arXiv subjects

Campbell D. Watson

Publications and source records attributed to Campbell D. Watson.

8 recordsLinked to original sources

arXiv2026

Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing

We present a multimodal foundation model for lunar remote sensing, pretrained from scratch on SomBench, a geographically partitioned corpus of nearly two million co-registered tile bundles spanning 11 modalities at two spatial scales (1 m/pixel and 100 m/pixel). The model adapts the TerraMind masked-token architecture with two lunar-specific extensions: acquisition geometry is provided as explicit context, and meter- and hundred-meter-scale tiles are trained jointly so that a single set of weights covers both resolutions. FlexiViT patch embeddings allow adaptation to different patch sizes without retraining, while modality-wise inputs enable flexible multimodal fine-tuning. Qualitative generation experiments suggest the model learns meaningful cross-modal correspondences, including terrain derivatives from elevation and illumination-consistent reflectance from geometry. We evaluate on four benchmarks: crater detection at WAC and NAC scales, irregular mare patch (IMP) segmentation, and polar ice prospectivity regression. Across tasks, the pretrained model matches or outperforms ImageNet-pretrained baselines and an architecturally identical random-init control. On multimodal ice prospectivity regression, pretrained variants achieve the best results, while the random-init model outperforms most baselines, suggesting gains arise from both the architecture and pretraining. Label efficiency is notable for WAC crater detection, where the pretrained model trained on 50% of the data exceeds the strongest ImageNet baseline trained on the full dataset. Among adaptation strategies, LoRA matches or surpasses full fine-tuning on crater detection and IMP segmentation while using far fewer trainable parameters, whereas full fine-tuning performs best for ice prospectivity regression. We release the pretrained checkpoint, benchmark datasets, and fine-tuning code to support reproducible lunar AI research.

cs.CV↗

arXiv2023

Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling

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 up climate simulations, neural networks have been used to downscale climate variables from fast-running low-resolution simulations, but high-resolution training data are often unobtainable or scarce, greatly limiting accuracy. In this work, we propose a downscaling method based on the Fourier neural operator. It trains with data of a small upsampling factor and then can zero-shot downscale its input to arbitrary unseen high resolution. Evaluated both on ERA5 climate model data and on the Navier-Stokes equation solution data, our downscaling model significantly outperforms state-of-the-art convolutional and generative adversarial downscaling models, both in standard single-resolution downscaling and in zero-shot generalization to higher upsampling factors. Furthermore, we show that our method also outperforms state-of-the-art data-driven partial differential equation solvers on Navier-Stokes equations. Overall, our work bridges the gap between simulation of a physical process and interpolation of low-resolution output, showing that it is possible to combine both approaches and significantly improve upon each other.

cs.LG↗

arXiv2022

Aboveground carbon biomass estimate with Physics-informed deep network

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 (AGB) is required. Here, we use deep neural network to generate a wall-to-wall map of AGB within the Continental USA (CONUS) with 30-meter spatial resolution for the year 2021. We combine radar and optical hyperspectral imagery, with a physical climate parameter of SIF-based GPP. Validation results show that a masked variation of UNet has the lowest validation RMSE of 37.93 $\pm$ 1.36 Mg C/ha, as compared to 52.30 $\pm$ 0.03 Mg C/ha for random forest algorithm. Furthermore, models that learn from SIF-based GPP in addition to radar and optical imagery reduce validation RMSE by almost 10% and the standard deviation by 40%. Finally, we apply our model to measure losses in AGB from the recent 2021 Caldor wildfire in California, and validate our analysis with Sentinel-based burn index.

cs.LG↗

arXiv2021

Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion

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 such extreme events. Although machine learning approaches have shown promising results in long-range climate forecasting, the associated model uncertainties may reduce their reliability. To address this issue, we propose a late fusion approach that systematically combines the predictions from multiple models to reduce the expected errors of the fused results. We also propose a network architecture with the novel denormalization layer to gain the benefits of data normalization without actually normalizing the data. The experimental results on long-range 2m temperature forecasting show that the framework outperforms the 30-year climate normals, and the accuracy can be improved by increasing the number of models.

cs.LG↗

arXiv2021

Reduced order modeling of dynamical systems using artificial neural networks applied to water circulation

General circulation models are essential tools in weather and hydrodynamic simulation. They solve discretized, complex physical equations in order to compute evolutionary states of dynamical systems, such as the hydrodynamics of a lake. However, high-resolution numerical solutions using such models are extremely computational and time consuming, often requiring a high performance computing architecture to be executed satisfactorily. Machine learning (ML)-based low-dimensional surrogate models are a promising alternative to speed up these simulations without undermining the quality of predictions. In this work, we develop two examples of fast, reliable, low-dimensional surrogate models to produce a 36 hour forecast of the depth-averaged hydrodynamics at Lake George NY, USA. Our ML approach uses two widespread artificial neural network (ANN) architectures: fully connected neural networks and long short-term memory. These ANN architectures are first validated in the deterministic and chaotic regimes of the Lorenz system and then combined with proper orthogonal decomposition (to reduce the dimensionality of the incoming input data) to emulate the depth-averaged hydrodynamics of a flow simulator called SUNTANS. Results show the ANN-based reduced order models have promising accuracy levels (within 6% of the prediction range) and advocate for further investigation into hydrodynamic applications.

physics.ao-ph↗

arXiv2021

A modular framework for extreme weather generation

Extreme weather events have an enormous impact on society and are expected to become more frequent and severe with climate change. In this context, resilience planning becomes crucial for risk mitigation and coping with these extreme events. Machine learning techniques can play a critical role in resilience planning through the generation of realistic extreme weather event scenarios that can be used to evaluate possible mitigation actions. This paper proposes a modular framework that relies on interchangeable components to produce extreme weather event scenarios. We discuss possible alternatives for each of the components and show initial results comparing two approaches on the task of generating precipitation scenarios.

cs.LG↗

arXiv2021

Long-Range Seasonal Forecasting of 2m-Temperature with Machine Learning

A significant challenge in seasonal climate prediction is whether a prediction can beat climatology. We hereby present results from two data-driven models - a convolutional (CNN) and a recurrent (RNN) neural network - that predict 2 m temperature out to 52 weeks for six geographically-diverse locations. The motivation for testing the two classes of ML models is to allow the CNN to leverage information related to teleconnections and the RNN to leverage long-term historical temporal signals. The ML models boast improved accuracy of long-range temperature forecasts up to a lead time of 30 weeks for PCC and up 52 weeks for RMSESS, however only for select locations. Further iteration is required to ensure the ML models have value beyond regions where the climatology has a noticeably reduced correlation skill, namely the tropics.

physics.ao-ph↗

arXiv2020

Investigating two super-resolution methods for downscaling precipitation: ESRGAN and CAR

In an effort to provide optimal inputs to downstream modeling systems (e.g., a hydrodynamics model that simulates the water circulation of a lake), we hereby strive to enhance resolution of precipitation fields from a weather model by up to 9x. We test two super-resolution models: the enhanced super-resolution generative adversarial networks (ESRGAN) proposed in 2017, and the content adaptive resampler (CAR) proposed in 2020. Both models outperform simple bicubic interpolation, with the ESRGAN exceeding expectations for accuracy. We make several proposals for extending the work to ensure it can be a useful tool for quantifying the impact of climate change on local ecosystems while removing reliance on energy-intensive, high-resolution weather model simulations.

physics.ao-ph↗