top of page

Artificial Intelligence for Climate Change

#DidYouKnow that glaciers are melting faster than ever, causing sea levels to rise?

🏔 A glacier is a build-up of snow and ice moving slowly under its own weight, and there are about 200,000 glaciers distributed in the high mountains around the world. [1]

🧊 Glaciers represent the main indicator of #climatechange. Due to global warming, higher sea levels are observed caused by the melting of ice sheets and glaciers.

Over the years, the #Earth has been extensively observed; therefore, one of our biggest datasets is earth observations (#EO).

🛰 EO #satellites play a huge role in the fight against climate change on a global scale by tracking many of its consequences over time. One of those out-turns observed by satellites is glacier shrinkage.

Tracking glacier changes automatically would allow the creation of a global record of glacier area, volume, and mass balance fluctuation. [2] Hence allowing a better understanding of what we could be facing in the past, present, near-and-far future.

💻 Advanced #machinelearning toolkits are being developed, empowering immense progress in the data processing.

🌎 Earth-related research uses #ML tools such as #deeplearning #image #segmentation which has proven to be an efficient method to handle remote sensing satellite observations such as those taken by Sentinel2, among other missions. [3],[4],[5]

#AI will allow us to advance in finding solutions to our fast-regressing climate. But are we contributing enough❓

🔍 #Sentinel2 data can be accessed freely on


[1] Ambinakudige S. (2022). Estimation of area and volume change in the glaciers of the Columbia Icefield, Canada using machine learning algorithms and Landsat images. Remote Sensing Applications. Society and Environment 26.

[2] Vinay Kumar Gaddam, Ramya Boddapati, Tanooj Kumar, Anil V. Kulkarni & Helgi Bjornsson (2022). Application of “OTSU”—an image segmentation method for differentiation of snow and ice regions of glaciers and assessment of mass budget in Chandra basin, Western Himalaya using Remote Sensing and GIS techniques.

Environmental Monitoring and Assessment volume 194.

[3] Yan S., Xu L., Yu G., Yang L., Yun W., Zhu D., Ye S., Yao X. (2021). Glacier classification from Sentinel-2 imagery using spatial-spectral attention convolutional model. International Journal of Applied Earth Observation and Geoinformation 102.

[4] Xie Z., Haritashya U., Asari V., Young B., Bishop M., Kargel J.(2020). GlacierNet: A Deep-Learning Approach for Debris-Covered Glacier Mapping. IEEE Access, (2020), 83495-83510, 8.

[5] Mohajerani Y., Wood M., Velicogna I., Rignot E. (2019). Detection of glacier calving margins with convolutional neural networks: A case study. Remote sensing 11(1).

Contributing Editor:

45 views0 comments

Recent Posts

See All


bottom of page