Despite advancements in environmental monitoring, the gap between data collection and user-friendly data interpretation remains. This paper introduces the Artificial Intelligence Data Expert (AI-DE), a novel data analytics system designed to facilitate on-demand analysis of time-series monitoring data for water quality using natural language queries. The AI-DE leverages features of ChatGPT, including named entity recognition, geocoding, and sentiment analysis, enabling natural language-based data analysis. This system allows for immediate, ad-hoc querying and interpretation of environmental data, tailored to the needs of diverse user groups. Key features include chat controls that customize user interaction, a chat bypass enabling data synchronization with an information system, and a data interpretation mode for detailed analysis. The AI-DE enhances user engagement with an understanding of water quality data, aiming to support informed decisions and actions for environmental management. The AI-DE represents a step forward in increasing access to complex environmental data through conversational AI technologies.

Drawing on a large-scale mobile trace dataset from the United States (N = 463 participants; N = 19,867,944 app logs), we examined variability in social app ecologies while directly contrasting social media and messaging apps. We found that users had primary apps that dominated their media and messaging usage, respectively; concurrently, users were more likely to draw on a wider set of social media (vs. messaging) apps. However, we observed small to insignificant correlations between social media and messaging use, suggesting that the two categories - or sub-ecologies - are not strongly displacing or driving one another. Both social media and messaging apps were used consistently across space - though individuals averaged slightly more time on social media at home and messaging on foot. Overall, the study affirms the importance of taking a naturalistic approach to studying app ecologies, while also offering insights into the increasingly complex relationship between social media and messaging use.

Flooding presents a significant risk to concentrated animal feeding operations (CAFOs), especially in regions increasingly affected by extreme weather events. This study uses advanced geospatial analysis techniques to assess the environmental and economic vulnerabilities of 12 703 CAFOs across Iowa, United States. We focused on the exposure of CAFOs to 100 year and 500 year floodplains, integrating floodplain maps with location data operational characteristics, and livestock types (cattle and swine) to assess flood risk. The analysis also considered the size and construction year of each CAFO, offering insights into how older and larger operations are disproportionately vulnerable. The results indicate that over 1.9 million animal units (13% of total), are located within the 100 year floodplain. In the 500 year flood floodplain, it increases to 2.05 million animal units, representing 14% of the state’s total. Sioux, Lyon, and Hancock counties were identified as having particularly high potential flood exposure, with over 16% of animal units in Sioux County located within the 100 year floodplain, increasing to 17% within the 500 year floodplain. The study shows that larger CAFOs, particularly those built before 2004, were often located in flood-prone areas and, if either a 100- or 500 year flood occurs, would potentially affect a larger number of animal units due to their operational scale. These risks not only threaten livestock but also have far-reaching economic consequences, including significant operational disruptions, infrastructure damage, and cascading effects on supply chains and market stability. As extreme weather events become more frequent due to climate change, these findings highlight the need for heightened awareness of CAFO vulnerabilities and call for further research into adaptive strategies to protect Iowa’s agricultural sector.

Flood impacts are shaped not only by environmental or economic consequences but also by the social, ecological, and infrastructural conditions that influence how communities experience and recover from hazards. This study aims to assess multi-domain flood vulnerability across Polk County, Iowa utilizing a Social–Ecological–Technological Systems (SETS) framework. Eighteen indicators were standardized and aggregated to produce domain-specific and composite indices, which were evaluated independently from mapped flood exposure at the census block group scale. Results show that social, ecological, and technological vulnerabilities exhibit distinct and non-coincident spatial patterns, while composite indices reveal broader zones where multiple weaknesses co-occur. The highest compounded susceptibility is concentrated in the Des Moines urban core and along the Des Moines River corridor, although each domain highlights different localized patterns across the county. Weak correlations between vulnerability scores and flood extent support that intrinsic susceptibility and hydraulic exposure represent separate and complementary processes. Overall, the framework provides a transparent and transferable approach to support targeted mitigation, planning, and resilience strategies in flood-prone urban communities.

