Campbell Watson
YOU?
Author Swipe
View article: Local Off‐Grid Weather Forecasting With Multi‐Modal Earth Observation Data
Local Off‐Grid Weather Forecasting With Multi‐Modal Earth Observation Data Open
Urgent applications like wildfire management and renewable energy generation require precise, localized weather forecasts near the Earth's surface. However, forecasts produced by machine learning models or numerical weather prediction syst…
View article: SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction
SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction Open
This paper introduces a high resolution, machine learning-ready heliophysics dataset derived from NASA's Solar Dynamics Observatory (SDO), specifically designed to advance machine learning (ML) applications in solar physics and space weath…
View article: Surya: Foundation Model for Heliophysics
Surya: Foundation Model for Heliophysics Open
Heliophysics is central to understanding and forecasting space weather events and solar activity. Despite decades of high-resolution observations from the Solar Dynamics Observatory (SDO), most models remain task-specific and constrained b…
View article: Data for "Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data"
Data for "Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data" Open
This repository contains the data for the paper "Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data". The paper presents a novel multi-modal deep learning method that downscales gridded weather forecasts, such as ER…
View article: QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation Platform
QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation Platform Open
We present QGen Studio: an adaptive question-answer generation, training, and evaluation platform. QGen Studio enables users to leverage large language models (LLMs) to create custom question-answer datasets and fine-tune models on this sy…
View article: EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues Open
Automated analysis of vast Earth observation data via interactive Vision-Language Models (VLMs) can unlock new opportunities for environmental monitoring, disaster response, and {resource management}. Existing generic VLMs do not perform w…
View article: Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications Open
This technical report presents Prithvi-EO-2.0, a new geospatial foundation model that offers significant improvements over its predecessor, Prithvi-EO-1.0. Trained on 4.2M global time series samples from NASA's Harmonized Landsat and Senti…
View article: Prithvi WxC: Foundation Model for Weather and Climate
Prithvi WxC: Foundation Model for Weather and Climate Open
Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecas…
View article: Evaluating the transferability potential of deep learning models for climate downscaling
Evaluating the transferability potential of deep learning models for climate downscaling Open
Climate downscaling, the process of generating high-resolution climate data from low-resolution simulations, is essential for understanding and adapting to climate change at regional and local scales. Deep learning approaches have proven u…
View article: A sequence of weather‐driven hydrodynamic events stimulates the formation of harmful algal blooms on an oligotrophic lake
A sequence of weather‐driven hydrodynamic events stimulates the formation of harmful algal blooms on an oligotrophic lake Open
Harmful algal blooms (HABs) are common in many eutrophic lakes and frequently associated with nutrient excesses, warm waters, and calm conditions. While HABs can also occur in oligotrophic waterbodies, bloom‐stimulating factors remain elus…
View article: Fine-tuning of Geospatial Foundation Models for Aboveground Biomass Estimation
Fine-tuning of Geospatial Foundation Models for Aboveground Biomass Estimation Open
Global vegetation structure mapping is critical for understanding the global carbon cycle and maximizing the efficacy of nature-based carbon sequestration initiatives. Moreover, vegetation structure mapping can help reduce the impacts of c…
View article: Direct Sampling for Spatially Variable Extreme Event Generation in Resampling‐Based Stochastic Weather Generators
Direct Sampling for Spatially Variable Extreme Event Generation in Resampling‐Based Stochastic Weather Generators Open
Resampling‐based weather generators simulate new time series of weather variables by reordering the observed values such that the statistics of the simulated data are consistent with the observed ones. These generators are fully data‐drive…
View article: AI Foundation Models for Weather and Climate: Applications, Design, and Implementation
AI Foundation Models for Weather and Climate: Applications, Design, and Implementation Open
Machine learning and deep learning methods have been widely explored in understanding the chaotic behavior of the atmosphere and furthering weather forecasting. There has been increasing interest from technology companies, government insti…
View article: Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling
Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling Open
Climate simulations are essential in guiding our understanding of climate change and responding to its effects. However, it is computationally expensive to resolve complex climate processes at high spatial resolution. As one way to speed u…
