arXiv subjects

Srija Chakraborty

Publications and source records attributed to Srija Chakraborty.

10 recordsLinked to original sources

arXiv2026

GAIA: A Foundation Model for Operational Atmospheric Dynamics

We introduce GAIA (Geospatial Artificial Intelligence for Atmospheres), a hybrid self-supervised geospatial foundation model that fuses Masked Autoencoders (MAE) with self-distillation with no labels (DINO) to generate semantically rich representations from global geostationary satellite imagery. Pre-trained on 15 years of globally-merged infrared observations (2001-2015), GAIA learns disentangled representations that capture atmospheric dynamics rather than trivial diurnal patterns, as evidenced by distributed principal component structure and temporal coherence analysis. We demonstrate robust reconstruction capabilities across varying data availability (30-95% masking), achieving superior gap-filling performance on real missing data patterns. When transferred to downstream tasks, GAIA consistently outperforms an MAE-only baseline: improving atmospheric river segmentation (F1: 0.58 vs 0.52), enhancing tropical cyclone detection (storm-level recall: 81% vs 75%, early detection: 29% vs 17%), and maintaining competitive precipitation estimation performance. Analysis reveals that GAIA's hybrid objectives encourage learning of spatially coherent, object-centric features distributed across multiple principal components rather than concentrated representations focused on reconstruction. This work demonstrates that combining complementary self-supervised objectives yields more transferable representations for diverse atmospheric modeling tasks. Model weights and code are available at: https://huggingface.co/bcg-usra-nasa-gaia/GAIA-v1.

cs.LG↗

arXiv2026

Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications

This paper presents Prithvi-EO-2.0, a new geospatial foundation model that offers significant improvements over its predecessor, Prithvi-EO-1.0. Trained on 4.2 million global time series samples from NASA's Harmonized Landsat and Sentinel-2 data archive at 30-m resolution, the new model incorporates temporal and location embeddings for enhanced performance across various geospatial tasks. Through extensive benchmarking with GEO-Bench, the model outperforms the previous Prithvi-EO model by 8% across a range of tasks. It also outperforms six other geospatial foundation models when benchmarked on remote sensing tasks from different domains and resolutions (i.e. from 0.1 m to 15 m). The results demonstrate the versatility of the model in both classical Earth observation and high-resolution applications. Early involvement of end-users and subject matter experts (SMEs) allowed constant feedback on model and dataset design, enabling customization across diverse SME-led applications in disaster response, land cover and crop mapping, and ecosystem dynamics monitoring. Prithvi-EO-2.0 is available as an open-source model on Hugging Face and IBM TerraTorch, with additional resources on GitHub. The project exemplifies the Trusted Open Science approach embraced by all involved organizations.

cs.CV↗

arXiv2025

Data-Centric Safety and Ethical Measures for Data and AI Governance

Datasets play a key role in imparting advanced capabilities to artificial intelligence (AI) foundation models that can be adapted to various downstream tasks. These downstream applications can introduce both beneficial and harmful capabilities -- resulting in dual use AI foundation models, with various technical and regulatory approaches to monitor and manage these risks. However, despite the crucial role of datasets, responsible dataset design and ensuring data-centric safety and ethical practices have received less attention. In this study, we pro-pose responsible dataset design framework that encompasses various stages in the AI and dataset lifecycle to enhance safety measures and reduce the risk of AI misuse due to low quality, unsafe and unethical data content. This framework is domain agnostic, suitable for adoption for various applications and can promote responsible practices in dataset creation, use, and sharing to facilitate red teaming, minimize risks, and increase trust in AI models.

cs.CY↗

arXiv2025

Multi-wavelength properties of $z\gtrsim 6$ LISA detectable events

We investigate the intrinsic and observational properties of $z\gtrsim 6$ galaxies hosting coalescing massive black holes (MBHs) that gives rise to gravitational waves (GWs) detectable with the Laser Interferometer Space Antenna (LISA). We adopt a zoom-in cosmological hydrodynamical simulation of galaxy formation and black hole (BH) co-evolution, zoomed-in on a $M_h \sim 10^{12}~\rm M_{\odot}$ dark matter halo at z = 6, which hosts a fast accreting super-massive black hole (SMBH) and a star-forming galaxy. Following the SMBH formation backward in time, we identify the merging events that concurred to its formation and we pick up the ones that are detectable with LISA. Among these LISA detectable events (LDEs), we select those that, based on their intrinsic properties are expected to be bright in one or more electromagnetic (EM) bands. We post-process these events with dust radiative transfer calculations to make predictions about their spectral energy distributions and continuum maps in the JWST to ALMA wavelength range. We compare the spectra arising from galaxies hosting the merging MBHs with those arising from AGN powered by single accreting BHs. We find that it will be impossible to identify an LDE from the continuum SEDs because of the absence of specific imprints from the merging MBHs. We also compute the profile of the H$_{\rm α}$ line arising from LDEs, considering the contribution from their star-forming regions and the accreting MBHs. We find that the presence of two accreting MBHs would be difficult to infer even if both MBHs accrete at super-Eddington rates. We conclude that the combined detection of GW and EM signals from $z\gtrsim 6$ MBHs is challenging not only because of the poor sky-localization provided by LISA, but also because the loudest GW emitters are not massive enough to leave significant signatures in the emission lines arising from the broad line region.

