Decoding PM2.5 Prediction in Nanning Urban Area, China: Unraveling Model Superiorities and Drawbacks Through SARIMA, Prophet, and LightGBM

Algorithms, Journal Year: 2025, Volume and Issue: 18(3), P. 167 - 167

Published: March 14, 2025

With the rapid development of industrialization and urbanization, air pollution is becoming increasingly serious. Accurate prediction PM2.5 concentration great significance to environmental protection public health. Our study takes Nanning urban area, which has unique geographical, climatic source characteristics, as object. Based on dual-time resolution raster data China High-resolution High-quality Dataset (CHAP) from 2012 2023, carried out using SARIMA, Prophet LightGBM models. The systematically compares performance each model spatial temporal dimensions indicators such mean square error (MSE), absolute (MAE) coefficient determination (R2). results show that a strong ability mine complex nonlinear relationships, but its stability poor. obvious advantages in dealing with seasonality trend time series, it lacks adaptability changes. SARIMA based series theory performs well some scenarios, limitations non-stationary heterogeneity. research provides multi-dimensional reference for subsequent predictions, helps researchers select models reasonably according different scenarios needs, new ideas analyzing change patterns, promotes related field science.

Language: Английский

---

Algorithms Facilitating the Observation of Urban Residential Vacancy Rates: Technologies, Challenges and Breakthroughs

Algorithms, Journal Year: 2025, Volume and Issue: 18(3), P. 174 - 174

Published: March 20, 2025

In view of the challenges brought by a complex environment, diverse data sources and urban development needs, our study comprehensively reviews application algorithms in residential vacancy rate observation. First, we explore definition measurement rate, pointing out difficulties accurately defining vacant houses obtaining reliable data. Then, introduce various such as traditional statistical learning, machine deep learning ensemble analyze their applications The algorithm builds prediction model based on historical mining analysis, which has certain advantages dealing with linear problems regular However, facing high nonlinear relationships complexity observation, its accuracy is difficult to meet actual needs. With powerful modeling ability, have significant capturing they require quality are prone overfitting phenomenon. Deep can automatically learn feature representation, perform well processing large amounts high-dimensional data, effectively deal sources, but training process computational cost high. combines multiple models improve stability. By comparing these algorithms, clarify adaptability different scenarios. Facing observation affected many factors. unbalanced leads differences rates areas. Spatiotemporal heterogeneity means that vary geographical locations over time. factors jointly macroeconomic factors, policy regulatory market supply demand individual resident These intertwined, increasing difficulty analysis. diversity discuss multi-source fusion technology, aims integrate including geographic information system (GIS) (Geographic Information System) remote sensing images, statistics social media grid management requires integration format, scale, precision spatiotemporal resolution through preprocessing, standardization normalization. should not only ability intelligent extraction related also uncertainty redundancy adapt dynamic needs development. We elaborate optimization methods for sources. Through this study, find play vital role improving enhancing understanding housing conditions. Algorithms handle spatial economic behind rates. future, will continue deepen processing, building decision support, strive provide smarter more accurate solutions sustainable

Language: Английский

---

Analysis of the Coupling Coordination between Land Resource Development Intensity and Sustainable Development Level in China: Implications for Policy and Strategic Management

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2025, Volume and Issue: unknown, P. 103954 - 103954

Published: April 1, 2025

Language: Английский

---

Integrating System Perspectives to Optimize Ecosystem Service Provision in Urban Ecological Development

Systems, Journal Year: 2024, Volume and Issue: 12(9), P. 375 - 375

Published: Sept. 17, 2024

System-based approaches are critical for addressing the complex and interconnected nature of urban ecological development restoration ecosystem services. This study adopts a system perspective to investigate spatiotemporal drivers key services, including carbon sequestration, water conservation, sediment reduction, pollution mitigation, stormwater regulation, within Yangtze River Delta Eco-Green Integrated Development Demonstration Area (YRDDA) from 2000 2020. We propose novel framework defining enhanced-efficiency service management regions (EESMR) guide targeted restoration. Our analysis revealed interplay 11, 9, 6, 10 driving factors selected highlighting heterogeneity these drivers. By overlaying factors, we identified high-efficiency priority areas EESMR that ensure high returns on investment efficient functions. system-oriented approach provided spatial guidance integrated restoration, green development, eco-planning. These findings offer valuable insights policymakers planners in other rapidly urbanizing regions, supporting formulation effective land-use policies balance environmental sustainability growth.

Language: Английский

---