Crisis-FACTs Reworked

Motivation

Consistent and reproducible evaluation enables research advancements. While CrisisFACTs presents a unique challenge in the current retrieval landscape, its evaluation needs to be reconsidered from the ground up to support new research efforts. The objective of the task is to select relevant texts for crisis operators and then create concise summaries. Currently, the evaluation relies on humans, which is impractical for testing any new model.

Task

The thesis aims to develop a new evaluation system and replicate previous solutions to establish a new working benchmark.

References

CrisisFACTS: Building and Evaluating Crisis Timelines

Water Dynamic Forecasting

Motivation

Forecasting surface water dynamics is crucial for managing water resources and adapting to climate change. While the introduction of multi-modal datasets that include satellite imagery, climate data, and elevation models represents a significant step forward, we still need to effectively investigate how specific climate variables influence the model's predictions. Moreover, the investigation of which geographical areas are more prone to model failure was not fully exploited, particularly since we do not know if certain climate conditions make predictions harder. The relationship between different input channels and the type of change (e.g., positive or negative) was not investigated in depth to determine which spectral bands are more relevant.

Task

• Investigate the relationship between climate variables and water changes.
• Investigate which spectral bands are more sensitive to water changes.
• Investigate if certain geographical areas are more difficult to predict.
• Investigate if the models are biased toward certain climate conditions.
• Introduce other variables
• Improve the existing model

Reference

HydroChronos: Forecasting Decades of Surface Water Change

Hyperspectral Canopy Height Maps