Lei Yuan

Land-use and land-cover change (LULCC) is one of the key drivers altering terrestrial ecosystem carbon storage. Accurate simulation of LULCC is crucial for assessing ecosystem sustainability and formulating global climate change mitigation strategies. Within this context, this study proposes a novel deep learning model integrating U-Net architecture, an attention mechanism, and ConvLSTM-termed U-Net-Attention-ConvLSTM (UNA-CL), to enhance the accuracy of LULCC simulation. The model's effectiveness was validated using land use and land cover (LULC) data from Kunming (2000-2020) and compared with a widely applied convolutional neural network (CNN) model (CNNA-CL) and Random Forest-Cellular Automata (RF-CA) model. Furthermore, this study coupled the UNA-CL model with the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model, which is designed for ecosystem service assessment, to jointly reveal the spatiotemporal evolution characteristics of future LULC patterns and carbon storage. The results indicate that (1) the UNA-CL model outperformed the comparative models in classification accuracy, achieving an overall accuracy (OA) of 94.36%, which is 5.72% and 0.5% higher than the CNNA-CL and RF-CA models, respectively; (2) in terms of spatial allocation accuracy, the UNA-CL model not only accurately simulated land cover categories with complex distribution patterns but also mitigated the simulation bias caused by spatial heterogeneity in the RF-CA model; (3) from 2000 to 2030, the net increase in carbon storage was 3.74 Mega tons (Mt), exhibiting a trend of increase followed by decrease. Specifically, the conversion of grassland and cultivated land to forest land led to an accumulation of 3.81 Mt during 2000-2020. However, from 2020 to 2030, a combination of forest land loss and continued construction land expansion resulted in a net decrease of 0.07 Mt.

Exploring the spatial and temporal changes in vegetation net primary productivity (NPP) and analyzing its complex relationship with influencing factors is crucial for assessing the carbon absorption capability of vegetation. However, most of the existing studies have been conducted from a temporal or spatial perspective, resulting in an unclear characterization of the spatio-temporal divergence between NPP and the main influencing factors. This paper tries to break through the lack of research on the spatiotemporal heterogeneity of the relationship between NPP and influencing factors and proposes a joint spatiotemporal analysis method that integrates natural and anthropogenic factors, uses correlation analysis to determine their relationship with NPP, then combines GeoDetector (GD) and Geographically Weighted Regression (GWR), and carries out an empirical study based on the data of 2001-2017, taking Yunnan Province as an example, to reveal the characteristics of influencing factors’ divergence in different time and space. The results indicate that: (1) NPP in Yunnan Province experienced fluctuations and increases from 2001 to 2017. (2) NDVI, precipitation, and temperature exert a substantial influence on the spatial and temporal variation of NPP, although this impact is diminishing. (3) Solar radiation, topography, and land use are secondary factors that affect the spatial and temporal differentiation of NPP, but their influence is increasing. (4) From 2001 to 2010, land use transfer was the main cause of NPP loss, but from 2010 to 2017, land use transfer was the main cause of NPP gain. The collective effect of anthropogenic activities and natural factors is considerably more substantial than the influence of any individual factor. This study aims to improve our understanding of how the NPP responds to climate change and urbanization. Additionally, it seeks to clarify spatial and temporal variations in NPP and identify its primary drivers. Furthermore, it can serve as a useful scientific foundation and point of reference for improving the performance of ecosystem carbon sinks and achieving carbon neutrality.

Mountainous area account for 94% in Yunnan, China. Among them, cultivated land only 16.20%. In order to classify and protect cultivated land contiguous, take Huaping , a typical mountainous area as an example, and integrates the entropy weight method, TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and spatial autocorrelation method to construct a zoning method based on CLQE (Cultivated Land Quality Evaluation). The results showed that the CLQE was divided into five grades. Class 1 and Class 2 was higher, respectively accounting for 24.98% and 29.98% of the total cultivated land area, Class 3 and Class 4 was accounting for 23.17% and 13.76%, Class 5 was the worst, accounting for 8.11%. In terms of layout, it can be divided into 4 areas, key protected areas are distributed in Class 1 and 2, accounting for 52.52% of the total, suitable adjustment areas are distributed in Class 1, 2 and 3, accounting for 9.02%, key control areas are distributed in Class 3 and 4, accounting for 25.41%, reduce reserved areas are distributed in Class 4 and 5, accounting for 13.05%. The results are consistent with the actual situation, and provide a feasible method for cultivated land classification and zoning protection.