View article: Establishing a Geospatial Discovery Network with efficient discovery and modeling services in multi-cloud environments
Establishing a Geospatial Discovery Network with efficient discovery and modeling services in multi-cloud environments Open
The ballooning volume and complexity of geospatial data is one of the main inhibitors for advancements in climate & sustainability research. Oftentimes, researchers need to create bespoke and time-consuming workflows to harmonize datasets,…
View article: Physics-Constrained Deep Learning for Downscaling
Physics-Constrained Deep Learning for Downscaling Open
The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and mitigation and to guide rapid responses to extreme events. Forecasting models are limited by comput…
View article: Aboveground carbon biomass estimate with Physics-informed deep network
Aboveground carbon biomass estimate with Physics-informed deep network Open
The global carbon cycle is a key process to understand how our climate is changing. However, monitoring the dynamics is difficult because a high-resolution robust measurement of key state parameters including the aboveground carbon biomass…
View article: Hard-Constrained Deep Learning for Climate Downscaling
Hard-Constrained Deep Learning for Climate Downscaling Open
The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and mitigation and to guide rapid responses to extreme events. Forecasting models are limited by comput…
View article: Controlling Weather Field Synthesis Using Variational Autoencoders
Controlling Weather Field Synthesis Using Variational Autoencoders Open
One of the consequences of climate change is anobserved increase in the frequency of extreme cli-mate events. That poses a challenge for weatherforecast and generation algorithms, which learnfrom historical data but should embed an often u…
View article: Choose your own weather adventure: deep weather generation for “what-if” climate scenarios
Choose your own weather adventure: deep weather generation for “what-if” climate scenarios Open
<p>Climate change is making extreme weather more extreme. Given the inherent uncertainty of long-term climate projections, there is growing need for rapid, plausible &#8220;what-if&#8221; climate scenarios to help users under…
View article: ML-based Probabilistic Prediction of 2m Temperature and Total Precipitation
ML-based Probabilistic Prediction of 2m Temperature and Total Precipitation Open
<p>The need to build reliable weather forecasting systems for subseasonal to seasonal (S2S) timescales has never been greater as the world continues to experience increased numbers of extreme weather events. This study addresses the …
View article: S2S Extreme Weather Featurization: A Global Skill Assessment Study
S2S Extreme Weather Featurization: A Global Skill Assessment Study Open
<p><span>A more accurate characterization of S2S </span><span>extremes</span> <span>may result in great positive </span><span>societal impact. </span><span>Featurized S2S forecast…
View article: Wildfire risk forecast: An optimizable fire danger index
Wildfire risk forecast: An optimizable fire danger index Open
Wildfire events have caused severe losses in many places around the world and are expected to increase with climate change. Throughout the years many technologies have been developed to identify fire events early on and to simulate fire be…
View article: Matryoshka Neural Operators: Learning Fast PDE Solvers for Multiscale Physics
Matryoshka Neural Operators: Learning Fast PDE Solvers for Multiscale Physics Open
<p>Running a high-resolution global climate model can take multiple days on the world's largest supercomputers. Due to the long runtimes that are caused by solving the underlying partial differential equations (PDEs), climate researc…
View article: Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion
Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion Open
Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property. Accurate long-range climate prediction allows more time for preparation and disaster risk management for …
View article: A comparative study of stochastic and deep generative models for multisite precipitation synthesis.
A comparative study of stochastic and deep generative models for multisite precipitation synthesis. Open
Future climate change scenarios are usually hypothesized using simulations from weather generators. However, there only a few works comparing and evaluating promising deep learning models for weather generation against classical approaches…
View article: A comparative study of stochastic and deep generative models for multisite precipitation synthesis
A comparative study of stochastic and deep generative models for multisite precipitation synthesis Open
Future climate change scenarios are usually hypothesized using simulations from weather generators. However, there only a few works comparing and evaluating promising deep learning models for weather generation against classical approaches…
View article: Extreme Precipitation Seasonal Forecast Using a Transformer Neural\n Network
Extreme Precipitation Seasonal Forecast Using a Transformer Neural\n Network Open
An impact of climate change is the increase in frequency and intensity of\nextreme precipitation events. However, confidently predicting the likelihood of\nextreme precipitation at seasonal scales remains an outstanding challenge.\nHere, w…