BiDepth: A Bidirectional-Depth Neural Network for Spatio-Temporal Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ehsani, Sina, Pan, Fenglian, Hu, Qingpei, Liu, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912480262881280
author Ehsani, Sina
Pan, Fenglian
Hu, Qingpei
Liu, Jian
author_facet Ehsani, Sina
Pan, Fenglian
Hu, Qingpei
Liu, Jian
contents Accurate spatial-temporal (ST) prediction for dynamic systems, such as urban mobility and weather patterns, is crucial but hindered by complex ST correlations and the challenge of concurrently modeling long-term trends with short-term fluctuations. Existing methods often falter in these areas. This paper proposes the BiDepth Multimodal Neural Network (BDMNN), which integrates two key innovations: 1) a bidirectional depth modulation mechanism that dynamically adjusts network depth to comprehensively capture both long-term seasonality and immediate short-term events; and 2) a novel convolutional self-attention cell (CSAC). Critically, unlike many attention mechanisms that can lose spatial acuity, our CSAC is specifically designed to preserve crucial spatial relationships throughout the network, akin to standard convolutional layers, while simultaneously capturing temporal dependencies. Evaluated on real-world urban traffic and precipitation datasets, BDMNN demonstrates significant accuracy improvements, achieving a 12% Mean Squared Error (MSE) reduction in urban traffic prediction and a 15% improvement in precipitation forecasting over leading deep learning benchmarks like ConvLSTM, using comparable computational resources. These advancements offer robust ST forecasting for smart city management, disaster prevention, and resource optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BiDepth: A Bidirectional-Depth Neural Network for Spatio-Temporal Prediction
Ehsani, Sina
Pan, Fenglian
Hu, Qingpei
Liu, Jian
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Applications
Accurate spatial-temporal (ST) prediction for dynamic systems, such as urban mobility and weather patterns, is crucial but hindered by complex ST correlations and the challenge of concurrently modeling long-term trends with short-term fluctuations. Existing methods often falter in these areas. This paper proposes the BiDepth Multimodal Neural Network (BDMNN), which integrates two key innovations: 1) a bidirectional depth modulation mechanism that dynamically adjusts network depth to comprehensively capture both long-term seasonality and immediate short-term events; and 2) a novel convolutional self-attention cell (CSAC). Critically, unlike many attention mechanisms that can lose spatial acuity, our CSAC is specifically designed to preserve crucial spatial relationships throughout the network, akin to standard convolutional layers, while simultaneously capturing temporal dependencies. Evaluated on real-world urban traffic and precipitation datasets, BDMNN demonstrates significant accuracy improvements, achieving a 12% Mean Squared Error (MSE) reduction in urban traffic prediction and a 15% improvement in precipitation forecasting over leading deep learning benchmarks like ConvLSTM, using comparable computational resources. These advancements offer robust ST forecasting for smart city management, disaster prevention, and resource optimization.
title BiDepth: A Bidirectional-Depth Neural Network for Spatio-Temporal Prediction
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Applications
url https://arxiv.org/abs/2501.08411