Meeting roles in:
Beyond Lumped Inputs: Transformer Models and Spatially-Explicit Data Integration for Streamflow Forecasting in Arizona
Overlooked Biases in Machine‑Learning Soil‑Carbon Maps: Depth Autocorrelation, Circular Density Logic, and Validation Gaps
My research trajectory integrates theoretical models with AI/ML-driven methodologies to elucidate complex real-world scenarios. During my Ph.D., my research emphasized the significance of decision making in diverse domains, from geosciences to economics to deep learning, illuminating how behaviors perceived as anomalies often harbor mathematical rationales. Transitioning to my postdoc, my focus has shifted to natural system sciences, using data-based AI/ML models and remote sensing in projects such as analyzing baseline and attainable soil organic carbon dynamics, assessing soil risk and health, modeling streamflow patterns, examining heat wave impacts, and computing farm-scale evapotranspiration benchmarks for agricultural water optimization. My current work improves the granularity and scalability of environmental models, using machine learning and remote sensing to provide actionable insights for modeling natural systems, climate resilience, regenerative agriculture, crop management, carbon sequestration strategies, sustainable water use, and broader environmental management.