Physical Sciences and Mathematics Commons^™

Deep Learning Approaches For Chaotic Dynamics And High-Resolution Weather Simulations In The Us Midwest, Vlada Volyanskaya, Kabir Batra, Shubham Shrivastava

Discovery Undergraduate Interdisciplinary Research Internship

Weather prediction is indispensable across various sectors, from agriculture to disaster forecasting, deeply influencing daily life and work. Recent advancement of AI foundation models for weather and climate predictions makes it possible to perform a large number of predictions in reasonable time to support timesensitive policy- and decision-making. However, the uncertainty quantification, validation, and attribution of these models have not been well explored, and the lack of knowledge can eventually hinder the improvement of their prediction accuracy and precision. Our project is embarking on a two-fold approach leveraging deep learning techniques (LSTM and Transformer) architectures. Firstly, we model the Lorenz …

Physics-Informed Machine Learning To Predict Extreme Weather Events, Rthvik Raviprakash, Jonathan Buchanan, Mahdi Bu Ali

Discovery Undergraduate Interdisciplinary Research Internship

Extreme weather events refer to unexpected, severe, or unseasonal weather events, which are dynamically related to specific large-scale atmospheric patterns. These extreme weather events have a significant impact on human society and also natural ecosystems. For example, natural disasters due to extreme weather events caused more than $90 billion global direct losses in 2015. These extreme weather events are challenging to predict due to the chaotic nature of the atmosphere and are highly correlated with the occurrence of atmospheric blocking. A key aspect for preparedness and response to extreme climate events is accurate medium-range forecasting of atmospheric blocking events.

Unlike …

Internet Of Things For Environmental Sustainability And Climate Change, Abdul Salam

Faculty Publications

Our world is vulnerable to climate change risks such as glacier retreat, rising temperatures, more variable and intense weather events (e.g., floods, droughts, and frosts), deteriorating mountain ecosystems, soil degradation, and increasing water scarcity. However, there are big gaps in our understanding of changes in regional climate and how these changes will impact human and natural systems, making it difficult to anticipate, plan, and adapt to the coming changes. The IoT paradigm in this area can enhance our understanding of regional climate by using technology solutions, while providing the dynamic climate elements based on integrated environmental sensing and communications that …

Internet Of Things For Water Sustainability, Abdul Salam

Faculty Publications

The water is a finite resource. The issue of sustainable withdrawal of freshwater is a vital concern being faced by the community. There is a strong connection between the energy, food, and water which is referred to as water-food-energy nexus. The agriculture industry and municipalities are struggling to meet the demand of water supply. This situation is particularly exacerbated in the developing countries. The projected increase in world population requires more fresh water resources. New technologies are being developed to reduce water usage in the field of agriculture (e.g., sensor guided autonomous irrigation management systems). Agricultural water withdrawal is also …

Building An Enhanced Drought Early Warning System (Dews): Tools And Services For Decision Support, Mark Svoboda

2011 Symposium on Data-Driven Approaches to Droughts

Perhaps no other hazard lends itself as well to the need for a diligent early warning system (DEWS) than drought. Droughts typically evolve slowly, but have the potential to cover very large areas compared to hazards like hurricanes, tornadoes and floods, which have a much smaller geographic footprint. The U.S. took first steps in 2006 toward developing coordinated and integrated DEWS through the creation of the National Integrated Drought Information System, or NIDIS. More recently, the National Drought Mitigation Center (http://drought.unl.edu) has been working with NIDIS and other international parties (WMO, GEO, United Nations, etc.) with a goal of developing …

Analyzing Past And Predicting Future Drought With Comprehensive Drought Indices For Arkansas-Red River Basin, Lu Liu, Yang Hong, James E. Hocker

2011 Symposium on Data-Driven Approaches to Droughts

This study is intended to examine the past drought and predict future drought scenarios for Arkansas-Red River Basin with comprehensive drought indices ranging from meteorology, hydro-meteorology to hydrology. In this proceeding, we present some early results and analysis with the Standardized Precipitation Index (SPI) and the Palmer Drought Severity Index (PDSI). Historical climate data within the 1900-2009 timeframe were archived to derive the drought indices calculations. The projected A2, A1B climate data modules from 16 statistically downscaled Global Climate Models (GCM) were applied in drought occurrence frequency and affected area prediction. The results from the SPI and PDSI show that …

Exploring The Link Between Droughts And Atmospheric Aerosol Loading, Umarporn Charusombat, Dev Niyogi

2011 Symposium on Data-Driven Approaches to Droughts

Are higher atmospheric aerosol levels and droughts related? To address this question, we explore the relation between atmospheric aerosol loading and droughts using insitu and satellite observations over different urban/rural settings and heterogeneous drought conditions. A related objective was to report on the relationship and the variability between aerosol optical depth (AOD) retrieved from the Moderate Resolution Imaging Spectroradiometer (MODIS) and insitu particular matter (PM2.5 and PM10) over different land use. Daily measurement of PM2.5 and PM10 data were retrieved from seven EPA air quality monitoring stations in Indiana: Virgo, Lake and Clark County in urban area, Marion, Know and …

Monitoring Drought In The Midwest, Steve Hilberg

2011 Symposium on Data-Driven Approaches to Droughts

Climate monitoring is one component of the mission of the Regional Climate Centers, and the Midwestern Regional Climate Center (MRCC) has created web pages to provide near real-time monitoring of the weather and climate of the Midwest. A dedicated drought monitoring page was developed by the MRCC to provide a snapshot of current moisture conditions in the region using a number of specialized maps and products. Users are able to drill down to state and local conditions and impacts through links to the respective state climate offices and water resources agencies.

Monitoring Drought Across Many Scales, Chris Funk

2011 Symposium on Data-Driven Approaches to Droughts

Monitoring drought across many scales Chris Funk As gas and food prices increase while per capita harvested area decreases, drought and disruptions in food availability exert more and more pressure on the political and economic stability of ‘frailed’ states. Improved drought monitoring across many spatial and temporal time scales has therefore become increasingly important. As this need mounts, so have our capacities to observe and understand the earth’s climate. Relatively new satellite systems, such as the Moderate Resolution Imaging Spectrometer, allow us to watch the earth at scales of ~100 meters. Improved rainfall retrievals give us more timely and accurate …

A Modified Standardized Precipitation Index For Drought Monitoring, Brent Mcroberts, John Nielsen-Gammon

2011 Symposium on Data-Driven Approaches to Droughts

The SPI Blend is a modified Standardized Precipitation Index (SPI) created for use in a newly developed, high-resolution drought monitoring tool, assessing drought using precipitation data on multiple time scales. Unlike the traditional SPI, the SPI Blend uses a linear weighting system that places a higher importance on recent precipitation within a time period. At each time scale, the MPE precipitation data are divided into several periods and the precipitation total from the most recent period is given the highest weight, with a linear decrease in the weights for succeeding periods. The high-resolution (4 km) precipitation data are obtained daily …