ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data

Maria C. Novitasari, Johannes Quaas, Miguel Rodrigues
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:3358-3366, 2024.

Abstract

High-resolution simulations, such as the ICOsahedral Non-hydrostatic Large-Eddy Model (ICON-LEM), provide valuable insights into the complex interactions among aerosols, clouds, and precipitation, which are the major contributors to climate change uncertainty. However, due to their exorbitant computational costs, they can only be employed for a limited period and geographical area. To address this, we propose a more cost-effective method powered by an emerging machine learning approach to better understand the intricate dynamics of the climate system. Our approach involves active learning techniques by leveraging high-resolution climate simulation as an oracle that is queried based on an abundant amount of unlabeled data drawn from satellite observations. In particular, we aim to predict autoconversion rates, a crucial step in precipitation formation, while significantly reducing the need for a large number of labeled instances. In this study, we present novel methods: custom fusion query strategies for labeling instances – weight fusion (WiFi) and merge fusion (MeFi) – along with active feature selection based on SHAP. These methods are designed to tackle real-world challenges – in this case, climate change, with a specific focus on the prediction of autoconversion rates – due to their simplicity and practicality in application.

Cite this Paper


BibTeX
@InProceedings{pmlr-v238-novitasari24a, title = {{ALAS}: Active Learning for Autoconversion Rates Prediction from Satellite Data}, author = {Novitasari, Maria C. and Quaas, Johannes and Rodrigues, Miguel}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {3358--3366}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/novitasari24a/novitasari24a.pdf}, url = {https://proceedings.mlr.press/v238/novitasari24a.html}, abstract = {High-resolution simulations, such as the ICOsahedral Non-hydrostatic Large-Eddy Model (ICON-LEM), provide valuable insights into the complex interactions among aerosols, clouds, and precipitation, which are the major contributors to climate change uncertainty. However, due to their exorbitant computational costs, they can only be employed for a limited period and geographical area. To address this, we propose a more cost-effective method powered by an emerging machine learning approach to better understand the intricate dynamics of the climate system. Our approach involves active learning techniques by leveraging high-resolution climate simulation as an oracle that is queried based on an abundant amount of unlabeled data drawn from satellite observations. In particular, we aim to predict autoconversion rates, a crucial step in precipitation formation, while significantly reducing the need for a large number of labeled instances. In this study, we present novel methods: custom fusion query strategies for labeling instances – weight fusion (WiFi) and merge fusion (MeFi) – along with active feature selection based on SHAP. These methods are designed to tackle real-world challenges – in this case, climate change, with a specific focus on the prediction of autoconversion rates – due to their simplicity and practicality in application.} }
Endnote
%0 Conference Paper %T ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data %A Maria C. Novitasari %A Johannes Quaas %A Miguel Rodrigues %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-novitasari24a %I PMLR %P 3358--3366 %U https://proceedings.mlr.press/v238/novitasari24a.html %V 238 %X High-resolution simulations, such as the ICOsahedral Non-hydrostatic Large-Eddy Model (ICON-LEM), provide valuable insights into the complex interactions among aerosols, clouds, and precipitation, which are the major contributors to climate change uncertainty. However, due to their exorbitant computational costs, they can only be employed for a limited period and geographical area. To address this, we propose a more cost-effective method powered by an emerging machine learning approach to better understand the intricate dynamics of the climate system. Our approach involves active learning techniques by leveraging high-resolution climate simulation as an oracle that is queried based on an abundant amount of unlabeled data drawn from satellite observations. In particular, we aim to predict autoconversion rates, a crucial step in precipitation formation, while significantly reducing the need for a large number of labeled instances. In this study, we present novel methods: custom fusion query strategies for labeling instances – weight fusion (WiFi) and merge fusion (MeFi) – along with active feature selection based on SHAP. These methods are designed to tackle real-world challenges – in this case, climate change, with a specific focus on the prediction of autoconversion rates – due to their simplicity and practicality in application.
APA
Novitasari, M.C., Quaas, J. & Rodrigues, M.. (2024). ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:3358-3366 Available from https://proceedings.mlr.press/v238/novitasari24a.html.

Related Material