Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

5111621 · Oct 201919922001200920182026
48 results for weather satellites

Probabilistic NDVI forecasting from sparse satellite data.

problem Challenges in short-term NDVI forecasting due to sparse and irregular satellite data.
method Probabilistic forecasting framework using historical NDVI and meteorological observations, with temporal-distance weighted quantile loss and extreme-weather feature engineering.
result The proposed method outperforms baselines on pointwise and probabilistic evaluation metrics.

Deep learning model predicts tropical cyclone intensification using satellite images.

problem Accurately predicting rapid intensification of tropical cyclones.
method Attention-based deep learning model using satellite images.
result Deep learning models outperform traditional methods in RI prediction.

WeatherFormer learns robust weather features from small datasets.

problem Modeling complex weather dynamics from limited data.
method Pretrained transformer encoder on large satellite dataset, with spatiotemporal encoding.
result State-of-the-art performance in county-level soybean yield prediction and influenza forecasting.

A model predicts solar irradiance without local data using satellite and weather forecasts.

problem Forecasting solar irradiance without local measurements for geographically dispersed solar generators.
method Uses satellite data and weather forecasts with a deep neural network trained on a subset of ground data.
result Proposed model performs as well or better than local models across 25 locations and prediction horizons.

New model predicts particle precipitation from magnetosphere to ionosphere.

problem Improving prediction of electron particle precipitation from magnetosphere to ionosphere.
method Compilation of new database, use of machine learning (ML) tools, neural network (PrecipNet).
result PrecipNet achieves >50% reduction in errors and better captures dynamic changes.

Paper compares neural networks and time-series models for weather derivative pricing.

problem Pricing accuracy and regime adaptation for temperature and precipitation weather derivatives.
method Benchmarked harmonic-regression/ARMA vs. feed-forward neural network for temperature. Used CNN for precipitation, adapting to seasonal heterogeneity.
result CNN yields more accurate pricing, especially for regime-adapted seasonal data.

Sparse point observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.

problem Improving dense radar-field forecasts with sparse point observations
method A multimodal graph neural network nowcasting system over the Nordic radar domain
result Each source improves a different part of the forecast problem

A framework converts spatial data into embeddings for insurance risk modelling.

problem Improving underwriting precision and risk management in insurance with spatial data.
method Multi-view contrastive learning framework for generating spatial embeddings.
result Spatial embeddings consistently improve predictive accuracy across various models.

AI helps forecasters understand TC convective evolution before intensification.

problem Challenges in extracting scientific insights from complex TC data.
method Combining AI prediction algorithms and classical statistical inference.
result Identifies patterns in TC convective structure leading to intensification.

CBGP boosts GP covariance to model spatiotemporal irregularities.

problem Overfitting and overconfident uncertainty in nonstationary GP models.
method Boosting covariance priors, partially-whitened observations, gradient descent-like procedure.
result Accurate and reliable SBAS ionospheric corrections in challenging space weather.

Weather balloons deploy sensors to collect stratospheric data.

problem Limited data collection in the stratosphere.
method Modeling forecast deviation as a Gaussian process to determine sensor release times; novel hardware system for optimal sensor release.
result Data engineering framework effectively collects stratospheric data through real flights and simulations.

This study analyzes satellite communication latency using a stochastic geometry model.

problem Latency analysis of LEO satellite relay communication systems.
method Stochastic geometry framework with spherical BPP models, suboptimal satellite relay selection strategy.
result Derives distance distributions and analytical expressions for transmission delays.

Any knot in a solid torus, called a pattern or satellite operator, acts on knots in the 3-sphere via the satellite construction. We introduce a generalization of satellite operators which form a group (unlike traditional satellite operators), modulo a generalization of concordance. This group has an action on the set o…

2013-06-19abs ↗pdf ↗

Weather derivatives help farmers hedge against crop yield risks.

problem High basis risks in weather derivatives pricing models.
method Machine learning ensemble technique to determine yield-weather relationships; mean-reverting model with local temperature dependence.
result Average temperature is the most significant weather variable affecting maize yield.

Develops a new framework for integrating satellite allocations in small portfolios.

problem Feasibility constraints in small portfolios, not return predictability, are the primary concerns.
method A four-layer feasibility framework: physical, economic, structural, and epistemic.
result Closed-form feasibility bounds on satellite size, turnover, and breadth without return forecasts.

Model predicts one-year NDVI for Four Corners region.

problem Long-term forecasting of vegetation conditions using climate attributes.
method Two-phase machine learning model using historical climate data.
result Open-source tools outperform alternative methods for NDVI forecasts.

FedSpace optimizes ML training on satellites and ground stations.

problem Training machine learning models on satellites with limited bandwidth.
method Federated Learning framework that dynamically schedules model aggregation based on satellite orbits.
result Reduces training time by 1.7 days over state-of-the-art algorithms.

The Gluck twist preserves the diffeomorphism type of certain satellite 2-knots.

problem Preserving the diffeomorphism type of satellite 2-knots under the Gluck twist.
method Using new descriptions of satellite 2-knots, the paper shows that the Gluck twist does not change the diffeomorphism type of certain satellite 2-knots in three ways.
result The Gluck twist preserves the diffeomorphism type of certain satellite 2-knots.

Researchers compute Khovanov polynomials for satellite knots.

problem Computing Khovanov polynomials for satellite knots.
method Explicit computation using a computer program for two families of satellite knots.
result Khovanov polynomials can be expressed as a linear combination of pattern and companion invariants, with a jump at a critical point.

Deep neural networks reduce weather forecast uncertainty estimation costs.

problem Accurate estimation of weather forecast uncertainty using ensemble prediction systems.
method Modified 3D U-Net architecture and models incorporating temporal data.
result Deep neural networks can estimate weather forecast uncertainty with fewer simulations.

The study computes invariants of satellite knots using bordered Floer homology.

problem Computing invariants of satellite knots with specific patterns.
method Using bordered Floer homology and the immersed curve interpretation of the bordered pairing theorem.
result Satellites with thin fibered companions or specific patterns have thin knot Floer homology.

Necessary and sufficient conditions are given for a satellite knot to be fibered. Any knot k~\tilde k embeds in an unknotted solid torus V~\tilde V with arbitrary winding number in such a way that no satellite knot with pattern (V~,k~)(\tilde V, \tilde k) is fibered. In particular, there exist nonfibered satellite knots wit…

2007-04-30abs ↗pdf ↗

Signature kernel scoring rule improves weather forecasting by capturing temporal and spatial dependencies.

problem Lack of suitable scoring rules for probabilistic weather forecasting.
method Reframe weather variables as continuous paths using iterated integrals (signature kernels) to capture temporal and spatial dependencies.
result Signature kernel scoring rule outperforms conventional methods in weather forecasting, especially for long-term forecasts.