The rapid evolution of Mixed Reality (MR) technologies, particularly Virtual Reality (VR), offers powerful new means of visualizing and interacting with geographic and environmental data. This paper presents Virtual Reality Flood Information System (VRFIS), an immersive information platform developed using Unreal Engine 5 and Google Photo Realistic 3D Tiles to enable real-time exploration of high-resolution geospatial datasets across the United States. VRFIS integrates photorealistic terrain rendering, dynamic environmental simulation, and multimodal interaction within a fully immersive 3D environment, allowing users to visualize, query, and interpret complex environmental phenomena with unprecedented realism and spatial context. By coupling high-fidelity visualization with live data streams from authoritative sources such as USGS and NOAA, the system delivers an intuitive decision-support and educational tool for environmental science, hydrology, urban planning, and geography education. The results demonstrate how next-generation virtual reality environments, exemplified by VRFIS, can enhance spatial awareness, promote experiential learning, and improve data-driven decision-making in environmental and geospatial domains.

Agricultural drought develops when inadequate soil moisture, frequently caused by extended precipitation shortages and heightened evaporative demand, results in substantial declines in crop output. In Iowa, where maize and soybeans comprise almost 90% of total crop output, comprehending drought-crop dynamics is crucial for climate-resilient agriculture. This study evaluated the efficacy of many commonly utilized drought indicators in elucidating the variability of corn and soybean yields from 2000 to 2022. Both meteorological and satellite-derived indices were assessed, including the Standardized Precipitation Index (SPI), Standardized Precipitation-Evapotranspiration Index (SPEI), Palmer Drought Severity Index (PDSI), Evaporative Demand Drought Index (EDDI), Crop Moisture Index (CMI), and Normalized Difference Vegetation Index (NDVI), all utilized across various temporal scales. Spearman correlation study indicated a favorable association between soybean yields and long-term indicators, including SPI-6, SPI-12, SPEI-6, and SPEI-12, with PDSI exhibiting the most robust temporal link, underscoring soybeans' need on consistent moisture availability. Corn yields had more pronounced negative relationships with EDDI, highlighting their susceptibility to atmospheric dryness and thermal stress. A Random Forest regression model was utilized to assess the relative significance of each drought measure, therefore complementing these findings. The machine learning findings indicated that CMI is the most significant predictor for both crops, although EDDI and SPI-3 were predominant factors for corn yield, underscoring the necessity to observe both short-term moisture and atmospheric demand. These findings provide significant insights for agricultural planning, drought alleviation, and the creation of data-informed decision-support systems. The combined use of several drought indices and multivariate analysis underscores the potential for adaptive agricultural practices and resilient crop management in response to changing climate conditions.

Societal risks from flooding are evident at a range of spatial scales and climate change will exacerbate these risks in the future. Assessing flood risks across broad geographical regions is a challenge, and often done using streamflow time-series records or hydrologic models. In this study, we used a national-scale hydrological model to identify, assess, and map 16 different streamflow metrics that could be used to describe flood risks across 34,987 HUC12 subwatersheds within the Mississippi-Atchafalaya River Basin (MARB). A clear spatial difference was observed among two different classes of metrics. Watersheds in the eastern half of the MARB exhibited higher overall flows as characterized by the mean, median, and maximum daily values, whereas western MARB watersheds were associated with flood indicative of high extreme flows such as skewness, standardized streamflow index and top days. Total agricultural and building losses within HUC12 watersheds were related to flood metrics and those focused on higher overall flows were more correlated to expected annual losses (EAL) than extreme value metrics. Results from this study are useful for identifying continental scale patterns of flood risks within the MARB and should be considered a launching point from which to improve the connections between watershed scale risks and the potential use of natural infrastructure practices to reduce these risks.

Floods have a catastrophic impact on human life in terms of economic loss, infrastructure damage and loss of life. Understanding vulnerable transportation segments is critical to addressing potential disruptions that may be caused by a flood event. This study employs a systematic framework to analyze flood impacts by evaluating bridge inundation, waterway crossings and traffic disruptions across Iowa under 50-, 100- and 500-year flood scenarios. The southeast part of Iowa, which has been designated as a critical area because of the significant bridge inundation during these flood events, is given particular attention. Marion, a moderately populated county in the southeast of Des Moines, stands out as a critical region due to its significant bridge inventory inundation in 100- and 500-year flood cases. Our study also explores the conditions and construction years of bridges, their correlation with inundation risk and their impact on flood-related vulnerability. Additionally, we assess the effects of waterway bridge evaluations for different flood magnitudes on evacuation plans and analyze the vulnerability of the transportation network through the effects of closed bridges on traffic. These insights underscore the intricate interplay between floods and transportation, shedding light on bridge vulnerability, waterway evaluation and traffic disruption.

