Journal
REMOTE SENSING
Volume 13, Issue 9, Pages -Publisher
MDPI
DOI: 10.3390/rs13091623
Keywords
genetic programming; evolutionary computation; machine learning; classification; multiclass classification; feature construction; hyperfeatures; spectral indices
Categories
Funding
- FCT of LASIGE Research Unit [UIDB/00408/2020, UIDP/00408/2020]
- FCT of CEF [UIDB/00239/2020]
- project BINDER [PTDC/CCIINF/29168/2017]
- project OPTOX [PTDC/CTA-AMB/30056/2017]
- project PREDICT [PTDC/CCI-CIF/29877/2017]
- project INTERPHENO [PTDC/ASP-PLA/28726/2017]
- project GADgET [DSAIPA/DS/0022/2018]
- project AICE [DSAIPA/DS/0113/2019]
- [SFRH/BD/143972/2019]
- Fundação para a Ciência e a Tecnologia [SFRH/BD/143972/2019] Funding Source: FCT
Ask authors/readers for more resources
Genetic Programming (GP) is a powerful machine learning algorithm that can produce readable white-box models. In this work, the M3GP algorithm is used to create hyperfeatures from satellite bands in order to improve the classification of land cover types. The addition of evolved hyperfeatures results in better performance of ML algorithms in multiclass classifications.
Genetic programming (GP) is a powerful machine learning (ML) algorithm that can produce readable white-box models. Although successfully used for solving an array of problems in different scientific areas, GP is still not well known in the field of remote sensing. The M3GP algorithm, a variant of the standard GP algorithm, performs feature construction by evolving hyperfeatures from the original ones. In this work, we use the M3GP algorithm on several sets of satellite images over different countries to create hyperfeatures from satellite bands to improve the classification of land cover types. We add the evolved hyperfeatures to the reference datasets and observe a significant improvement of the performance of three state-of-the-art ML algorithms (decision trees, random forests, and XGBoost) on multiclass classifications and no significant effect on the binary classifications. We show that adding the M3GP hyperfeatures to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI, and NBR. We also compare the performance of the M3GP hyperfeatures in the binary classification problems with those created by other feature construction methods such as FFX and EFS.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available