Exploring the urban spatial pattern and expansion characteristics of African countries under shared socioeconomic pathways (SSPs) is crucial to optimizing urban development in Africa and ensuring ecological sustainability. We use land and socioeconomic panel data and the least squares dummy variable regression method to predict the urban land increment in African countries from 2030 to 2060, we use the FLUS model to simulate the urban spatial layout in 2060, and we analyze from the perspective of the relationship between population density and urban expansion. The results show that the urban space of African countries will show a significant expansion trend from 2020 to 2060, with stronger growth under the SSP1 and SSP5 scenarios and relatively weaker growth under the SSP3 scenario; the urban land expansion patterns of different countries under different SSP scenarios are significantly different, and countries with rapid urbanization and economic growth are mostly urban patch agglomeration and extended expansion, while urban patches are relatively evenly distributed; a large number of cities in Africa show specific expansion patterns, with large cities mostly showing loose expansion and small- and medium-sized cities mostly showing compact expansion; and cities in different regions such as North Africa and sub-Saharan Africa have their own expansion characteristics in terms of population density and urban form. Our research provides important data support and inspiration for promoting the rational development of African cities and enhancing regional ecological resilience.

China’s Yellow (Bohai) Sea bird habitat is an important ecological region. Its unique ecology and challenges provide rich resources for research and study. Our course design concept is supported by AI technology, and improves students’ abilities through innovative functions such as dynamic data support, personalized learning paths, immersive research and study experience, and diversified evaluation mechanisms. The course content revolves around the “human–land coordination concept”, including pre-trip thinking, research and study during the trip, and post-trip exhibition learning, covering regional cognition, remote sensing image analysis, field investigation, and protection plan display activities. ERNIE Bot participates in optimizing the learning path throughout the process. The course evaluation system starts from the three dimensions of “land to people”, “people to land”, and the “coordination of the human–land relationship”, adopts processes and final evaluation, and uses ERNIE Bot to achieve real-time monitoring, data analysis, personalized reports, and dynamic feedback, improving the objectivity and efficiency of evaluation, and helping students and teachers optimize learning and teaching. However, AI has limitations in geographical research and study, such as insufficient technical adaptability, the influence of students’ abilities and habits, and the adaptation of teachers’ role changes. To this end, optimization strategies such as improving data quality and technical platforms, strengthening student technical training, enhancing teachers’ AI application capabilities, and enriching AI functions and teaching scenarios are proposed to enhance the application effect of AI in geographical research and promote innovation in educational models and student capacity building.

With the rapid development of industrialization and urbanization, air pollution is becoming increasingly serious. Accurate prediction of PM_2.5 concentration is of great significance to environmental protection and public health. Our study takes Nanning urban area, which has unique geographical, climatic and pollution source characteristics, as the object. Based on the dual-time resolution raster data of the China High-resolution and High-quality PM_2.5 Dataset (CHAP) from 2012 to 2023, the PM_2.5 concentration prediction study is carried out using SARIMA, Prophet and LightGBM models. The study systematically compares the performance of each model from the spatial and temporal dimensions using indicators such as mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R²). The results show that the LightGBM model has a strong ability to mine complex nonlinear relationships, but its stability is poor. The Prophet model has obvious advantages in dealing with seasonality and trend of time series, but it lacks adaptability to complex changes. The SARIMA model is based on time series prediction theory and performs well in some scenarios, but has limitations in dealing with non-stationary data and spatial heterogeneity. Our research provides a multi-dimensional model performance reference for subsequent PM_2.5 concentration predictions, helps researchers select models reasonably according to different scenarios and needs, provides new ideas for analyzing concentration change patterns, and promotes the development of related research in the field of environmental science.

The coastal region of Jiangsu Province, a critical ecological and economic zone in eastern China, faces significant spatial vulnerability due to combined natural and anthropogenic pressures. This study employs a multi-factorial assessment framework integrating Geographic Information System (GIS) tools to analyze vulnerability across three dimensions: basic conditions, ecological environment, and human activities. Key findings reveal distinct spatial disparities in vulnerability, quantified through a vulnerability index (VI) ranging from 1 (highest vulnerability) to 5 (lowest).Statistical results indicate that 5.49% of the coastal zone is classified as high vulnerability (VI = 1) and 21.15% as relatively high (VI = 2), primarily concentrated in inland areas such as Ganyu, Lianyun, and Binhai districts. Conversely, 39.31% of the region exhibits moderate vulnerability (VI = 3), while 32.04% and 2.02% are categorized as relatively low (VI = 4) and low vulnerability (VI = 5), respectively. Notably, inland regions consistently show higher vulnerability compared to coastal areas, contradicting initial assumptions of uniform north-south gradients. Spatial analysis further demonstrates that central coastal zones (e.g., Dafeng, Dongtai) exhibit lower vulnerability due to balanced human-environment interactions, whereas northern and southern inland regions face intensified pressures from urbanization, industrialization, and land subsidence.To address these disparities, this study proposes targeted ecological restoration strategies, including: (1) infrastructure reinforcement in high-vulnerability inland areas; (2) wetland conservation and reforestation in ecologically sensitive zones; (3) sustainable land-use planning to mitigate human-induced degradation; and (4) community-based adaptive management frameworks. These recommendations aim to enhance resilience while balancing socioeconomic development and environmental protection. This research provides a data-driven foundation for policymakers to prioritize interventions in Jiangsu’s coastal zone and offers a replicable methodology for vulnerability assessments in other deltaic regions.

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