3 papers
cs.CV2026
SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models
Xingyan Li, Jordan A. Caraballo-Vega, Jie Gong +2
Geospatial foundation models (GeoFMs), pretrained on large-scale geospatial data such as Earth observation (EO), climate, and weather data, have shown promising performance when fi…
physics.data-an2024
Causality for Earth Science -- A Review on Time-series and Spatiotemporal Causality Methods
Sahara Ali, Uzma Hasan, Xingyan Li +5
This survey paper covers the breadth and depth of time-series and spatiotemporal causality methods, and their applications in Earth Science. More specifically, the paper presents a…
cs.LG2024
MT-HCCAR: Multi-Task Deep Learning with Hierarchical Classification and Attention-based Regression for Cloud Property Retrieval
Xingyan Li, Andrew M. Sayer, Ian T. Carroll +2
In the realm of Earth science, effective cloud property retrieval, encompassing cloud masking, cloud phase classification, and cloud optical thickness (COT) prediction, remains piv…