arXiv subjects

Silja Sormunen

Publications and source records attributed to Silja Sormunen.

4 recordsLinked to original sources

arXiv2026

TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis

Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction. Compositing addresses these issues but loses information with respect to vegetation phenology, which is critical for many downstream tasks. Instead, we present TESSERA, a pixel-wise foundation model for multi-modal (Sentinel-1/2) EO time series that learns robust, label-efficient embeddings. During model training, TESSERA uses Barlow Twins and sparse random temporal sampling to enforce invariance to the selection of valid observations. We employ two key regularizers: global shuffling to decorrelate spatial neighborhoods and mix-based regulation to improve invariance under extreme sparsity. We find that for diverse classification, segmentation, and regression tasks, TESSERA embeddings deliver state-of-the-art accuracy with high label efficiency, often requiring only a small task head and minimal computation. To democratize access, adhere to FAIR - principles, and simplify use, we release global, annual, 10m, pixel-wise int8 embeddings together with open weights/code and lightweight adaptation heads, thus providing practical tooling for large-scale retrieval and inference at planetary scale. All code and data are available at: https://github.com/ucam-eo/tessera.

cs.LG↗

arXiv2025

Self-organization to multicriticality

Self-organized criticality is a well-established phenomenon, where a system dynamically tunes its structure to operate on the verge of a phase transition. Here, we show that the dynamics inside the self-organized critical state are fundamentally far more versatile than previously recognized, to the extent that a system can self-organize to a new type of phase transition while staying on the verge of another. In this first demonstration of self-organization to multicriticality, we investigate a model of coupled oscillators on a random network, where the network topology evolves in response to the oscillator dynamics. We show that the system first self-organizes to the onset of oscillations, after which it drifts to the onset of pattern formation while still remaining at the onset of oscillations, thus becoming critical in two different ways at once. The observed evolution to multicriticality is robust generic behavior that we expect to be widespread in self-organizing systems. Overall, these results offer a unifying framework for studying systems, such as the brain, where multiple phase transitions may be relevant for proper functioning.

nlin.AO↗

arXiv2024

Distinguishing subsampled power laws from other heavy-tailed distributions

Distinguishing power-law distributions from other heavy-tailed distributions is challenging, and this task is often further complicated by subsampling effects. In this work, we evaluate the performance of two commonly used methods for detecting power-law distributions - the maximum likelihood method of Clauset et al. and the extreme value method of Voitalov et al. - in distinguishing subsampled power laws from two other heavy-tailed distributions, the lognormal and the stretched exponential distributions. We focus on a random subsampling method commonly applied in network science and biological sciences. In this subsampling scheme, we are ultimately interested in the frequency distribution of elements with a certain number of constituent parts, and each part is selected to the subsample with an equal probability. We investigate how well the results obtained from subsamples generalize to the original distribution. Our results show that the power-law exponent of the original distribution can be estimated fairly accurately from subsamples, but classifying the distribution correctly is more challenging. The maximum likelihood method falsely rejects the power-law hypothesis for a large fraction of subsamples from power-law distributions. While the extreme value method correctly recognizes subsampled power-law distributions with all tested subsampling depths, its capacity to distinguish power laws from the heavy-tailed alternatives is limited. However, these false positives tend to result not from the subsampling itself but from the estimators' inability to classify the original sample correctly. In fact, we show that the extreme value method can sometimes be expected to perform better on subsamples than on the original samples from the lognormal and the stretched exponential distributions, while the contrary is true for the main tests included in the maximum likelihood method.

physics.data-an↗

arXiv2023

Critical drift in a neuro-inspired adaptive network

It has been postulated that the brain operates in a self-organized critical state that brings multiple benefits, such as optimal sensitivity to input. Thus far, self-organized criticality has typically been depicted as a one-dimensional process, where one parameter is tuned to a critical value. However, the number of adjustable parameters in the brain is vast, and hence critical states can be expected to occupy a high-dimensional manifold inside a high-dimensional parameter space. Here, we show that adaptation rules inspired by homeostatic plasticity drive a neuro-inspired network to drift on a critical manifold, where the system is poised between inactivity and persistent activity. During the drift, global network parameters continue to change while the system remains at criticality.

nlin.AO↗