This code repository is part of the project Bridging the gap between artificial intelligence and society: Developing responsible and viable solutions for geospatial data (with project no. 18091) of the research program Talent Program Veni 2020, which is (partly) financed by the Dutch Research Council (NWO).
The similarity metrics used to calculate the coherence between a new testing image and the distribution of landscape metrics within the training dataset. It provides the code utilized in publication [1] below.
- Gevaert, C.M. & Belgiu, M. (2022) Assessing the generalization capability of deep learning networks for aerial image classification using landscape metrics. International Journal of Applied Earth Observation and Geoinformation doi: 10.1016/j.jag.2022.103054
- Gevaert, C.M. (2022) Explainable AI for Earth Observation: A review including societal and regulatory perspectives. International Journal of Applied Earth Observations and Geoinformation doi: 10.1016/j.jag.2022.102869
- Micheli, M., Gevaert, C.M., Carman, M., Craglia, M., Daemen, E., Ibrahimb, R.E., Kotsev, A., Mohamed-Ghouse, Z., Schade, S., Schneider, I., Shanley, L.A., Tartaro, A., & Vespe, M. (2022) AI ethics and data governance in the geospatial domain of Digital Earth. Big Data & Soceity doi: 10.1177/20539517221138767
- Gevaert, C.M., Carman, M., Rosman, B., Georgiadou, Y., & Soden, R. (2021) Fairness and accountability of AI in disaster risk management: Opportunities and challenges. Patterns doi: 10.1016/j.patter.2021.100363
Caroline Gevaert
University of Twente / Faculty ITC