arXiv subjects

Asim Zia

Publications and source records attributed to Asim Zia.

5 recordsLinked to original sources

arXiv2025

From Remote Sensing to Multiple Time Horizons Forecasts: Transformers Model for CyanoHAB Intensity in Lake Champlain

Cyanobacterial Harmful Algal Blooms (CyanoHABs) pose significant threats to aquatic ecosystems and public health globally. Lake Champlain is particularly vulnerable to recurring CyanoHAB events, especially in its northern segment: Missisquoi Bay, St. Albans Bay, and Northeast Arm, due to nutrient enrichment and climatic variability. Remote sensing provides a scalable solution for monitoring and forecasting these events, offering continuous coverage where in situ observations are sparse or unavailable. In this study, we present a remote sensing only forecasting framework that combines Transformers and BiLSTM to predict CyanoHAB intensities up to 14 days in advance. The system utilizes Cyanobacterial Index data from the Cyanobacterial Assessment Network and temperature data from Moderate Resolution Imaging Spectroradiometer satellites to capture long range dependencies and sequential dynamics in satellite time series. The dataset is very sparse, missing more than 30% of the Cyanobacterial Index data and 90% of the temperature data. A two stage preprocessing pipeline addressed data gaps by applying forward fill and weighted temporal imputation at the pixel level, followed by smoothing to reduce the discontinuities of CyanoHAB events. The raw dataset is transformed into meaningful features through equal frequency binning for the Cyanobacterial Index values and extracted temperature statistics. Transformer BiLSTM model demonstrates strong forecasting performance across multiple horizons, achieving F1 scores of 89.5%, 86.4%, and 85.5% at one, two, and three-day forecasts, respectively, and maintaining an F1 score of 78.9% with an AUC of 82.6% at the 14-day horizon. These results confirm the model's ability to capture complex spatiotemporal dynamics from sparse satellite data and to provide reliable early warning for CyanoHABs management.

cs.CV↗

arXiv2023

Temporal Evolution of Risk Behavior in a Disease Spread Simulation

Human behavior is a dynamic process that evolves with experience. Understanding the evolution of individual's risk propensity is critical to design public health interventions to propitiate the adoption of better biosecurity protocols and thus, prevent the transmission of an infectious disease. Using an experimental game that simulates the spread of a disease in a network of porcine farms, we measure how learning from experience affects the risk aversion of over $1000$ players. We used a fully automated approach to segment the players into 4 categories based on the temporal trends of their game plays and compare the outcomes of their overall game performance. We found that the risk tolerant group is $50\%$ more likely to incur an infection than the risk averse one. We also find that while all individuals decrease the amount of time it takes to make decisions as they become more experienced at the game, we find a group of players with constant decision strategies who rapidly decrease their time to make a decision and a second context-aware decision group that contemplates longer before decisions while presumably performing a real-time risk assessment. The behavioral strategies employed by players in this simulated setting could be used in the future as an early warning signal to identify undesirable biosecurity-related risk aversion preferences, or changes in behavior, which may allow for targeted interventions to help mitigate them.

cs.CY↗

arXiv2019

Effects of Social Cues on Biosecurity Compliance in Livestock Facilities: Evidence from Experimental Simulations

Disease outbreaks in U.S. animal livestock industries have economic impacts measured in hundreds of millions of dollars per year. Biosecurity, or procedures intended to protect animals against disease, is known to be effective at reducing infection risk at facilities. Yet to the detriment of animal health, humans do not always follow biosecurity protocols. Human behavioral factors have been shown to influence willingness to follow biosecurity protocols. Here we show how social cues may affect cooperation with a biosecurity practice. Participants were immersed in a simulated swine production facility through a graphical user interface and prompted to make a decision that addressed their willingness to comply with a biosecurity practice. We tested the effect of varying three experimental variables: (1) the risk of acquiring an infection, (2) the delivery method of the infection risk information (numerical versus graphical), and (3) behavior of an automated coworker in the facility. We provide evidence that participants changed their behavior when they observed a simulated worker making a choice to follow or not follow a biosecurity protocol, even though the simulated worker had no economic effect on the participants' payouts. These results advance the understanding of human behavioral effects on biosecurity protocol decisions; demonstrating that social cues need to be considered by livestock facility managers when developing policies to make agricultural systems more disease resilient.

cs.CY↗

arXiv2019

Using Digital Field Experiments To Elicit Risk Mitigation Behavioral Strategies For Disease Management Across Agricultural Production Systems

Failing to mitigate propagation of disease spread can result in dire economic consequences for agricultural networks. Pathogens like Porcine Epidemic Diarrhea virus, can quickly spread among producers. Biosecurity is designed to prevent infection transmission. When considering biosecurity investments, management must balance the cost of protection versus the consequences of contracting an infection. Thus, an examination of the decision making processes associated with investment in biosecurity is important for enhancing system wide biosecurity. Data gathered from digital field experiments can provide insights into behavioral strategies and inform the development of decision support systems. We created an online digital experiment to simulate outbreak scenarios among swine production supply chains, where participants were tasked with making biosecurity investment decisions. In Experiment One, we quantified the risk associated with each participant's decisions and delineated three dominant categories of risk attitudes: risk averse, risk tolerant, and opportunistic. Each risk class exhibited unique approaches in reaction to risk and disease information. We also tested how information uncertainty affects risk aversion, by varying the amount of visibility of the infection as well as the amount of biosecurity implemented across the system. We found evidence that more visibility in the number of infected sites increases risk averse behaviors, while more visibility in the amount of neighboring biosecurity increased risk taking behaviors. In Experiment Two, we were surprised to find no evidence for differences in behavior of livestock specialists compared to Amazon Mechanical Turk participants. Our findings provide support for using digital field experiments to study how risk communication affects behavior, which can provide insights towards more effective messaging strategies.

cs.CY↗

arXiv2019

Decision-making in Livestock Biosecurity Practices amidst Environmental and Social Uncertainty: Evidence from an Experimental Game

Livestock industries are vulnerable to disease threats, which can cost billions of dollars and have substantial negative social ramifications. Losses are mitigated through increased use of disease-related biosecurity practices, making increased biosecurity an industry goal. Currently, there is no industry-wide standard for sharing information about disease incidence or on-site biosecurity strategies, resulting in uncertainty regarding disease prevalence and biosecurity strategies employed by industry stakeholders. Using an experimental simulation game, we examined human participant's willingness to invest in biosecurity when confronted with disease outbreak scenarios. We varied the scenarios by changing the information provided about 1) disease incidence and 2) biosecurity strategy or response by production facilities to the threat of disease. Here we show that willingness to invest in biosecurity increases with increased information about disease incidence, but decreases with increased information about biosecurity practices used by nearby facilities. Thus, the type or context of the uncertainty confronting the decision maker may be a major factor influencing behavior. Our findings suggest that policies and practices that encourage greater sharing of disease incidence information should have the greatest benefit for protecting herd health.

econ.GN↗