Machine Learning / AI for Earth Observation

What is this about?

Machine learning for Earth observation refers to the application of machine learning techniques and algorithms to analyze data collected from satellites and other remote sensing sources.
Earth observation involves monitoring the Earth's surface, atmosphere, and oceans using various sensors and platforms like satellites, aircraft, drones, and ground-based instruments.
Machine learning algorithms enable the automated processing and analysis of vast amounts of Earth observation data, providing valuable insights and supporting various applications.

‍

Main research areas

Image classification for land-cover mapping

Machine learning models can be trained to identify and classify various features on Earth's surface, such as buildings, roads, forests, water bodies, agricultural fields, and urban areas, in satellite or aerial images. We develop pipelines involving supervised learning algorithms including tree-based models (e.g, random forest, XGBoost), support vector machines, and deep learning.

‍

Change detection and time-series analysis

Change detection and time-series analysis are important techniques used in remote sensing and geospatial analysis to monitor and understand changes that occur on the Earth's surface over time. These methods involve comparing multiple images acquired at different times to identify and quantify changes in land cover, land use, and other environmental features. Time-series analysis focuses on studying how these changes evolve over a specific period.

‍

Multi-source data integration

Multi-source data integration refers to the process of combining and analyzing information from multiple diverse sources to gain a more comprehensive and accurate understanding of a particular phenomenon, system, or problem. This integration allows for a more holistic perspective and can lead to insights that would be difficult to achieve by considering each data source in isolation. In the context of remote sensing and geospatial analysis, multi-source data integration involves combining data from different sensors, platforms, or types of measurements.

‍

Selected publications

  • Lv, Z., Zhong, P., Wang, W., You, Z., & Falco, N. (2023). Multiscale Attention Network Guided With Change Gradient Image for Land Cover Change Detection Using Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters, 20, 1–5. Link
  • Falco, N., Xia, J., Kang, X., Li, S., & Benediktsson, J. A. (2020). Supervised classification methods in hyperspectral imaging—Recent advances. In Hyperspectral Imaging (Vol. 32, pp. 247–279). Elsevier. Link
  • Benediktsson, J. A., Cavallaro, G., Falco, N., Hedhli, I., Krylov, V. A., Moser, G., Serpico, S. B., & Zerubia, J. (2018). Remote Sensing Data Fusion: Markov Models and Mathematical Morphology for Multisensor, Multiresolution, and Multiscale Image Classification. In Mathematical Models for Remote Sensing Image Processing (pp. 277–323). Springer International Publishing. Link
  • Falco, N., Marpu, P. R., & Benediktsson, J. A. (2016). A toolbox for unsupervised change detection analysis. International Journal of Remote Sensing, 37(7), 1505–1526. Link
  • Xia, J., Falco, N., Benediktsson, J. A., Chanussot, J., & Du, P. (2016). Class-Separation-Based Rotation Forest for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, 13(4), 584–588. Link
  • Falco, N., Benediktsson, J. A., & Bruzzone, L. (2015). Spectral and Spatial Classification of Hyperspectral Images Based on ICA and Reduced Morphological Attribute Profiles. IEEE Transactions on Geoscience and Remote Sensing, 53(11), 6223–6240. Link
  • Falco, N., Benediktsson, J. A., & Bruzzone, L. (2014). A Study on the Effectiveness of Different Independent Component Analysis Algorithms for Hyperspectral Image Classification. Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal Of, 7(6), 2183–2199. Link
  • Falco, N., Mura, M. D., Bovolo, F., Benediktsson, J. A., & Bruzzone, L. (2013). Change Detection in VHR Images Based on Morphological Attribute Profiles. IEEE Geoscience and Remote Sensing Letters, 10(3), 636–640. Link
No items found.

No items found.
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.