The rapid development of industrialization and the continuous acceleration of the urbanization process have continuously improved the quality of life of the people, but at the same time brought important environmental problems such as air pollution and climate change that humans have to face today. In this paper, the meteorological data of Dongfeng East Road Station in Kunming is taken as the research object, and the Spark platform is used to quickly and effectively analyze the air pollution data of Dongfeng East Road Station. Through analysis and research on the air pollution-related conditions of major transportation hubs in Kunming in recent years, the results show that the concentration of air pollutants at Dongfeng East Road Station in Kunming has a relatively obvious downward trend, especially the significant decline in SO2 and CO. As far as air quality is concerned, the air quality in some areas of Kunming continues to improve.

The rapid development of urbanization has changed the type of underlying surface within the city and affected the temperature changes in the city. Mastering the relationship between urban temperature and the temperature of the different underlying surface is the basis for improving the urban heat island effect. To this end, select the school with representative urban characteristics to study the relationship between urban temperature and urban underlying surface types under different weather conditions. The Chenggong Campus of Yunnan Normal University in Kunming, Yunnan Province is the typical urban research object. Extracting the underlying surface type data of four main active areas such as grassland, water surface, bare soil and asphalt by means of artificial field measurement, and analyzed. The experimental results show that under different underlying conditions, the influence of environmental climatic conditions on urban temperature is different. This shows that in urban planning, the rational planning and design of different underlying surface types can effectively solve the urban heat island and rain island effect problem.

In recent years, with the acceleration of urbanization and the rapid growth of urban population, the impact of urban human activities on the ecological environment system has become more and more significant. How to scientifically to analyze the evolution characteristics of urban spatial form and demarcate the urban extension boundary scientifically and reasonably is of great significance to grasp the urban development context, construct a scientific and reasonable urban spatial form framework and guide the healthy and sustainable development of the city. This paper takes the Chenggong District of Kunming City, which has been developing rapidly in recent years, as the research object. It uses the Landsat remote sensing satellite image data onto different periods to extract the information on the land use type of the study area, and then combines the GIS technology to analyze the temporal and spatial characteristics of the urban form evolution in the Chenggong District. Finally, qualitative analysis is carried out in the aspects of the natural environment, policy orientation, economy and society in combination with the evolution of urban form. After introducing the four types of indicators: extended annual speed, extended dynamics, extended intensity and extended comprehensive index, the urban form evolution of Chenggong District was quantitatively analyzed. It was found that Chenggong District was in the stage of rapid development of urbanization in the past 15 years. There is obvious differentiation in the pattern, the southwest and northwest directions are the main expansion directions, and the southeast direction is the slowest. Natural factors have greatly restricted the expansion of Chenggong District. The development of economic construction and policy planning has become the main driving factors for urban land expansion and space-time evolution.

In order to break the difficult realistic predicament of the promoting special agricultural product, so that, the agricultural product resources can be effectively promoted, the survey based on the mobile GIS technology architecture, integrated application of mobile Internet technology and JavaScript dynamic, interactive technology, having the aid of Android Studio development tools to design and implement a set of special agricultural products promotion system based on Android. The system adopts the four-tier architecture model of the database layer, platform layer, business logic layer and application layer to achieve high cohesion and low coupling characteristics of the system. Based on the comprehensive application of technology architecture of mobile GIS and various technologies, solving the deficiency of two-dimensional presentation of agricultural product promotion information for the traditional mobile terminal system. The practical application in Fumin county shows that the system has the advantages of strong real-time dynamic interaction and vivid visualization of information, it has effectively built a visual, interactive platform of mobile communication between supply and demand sides for local agricultural product promotion to increase the application level of rural information technology, helping rural agricultural development and raising farmers' income have important application value and practical significance.

With the rapid development of Internet of Things technology in recent years, speech recognition technology based on artificial intelligence and Internet of Things has gradually penetrated into various fields.In the traditional field of smart home systems, users generally need to manually set function scenes, which are time-consuming and labor-intensive and inconvenient for human-machine system interaction. In order to better meet the needs of people's intelligent life, to provide users with better control experience on smart home appliances, improve the quality of intelligent home life. This article designed a smart home control system that uses iOS as the core, voice recognition module as the interactive means, and MQTT communication protocol as data transfer.The system uses speech recognition technology based on artificial intelligence and deep learning to improve the recognition rate of speech input, achieve perfect interaction between humans and computers, and enable users to truly experience the intelligent and humanized characteristics of smart home systems.

In view of the fact that the traditional way of flower shop information management is based on manual processing of paper media such as text and forms, manual calculations are often used to count and verify the order of flowers. Data processing is tedious and error-prone. Therefore, this design uses ASP technology and IIS technology, combined with database SQL Server 2008, using Visual Studio 2010 development tools, designed and implemented a dynamic intelligent flower shop management system based on MIS. The system makes the flower sales management work standardized, systematic and procedural, avoids arbitrariness, improves the speed and accuracy of sales, and timely, accurately and effectively inquiries about and revise orders and flowers. The low operating costs of on-line flower shops, short cycle of capital turnover, and faster information updates are more conducive to market development.