Geochemical divergence of oxygen and sulfur compounds in high-maturity bitumen: Implications for thermal maturity assessment

Chi Zhang

doi:10.1016/j.apgeochem.2026.106965

Addressing Long-Tailed Spatial and Category Imbalances in Citywide Incident Prediction

2026-04-01

0

PRE

AI

B

Bhumika

D

Debasis Das

DOI：10.1109/tbdata.2026.3679574

Original

Original request for help

Save

Abstract

En 中文

Citywide incidents such as crimes, accidents, and public safety threats contribute to substantial societal disruption and economic loss. Accurate prediction of such incidents can significantly aid city administrators in proactive response planning. Existing approaches model the incident prediction as a spatio-temporaltask, but often neglect the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">inter-region spatial long-tailed distribution of incidents. This uneven distribution introduces spatial bias in learning which causes models to overfit regions with frequent incidents (head regions) while underfit the regions with occasional incidents (tail regions). Furthermore, model learning is hindered by <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">intra-region category imbalance, where certain incident types (e.g., theft) dominate over rarer categories (e.g., robbery) within the same region. To address inter and intra region challenges, we propose an approach named <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SLIP (<underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Spatial <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Long-tail <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Incident <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Prediction). Specifically, for inter-region skewness, SLIP adopts a multi-expert design comprising a common feature extraction backbone followed by three expert branches. In addition, to mitigate the intra-region category imbalance, we utilizes a variant of focal loss, particularly for positive-negative imbalance. SLIP outperforms spatio-temporal state-of-the-art methods by 2–11% in Macro F1, 4–11% in Micro F1, and 1–11% in Severity Weighted F1 across Los Angeles and Chicago cities for the urban crime dataset. Additionally, we incorporate fairness metrics into the evaluation and present a comprehensive comparison of spatio-temporal incident prediction.

Keywords:

Incident prediction

long-tail learning

spatio-temporal analysis

Addressing Long-Tailed Spatial and Category Imbalances in Citywide Incident Prediction

Abstract

Journal

Organization

Cited Papers

Citing Papers