arXiv subjects

Lucia Gordon

Publications and source records attributed to Lucia Gordon.

8 recordsLinked to original sources

arXiv2026

MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training

Recent research in geospatial machine learning demonstrates that models pretrained with self-supervised learning on Earth observation data can perform well on downstream tasks with limited labeled data. However, most benchmark datasets have few data modalities and poor global representation, limiting the ability to evaluate multimodal pretrained models at global scales. In order to fill this gap, we introduce MMEarth-Bench, a collection of five new environmental tasks with 12 modalities, globally distributed data, and both random and geographic test splits. We benchmark a diverse set of pretrained models and find that while (multimodal) pretraining tends to improve model robustness in limited data settings, geographic generalization abilities remain poor. Moreover, a simple randomly initialized multimodal model is competitive given enough labeled data. Although data is abundant, models can currently only make use of the modalities on which they were pretrained. To solve this problem, we propose using all the modalities available at test time as auxiliary tasks for test-time adaptation. Our model-agnostic method for test-time training with multimodal reconstruction (TTT-MMR) can improve performance across all models and tasks on both test splits. Furthermore, geographic batching leads to a good trade-off between regularization and specialization during TTT, which is especially beneficial for long-tail distributions. Our dataset, code, and visualization tool are linked on the project page: lgordon99.github.io/mmearth-bench.

cs.CV↗

arXiv2026

Dynamic Framework for Collaborative Learning: Leveraging Advanced LLM with Adaptive Feedback Mechanisms

This paper presents a framework for integrating LLM into collaborative learning platforms to enhance student engagement, critical thinking, and inclusivity. The framework employs advanced LLMs as dynamic moderators to facilitate real-time discussions and adapt to learners' evolving needs, ensuring diverse and inclusive educational experiences. Key innovations include robust feedback mechanisms that refine AI moderation, promote reflective learning, and balance participation among users. The system's modular architecture featuring ReactJS for the frontend, Flask for backend operations, and efficient question retrieval supports personalized and engaging interactions through dynamic adjustments to prompts and discussion flows. Testing demonstrates that the framework significantly improves student collaboration, fosters deeper comprehension, and scales effectively across various subjects and user groups. By addressing limitations in static moderation and personalization in existing systems, this work establishes a strong foundation for next-generation AI-driven educational tools, advancing equitable and impactful learning outcomes.

cs.AI↗

arXiv2024

Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas

While advances in machine learning with satellite imagery (SatML) are facilitating environmental monitoring at a global scale, developing SatML models that are accurate and useful for local regions remains critical to understanding and acting on an ever-changing planet. As increasing attention and resources are being devoted to training SatML models with global data, it is important to understand when improvements in global models will make it easier to train or fine-tune models that are accurate in specific regions. To explore this question, we contrast local and global training paradigms for SatML through a case study of tree canopy height (TCH) mapping in the Karingani Game Reserve, Mozambique. We find that recent advances in global TCH mapping do not necessarily translate to better local modeling abilities in our study region. Specifically, small models trained only with locally-collected data outperform published global TCH maps, and even outperform globally pretrained models that we fine-tune using local data. Analyzing these results further, we identify specific points of conflict and synergy between local and global modeling paradigms that can inform future research toward aligning local and global performance objectives in geospatial machine learning.

cs.LG↗

arXiv2024

Multimodal Fusion Strategies for Mapping Biophysical Landscape Features

Multimodal aerial data are used to monitor natural systems, and machine learning can significantly accelerate the classification of landscape features within such imagery to benefit ecology and conservation. It remains under-explored, however, how these multiple modalities ought to be fused in a deep learning model. As a step towards filling this gap, we study three strategies (Early fusion, Late fusion, and Mixture of Experts) for fusing thermal, RGB, and LiDAR imagery using a dataset of spatially-aligned orthomosaics in these three modalities. In particular, we aim to map three ecologically-relevant biophysical landscape features in African savanna ecosystems: rhino middens, termite mounds, and water. The three fusion strategies differ in whether the modalities are fused early or late, and if late, whether the model learns fixed weights per modality for each class or generates weights for each class adaptively, based on the input. Overall, the three methods have similar macro-averaged performance with Late fusion achieving an AUC of 0.698, but their per-class performance varies strongly, with Early fusion achieving the best recall for middens and water and Mixture of Experts achieving the best recall for mounds.

cs.CV↗

arXiv2024

Find Rhinos without Finding Rhinos: Active Learning with Multimodal Imagery of South African Rhino Habitats

