Automated Testing of Spatially-Dependent Environmental Hypotheses through Active Transfer Learning
Abstract: The efficient collection of samples is an important factor in outdoor information gathering applications on account of high sampling costs such as time, energy, and potential destruction to the environment. Utilization of available a-priori data can be a powerful tool for increasing efficiency. However, the relationships of this data with the quantity of interest are often not known ahead of time, limiting the ability to leverage this knowledge for improved planning efficiency. To this end, this work combines transfer learning and active learning through a Multi-Task Gaussian Process and an information-based objective function. Through this combination it can explore the space of hypothetical inter-quantity relationships and evaluate these hypotheses in real-time, allowing this new knowledge to be immediately exploited for future plans. The performance of the proposed method is evaluated against synthetic data and is shown to evaluate multiple hypotheses correctly. Its effectiveness is also demonstrated on real datasets. The technique is able to identify and leverage hypotheses which show a medium or strong correlation to reduce prediction error by a factor of 1.4--3.4 within the first 7 samples, and poor hypotheses are quickly identified and rejected eventually having no adverse effect.
- S.-J. Kwon, et al., “Effects of nitrogen, phosphorus and potassium fertilizers on growth characteristics of two species of bellflower (platycodon grandiflorum),” Journal of Crop Science and Biotechnology, vol. 22, pp. 481–487, 2019.
- M. Guntiñas, et al., “Effects of moisture and temperature on net soil nitrogen mineralization: a laboratory study,” European Journal of Soil Biology, vol. 48, pp. 73–80, 2012. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1164556311000732
- P. M. Furlong, “Foraging, prospecting, and falsification-improving three aspects of autonomous science,” 2018.
- B. Burger, et al., “A mobile robotic chemist,” Nature, vol. 583, no. 7815, pp. 237–241, Jul 2020.
- A. Arora, et al., “Online multi-modal learning and adaptive informative trajectory planning for autonomous exploration,” in Field and Service Robotics, M. Hutter and R. Siegwart, Eds. Cham: Springer International Publishing, 2018, pp. 239–254.
- R. Marchant and F. Ramos, “Bayesian optimisation for intelligent environmental monitoring,” in 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 10 2012, p. nil.
- K. Edelson, “Ergodic trajectory optimization for information gathering,” Master’s thesis, Carnegie Mellon University, Pittsburgh, PA, October 2020.
- A. Candela, et al., “Planetary rover exploration combining remote and in situ measurements for active spectroscopic mapping,” in 2020 IEEE Intl. Conf. on Robotics and Automation (ICRA), 2020, pp. 5986–5993.
- J. N. Fuhg, et al., “State-of-the-art and comparative review of adaptive sampling methods for kriging,” Archives of Computational Methods in Engineering, vol. 28, no. 4, pp. 2689–2747, Aug 2020.
- B. Shahriari, et al., “Taking the human out of the loop: a review of bayesian optimization,” Proceedings of the IEEE, vol. 104, no. 1, pp. 148–175, 2016. [Online]. Available: http://dx.doi.org/10.1109/JPROC.2015.2494218
- H. Leenaers, et al., “Employing elevation data for efficient mapping of soil pollution on floodplains,” Soil Use and Management, vol. 6, no. 3, pp. 105–114, 1990.
- M. Mehta and C. Shao, “Adaptive sampling design for multi-task learning of gaussian processes in manufacturing,” Journal of Manufacturing Systems, vol. 61, no. nil, pp. 326–337, 2021.
- E. V. Bonilla, et al., “Multi-task gaussian process prediction,” in Advances in Neural Information Processing Systems, J. Platt, et al., Eds., vol. 20. Curran Associates, Inc., 2008.
- C. Q. Lam, “Sequential adaptive designs in computer experiments for response surface model fit,” Ph.D. dissertation, The Ohio State University, 2008.
- NEO, “Dataset index.” [Online]. Available: https://neo.gsfc.nasa.gov/dataset_index.php
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.