相关论文: EarthPT: a time series foundation model for Earth …
The Landsat program is the longest-running Earth observation program in history, with 50+ years of data acquisition by 8 satellites. The multispectral imagery captured by sensors onboard these satellites is critical for a wide range of…
The innovative application of precise geospatial vegetation forecasting holds immense potential across diverse sectors, including agriculture, forestry, humanitarian aid, and carbon accounting. To leverage the vast availability of satellite…
Monitoring vegetation dynamics is crucial for addressing global environmental challenges like degradation and deforestation, but traditional remote sensing methods are often complex and resource-intensive. To overcome these barriers, we…
We present AiTLAS: Benchmark Arena -- an open-source benchmark suite for evaluating state-of-the-art deep learning approaches for image classification in Earth Observation (EO). To this end, we present a comprehensive comparative analysis…
Precipitation nowcasting -- the short-term prediction of rainfall using recent radar observations -- is critical for weather-sensitive sectors such as transportation, agriculture, and disaster mitigation. While recent deep learning models…
This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state of the art on…
In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning. While thousands of…
Precipitation nowcasting is to predict the future rainfall intensity over a short period of time, which mainly relies on the prediction of radar echo sequences. Though convolutional neural network (CNN) and recurrent neural network (RNN)…
As repositories of large scale data in earth observation (EO) have grown, so have transfer and storage costs for model training and inference, expending significant resources. We introduce Neural Embedding Compression (NEC), based on the…
Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets to enable versatile downstream applications through finetuning, separating them from task-specific weather…
Despite the unprecedented volume of multimodal data provided by modern Earth observation systems, our ability to model atmospheric dynamics remains constrained. Traditional modeling frameworks force heterogeneous measurements into…
Earth observation (EO) data spans a wide range of spatial, spectral, and temporal resolutions, from high-resolution optical imagery to low resolution multispectral products or radar time series. While recent foundation models have improved…
We have assessed accuracy of estimates of Earth orientation parameters (EOP) determined from several very long baseline interferometry (VLBI) observing programs that ran concurrently at different networks. We consider that the root mean…
It is customary to perform analysis of the Earth's rotation in two steps: first, to present results of estimation of the Earth orientation parameters in the form of time series based on a simplified model of variations of the Earth's…
We introduce an interpretable-by-design method, optimized model-analog, that integrates deep learning with model-analog forecasting which generates forecasts from similar initial climate states in a repository of model simulations. This…
The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process…
Forest monitoring is critical for climate change mitigation. However, existing global tree height maps provide only static snapshots and do not capture temporal forest dynamics, which are essential for accurate carbon accounting. We…
The predictive brain hypothesis suggests that perception can be interpreted as the process of minimizing the error between predicted perception tokens generated by an internal world model and actual sensory input tokens. When implementing…
The Earth Mover's Distance is a popular similarity measure in several branches of computer science. It measures the minimum total edge length of a perfect matching between two point sets. The Earth Mover's Distance under Translation…
Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this…