BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//C2SMART Home - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://c2smart.engineering.nyu.edu
X-WR-CALDESC:Events for C2SMART Home
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250411T093000
DTEND;TZID=America/New_York:20250411T103000
DTSTAMP:20260430T122116
CREATED:20250407T164354Z
LAST-MODIFIED:20250407T180200Z
UID:88400-1744363800-1744367400@c2smart.engineering.nyu.edu
SUMMARY:Seminar: Spatiotemporal Drought Analysis and Prediction: From Pattern Tracking to Impact Assessment
DESCRIPTION:The increasing frequency and severity of drought events worldwide demand innovative approaches that can effectively characterize\, track\, predict\, and assess impacts of the complex spatiotemporal dynamics of water scarcity. This presentation explores how integrated spatiotemporal methodologies enhance drought monitoring\, forecasting\, and impact assessment across diverse global regions. \nOur research demonstrates a logical progression from fundamental spatiotemporal drought tracking to advanced prediction methodologies and practical impact assessment. Beginning with approaches to construct drought tracks through space and time in India\, we identify key drought characteristics including onset location\, pathway\, duration\, severity\, and rotation. These spatial patterns reveal critical information about drought migration and evolution that provide insights into underlying climate and land surface drivers. \nBuilding on this foundation of spatiotemporal drought characterization\, we apply machine learning techniques to predict drought occurrence and intensity across Kazakhstan’s diverse climate zones. By utilizing non-contiguous drought analysis for feature extraction\, machine learning models achieve remarkable prediction accuracy at lead times of up to six months in these arid and semi-arid regions. Additionally\, deep learning techniques enhanced with ensemble empirical mode decomposition substantially improve soil moisture anomaly forecasting in China’s Huai River basin by better capturing the complex non-stationary time series characteristics of drought evolution. \nBeyond monitoring and forecasting\, we extend our approach to predict drought impacts on agriculture in Northeast India using spatiotemporal drought patterns as input for crop yield forecasting. This methodology integrates polynomial regression and artificial neural network models\, where the spatial extent and temporal evolution of drought areas serve as key predictive features. The results demonstrate that changes in drought area and its temporal aggregation provide an important pre-processing alternative for implementing machine learning models for drought impact prediction. \nThese integrated approaches\, spanning regions from Central Asia to South and East Asia\, contribute to a more robust understanding of drought dynamics by revealing how drought moves and evolves in space and time\, enabling more effective early warning systems and supporting agricultural decision-making in increasingly water-stressed environments. Across all applications and geographical contexts\, the spatiotemporal properties of drought emerge as key features that significantly enhance the performance of machine learning prediction models. \nBio: Dr. Gerald A. Corzo is an Associate Professor of Hydroinformatics at IHE Delft Institute for Water Education\, where he leads cutting-edge research that uses Artificial Intelligence and Machine Learning to address critical challenges in climate adaptation and water resource management. His research on hydrometeorological extremes has helped us better understand\, predict\, and respond to floods and droughts across the globe. As Principal Investigator on significant EU-funded projects like EU-WATCH\, Climate Intelligent (EU-CLINT) and EU-NAIADES\, Dr. Corzo has developed cutting-edge AI-driven tools that enhance decision-making in water management and climate resilience. He currently serves as an Editor of the Journal of Hydrology (Elsevier) and was recognized with the prestigious IAHS Tison Award for his contributions to hydrological sciences in 2012. Dr. Corzo’s interdisciplinary approach integrates environmental science with advanced computational technologies to create practical solutions aligned with sustainable development goals\, particularly for enhancing ecosystem resilience in vulnerable communities worldwide.
URL:https://c2smart.engineering.nyu.edu/event/seminar-spatiotemporal-drought-analysis-and-prediction-from-pattern-tracking-to-impact-assessment/
LOCATION:C2SMART Center Viz Lab\, 6 Metrotech Center\, Room 460\, Brooklyn\, 11201
CATEGORIES:Seminars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250411T120000
DTEND;TZID=America/New_York:20250411T130000
DTSTAMP:20260430T122116
CREATED:20250304T191106Z
LAST-MODIFIED:20250304T191106Z
UID:87962-1744372800-1744376400@c2smart.engineering.nyu.edu
SUMMARY:SLH: Discrete Choice Modeling for Travel Behavior Analysis: From Multinomial Logit to More Advanced Forms
DESCRIPTION:Abstract: In this course\, we will discuss the decision theory of random utility maximization and discrete choice models (DCMs) including multinomial logit (MNL)\, nested logit (NL)\, mixed logit (MXL)\, and agent-based mixed logit (AMXL). You will learn about their applications in travel behavior analysis (e.g.\, travel mode choice\, activity scheduling choice\, etc.) and how to build DCMs with long-shape and wide-shape choice datasets in R and Python. A recent study on New York State travel mode choice will be introduced as an example.
URL:https://c2smart.engineering.nyu.edu/event/slh-discrete-choice-modeling-for-travel-behavior-analysis-from-multinomial-logit-to-more-advanced-forms/
CATEGORIES:Student Events,Webinars
END:VEVENT
END:VCALENDAR