Multi-Label Classification on Remote-Sensing Images

TL;DR

This paper applies machine learning and deep learning models to classify land cover and atmospheric features in satellite images of the Amazon rainforest, achieving high accuracy with an F2 score of 0.927.

Contribution

It introduces a multi-label classification approach using transfer learning and ensemble methods on satellite imagery for land and atmospheric feature detection.

Findings

Best F2 score achieved is 0.927

Transfer learning with pre-trained ImageNet models is effective

Ensemble models outperform individual classifiers

Abstract

Acquiring information on large areas on the earth's surface through satellite cameras allows us to see much more than we can see while standing on the ground. This assists us in detecting and monitoring the physical characteristics of an area like land-use patterns, atmospheric conditions, forest cover, and many unlisted aspects. The obtained images not only keep track of continuous natural phenomena but are also crucial in tackling the global challenge of severe deforestation. Among which Amazon basin accounts for the largest share every year. Proper data analysis would help limit detrimental effects on the ecosystem and biodiversity with a sustainable healthy atmosphere. This report aims to label the satellite image chips of the Amazon rainforest with atmospheric and various classes of land cover or land use through different machine learning and superior deep learning models. Evaluation is done based on the F2 metric, while for loss function, we have both sigmoid cross-entropy as well as softmax cross-entropy. Images are fed indirectly to the machine learning classifiers after only features are extracted using pre-trained ImageNet architectures. Whereas for deep learning models, ensembles of fine-tuned ImageNet pre-trained models are used via transfer learning. Our best score was achieved so far with the F2 metric is 0.927.