Events

November 2021 January 2022
Legend
 JSG  BEG  UTIG  EPS 

HydroML 2026 Symposium

May, 19 2026

Time: 12:00 AM - 12:00 AM
Location: POB 2.302

The HydroML 2026 symposium will explore how AI/ML concepts can be used to enhance the predictive understanding of complex systems in hydrological and geological sciences. The overarching goal is to discuss process-based scientific principles that can help integrate AI/ML with earth system science. In essence, the symposium seeks to stimulate discussions that will help develop physically guided AI/ML approaches which are explainable, interpretable, and improve the mechanistic understanding of earth system science. It will foster collaborations among researchers who are both new to the field and already involved, thereby strengthening ties within the community of AI/ML researchers.

 

Environmental Science Institute’s Community-Based Research Symposium

May, 19 2026

Time: 12:00 AM - 12:00 AM
Location: WCP 2.302

Community-based research is essential for understanding and addressing challenges that reflect real community needs. For example, rapid urban growth and increasing weather extremes are already straining communities, and these pressures are expected to intensify in the years ahead. This in-person symposium will bring together university researchers and students, community organizations and members, government entities, industry representatives, and other interested stakeholders to explore the opportunities and benefits of Community-based research in Texas and beyond.

Urban Climate Lecture

May, 22 2026

Time: 12:00 PM - 1:30 AM
Location: Barrow Conference Room (JGB 4.102)

Capturing Spatial Variability of Urban Microclimate in Process-Based and Machine Learning Models by Dr. Tirthankar \"TC\" Chakraborty, Earth Scientist at the Pacific Northwest National Laboratory (PNNL)

Abstract: Cities modify their local microclimate via process-level changes and through alterations in bulk radiative, morphological, and thermal properties. Cities are also highly heterogeneous, leading to spatial variability in environmental hazards, with potential disparities in climate risks for different urban residents. While significant efforts have been made to improve urban representation in models to isolate broader urban climate signals, current models often struggle to resolve intra-urban variability due to poor structural and parameter constraints at the neighborhood scale.

In this seminar, I will provide an overview of this urban spatial variability and its importance, our current limitations in capturing this variability, and potential ways forward by leveraging current-generation fine-grained satellite observations. Specifically, I will highlight our past and ongoing research involving both process-based numerical modeling and machine learning approaches to capture the spatial distribution of urban heat hazards. The lessons learned from these studies can guide future urban model development efforts to enable more accurate neighborhood-scale climate mitigation and adaptation strategies.