arXiv subjects

Upmanu Lall

Publications and source records attributed to Upmanu Lall.

15 recordsLinked to original sources

arXiv2026

Steering Tropical Cyclones Using Small Perturbations in an AI Weather Model

Tropical cyclone (TC) trajectories are governed by large-scale steering flows and exhibit sensitive dependence on atmospheric initial conditions. Using Hurricane Sandy (2012) in the Aurora AI weather model, we investigate whether targeted thermodynamic perturbations can induce meaningful track deviations. Two distinct perturbation regimes emerge. In the Caribbean, forward finite-time Lyapunov exponent (FTLE) diagnostics identify dynamically sensitive regions within Sandy's steering flow, where perturbations produce substantially larger responses than random placement. In the Pacific, a preferred corridor near 165W influences Sandy through Rossby wave teleconnections, confirmed using Takaya-Nakamura wave activity flux diagnostics. Despite their different physical pathways, both regimes share a common amplification mechanism: small initial perturbations generate modest trajectory offsets that are rapidly amplified when Sandy enters the highly sensitive recurvature region. The largest experiments produce track deviations exceeding 500 km after seven days. These results provide a proof-of-concept demonstration of the Weather Jiu-Jitsu framework, illustrating how targeted perturbations can be amplified through atmospheric dynamics in an AI weather model. Because the required perturbations exceed current operational cloud-seeding capabilities, the experiments should be interpreted as a theoretical sensitivity analysis rather than an operational weather modification strategy.

physics.ao-ph↗

arXiv2026

A 10,000-Year Global Stochastic Tropical Cyclone Catalog with Wind-Dependent Track Transitions (WHITS)

Reliable assessment of tropical cyclone risk is limited by the short and spatially uneven historical record, especially for rare, high-intensity landfalls that dominate insured loss. We present WHITS, the Wind-focused Hurricane Interactive Track Simulator, a non-parametric semi-Markov model that generates a 10,000-year global synthetic catalog of tropical cyclone tracks. WHITS builds new storms by resampling variable-length segments of historical tracks, with segment choices conditioned on local wind speed, location, storm age, and forward motion. This structure preserves both the statistical grounding of the historical record and a form of system memory along realized storm pathways. The resulting catalog reproduces observed track density and the annual probability that hurricane- or typhoon-force winds pass a given location across the major tropical cyclone basins. WHITS is designed to support climate risk analysis, insurance applications, and extreme event research over operational planning time scales by providing a large, low-bias sample of physically plausible storms. This low-bias design is important for applications in which introduced bias cannot simply be corrected after the fact and small errors in storm frequency, track, or intensity can substantially affect loss estimates. Because loss accumulates along the storm path, track geometry matters: storms that loop, stall, or turn sharply can produce damage footprints that differ fundamentally from straight-moving events. By preserving these irregular shapes while greatly expanding the sample of plausible storms, WHITS provides risk analysts, insurers, and coastal planners with information unavailable from observations alone.

cs.LG↗

arXiv2026

Urban Flood Observations: A hand-labeled training and validation dataset of post-flood inundation

Urban flooding affects lives and infrastructure worldwide. Mapping inundation in complex urban environments from satellite imagery remains challenging due to limited spatial resolution, infrequent acquisitions, and cloud cover. We present Urban Flood Observations (UFO), a global, hand-labeled dataset of post-flood inundation in diverse urban settings. UFO comprises 215 image chips (1024 by 1024 pixels) from 14 flood events between 2017 and 2021, derived from 3 m PlanetScope imagery. Each chip is annotated with two classes: 'inundated' (all visible surface water, including floodwater and pre-existing water bodies (permanent or seasonal)) and 'non-inundated'. To demonstrate the dataset's utility, we trained a segmentation model using leave-one-event-out cross-validation, achieving a mean Intersection over Union (IoU) of 77.3. We also used UFO to evaluate two widely used surface water products, the Sentinel-1-based NASA IMPACT model and Google's 10 m Dynamic World water class, which yielded IoUs of 44.1 and 48.1, respectively. UFO is publicly available to support the development and validation of urban inundation mapping methods.

cs.CV↗

arXiv2026

Instability-Aware Steering of an Extreme Atmospheric River in an AI Weather Foundation Model

