The paper introduces SPALT, a method that models spatio‑temporal locality for multi‑step forecasting of geo‑referenced time series. SPALT uses linear model trees to group series with similar trends, injecting spatial features locally, and employs a Reduced Error Pruning strategy that respects spatio‑temporal locality. Experiments on three real‑world renewable‑energy datasets show SPALT outperforms both tree‑based models and state‑of‑the‑art neural networks in forecasting energy production at multiple horizons.
By Annunziata D'Aversa, Gianvito Pio, Michelangelo Ceci
arXiv:2608.20980v1 Announce Type: new
Abstract: Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the...
By Kenneth Martin, Simon Heilig, Asja Fischer, Michel F. C. Haddad, Adam M. Sykulski, Moshe Eliasof
arXiv:2606. 13119v2 Announce Type: replace-cross Abstract: Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy.
By Lilan Peng, Yandi Liu, Qingren Yao, Chongshou Li, Tianrui Li
arXiv:2606. 13119v1 Announce Type: cross Abstract: Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy.
By Lilan Peng, Yandi Liu, Qingren Yao, Chongshou Li, Tianrui Li
MoRA is a human‑centric geospatial representation learning framework that uses a large mobility graph as its backbone to fuse spatial tokenization, graph neural networks, and asymmetric contrastive learning. It aligns over 100 million points of interest, massive remote sensing imagery, and structured demographic data with a billion‑edge mobility graph, producing compact 128‑dimensional embeddings that capture socio‑economic context and functional roles of locations. On a benchmark of nine downstream social and economic prediction tasks, MoRA outperforms state‑of‑the‑art models by an average of 12.9% and demonstrates scaling behavior analogous to large language models.
By Ya Wen, Jixuan Cai, Qiyao Ma, Linyan Li, Xinhua Chen, Chris Webster, Yulun Zhou
The paper introduces ICI-Time, a framework that casts time series forecasting as a visual inpainting problem. By converting series into area‑chart images, it enables pre‑trained vision transformers to perform forecasting through in‑context learning without fine‑tuning or new temporal architectures. Experiments on epidemiology, meteorology, and power systems show competitive performance and strong adaptability in low‑data scenarios.
By Thang Nguyen, Dung Nguyen, Romero Morais, Truyen Tran
We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task, leveraging the generalisation power of large vision models (LVMs). Unlike methods that require...
arXiv:2507. 02921v4 Announce Type: replace-cross Abstract: Learning effective representations of urban environments requires capturing spatial structure beyond fixed administrative boundaries.
By Mohammad Hashemi, Hossein Amiri, Andreas Zufle
The paper presents an empirical benchmark of nine deep learning models for smart meter energy forecasting, evaluating them on two public datasets. It examines how historical input length, prediction horizon, and model architecture affect accuracy, finding that longer historical context improves performance up to a saturation point while accuracy declines with longer horizons. The study also compares computational cost, showing lightweight models achieve similar accuracy to heavier ones, and notes that model choice matters less across most population segments.
GTPred is a new benchmark for geo‑temporal prediction that evaluates multi‑modal large language models (MLLMs) on 370 images taken across 120 years worldwide. It assesses predictions by matching both the year and a hierarchical location sequence, and includes annotated reasoning chains to test intermediate reasoning. Experiments on 15 MLLMs show that while visual perception is strong, models still lack world knowledge and geo‑temporal reasoning, and that adding temporal data improves location inference.
By Jinnao Li, Tingzhu Chen, Changbo Wang
The paper presents an empirical benchmark of nine modern deep‑learning models for time‑series forecasting of smart‑meter energy consumption, evaluated on two publicly available datasets. It examines how historical input length, prediction horizon, and model architecture affect accuracy, finding that longer historical context improves performance up to a saturation point and that accuracy declines with longer horizons. The study also compares computational complexity, showing that lightweight architectures achieve similar performance to heavier models, and notes that model choice has limited impact across most demographic and household subgroups.
By Behnaz Kavoosighafi, Maria Eidenskog, Wiktoria Glad, Katerina Vrotsou
arXiv:2609.05721v1 Announce Type: new
Abstract: Understanding whether language-model embeddings encode structured real-world information is important for both representation analysis and information...
By Esteban Feuerstein, Victoria Klimkowski, Juan Manuel Ortiz de Zarate, Federico Hern\'an Suaiter