Much of Earth's charismatic megafauna is endangered by human activities, particularly the rhino, which is at risk of extinction due to the poaching crisis in Africa. Monitoring rhinos' movement is crucial to their protection but has unfortunately proven difficult because rhinos are elusive. Therefore, instead of tracking rhinos, we propose the novel approach of mapping communal defecation sites, called middens, which give information about rhinos' spatial behavior valuable to anti-poaching, management, and reintroduction efforts. This paper provides the first-ever mapping of rhino midden locations by building classifiers to detect them using remotely sensed thermal, RGB, and LiDAR imagery in passive and active learning settings. As existing active learning methods perform poorly due to the extreme class imbalance in our dataset, we design MultimodAL, an active learning system employing a ranking technique and multimodality to achieve competitive performance with passive learning models with 94% fewer labels. Our methods could therefore save over 76 hours in labeling time when used on a similarly-sized dataset. Unexpectedly, our midden map reveals that rhino middens are not randomly distributed throughout the landscape; rather, they are clustered. Consequently, rangers should be targeted at areas with high midden densities to strengthen anti-poaching efforts, in line with UN Target 15.7.

cs.CV↗

arXiv2024

Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents

Stochastic multi-agent multi-armed bandits typically assume that the rewards from each arm follow a fixed distribution, regardless of which agent pulls the arm. However, in many real-world settings, rewards can depend on the sensitivity of each agent to their environment. In medical screening, disease detection rates can vary by test type; in preference matching, rewards can depend on user preferences; and in environmental sensing, observation quality can vary across sensors. Since past work does not specify how to allocate agents of heterogeneous but known sensitivity of these types in a stochastic bandit setting, we introduce a UCB-style algorithm, Min-Width, which aggregates information from diverse agents. In doing so, we address the joint challenges of (i) aggregating the rewards, which follow different distributions for each agent-arm pair, and (ii) coordinating the assignments of agents to arms. Min-Width facilitates efficient collaboration among heterogeneous agents, exploiting the known structure in the agents' reward functions to weight their rewards accordingly. We analyze the regret of Min-Width and conduct pseudo-synthetic and fully synthetic experiments to study the performance of different levels of information sharing. Our results confirm that the gains to modeling agent heterogeneity tend to be greater when the sensitivities are more varied across agents, while combining more information does not always improve performance.

cs.MA↗

arXiv2022

Lensing in the Darkness: A Bayesian Analysis of 22 Chandra Sources at $z \gtrsim 6$ Shows No Evidence of Lensing

More than $200$ quasars have been detected so far at $z > 6$, with only one showing clear signs of strong gravitational lensing. Some studies call for a missing population of lensed high-$z$ quasars, but their existence is still in doubt. A large fraction of high-$z$ quasars being lensed would have a significant effect on the shape of the intrinsic quasar luminosity function (QLF). Here, we perform the first systematic search for lensed X-ray-detected quasars at $z \gtrsim 6$ employing a Bayesian analysis, with the code BAYMAX, to look for morphological evidence of multiple images that may escape a visual inspection. We analyzed a sample of 22 quasars at $z > 5.8$ imaged by the Chandra X-ray observatory and found none with statistically significant multiple images. In the sub-sample of the 8 sources with photon counts $>20$ we exclude multiple images with separations $r>1''$ and count ratios $f>0.4$, or with separations as small as $0.''7$ and $f>0.7$ at $95\%$ confidence level. Comparing this non-detection with predictions from theoretical models suggesting a high and a low lensed fraction, we placed upper limits on the bright-end slope, $\beta$, of the QLF. Using only the sub-sample with 8 sources, we obtain, in the high-lensing model, a limit $\beta < 3.38$. Assuming no multiple source is present in the full sample of 22 sources, we obtain $\beta < 2.89$ and $\beta < 3.53$ in the high and low lensing models, respectively. These constraints strongly disfavor steep QLF shapes previously proposed in the literature.

astro-ph.GA↗

arXiv2020

Quantum gravitational onset of Starobinsky inflation in a closed universe

Recent cosmic microwave background observations favor low energy scale inflationary models in a closed universe. However, onset of inflation in such models for a closed universe is known to be severely problematic. In particular, such a universe recollapses within a few Planck seconds and encounters a big crunch singularity when initial conditions are given in the Planck regime. We show that this problem of onset of inflation in low energy scale inflationary models can be successfully overcome in a quantum gravitational framework where the big bang/big crunch singularities are resolved and a non-singular cyclic evolution exists prior to inflation. As an example we consider a model in loop quantum cosmology and demonstrate that the successful onset of low energy scale inflation in a closed universe is possible for the Starobinsky inflationary model starting from a variety of initial conditions where it is impossible in the classical theory. For comparison we also investigate the onset of inflation in the $\phi^2$ inflationary model under similar unfavorable conditions. The pre-inflationary phase with quantum gravity effects is shown to be composed of non-identical cycles of bounces and recollapses resulting in a hysteresis-like phenomenon, which plays an important role in creating suitable conditions for inflation to occur after some number of non-singular cycles. Our analysis shows that the tension in the classical theory amounting to the unsuitability of closed FLRW universes with respect to the onset of low energy scale inflation can be successfully resolved in loop quantum cosmology.

gr-qc↗