Advances in deep learning methods for weather forecasting are creating opportunities to computationally explore the potential for steering or control of extreme weather trajectories for societal risk reduction. We present initial investigations into the feasibility of redirecting extreme atmospheric rivers (ARs) through small, instability-aware perturbations. Using the Aurora AI weather foundation model, we identify sensitive upstream locations using finite-time Lyapunov exponents and jet-eddy interaction criteria. We apply an idealized cloud-seeding operator that mimics latent heat release to assess whether these Lyapunov-guided interventions can influence downstream evolution. In a case study of a severe California AR, perturbations induce coherent downstream shifts in moisture transport, reducing intensity at landfall under favorable kinematic conditions. The response is nonlinear and contingent on the local flow geometry. These initial results suggest that the atmosphere's intrinsic chaotic sensitivity could be leveraged for dynamical control, offering a new research direction for extreme event risk mitigation.

physics.ao-ph↗

arXiv2026

Real-time Coordination of Cascaded Hydropower under Decision-Dependent Uncertainty

This study proposes a real-time control framework for cascaded hydropower systems that incorporates decision-dependent uncertainty (DDU) to capture the coupling of streamflow uncertainties across the reservoirs. The framework jointly models exogenous forecast errors and endogenous uncertainty propagation, explicitly characterizing the dependence between upstream releases and downstream inflow variability through a heteroskedastic variance model conditioned on past errors, variance, and control actions. We formulate a joint chance-constrained optimization problem to ensure reliable system operation under uncertainty and develop a tractable supporting hyperplane algorithm that enables explicit and adaptive risk allocation under DDU. We establish the convergence of the proposed method and show its risk allocation behavior under steady-state conditions. A randomized case study based on Columbia River data demonstrates that incorporating DDU reduces the constraint violations by up to 7.0\% and increases total generation by up to 0.5\% relative to decision-independent uncertainty (DIU). Sensitivity analyses of the dry-season streamflow conditions further highlight the value of adaptive risk allocation for resilient and risk-aware hydropower operations.

eess.SY↗

arXiv2026

Evaluating the Predictability of Selected Weather Extremes with Aurora, an AI Weather Forecast Model

AI weather foundation models now achieve forecast skill comparable to numerical weather prediction at far lower computational cost, yet their predictability for high-impact extremes across dynamical regimes remains uncertain. We evaluate Aurora using an event-based framework spanning tropical cyclones, freezes, heatwaves, atmospheric rivers, and extreme precipitation at lead times from 1 to 21 days. Aurora demonstrates strong short-range (1-7 day) skill across event types, including competitive tropical cyclone track accuracy and high spatial agreement for temperature and moisture extremes. However, a consistent subseasonal failure mode emerges: while large-scale circulation patterns remain moderately skillful at 14-21 day leads, threshold-based extreme intensity collapses as fields regress toward climatology. This divergence indicates that Aurora retains synoptic-scale dynamical structure but loses surface-impact amplitude beyond 7-10 days. The practical predictability horizon for deterministic AI extreme-event forecasting therefore remains constrained by intrinsic atmospheric dynamics.

physics.ao-ph↗

arXiv2025

Regime identification and control of extremes in the non-autonomous Lorenz model with chaos and intransitivity

Adaptive chaos control has been studied extensively for autonomous systems. For real world, non-autonomous systems, such as the planetary weather, observations of the system state in response to seasonally and diurnally varying forcing are available only at discrete times and locations, over which system trajectories are likely to have diverged given uncertainties in initial conditions. We consider a stochastic representation of such systems, as a building block for adaptive control, and develop and test control strategies in an idealized setting. We present the first example of finite time adaptive chaos control for a seasonally forced and noise-perturbed Lorenz84 model. We demonstrate two strategies for triggering control: (1) local Lyapunov exponents (LLE), and (2) transition probabilities for the latent states of a non-homogeneous Hidden Markov Model (NHMM). The second approach is motivated by thinking of future applications to a latent embedding space of planetary atmospheric circulation that would get us closer to real world analyses. The NHMM triggers are found to coincide with strongly positive LLE regimes, confirming their dynamical interpretability. These results provide a conceptual bridge towards the use of deep learning based weather and climate foundation models, whose hidden states could be leveraged for adaptive control to mitigate extreme weather events.

nlin.CD↗

arXiv2025

An Attention-Based Stochastic Simulator for Multisite Extremes to Evaluate Nonstationary, Cascading Flood Risk

