MVG-KAN: Multi-View Geo-Wind Guided KAN for PM$_{2.5}$ Forecasting

Computer Science > Artificial Intelligence [Submitted on 23 Jun 2026] MVG-KAN: Multi-View Geo-Wind Guided KAN for PM_{2.5} Forecasting Cheng Huang, Muyao Guan, Jairus Yougui Railey, Ning Xu, Honghui Xu, Changjiang Zhang, Zhen Zhang, Shiqing Zhang, Cong Bai Accurate short-term PM_{2.5} forecasting is important for public health protection, air-quality early warning, and urban environmental management. However, PM_{2.5} variation is driven by multiple coupled factors, including stable periodic changes induced by human activities and meteorological regularity, station-specific short-term concentration evolution, and meteorology-driven pollutant dispersion among monitoring stations. Existing spatio-temporal forecasting methods may capture station relationships to some extent, but distance-only, correlation-based, or purely adaptive graphs are often insufficient to comprehensively represent these heterogeneous factors, especially wind-direction-dependent pollutant transport. To address this problem, we propose a Multi-View Geo-Wind Guided KAN model for PM_{2.5} forecasting, named \textbf{MVG-KAN}, which models station-level PM_{2.5} evolution from three complementary views: local periodic regularity, station-wise residual temporal dynamics, and meteorological-environment-guided spatial dispersion. Specifically, the periodic-residual forecasting backbone first separates stable daily and weekly patterns from non-periodic residual variations. A Geo-Wind Graph is constructed by combining geographic distance decay with wind-direction- and wind-speed-aware transport, providing a lightweight physically motivated directed spatial prior for residual propagation among stations. In addition, a temporal Kolmogorov-Arnold network (TKAN) residual head is then introduced to learn station-wise nonlinear autoregressive correction from de-periodized PM_{2.5} residuals and historical multi-pollutant sequences, thereby enhancing the modeling of local residual inertia and pollutant co-variation. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.24347 [cs.AI]   (or arXiv:2606.24347v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.24347 Focus to learn more Submission history From: Cheng Huang [view email] [v1] Tue, 23 Jun 2026 09:38:14 UTC (4,949 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)