astro-ph.GA↗

arXiv2024

Towards A Comprehensive Assessment of AI's Environmental Impact

Artificial Intelligence, machine learning (AI/ML) has allowed exploring solutions for a variety of environmental and climate questions ranging from natural disasters, greenhouse gas emission, monitoring biodiversity, agriculture, to weather and climate modeling, enabling progress towards climate change mitigation. However, the intersection of AI/ML and environment is not always positive. The recent surge of interest in ML, made possible by processing very large volumes of data, fueled by access to massive compute power, has sparked a trend towards large-scale adoption of AI/ML. This interest places tremendous pressure on natural resources, that are often overlooked and under-reported. There is a need for a framework that monitors the environmental impact and degradation from AI/ML throughout its lifecycle for informing policymakers, stakeholders to adequately implement standards and policies and track the policy outcome over time. For these policies to be effective, AI's environmental impact needs to be monitored in a spatially-disaggregated, timely manner across the globe at the key activity sites. This study proposes a methodology to track environmental variables relating to the multifaceted impact of AI around datacenters using openly available energy data and globally acquired satellite observations. We present a case study around Northern Virginia, United States that hosts a growing number of datacenters and observe changes in multiple satellite-based environmental metrics. We then discuss the steps to expand this methodology for comprehensive assessment of AI's environmental impact across the planet. We also identify data gaps and formulate recommendations for improving the understanding and monitoring AI-induced changes to the environment and climate.

cs.CY↗

arXiv2024

Global urban activity changes from COVID-19 physical distancing restrictions

During the COVID-19 pandemic changes in human activity became widespread through official policies and organically in response to the virus's transmission, which in turn, impacted the environment and the economy. The pandemic has been described as a natural experiment that tested how social and economic disruptions impacted different components of the global Earth System. To move this beyond hypotheses, locally-resolved, globally-available measures of how, where, and when human activity changed are critically needed. Here we use satellite-derived nighttime lights to quantify and map daily changes in human activity that are atypical for each urban area globally for two years after the onset of the pandemic using machine learning anomaly detectors. Metrics characterizing changes in lights from pre-COVID baseline in human settlements and quality assurance measures are reported. This dataset, TRacking Anomalous COVID-19 induced changEs in NTL (TRACE-NTL), is the first to resolve COVID-19 disruptions for all metropolitan regions globally, daily. It is suitable to support a variety of post-pandemic studies that assess how changes in human activity impact environmental systems.

physics.soc-ph↗

arXiv2024

Is GN-z11 powered by a super-Eddington massive black hole?

Observations of $z \sim 6$ quasars powered by supermassive black holes (SMBHs; $M_{\rm BH} \sim 10^{8-10}\, M_\odot$) challenge our current understanding of early black hole (BH) formation and evolution. The advent of the James Webb Space Telescope (JWST) has enabled the study of massive BHs (MBHs; $M_{\rm BH}\sim 10^{6-7} \ \mathrm{M}_\odot$) up to $z\sim 11$, thus bridging the properties of $z\sim 6$ quasars to their ancestors. The JWST spectroscopic observations of GN-z11, a well-known $z=10.6$ star-forming galaxy, have been interpreted with the presence of a super-Eddington (Eddington ratio $\equiv \,λ_{\rm Edd}\sim 5.5$) accreting MBH. To test this hypothesis, we used a zoom-in cosmological simulation of galaxy formation and BH co-evolution. We first tested the simulation results against the observed probability distribution function (PDF) of $λ_{\rm Edd}$ found in $z\sim 6$ quasars. Then, in the simulation we selected the BHs that satisfy the following criteria: (a) $10 < z < 11 $, (b) $M_{\rm BH} > 10^6 \ \mathrm{M}_\odot$. Next, we apply the extreme value statistics to the PDF of $λ_{\rm Edd}$ resulting from the simulation and we find that the probability of observing a $z\sim 10-11$ MBH accreting with $λ_{\rm Edd} \sim 5.5$ in the volume surveyed by JWST is very low ($<0.2\%$). We compared our predictions with those in the literature, and discuss the main limitations of our work. Our simulation cannot explain the JWST observations of GN-z11. This might be due to (i) poor resolution and statistics in simulations, (ii) simplistic sub-grid models (e.g. BH accretion and seeding), (iii) uncertainties in the data analysis and interpretation.

