Related papers: Utilizing a Geospatial Foundation Model for Coastl…
Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy. We synthesize the growing literature that uses satellite imagery to understand these outcomes, with…
Bird's-eye-view (BEV) images have been widely demonstrated to provide valuable prior information for navigation. Given the global information provided by such views, two key challenges remain: how to fully exploit this information and how…
The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has become common practice within the field of natural language processing, progress…
Landslide detection from high resolution satellite imagery is a critical task for disaster response and risk assessment, yet the relative effectiveness of modern segmentation architectures and finetuning strategies for this problem remains…
High resolution crop type maps are an important tool for improving food security, and remote sensing is increasingly used to create such maps in regions that possess ground truth labels for model training. However, these labels are absent…
The use of satellite imagery combined with deep learning to support automatic landslide detection is becoming increasingly widespread. However, selecting an appropriate deep learning architecture to optimize performance while avoiding…
Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient methods reduce training cost but retain full inference…
Advances in underwater imaging enable collection of extensive seafloor image datasets necessary for monitoring important benthic ecosystems. The ability to collect seafloor imagery has outpaced our capacity to analyze it, hindering…
Spectral imaging data acquired via multispectral and hyperspectral cameras can have hundreds of channels, where each channel records the reflectance at a specific wavelength and bandwidth. Time and resource constraints limit our ability to…
In numerical ocean models coast lines change the direction from one grid cell to its neighbor and the value for viscosity is set to be as small as possible. Therefore, model simulations are not converged with resolution and boundary…
The atmospheres of Mars and Titan are loaded with aerosols that impact remote sensing observations of their surface. Here we present the algorithm and the first applications of a radiative transfer model in spherical geometry designed for…
Global climate models parameterize a range of atmospheric-oceanic processes like gravity waves, clouds, moist convection, and turbulence that cannot be sufficiently resolved. These subgrid-scale closures for unresolved processes are a…
Data from NASA's Orbiting Carbon Observatory-2 (OCO-2) satellite is essential to many carbon management strategies. A retrieval algorithm is used to estimate CO2 concentration using the radiance data measured by OCO-2. However, due to…
The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from…
Dense ground displacement measurements are crucial for geological studies but are impractical to collect directly. Traditionally, displacement fields are estimated using patch matching on optical satellite images from different acquisition…
Marine debris detection for ocean robot is crucial for ecological protection, yet performance is often degraded by low-quality images with blur, complex backgrounds, and small targets. To address these challenges, we propose YOLO-MD, an…
We explore the scaling behaviors of artificial intelligence to establish practical techniques for training foundation models on high-resolution electro-optical (EO) datasets that exceed the current state-of-the-art scale by orders of…
Birds Eye View perception models require extensive data to perform and generalize effectively. While traditional datasets often provide abundant driving scenes from diverse locations, this is not always the case. It is crucial to maximize…
Accurate global glacier mapping is critical for understanding climate change impacts. Despite its importance, automated glacier mapping at a global scale remains largely unexplored. Here we address this gap and propose…
Continuous monitoring for road flooding could be achieved through onboard computing of satellite imagery to generate near real-time insights made available to generate dynamic information for maps used for navigation. Given the existing…