W. (eds.) COSIT 1995. LNCS, vol. 988, pp. 139–156. Springer, Heidelberg (1995). https://doi.org/10.1007/3-540-60392-1_10
Yoeli, P.: The logic of automated map lettering. The Cartographic J. 9(2), 99–108 (1972)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply
About this chapter
Cite this chapter
Scheuerman, J., Michael, C.J., Landreneau, B., Acklin, D.M., Harman, J.L. (2021). Designing Interactive Machine Learning Systems for GIS Applications. In: Lawless, W.F., Llinas, J., Sofge, D.A., Mittu, R. (eds) Engineering Artificially Intelligent Systems. Lecture Notes in Computer Science(), vol 13000. Springer, Cham. https://doi.org/10.1007/978-3-030-89385-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-89385-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89384-2
Online ISBN: 978-3-030-89385-9
eBook Packages: Computer ScienceComputer Science (R0)