astro-ph.GA↗

arXiv2023

Adaptive Modeling of Satellite-Derived Nighttime Lights Time-Series for Tracking Urban Change Processes Using Machine Learning

Remotely sensed nighttime lights (NTL) uniquely capture urban change processes that are important to human and ecological well-being, such as urbanization, socio-political conflicts and displacement, impacts from disasters, holidays, and changes in daily human patterns of movement. Though several NTL products are global in extent, intrinsic city-specific factors that affect lighting, such as development levels, and social, economic, and cultural characteristics, are unique to each city, making the urban processes embedded in NTL signatures difficult to characterize, and limiting the scalability of urban change analyses. In this study, we propose a data-driven approach to detect urban changes from daily satellite-derived NTL data records that is adaptive across cities and effective at learning city-specific temporal patterns. The proposed method learns to forecast NTL signatures from past data records using neural networks and allows the use of large volumes of unlabeled data, eliminating annotation effort. Urban changes are detected based on deviations of observed NTL from model forecasts using an anomaly detection approach. Comparing model forecasts with observed NTL also allows identifying the direction of change (positive or negative) and monitoring change severity for tracking recovery. In operationalizing the model, we consider ten urban areas from diverse geographic regions with dynamic NTL time-series and demonstrate the generalizability of the approach for detecting the change processes with different drivers and rates occurring within these urban areas based on NTL deviation. This scalable approach for monitoring changes from daily remote sensing observations efficiently utilizes large data volumes to support continuous monitoring and decision making.

cs.LG↗

arXiv2023

Probing $z \gtrsim 6$ massive black holes with gravitational waves

We investigate the coalescence of massive black hole ($M_{\rm BH}\gtrsim 10^{6}~\rm M_{\odot}$) binaries (MBHBs) at $6 3 σ$) overdense regions ($M_h\sim 10^{12}~\rm M_{\odot}$ dark matter halos at $z = 6$) of the Universe. We first analyse the impact of different resolutions and AGN feedback prescriptions on the merger rate, assuming instantaneous mergers. Then, we compute the halo bias correction factor due to the overdense simulated region. Our simulations predict merger rates that range between 3 - 15 $\rm yr^{-1}$ at $z\sim 6$, depending on the run considered, and after correcting for a bias factor of $\sim 20-30$. For our fiducial model, we further consider the effect of delay in the MBHB coalescence due to dynamical friction. We find that 83 per cent of MBHBs will merge within the Hubble time, and 21 per cent within 1 Gyr, namely the age of the Universe at $z > 6$. We finally compute the expected properties of the gravitational wave (GW) signals and find the fraction of LISA detectable events with high signal-to-noise ratio (SNR $>$ 5) to range between 66-69 per cent. However, identifying the electro-magnetic counterpart of these events remains challenging due to the poor LISA sky localization that, for the loudest signals ($\mathcal M_c\sim 10^6~\rm M_{\odot}$ at $z=6$), is around 10 $\rm deg^2$.

astro-ph.GA↗

arXiv2021

Application of Machine Learning in understanding plant virus pathogenesis: Trends and perspectives on emergence, diagnosis, host-virus interplay and management

Inclusion of high throughput technologies in the field of biology has generated massive amounts of biological data in the recent years. Now, transforming these huge volumes of data into knowledge is the primary challenge in computational biology. The traditional methods of data analysis have failed to carry out the task. Hence, researchers are turning to machine learning based approaches for the analysis of high-dimensional big data. In machine learning, once a model is trained with a training dataset, it can be applied on a testing dataset which is independent. In current times, deep learning algorithms further promote the application of machine learning in several field of biology including plant virology. Considering a significant progress in the application of machine learning in understanding plant virology, this review highlights an introductory note on machine learning and comprehensively discusses the trends and prospects of machine learning in diagnosis of viral diseases, understanding host-virus interplay and emergence of plant viruses.

cs.LG↗