Tagged by: Machine Learning

Fusing PlanetScope & Sentinel-2 for Daily, High-resolution Leaf Area

Paper

Improving crop yields, vigor and health, can be facilitated by better monitoring of the cross-sectional area of vegetation—i.e., Leaf Area Index or LAI. However, measuring LAI on the ground is time consuming and expensive. Sentinel-2, operated by the European Space Agency, publishes a global LAI product; but at 10m resolution and a […]

PlanetScope + Deep Learning Improves Understanding of Glacial Lake Risk

Blog

Glacial lakes in mountainous regions are prone to outburst floods that can devastate entire communities. With climate change, glacial ice is thinning and retreating in the Hindu Kush, Karakoram and Himalaya region, posing an increasing threat to human life and requiring improved monitoring. Nida Qayyum, in the Department of Space Science at […]

Mapping Landslide Susceptibility in Dove Imagery after the 2018 Tomakomai Earthquake

Paper

Globally, landslides kill ~5,000 people per year. If landslides—including rock falls, mudslides and other surface failures—can be better predicted, these deaths could be avoided. Landslides are highly heterogeneous, both spatially and temporally. They are more common in the steep, mountainous regions of the Earth, but also more frequent during particular seasons due […]

Convolutional Neural Networks used to Detect and Classify Ships in Dove Imagery

Paper

With daily imagery over ports and coastlines, one of the most useful potential applications of Planet’s Dove imagery is the detection and classification of maritime vessels. Ship tracking has a vital role in security, but the enormous number of ships at sea at any given time limits the effectiveness of classical, human-powered […]

Daily, High-resolution Leaf Area Index from Sensor Fusion with Planet, Landsat and MODIS

Paper

Classic remote sensing for agricultural relies heavily on indices like NDVI (Normalized Differential Vegetation Index), which uses information from the red and near-infrared portions of the spectrum to provide an indicator of vegetation greenness and vitality. However, other indices, often implicating other parts of the spectrum, may provided added and actionable information […]

Stanford Students Deploy Deep Learning with Planet Imagery

Features

As Planet’s Education and Research Community continues to grow, students are increasingly working with Planet imagery in college courses. At Stanford University, several students recently utilized Planet imagery in Computer Science 230: Deep Learning. Ian Avery Bick, Dennis Wang and Ben Mullet examined deforestation near Kibale National Park in Southern Uganda, an […]

Sensor Fusion of Planet, Landsat and MODIS Data for Unprecedented Land Surface Monitoring

Paper

In the midst of a revolution Earth Observation, due to increasingly diverse and temporally dense data feeds enabled by cubesats and other sensors, there is a need to be interoperable across sensors. In the journal Remote Sensing of Environment, Rasmus Houborg and Matt McCabe present the Cubesat-enabled Spatio-Temporal Enhancement Method (CESTEM), which […]

Change Detection of Mediterranean Seagrasses Using RapidEye Time Series

Paper

Seagrass beds are one of the most important ecosystems in the Mediterranean region, supporting an enormous diversity of marine fauna. However, with anthropogenic influences including dredging and modification of shorelines, pollution and other drivers, seagrass ecosystems facing increasing threats. To improve monitoring of seagrass extent, Dimosthenis Tranganos and Peter Reinartz from the […]