Flood risk is correlated in space and time, challenging insurance systems that rely on diversification across assets. Financial instruments governing flood coverage are typically structured as 1 to 5-year contracts, exposing portfolios to climate-driven risk at interannual-to-decadal scales. Yet existing tools address climate risk either through seasonal forecasts extending only months or multidecadal projections misaligned with fiscal horizons, leaving a critical gap in actionable flood risk simulation. We introduce a multisite flood simulation framework combining attention-based analog retrieval with stochastic generation of multivariate flood frequency, intensity, and duration sequences. Applied to over 100 sites in the Mississippi River Basin, the model produces spatiotemporally coherent flood portfolios conditioned on interannual climate variability. Explainable AI attribution paired with wavelet analysis links simulated clustering to large-scale climate drivers, yielding physically interpretable flood clusters for portfolio-scale loss simulation. The framework provides plausible, out-of-sample flood risk catalogs for interannual-to-decadal insurance risk assessment and financial planning.

physics.geo-ph↗

arXiv2025

Weather Jiu-Jitsu: Climate Adaptation for the 21st Century

Extreme climate events, e.g., droughts, floods, heat waves, and freezes, are becoming more frequent and intense with severe global socio-economic impacts. Growing populations and economic activity leads to increased exposure to these events. Scaling existing physical, financial, and social infrastructure to provide resilience against these extreme events is daunting, especially as one ponders projected climate changes. Climate extremes pose a challenge even if decarbonization and geoengineering are able to regulate Earth's radiation balance. We argue that there is an urgent need to explore a novel adaptive strategy that we call "Weather Jiu-Jitsu," which leverages the intrinsic chaotic dynamics of weather systems to subtly redirect or dissipate their destructive trajectories through precisely timed, small-energy interventions. By leveraging insights from adaptive chaos control, combined with improved observations, prediction and low-energy weather system interventions, humanity could develop a novel nature assisted global infrastructure to limit the impact of climate extremes in the 21st century.

physics.ao-ph↗

arXiv2025

A Lagrangian-Informed Long-Term Dispatch Policy for Coupled Hydropower and Photovoltaic Systems

This paper presents a long-term dispatch framework for coupled hydropower and floating photovoltaic systems. We introduce a temporal decomposition algorithm based on partial Lagrangian relaxation to address long-term water contract constraints. We derive a real-time, non-anticipatory dispatch policy based on water contract pricing. Our framework is evaluated with a case study using real-world hydrology and power system data from Lake Mead and Lake Powell, on the Colorado River, demonstrating competitive performance against commercial solvers for both linearized and nonlinear reservoir models. We conduct a sensitivity analysis on transmission capacity, electricity price and uncertainty scenarios, showing that the operational performance is significantly impacted by the transmission capacity and electricity prices while remaining relatively robust under uncertainty scenarios.

eess.SY↗

arXiv2025

Deep Learning and Foundation Models for Weather Prediction: A Survey

Physics-based numerical models have been the bedrock of atmospheric sciences for decades, offering robust solutions but often at the cost of significant computational resources. Deep learning (DL) models have emerged as powerful tools in meteorology, capable of analyzing complex weather and climate data by learning intricate dependencies and providing rapid predictions once trained. While these models demonstrate promising performance in weather prediction, often surpassing traditional physics-based methods, they still face critical challenges. This paper presents a comprehensive survey of recent deep learning and foundation models for weather prediction. We propose a taxonomy to classify existing models based on their training paradigms: deterministic predictive learning, probabilistic generative learning, and pre-training and fine-tuning. For each paradigm, we delve into the underlying model architectures, address major challenges, offer key insights, and propose targeted directions for future research. Furthermore, we explore real-world applications of these methods and provide a curated summary of open-source code repositories and widely used datasets, aiming to bridge research advancements with practical implementations while fostering open and trustworthy scientific practices in adopting cutting-edge artificial intelligence for weather prediction. The related sources are available at https://github.com/JimengShi/ DL-Foundation-Models-Weather.

cs.LG↗

arXiv2024

A Bayesian Hierarchical Framework for Capturing Preference Heterogeneity in Migration Flows

