Back to Search
Start Over
Spatial dependence between training and test sets: another pitfall of classification accuracy assessment in remote sensing
- Source :
- Machine Learning, Machine Learning, Springer Verlag, 2021, ⟨10.1007/s10994-021-05972-1⟩
- Publication Year :
- 2021
- Publisher :
- Springer Science and Business Media LLC, 2021.
-
Abstract
- International audience; Spatial autocorrelation is inherent to remotely sensed data. Nearby pixels are more similar than distant ones. This property can help to improve the classification performance, by adding spatial or contextual features into the model. However, it can also lead to overestimation of generalisation capabilities, if the spatial dependence between training and test sets is ignored. In this paper, we review existing approaches that deal with spatial autocorrelation for image classification in remote sensing and demonstrate the importance of bias in accuracy metrics when spatial independence between the training and test sets is not respected. We compare three spatial and non-spatial cross-validation strategies at pixel and object levels and study how performances vary at different sample sizes. Experiments based on Sentinel-2 data for mapping two simple forest classes show that spatial leave-one-out cross-validation is the better strategy to provide unbiased estimates of predictive error. Its performance metrics are consistent with the real quality of the resulting map contrary to traditional non-spatial cross-validation that overestimates accuracy. This highlight the need to change practices in classification accuracy assessment. To encourage it we developped Museo ToolBox, an open-source python library that makes spatial cross-validation possible.
- Subjects :
- Contextual image classification
Pixel
Property (programming)
Computer science
Overfitting
Cross-validation
02 engineering and technology
Remote sensing
Python (programming language)
Accuracy assessment
Artificial Intelligence
Sample size determination
020204 information systems
0202 electrical engineering, electronic engineering, information engineering
[INFO]Computer Science [cs]
020201 artificial intelligence & image processing
Spatial dependence
computer
Spatial analysis
Spatial autocorrelation
Software
Independence (probability theory)
computer.programming_language
Subjects
Details
- ISSN :
- 15730565 and 08856125
- Volume :
- 111
- Database :
- OpenAIRE
- Journal :
- Machine Learning
- Accession number :
- edsair.doi.dedup.....2135d44a6c6d656886049e907da00d63
- Full Text :
- https://doi.org/10.1007/s10994-021-05972-1