ECOP-02 Contributed Talks

Brian Zambrano

University of Alberta

"Cyanobacteria Hot Spot Detection Integrating Remote Sensing Data with Convolutional and Kolmogorov-Arnold Networks"

Monitoring cyanobacterial blooms promptly and accurately is crucial for public health management and understanding aquatic ecosystem dynamics. Remote sensing, particularly satellite observations, offers a viable approach for continuous monitoring. This study utilizes multispectral images from the Sentinel-2 satellite constellation in conjunction with ERA5-Land data to facilitate broad-scale data collection. We proposed a simple deep convolutional neural network (CNN) architecture to analyze cyanobacteria (CB) concentration dynamics in Pigeon Lake, Canada, over a five-year period. Utilizing the Local Getis-Ord statistic, we identified and analyzed trends in hot and cold spots under the null hypothesis of random distribution. We observed changes in the distribution and median CB concentration in hot spots over time. Additionally, we trained a Kolmogorov-Arnold Network (KAN) to classify segments of the lake shoreline into hot and non-hot spots using the Dynamic World dataset within a 500-meter radius of the lake.

---

Kyunghan Choi

Postdoctoral Research Fellow/ University of Alberta

"Animal movement models with spatiotemporal memory"

In this study, we examine how explicit spatial memory influences different mathematical models in various ecological dispersal contexts. Specifically, we analyze three memory-based dispersal strategies: (1) gradient-based movement, where individuals respond to environmental gradients; (2) environment matching, which promotes a uniform population distribution; and (3) location-based movement, where decisions are based solely on local suitability. These strategies correspond to diffusion-advection, Fickian diffusion, and Fokker-Planck diffusion models, respectively. Additionally, we explore steady-state problems for each strategy to highlight the differences between models incorporating temporal memory and those incorporating spatiotemporal memory.

---

Sureni Wickramasooriya

University of California - Davis

"Mathematical Model for Gene Drive Mosquito Releae On Principe Island"

Genetically engineered mosquitoes (GEMs) offer a promising malaria control strategy, yet their ecological interactions, dispersal, and long-term effects remain uncertain. Accurate modeling is essential to optimize GEM release strategies and assess their effectiveness in natural ecosystems. This study presents a high-performance, exascale agent-based model (ABM) simulating gene drive dynamics in wild mosquito populations. Incorporating mosquito population dynamics, spatial ecology, and genotype inheritance, the model provides insights into optimizing release timing, locations, and dispersal strategies. Our findings indicate that under optimal dispersal conditions, GEMs can achieve a 95% prevalence in wild populations within 112 days. Furthermore, our findings indicate that strategically coordinating GEM releases across multiple sites does not significantly impact gene drive establishment on the island. By capturing mosquito behaviors and movement in heterogeneous environments, this ABM serves as a powerful tool for evaluating GEM interventions, supporting evidence-based malaria control strategies, and enhancing ecological understanding of gene drive propagation..

---