Natural infrastructure (NI) is increasingly being utilized to reduce flood risk and improve water quality, with several different types of NI practices potentially being available for stakeholders. However, guidance on the amount of land available for NI and which practices are appropriate for a region has often been insufficient. This study investigated spatial differences for potential NI installation throughout the Mississippi-Atchafalaya River Basin (MARB)—specifically analyzing eight practices related to wetlands, row crop conversion, riparian buffers, and levee reconnection. The potential placement area of each NI practice was estimated for all HUC12s within the MARB, and a composite metric was used to gauge each HUC12’s overall NI suitability. We then aggregated these NI practice extents using four spatial grouping systems (states, HUC2 basins, land resource regions, and modified physiographic provinces). All eight practices demonstrated significant spatial differences across the MARB. Riparian buffers contained the greatest potential installation area (6.07 %), while floodplain wetlands contained the lowest (0.58 %). Particular regions, such as the Midwest and Louisiana, showed high suitability for NI implementation, while others, such as mountainous areas, exhibited minimal potential. The analysis of these spatial groupings suggested that boundaries along state and HUC2 lines often miss important parameters that influence NI potential. Modified physiographic provinces, which incorporated geology and glaciation history, best captured NI’s spatial variance and thus may be advantageous for future conservation considerations.

Flooding poses a significant threat to transportation infrastructure like bridges and culverts in regions like Iowa, where infrastructure deficiencies, unpredictable climate patterns, and geographic factors all contribute to vulnerability. This study evaluates the susceptibility of over 24,000 bridges in Iowa to flood-induced damage by considering both the likelihood of flooding and its potential negative impacts on bridge functionality, using the Analytic Hierarchy Process (AHP) and Fuzzy AHP methods. By combining bridge inventory datasets with historical flood data, this study assesses flood risks across multiple flood scenarios (50, 100, and 500 years return period). Factors such as bridge age, condition, traffic volume, detour lengths, and flood likelihood were used to calculate the impact indices for each bridge. Two distinct impact index sets were computed and visualized across the state at individual locations, county scales, and through a Kernel-based heatmap analysis where the population data was incorporated as an additional layer to provide a broader perspective on the potential societal impacts. The results indicate areas where a large portion of the bridge network is at risk of flooding, potentially leading to major disruptions and impacts on society. This research provides insights into the weaknesses in Iowa’s bridge network and contributes to understanding how transportation infrastructure is impacted by flooding.

Floods are among the most frequent and damaging natural hazards, posing serious risks to transportation infrastructure and public safety. Bridges, as essential links in road and rail networks, are especially vulnerable, and their closures can trigger widespread disruption, economic losses, and reduced access to vital services. Effective flood-risk mitigation and emergency response require systems that integrate diverse data sources and deliver actionable information on infrastructure vulnerability and operational risk. Although several web platforms support asset management or flood forecasting, few provide an environment dedicated to bridge-specific vulnerability, where hazard data, structural characteristics, and operational factors can be examined together. The Iowa Bridge Information Service (IBIS) addresses this gap through a web-based framework that combines structural, spatial, and hydrological datasets to support flood-focused risk assessment for communities in Iowa. IBIS enables users to analyze bridge exposure through configurable filters, scenario-based flood overlays, and interactive tools such as heatmaps and statistical summaries. It applies multiple criteria decision-making techniques, including the Analytic Hierarchy Process (AHP), to evaluate vulnerability based on condition, traffic, detour length, and closure potential. County and watershed views allow assessment at policy-relevant and hydrologically meaningful scales. By combining data, analysis, and visualization in a single framework, IBIS provides a practical tool for maintenance planning, emergency preparedness, and resilience strategies for infrastructures generalizable to many flood-prone regions around the world.

The Blue-Green Action Platform (BlueGAP) information system (IS) is an intelligent cyberinfrastructure framework designed to support large-scale water quality assessments in the context of demographic statistics and community stories about water issues. The system prioritizes collaboration with interested parties in three pilot watersheds with test cases implemented in US locations including Iowa, Tampa, and the U.S. Virgin Islands. The BlueGAP IS leverages Artificial Intelligence (AI) technologies with large language models based on regional nutrient management issues and community knowledge to provide access to water quality information. The current focus of the system is on nitrate in drinking water, rivers, and waterways, and can be expanded to incorporate other water quality information. BlueGAP identifies possible partnerships and promotes collaborations among diverse stakeholders to facilitate effective evaluation of nitrogen-related analytes, guide action to address possible pollution, and outline sustainable water management practices. The BlueGAP IS also emphasizes its educational mission by connecting water quality data with inclusive and accessible educational content through AI technology. By integrating nitrogen data and water quality issues into educational resources, BlueGAP fosters a deeper understanding of water quality issues across diverse communities, empowering users to make informed decisions and contribute to sustainable water management practices.