Understanding and predicting human migration patterns is a central challenge in population dynamics research. Traditional physics-inspired gravity and radiation models represent migration flows as functions of attractiveness using socio-economic features as proxies. They assume that the relationship between features and migration is spatially invariant, regardless of the origin and destination locations of migrants. We use Bayesian hierarchical models to demonstrate that migrant preferences likely vary based on geographical context, specifically the origin-destination pair. By applying these models to U.S. interstate migration data, we show that incorporating heterogeneity in a single latent migration parameter significantly improves the ability to explain variations in migrant flows. Accounting for such heterogeneity enables it to outperform classical methods and recent machine-learning approaches. A clustering analysis of spatially varying parameters reveals two distinct groups of migration paths. Individuals migrating along low-flow paths (typically between smaller populations or over larger distances) exhibit more nuanced decision-making. Their choices are less directly influenced by specific destination characteristics such as housing costs, land area, and climate-related disaster costs. High-flow path migrants appear to respond more directly to these destination attributes. Our results challenge assumptions of uniform preferences and underscore the value of capturing heterogeneity in migration models and policymaking.

stat.AP↗

arXiv2023

Flood Event Extraction from News Media to Support Satellite-Based Flood Insurance

Floods cause large losses to property, life, and livelihoods across the world every year, hindering sustainable development. Safety nets to help absorb financial shocks in disasters, such as insurance, are often unavailable in regions of the world most vulnerable to floods, like Bangladesh. Index-based insurance has emerged as an affordable solution, which considers weather data or information from satellites to create a "flood index" that should correlate with the damage insured. However, existing flood event databases are often incomplete, and satellite sensors are not reliable under extreme weather conditions (e.g., because of clouds), which limits the spatial and temporal resolution of current approaches for index-based insurance. In this work, we explore a novel approach for supporting satellite-based flood index insurance by extracting high-resolution spatio-temporal information from news media. First, we publish a dataset consisting of 40,000 news articles covering flood events in Bangladesh by 10 prominent news sources, and inundated area estimates for each division in Bangladesh collected from a satellite radar sensor. Second, we show that keyword-based models are not adequate for this novel application, while context-based classifiers cover complex and implicit flood related patterns. Third, we show that time series extracted from news media have substantial correlation Spearman's rho$=0.70 with satellite estimates of inundated area. Our work demonstrates that news media is a promising source for improving the temporal resolution and expanding the spatial coverage of the available flood damage data.

cs.IR↗

arXiv2020

Big Data links from Climate to Commodity Production Forecasts and Risk Management

Frozen concentrated orange juice (FCOJ) is a commodity traded in the International Commodity Exchange. The FCOJ future price volatility is high because the world's orange production is concentrated in a few places, which results in extreme sensitivity to weather and disease. Most of the oranges produced in the United States are from Florida. The United States Department of Agriculture (USDA) issues orange production forecasts on the second week of each month from October to July. The October forecast in particular seems to affect FCOJ price volatility. We assess how a prediction of the directionality and magnitude of the error of the USDA October forecast could affect the decision making process of multiple FCOJ market participants, and if the "production uncertainty" of the forecast could be reduced by incorporating other climate variables. The models developed open up the opportunity to assess the application of the resulting probabilistic forecasts of the USDA production forecast error on the trading decisions of the different FCOJ stakeholders, and to perhaps consider the inclusion of climate predictors in the USDA forecast.

q-fin.GN↗

arXiv2017

Spatial-temporal wind field prediction by Artificial Neural Networks

The prediction of near surface wind speed is becoming increasingly vital for the operation of electrical energy grids as the capacity of installed wind power grows. The majority of predictive wind speed modeling has focused on point-based time-series forecasting. Effectively balancing demand and supply in the presence of distributed wind turbine electricity generation, however, requires the prediction of wind fields in space and time. Additionally, predictions of full wind fields are particularly useful for future power planning such as the optimization of electricity power supply systems. In this paper, we propose a composite artificial neural network (ANN) model to predict the 6-hour and 24-hour ahead average wind speed over a large area (~3.15*106 km2). The ANN model consists of a convolutional input layer, a Long Short-Term Memory (LSTM) hidden layer, and a transposed convolutional layer as the output layer. We compare the ANN model with two non-parametric models, a null persistence model and a mean value model, and find that the ANN model has substantially smaller error than each of these models. Additionally, the ANN model also generally performs better than integrated autoregressive moving average models, which are trained for optimal performance in specific locations.

cs.LG↗