Search for: All records

As a key component of inherent optical properties (IOPs) in ocean color remote sensing, phytoplankton absorption coefficient (aphy), especially in hyperspectral, greatly enhances our understanding of phytoplankton community composition (PCC). The recent launches of NASA’s hyperspectral missions, such as EMIT and PACE, have generated an urgent need for hyperspectral algorithms for studying phytoplankton. Retrieving aphy from ocean color remote sensing in coastal waters has been extremely challenging due to complex optical properties. Traditional methods often fail under these circumstances, while improved machine-learning approaches are hindered by data scarcity, heterogeneity, and noise from data collection. In response, this study introduces a novel machine learning framework for hyperspectral retrievals of aphy based on the mixture-of-experts (MOEs), named PhA-MOE. Various preprocessing methods for hyperspectral training data are explored, with the combination of robust and logarithmic scalers identified as optimal. The proposed PhA-MOE for aphy prediction is tailored to both past and current hyperspectral missions, including EMIT and PACE. Extensive experiments reveal the importance of data preprocessing and improved performance of PhA-MOE in estimating aphy as well as in handling data heterogeneity. Notably, this study marks the first application of a machine learning–based MOE model to real PACE-OCI hyperspectral imagery, validated using match-up field data. This application enables the exploration of spatiotemporal variations in aphy within an optically complex estuarine environment. 

This paper reviews trends in GeoAI research and discusses cutting-edge advances in GeoAI and its roles in accelerating environmental and social sciences. It addresses ongoing attempts to improve the predictability of GeoAI models and recent research aimed at increasing model explainability and reproducibility to ensure trustworthy geospatial findings. The paper also provides reflections on the importance of defining the science of GeoAI in terms of its fundamental principles, theories, and methods to ensure scientific rigor, social responsibility, and lasting impacts. 

Abstract Static granular packings play a central role in numerous industrial applications and natural settings. In these situations, fluid or fine particle flow through a bed of static particles is heavily influenced by the narrowest passage connecting the pores of the packing, commonly referred to as pore throats, or constrictions. Existing studies predominantly assume monodisperse rigid particles, but this is an oversimplification of the problem. In this work, we illustrate the connection between pore throat size, polydispersity, and particle deformation in a packed bed of spherical particles. Simple analytical expressions are provided to link these properties of the packing, followed by examples from Discrete Element Method (DEM) simulations of fine particle percolation demonstrating the impact of polydispersity and particle deformation. Our intent is to emphasize the substantial impact of polydispersity and particle deformation on constriction size, underscoring the importance of accounting for these effects in particle transport in granular packings.