Saved in:
Bibliographic Details
Main Authors: Prabu, Ashwin, Tran, Nhat Thanh, Zhou, Guofa, Xin, Jack
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.03566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914073006833664
author Prabu, Ashwin
Tran, Nhat Thanh
Zhou, Guofa
Xin, Jack
author_facet Prabu, Ashwin
Tran, Nhat Thanh
Zhou, Guofa
Xin, Jack
contents A variety of models have been developed to forecast dengue cases to date. However, it remains a challenge to predict major dengue outbreaks that need timely public warnings the most. In this paper, we introduce CrossLag, an environmentally informed attention that allows for the incorporation of lagging endogenous signals behind the significant events in the exogenous data into the architecture of the transformer at low parameter counts. Outbreaks typically lag behind major changes in climate and oceanic anomalies. We use TimeXer, a recent general-purpose transformer distinguishing exogenous-endogenous inputs, as the baseline for this study. Our proposed model outperforms TimeXer by a considerable margin in detecting and predicting major outbreaks in Singapore dengue data over a 24-week prediction window.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03566
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CrossLag: Predicting Major Dengue Outbreaks with a Domain Knowledge Informed Transformer
Prabu, Ashwin
Tran, Nhat Thanh
Zhou, Guofa
Xin, Jack
Machine Learning
Computers and Society
A variety of models have been developed to forecast dengue cases to date. However, it remains a challenge to predict major dengue outbreaks that need timely public warnings the most. In this paper, we introduce CrossLag, an environmentally informed attention that allows for the incorporation of lagging endogenous signals behind the significant events in the exogenous data into the architecture of the transformer at low parameter counts. Outbreaks typically lag behind major changes in climate and oceanic anomalies. We use TimeXer, a recent general-purpose transformer distinguishing exogenous-endogenous inputs, as the baseline for this study. Our proposed model outperforms TimeXer by a considerable margin in detecting and predicting major outbreaks in Singapore dengue data over a 24-week prediction window.
title CrossLag: Predicting Major Dengue Outbreaks with a Domain Knowledge Informed Transformer
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2510.03566