The rapid advancement of Large Language Models (LLMs), such as ChatGPT, has opened new horizons in the field of Artificial Intelligence (AI), revolutionizing the way we can engage with and disseminate complex information. This paper presents an innovative application of ChatGPT in the domain of Water Quality (WQ) management, through the development of an AI Hub. The Hub encompasses a suite of conversational agents, each designed to address different aspects of water quality management, including nitrogen pollution, local water quality issues, and actionable planning for water conservation. These agents utilize the advanced natural language processing capabilities of ChatGPT, complemented with water quality-related data, to provide users with accurate, up-to-date, and contextually relevant information. The objective is to empower communities with the knowledge necessary to understand and address water quality challenges effectively. Our comprehensive evaluation of these agents demonstrates their proficiency in delivering valuable insights, with an overall performance accuracy exceeding 89%. This paper underscores the potential of AI-enabled platforms in enhancing public understanding and engagement in environmental conservation efforts. By bridging the gap between complex environmental data and public awareness, the AI Hub sets a precedent for the application of AI in sustainable environmental management.

Habits are a fundamental driver of human behavior. However, prior research has largely studied habits in isolation. This study investigates spatial and smartphone habits—two cornerstone habits in contemporary society—in tandem, revealing the multiplicative ways in which habitual processes can underlie human behavior. We provide evidence that smartphone habits are stronger in habitually traveled and visited spaces. We leverage a custom-designed app that logged mobility and app use while prompting map-based questionnaires of participants’ trips for two weeks (N = 419 participants; n = 27,446,977 GPS and app logs; n = 7,226 trip questionnaires). Overall, app habit strength predicted higher likelihood of app use (vs. non-use) and more app use (when used) on more habitually travelled routes and in more habitually visited destinations. The interaction between spatial and smartphone habits was most consistent for objective (vs. subjective) habit indicators. Social app habits were stronger and more context-independent than non-social app habits. Altogether, our findings reveal how distinct habitual processes can combine to shape daily behavior. Further, our method illustrates the potential of linking mobile sensing and surveying to measure habits in the real world.

Corn and soybeans are pivotal crops in the U.S. agricultural landscape, providing essential vitamins and oils. These two crops dominate approximately 90% of crop production in Iowa. However, their yields are significantly impacted by recurrent drought conditions. A prolonged deficiency in soil moisture characterizes agricultural drought due to sustained precipitation shortfalls. This study aims to quantify widely utilized drought indicators and ascertain their relationships with corn and soybean yields from 2000 to 2022 to identify each crop's most reliable drought indices. The analysis encompasses meteorological and satellite-derived indices alongside crop yield data from the U.S. Department of Agriculture's National Agricultural Statistics Service (NASS). Indices evaluated in this study include the Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI), Palmer Drought Severity Index (PDSI), Evaporative Demand Drought Index (EDDI), Crop Moisture Index (CMI), and Normalized Difference Vegetation Index (NDVI). Our results demonstrate a positive correlation between soybean yields and long-term moisture indices such as SPI-6, SPI-12, SPEI-6, and SPEI-12, indicating these indices' potential utility in forecasting soybean productivity. Conversely, corn yields exhibit fewer regular patterns and are negatively correlated with EDDI, with higher EDDI values coinciding with reduced corn yields, reflecting heightened drought sensitivity. The study finds that soybeans exhibit better resilience to longer-term moisture indicators, whereas corn yields are more adversely affected by drought conditions. The Palmer Drought Severity Index (PDSI) shows a stronger correlation with soybean yields than with corn yields. The findings indicate that corn is generally more susceptible to drought than soybeans in the study region. These insights can inform decision-making for drought relief efforts, farm management strategies, and grain market planning, enabling stakeholders to address potential drought conditions proactively.

