Remote-Sensing Image Classification

Mapping Coastal Forest Retreat Using Convolutional Neural Networks and Different Satellite Imagery

The paper uses convolutional neural networks with satellite imagery to quantify coastal forest loss and identify environmental drivers of ghost forest formation from 1985 to 2021.

Using a planted tree biodiversity experiment to evaluate imaging spectroscopy for species classification

The paper evaluates airborne imaging spectroscopy for tree species classification using a biodiversity experiment, finding high accuracy for few species but lower accuracy for many species.

Geospatial foundation models enable data-efficient tree species mapping in temperate mountain forests

This paper evaluates geospatial foundation models for tree species mapping in mountain forests, finding they outperform traditional methods with fewer labels and preserve ecological structure, though performance degrades over time.

Early Detection of an Invasive Alien Plant (Phragmites australis) Using Unoccupied Aerial Vehicles and Artificial Intelligence

This study uses UAVs and deep learning to detect invasive Phragmites australis, achieving high recall and F1-score for early detection.

Suaeda Salsa Hyperspectral Index (SSHI) for mapping S. salsa in coastal wetlands using hyperspectral satellite imagery

This paper introduces a hyperspectral index (SSHI) for mapping Suaeda Salsa using satellite imagery, achieving high accuracy in coastal wetland monitoring.

Hyperspectral Segmentation of Plants in Fabricated Ecosystems

This paper develops a hyperspectral segmentation workflow using sparse mixed-scale convolution neural networks to analyze plant characteristics in fabricated ecosystems with minimal user annotation.