The field of time series analysis and environmental science is rapidly advancing with the adoption of transformer-based foundation models. These models have shown unprecedented capabilities in tasks such as forecasting, anomaly detection, and classification, and are being applied to a wide range of environmental applications, including modeling ecological processes and capturing spatiotemporal dynamics. Notable papers in this area include the survey on foundation models for time series, which provides a comprehensive overview of the current state of the art in pre-trained foundation models. Another noteworthy paper is Climplicit, which introduces a spatio-temporal geolocation encoder pretrained to generate implicit climatic representations anywhere on Earth, reducing storage and computational needs for downstream tasks.