The Upper Mississippi Information System (UMIS) is a cyberinfrastructure framework designed to support large-scale real-time water quality data integration, analysis, and visualization for the Upper Mississippi River Basin (UMRB). UMIS is intended to directly address three of the Grand Challenges for Engineering including: 1) understanding access to clean drinking water, 2) management of the nitrogen cycle, and 3) engineering the tools of scientific discovery. The UMIS is designed to provide significant immediate and long-term impacts including a central platform for data access, integration, discovery, and adoption of cyberinfrastructure tools and services. The UMIS demonstrates that public data aggregators and central repositories can provide important services to anyone interested in water quality research or education. In addition, working across multiple scales (e.g., state, region, county, or watershed) allows researchers to understand broad and narrow effects of water quality strategies. Exploration of data across these scales encourages the development of problem-based research questions that can eventually provide feedback to public policies.

Transportation systems can be significantly affected by flooding, leading to physical damage and hindering accessibility. Despite flooding being a frequent occurrence, there are limited accessible online tools available for supporting routing and emergency planning decisions during flooding. Existing tools are generally based on complicated models and are not easily accessible to non-expert users, highlighting the need for efficient communication and decision-making tools for analyzing flood impacts on transportation networks for various stakeholders, including the public, to minimize the adverse impacts on those groups. This paper presents a web application that uses graph network methods and the latest web technologies and standards to assist in describing flood events in terms of operational constraints and provide analytical methods to support mobility and mitigation decisions during these events. The framework is designed to be user-friendly, enabling non-expert users to access information about road status, shortest paths to critical amenities, location-allocation, and service coverage. The study area includes the following two communities in the State of Iowa, Cedar Rapids and Charles City, which were used to test the application's functionality and explore the outcomes. Our research demonstrates that flooding can significantly affect bridge operation, routing from locations to critical amenities, arbitrary point-to-point routing, planning for emergency facility placement, and service area accessibility. The introduced framework can solve complex flood-related analytical decision tasks and provide an understandable representation of transportation vulnerability, enhancing mitigation strategies. Therefore, this web application provides a valuable tool for stakeholders to make informed decisions on transportation networks during flood events.

Despite advancements in environmental monitoring, the gap between data collection and user-friendly data interpretation remains a significant challenge, especially in the domain of water quality management. This paper introduces the Artificial Intelligence Data Expert (AI-DE), a novel data analytics system that is designed to facilitate on-demand analysis of time-series sensor data related to water quality using natural language queries. The AI-DE leverages features of ChatGPT, including Named Entity Recognition, geocoding, and sentiment analysis, to enable intuitive and natural language-based data analysis. This system transformation allows for immediate, ad-hoc querying and interpretation of environmental data, tailored to the needs of diverse user groups. Key features include chat controls that customize user interaction, a chat bypass enabling seamless integration with an integrated information system, and a data interpretation mode for detailed analysis. The AI-DE enhances user engagement and comprehension of water quality data, thereby supporting informed decisions and actions for environmental management. The AI-DE represents a step forward in increasing access to complex environmental data through conversational AI technologies.

The escalating prominence of floods globally, with their catastrophic potential to inflict substantial losses in terms of both human lives and economic resources, underscores their significance. Particularly susceptible to flooding between May and July, the US Midwest faces heightened risks during this critical period, characterized by the highest average precipitation rates of the year. Flood vulnerability assessments furnish organizations with crucial insights into expected extreme events and strive to mitigate potential harm from these risks. The Social-Ecological-Technological (SETS) framework, a comprehensive flood vulnerability assessment method, highlights the significance of aligning natural, technological, and demographic systems to comprehend and effectively address the complexity of natural hazards, facilitating the achievement of optimal results. In this study, the relationship between the 500-year flood event and the SETS vulnerability indices formed by 18 selected parameters was examined for Polk County, Iowa. Moreover, linear regression and spatial autocorrelation analyses were conducted on vulnerability indices. The results indicated that the S-E-T vulnerability map, which is the combined effects of all social, ecological, and technological exposure, sensitivity, and adaptive capacity parameters considered, the areas most impacted to damage are identified as the highly populated downtown Des Moines, where urban development is concentrated along a highway (I-235) and large industrial buildings. When looking at all the vulnerability maps produced, the number of census block groups in the very high vulnerability class is low. However, in Polk County, it has been presented that there is strong spatial autocorrelation indicating that vulnerability index values are highly clustered. These findings will support sustainable approaches and stronger contextual solutions for city managers and practitioners that decrease the risks of flooding in Polk County communities.